Aliderakhshan commited on
Commit
df8705c
·
1 Parent(s): 53972c9

add cot finetuned lora adapters for codegemma7b

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +2 -0
  2. codegemma_instruct_cot_ft_lora_r64_alpha64/README.md +202 -0
  3. codegemma_instruct_cot_ft_lora_r64_alpha64/adapter_config.json +39 -0
  4. codegemma_instruct_cot_ft_lora_r64_alpha64/adapter_model.safetensors +3 -0
  5. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/README.md +202 -0
  6. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/adapter_config.json +39 -0
  7. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/adapter_model.safetensors +3 -0
  8. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/optimizer.pt +3 -0
  9. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/rng_state.pth +3 -0
  10. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/scheduler.pt +3 -0
  11. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/special_tokens_map.json +30 -0
  12. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/tokenizer.json +3 -0
  13. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/tokenizer.model +3 -0
  14. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/tokenizer_config.json +2011 -0
  15. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/trainer_state.json +742 -0
  16. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/training_args.bin +3 -0
  17. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/README.md +202 -0
  18. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/adapter_config.json +39 -0
  19. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/adapter_model.safetensors +3 -0
  20. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/optimizer.pt +3 -0
  21. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/rng_state.pth +3 -0
  22. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/scheduler.pt +3 -0
  23. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/special_tokens_map.json +30 -0
  24. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/tokenizer.json +3 -0
  25. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/tokenizer.model +3 -0
  26. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/tokenizer_config.json +2011 -0
  27. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/trainer_state.json +1450 -0
  28. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/training_args.bin +3 -0
  29. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/README.md +202 -0
  30. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/adapter_config.json +39 -0
  31. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/adapter_model.safetensors +3 -0
  32. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/optimizer.pt +3 -0
  33. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/rng_state.pth +3 -0
  34. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/scheduler.pt +3 -0
  35. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/special_tokens_map.json +30 -0
  36. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/tokenizer.json +3 -0
  37. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/tokenizer.model +3 -0
  38. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/tokenizer_config.json +2011 -0
  39. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/trainer_state.json +2158 -0
  40. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/training_args.bin +3 -0
  41. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/README.md +202 -0
  42. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/adapter_config.json +39 -0
  43. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/adapter_model.safetensors +3 -0
  44. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/optimizer.pt +3 -0
  45. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/rng_state.pth +3 -0
  46. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/scheduler.pt +3 -0
  47. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/special_tokens_map.json +30 -0
  48. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/tokenizer.json +3 -0
  49. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/tokenizer.model +3 -0
  50. codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/tokenizer_config.json +2011 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ codegemma_instruct_cot_ft_lora_r64_alpha64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ codegemma_instruct_cot_ft_lora_r64_alpha64/**/tokenizer.json filter=lfs diff=lfs merge=lfs -text
codegemma_instruct_cot_ft_lora_r64_alpha64/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/codegemma-7b-it
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 0.15.0
codegemma_instruct_cot_ft_lora_r64_alpha64/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/codegemma-7b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9a683aab0635490d46fb72d7c531a3a443ffe4435c539ad2d7f933ae1397d5
3
+ size 800116456
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/codegemma-7b-it
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 0.15.0
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/codegemma-7b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e267050be1a43e3b401da7e45c66497974e0eb05f8f8a684c91b23aad584c4
3
+ size 800116456
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ec055e0ecb1d77f399dcf0d034378575853e437b45a99193e4df6760dc771c
3
+ size 406743412
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:203e9bfabd925cb4ec7129d24877156fcee87215187c35a867e358e56a9425a4
3
+ size 14244
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd58b39bd6bfb59bb506313d8c2a30b14e9dc11a2d99de48bc99568a9510416f
3
+ size 1064
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d964a2c8346d40f95791533eae48730d5f163c2e65fd16333560fd3e661df318
3
+ size 34362915
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583f2ebd2a1936009b7da991ea255504db68c7a9713a78673d1335a87098966c
3
+ size 4241023
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,2011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<|fim_prefix|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<|fim_middle|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<|fim_suffix|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<|file_separator|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": false
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": false
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "bos_token": "<bos>",
1999
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
2000
+ "clean_up_tokenization_spaces": false,
2001
+ "eos_token": "<eos>",
2002
+ "extra_special_tokens": {},
2003
+ "model_max_length": 1000000000000000019884624838656,
2004
+ "pad_token": "<pad>",
2005
+ "padding_side": "left",
2006
+ "sp_model_kwargs": {},
2007
+ "spaces_between_special_tokens": false,
2008
+ "tokenizer_class": "GemmaTokenizer",
2009
+ "unk_token": "<unk>",
2010
+ "use_default_system_prompt": false
2011
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.2058142526369951,
6
+ "eval_steps": 100,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0020581425263699513,
14
+ "grad_norm": 11.994463920593262,
15
+ "learning_rate": 2.061855670103093e-07,
16
+ "loss": 2.91,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.004116285052739903,
21
+ "grad_norm": 11.769092559814453,
22
+ "learning_rate": 4.123711340206186e-07,
23
+ "loss": 2.8686,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0061744275791098535,
28
+ "grad_norm": 13.05551815032959,
29
+ "learning_rate": 6.185567010309279e-07,
30
+ "loss": 3.0286,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.008232570105479805,
35
+ "grad_norm": 12.334521293640137,
36
+ "learning_rate": 8.247422680412372e-07,
37
+ "loss": 2.904,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.010290712631849755,
42
+ "grad_norm": 12.075353622436523,
43
+ "learning_rate": 1.0309278350515464e-06,
44
+ "loss": 2.8991,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.012348855158219707,
49
+ "grad_norm": 11.86032485961914,
50
+ "learning_rate": 1.2371134020618557e-06,
51
+ "loss": 3.0007,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.014406997684589657,
56
+ "grad_norm": 10.10457992553711,
57
+ "learning_rate": 1.4432989690721649e-06,
58
+ "loss": 2.8493,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.01646514021095961,
63
+ "grad_norm": 8.56408405303955,
64
+ "learning_rate": 1.6494845360824744e-06,
65
+ "loss": 2.9573,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.01852328273732956,
70
+ "grad_norm": 6.307392120361328,
71
+ "learning_rate": 1.8556701030927837e-06,
72
+ "loss": 2.9507,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.02058142526369951,
77
+ "grad_norm": 4.276430130004883,
78
+ "learning_rate": 2.061855670103093e-06,
79
+ "loss": 2.8988,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.022639567790069464,
84
+ "grad_norm": 2.5912015438079834,
85
+ "learning_rate": 2.268041237113402e-06,
86
+ "loss": 2.9926,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.024697710316439414,
91
+ "grad_norm": 2.018446207046509,
92
+ "learning_rate": 2.4742268041237115e-06,
93
+ "loss": 2.9874,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.026755852842809364,
98
+ "grad_norm": 1.8558588027954102,
99
+ "learning_rate": 2.680412371134021e-06,
100
+ "loss": 2.8608,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.028813995369179314,
105
+ "grad_norm": 1.9658265113830566,
106
+ "learning_rate": 2.8865979381443297e-06,
107
+ "loss": 2.8596,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.030872137895549268,
112
+ "grad_norm": 1.872044563293457,
113
+ "learning_rate": 3.0927835051546395e-06,
114
+ "loss": 2.8836,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.03293028042191922,
119
+ "grad_norm": 1.8884096145629883,
120
+ "learning_rate": 3.298969072164949e-06,
121
+ "loss": 2.9383,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.03498842294828917,
126
+ "grad_norm": 1.8795744180679321,
127
+ "learning_rate": 3.5051546391752577e-06,
128
+ "loss": 2.883,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.03704656547465912,
133
+ "grad_norm": 1.783678412437439,
134
+ "learning_rate": 3.7113402061855674e-06,
135
+ "loss": 2.8019,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.039104708001029075,
140
+ "grad_norm": 1.820617914199829,
141
+ "learning_rate": 3.917525773195877e-06,
142
+ "loss": 2.8813,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.04116285052739902,
147
+ "grad_norm": 1.8188731670379639,
148
+ "learning_rate": 4.123711340206186e-06,
149
+ "loss": 2.8401,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.043220993053768975,
154
+ "grad_norm": 1.7305251359939575,
155
+ "learning_rate": 4.329896907216495e-06,
156
+ "loss": 2.7478,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.04527913558013893,
161
+ "grad_norm": 1.7014551162719727,
162
+ "learning_rate": 4.536082474226804e-06,
163
+ "loss": 2.7356,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.047337278106508875,
168
+ "grad_norm": 1.677381157875061,
169
+ "learning_rate": 4.742268041237113e-06,
170
+ "loss": 2.7593,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.04939542063287883,
175
+ "grad_norm": 1.628554344177246,
176
+ "learning_rate": 4.948453608247423e-06,
177
+ "loss": 2.7689,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.051453563159248775,
182
+ "grad_norm": 1.4968128204345703,
183
+ "learning_rate": 5.154639175257732e-06,
184
+ "loss": 2.6613,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.05351170568561873,
189
+ "grad_norm": 1.4734832048416138,
190
+ "learning_rate": 5.360824742268042e-06,
191
+ "loss": 2.7095,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.05556984821198868,
196
+ "grad_norm": 1.3745571374893188,
197
+ "learning_rate": 5.567010309278351e-06,
198
+ "loss": 2.655,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.05762799073835863,
203
+ "grad_norm": 1.3381729125976562,
204
+ "learning_rate": 5.7731958762886594e-06,
205
+ "loss": 2.55,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.05968613326472858,
210
+ "grad_norm": 1.3388073444366455,
211
+ "learning_rate": 5.979381443298969e-06,
212
+ "loss": 2.5219,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.061744275791098535,
217
+ "grad_norm": 1.317008376121521,
218
+ "learning_rate": 6.185567010309279e-06,
219
+ "loss": 2.4491,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.06380241831746848,
224
+ "grad_norm": 1.3210794925689697,
225
+ "learning_rate": 6.391752577319588e-06,
226
+ "loss": 2.4358,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.06586056084383844,
231
+ "grad_norm": 1.182519555091858,
232
+ "learning_rate": 6.597938144329898e-06,
233
+ "loss": 2.4514,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.06791870337020839,
238
+ "grad_norm": 1.2238099575042725,
239
+ "learning_rate": 6.804123711340207e-06,
240
+ "loss": 2.442,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.06997684589657834,
245
+ "grad_norm": 1.1793314218521118,
246
+ "learning_rate": 7.010309278350515e-06,
247
+ "loss": 2.3864,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.0720349884229483,
252
+ "grad_norm": 1.1983020305633545,
253
+ "learning_rate": 7.216494845360825e-06,
254
+ "loss": 2.3796,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.07409313094931824,
259
+ "grad_norm": 1.2189652919769287,
260
+ "learning_rate": 7.422680412371135e-06,
261
+ "loss": 2.4152,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.07615127347568819,
266
+ "grad_norm": 1.14923095703125,
267
+ "learning_rate": 7.628865979381444e-06,
268
+ "loss": 2.3298,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.07820941600205815,
273
+ "grad_norm": 1.147013545036316,
274
+ "learning_rate": 7.835051546391754e-06,
275
+ "loss": 2.2488,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.0802675585284281,
280
+ "grad_norm": 1.133981466293335,
281
+ "learning_rate": 8.041237113402063e-06,
282
+ "loss": 2.1825,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.08232570105479804,
287
+ "grad_norm": 1.1686867475509644,
288
+ "learning_rate": 8.247422680412371e-06,
289
+ "loss": 2.2282,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.084383843581168,
294
+ "grad_norm": 1.131690502166748,
295
+ "learning_rate": 8.453608247422681e-06,
296
+ "loss": 2.0962,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.08644198610753795,
301
+ "grad_norm": 1.1626195907592773,
302
+ "learning_rate": 8.65979381443299e-06,
303
+ "loss": 2.1161,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.0885001286339079,
308
+ "grad_norm": 1.1508581638336182,
309
+ "learning_rate": 8.865979381443299e-06,
310
+ "loss": 1.9856,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.09055827116027786,
315
+ "grad_norm": 1.2286733388900757,
316
+ "learning_rate": 9.072164948453609e-06,
317
+ "loss": 2.076,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.0926164136866478,
322
+ "grad_norm": 1.82068932056427,
323
+ "learning_rate": 9.278350515463918e-06,
324
+ "loss": 1.9995,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.09467455621301775,
329
+ "grad_norm": 2.079101324081421,
330
+ "learning_rate": 9.484536082474226e-06,
331
+ "loss": 1.9601,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.0967326987393877,
336
+ "grad_norm": 1.1209226846694946,
337
+ "learning_rate": 9.690721649484536e-06,
338
+ "loss": 1.9346,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.09879084126575766,
343
+ "grad_norm": 1.0579711198806763,
344
+ "learning_rate": 9.896907216494846e-06,
345
+ "loss": 1.8764,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.1008489837921276,
350
+ "grad_norm": 1.0434011220932007,
351
+ "learning_rate": 1.0103092783505156e-05,
352
+ "loss": 1.8483,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.10290712631849755,
357
+ "grad_norm": 1.0089991092681885,
358
+ "learning_rate": 1.0309278350515464e-05,
359
+ "loss": 1.8018,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.10496526884486751,
364
+ "grad_norm": 1.0117324590682983,
365
+ "learning_rate": 1.0515463917525775e-05,
366
+ "loss": 1.8003,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.10702341137123746,
371
+ "grad_norm": 1.0006697177886963,
372
+ "learning_rate": 1.0721649484536083e-05,
373
+ "loss": 1.7482,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.1090815538976074,
378
+ "grad_norm": 2.1164329051971436,
379
+ "learning_rate": 1.0927835051546391e-05,
380
+ "loss": 1.7363,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.11113969642397736,
385
+ "grad_norm": 0.9573502540588379,
386
+ "learning_rate": 1.1134020618556703e-05,
387
+ "loss": 1.661,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.11319783895034731,
392
+ "grad_norm": 1.0059764385223389,
393
+ "learning_rate": 1.134020618556701e-05,
394
+ "loss": 1.6979,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.11525598147671726,
399
+ "grad_norm": 0.9719656109809875,
400
+ "learning_rate": 1.1546391752577319e-05,
401
+ "loss": 1.6318,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.11731412400308722,
406
+ "grad_norm": 1.0024539232254028,
407
+ "learning_rate": 1.175257731958763e-05,
408
+ "loss": 1.6283,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.11937226652945716,
413
+ "grad_norm": 0.9772456288337708,
414
+ "learning_rate": 1.1958762886597938e-05,
415
+ "loss": 1.5611,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.12143040905582711,
420
+ "grad_norm": 0.9947625994682312,
421
+ "learning_rate": 1.2164948453608248e-05,
422
+ "loss": 1.6073,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.12348855158219707,
427
+ "grad_norm": 2.112889051437378,
428
+ "learning_rate": 1.2371134020618558e-05,
429
+ "loss": 1.6208,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.12554669410856703,
434
+ "grad_norm": 1.0515345335006714,
435
+ "learning_rate": 1.2577319587628866e-05,
436
+ "loss": 1.569,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.12760483663493696,
441
+ "grad_norm": 1.0782145261764526,
442
+ "learning_rate": 1.2783505154639176e-05,
443
+ "loss": 1.5097,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.12966297916130692,
448
+ "grad_norm": 1.154104232788086,
449
+ "learning_rate": 1.2989690721649485e-05,
450
+ "loss": 1.5472,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.13172112168767688,
455
+ "grad_norm": 1.1614656448364258,
456
+ "learning_rate": 1.3195876288659795e-05,
457
+ "loss": 1.4833,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.13377926421404682,
462
+ "grad_norm": 1.1720911264419556,
463
+ "learning_rate": 1.3402061855670103e-05,
464
+ "loss": 1.4644,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.13583740674041678,
469
+ "grad_norm": 1.8903896808624268,
470
+ "learning_rate": 1.3608247422680415e-05,
471
+ "loss": 1.4286,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.13789554926678674,
476
+ "grad_norm": 1.2675013542175293,
477
+ "learning_rate": 1.3814432989690723e-05,
478
+ "loss": 1.416,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.13995369179315667,
483
+ "grad_norm": 1.266434907913208,
484
+ "learning_rate": 1.402061855670103e-05,
485
+ "loss": 1.3171,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.14201183431952663,
490
+ "grad_norm": 1.3408889770507812,
491
+ "learning_rate": 1.4226804123711342e-05,
492
+ "loss": 1.3396,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.1440699768458966,
497
+ "grad_norm": 1.3862446546554565,
498
+ "learning_rate": 1.443298969072165e-05,
499
+ "loss": 1.2642,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.14612811937226652,
504
+ "grad_norm": 2.110553026199341,
505
+ "learning_rate": 1.4639175257731958e-05,
506
+ "loss": 1.2593,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.14818626189863648,
511
+ "grad_norm": 1.7017499208450317,
512
+ "learning_rate": 1.484536082474227e-05,
513
+ "loss": 1.24,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.15024440442500644,
518
+ "grad_norm": 1.9851700067520142,
519
+ "learning_rate": 1.5051546391752578e-05,
520
+ "loss": 1.2313,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.15230254695137638,
525
+ "grad_norm": 2.009608030319214,
526
+ "learning_rate": 1.5257731958762888e-05,
527
+ "loss": 1.1281,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.15436068947774634,
532
+ "grad_norm": 2.7587485313415527,
533
+ "learning_rate": 1.5463917525773197e-05,
534
+ "loss": 1.1248,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.1564188320041163,
539
+ "grad_norm": 2.780954599380493,
540
+ "learning_rate": 1.5670103092783507e-05,
541
+ "loss": 1.0797,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.15847697453048623,
546
+ "grad_norm": 3.1470866203308105,
547
+ "learning_rate": 1.5876288659793813e-05,
548
+ "loss": 1.0064,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.1605351170568562,
553
+ "grad_norm": 4.653595447540283,
554
+ "learning_rate": 1.6082474226804127e-05,
555
+ "loss": 0.9219,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.16259325958322615,
560
+ "grad_norm": 4.157363414764404,
561
+ "learning_rate": 1.6288659793814433e-05,
562
+ "loss": 0.8709,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.16465140210959608,
567
+ "grad_norm": 4.5814924240112305,
568
+ "learning_rate": 1.6494845360824743e-05,
569
+ "loss": 0.7693,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.16670954463596604,
574
+ "grad_norm": 5.096139907836914,
575
+ "learning_rate": 1.6701030927835052e-05,
576
+ "loss": 0.6868,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.168767687162336,
581
+ "grad_norm": 4.858880519866943,
582
+ "learning_rate": 1.6907216494845362e-05,
583
+ "loss": 0.5971,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.17082582968870594,
588
+ "grad_norm": 4.42564582824707,
589
+ "learning_rate": 1.7113402061855672e-05,
590
+ "loss": 0.4719,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.1728839722150759,
595
+ "grad_norm": 7.720851421356201,
596
+ "learning_rate": 1.731958762886598e-05,
597
+ "loss": 0.3943,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.17494211474144586,
602
+ "grad_norm": 0.41923192143440247,
603
+ "learning_rate": 1.752577319587629e-05,
604
+ "loss": 0.3635,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.1770002572678158,
609
+ "grad_norm": 0.2771846354007721,
610
+ "learning_rate": 1.7731958762886598e-05,
611
+ "loss": 0.3597,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.17905839979418575,
616
+ "grad_norm": 0.24761857092380524,
617
+ "learning_rate": 1.793814432989691e-05,
618
+ "loss": 0.3735,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.1811165423205557,
623
+ "grad_norm": 0.23277048766613007,
624
+ "learning_rate": 1.8144329896907217e-05,
625
+ "loss": 0.3643,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.18317468484692565,
630
+ "grad_norm": 0.22931228578090668,
631
+ "learning_rate": 1.8350515463917527e-05,
632
+ "loss": 0.3519,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.1852328273732956,
637
+ "grad_norm": 0.20750615000724792,
638
+ "learning_rate": 1.8556701030927837e-05,
639
+ "loss": 0.3431,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.18729096989966554,
644
+ "grad_norm": 0.2080322951078415,
645
+ "learning_rate": 1.8762886597938147e-05,
646
+ "loss": 0.3632,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.1893491124260355,
651
+ "grad_norm": 0.20186181366443634,
652
+ "learning_rate": 1.8969072164948453e-05,
653
+ "loss": 0.3492,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.19140725495240546,
658
+ "grad_norm": 0.19172786176204681,
659
+ "learning_rate": 1.9175257731958766e-05,
660
+ "loss": 0.3552,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.1934653974787754,
665
+ "grad_norm": 0.1747850626707077,
666
+ "learning_rate": 1.9381443298969072e-05,
667
+ "loss": 0.3355,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.19552354000514535,
672
+ "grad_norm": 0.196411594748497,
673
+ "learning_rate": 1.9587628865979382e-05,
674
+ "loss": 0.3271,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.1975816825315153,
679
+ "grad_norm": 0.20063228905200958,
680
+ "learning_rate": 1.9793814432989692e-05,
681
+ "loss": 0.3351,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.19963982505788525,
686
+ "grad_norm": 0.19240939617156982,
687
+ "learning_rate": 2e-05,
688
+ "loss": 0.3266,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.2016979675842552,
693
+ "grad_norm": 0.18206572532653809,
694
+ "learning_rate": 1.997709049255441e-05,
695
+ "loss": 0.3393,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.20375611011062517,
700
+ "grad_norm": 0.20384562015533447,
701
+ "learning_rate": 1.9954180985108823e-05,
702
+ "loss": 0.3395,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.2058142526369951,
707
+ "grad_norm": 0.19944581389427185,
708
+ "learning_rate": 1.9931271477663232e-05,
709
+ "loss": 0.3268,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.2058142526369951,
714
+ "eval_loss": 0.3456890285015106,
715
+ "eval_runtime": 2114.0178,
716
+ "eval_samples_per_second": 3.677,
717
+ "eval_steps_per_second": 0.92,
718
+ "step": 100
719
+ }
720
+ ],
721
+ "logging_steps": 1,
722
+ "max_steps": 970,
723
+ "num_input_tokens_seen": 0,
724
+ "num_train_epochs": 2,
725
+ "save_steps": 100,
726
+ "stateful_callbacks": {
727
+ "TrainerControl": {
728
+ "args": {
729
+ "should_epoch_stop": false,
730
+ "should_evaluate": false,
731
+ "should_log": false,
732
+ "should_save": true,
733
+ "should_training_stop": false
734
+ },
735
+ "attributes": {}
736
+ }
737
+ },
738
+ "total_flos": 3.305891627680727e+17,
739
+ "train_batch_size": 4,
740
+ "trial_name": null,
741
+ "trial_params": null
742
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee55a11f5a306eb7c39b536fdfe2459bc279e468da50f6adda478c4deffcb812
3
+ size 5688
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/codegemma-7b-it
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 0.15.0
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/codegemma-7b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f49550075985c6448d99511eea8c0d140b5aa2a60faa2277a7890044a1b911
3
+ size 800116456
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9e27cacef57683319dff6c0d7b7cf66889116f9593d5c58fbafe7bfe73c72e
3
+ size 406743412
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4981123ff3cf7bd5b7f76839e90e4776f747ca4c38dcb41876fa010c0dea8b23
3
+ size 14244
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f316812b0c43f9354e615bde4cea4403d3ff2b0ee5dd42dfeae9f021d9e696
3
+ size 1064
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d964a2c8346d40f95791533eae48730d5f163c2e65fd16333560fd3e661df318
3
+ size 34362915
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583f2ebd2a1936009b7da991ea255504db68c7a9713a78673d1335a87098966c
3
+ size 4241023
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,2011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<|fim_prefix|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<|fim_middle|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<|fim_suffix|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<|file_separator|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": false
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": false
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "bos_token": "<bos>",
1999
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
2000
+ "clean_up_tokenization_spaces": false,
2001
+ "eos_token": "<eos>",
2002
+ "extra_special_tokens": {},
2003
+ "model_max_length": 1000000000000000019884624838656,
2004
+ "pad_token": "<pad>",
2005
+ "padding_side": "left",
2006
+ "sp_model_kwargs": {},
2007
+ "spaces_between_special_tokens": false,
2008
+ "tokenizer_class": "GemmaTokenizer",
2009
+ "unk_token": "<unk>",
2010
+ "use_default_system_prompt": false
2011
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,1450 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.4116285052739902,
6
+ "eval_steps": 100,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0020581425263699513,
14
+ "grad_norm": 11.994463920593262,
15
+ "learning_rate": 2.061855670103093e-07,
16
+ "loss": 2.91,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.004116285052739903,
21
+ "grad_norm": 11.769092559814453,
22
+ "learning_rate": 4.123711340206186e-07,
23
+ "loss": 2.8686,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0061744275791098535,
28
+ "grad_norm": 13.05551815032959,
29
+ "learning_rate": 6.185567010309279e-07,
30
+ "loss": 3.0286,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.008232570105479805,
35
+ "grad_norm": 12.334521293640137,
36
+ "learning_rate": 8.247422680412372e-07,
37
+ "loss": 2.904,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.010290712631849755,
42
+ "grad_norm": 12.075353622436523,
43
+ "learning_rate": 1.0309278350515464e-06,
44
+ "loss": 2.8991,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.012348855158219707,
49
+ "grad_norm": 11.86032485961914,
50
+ "learning_rate": 1.2371134020618557e-06,
51
+ "loss": 3.0007,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.014406997684589657,
56
+ "grad_norm": 10.10457992553711,
57
+ "learning_rate": 1.4432989690721649e-06,
58
+ "loss": 2.8493,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.01646514021095961,
63
+ "grad_norm": 8.56408405303955,
64
+ "learning_rate": 1.6494845360824744e-06,
65
+ "loss": 2.9573,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.01852328273732956,
70
+ "grad_norm": 6.307392120361328,
71
+ "learning_rate": 1.8556701030927837e-06,
72
+ "loss": 2.9507,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.02058142526369951,
77
+ "grad_norm": 4.276430130004883,
78
+ "learning_rate": 2.061855670103093e-06,
79
+ "loss": 2.8988,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.022639567790069464,
84
+ "grad_norm": 2.5912015438079834,
85
+ "learning_rate": 2.268041237113402e-06,
86
+ "loss": 2.9926,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.024697710316439414,
91
+ "grad_norm": 2.018446207046509,
92
+ "learning_rate": 2.4742268041237115e-06,
93
+ "loss": 2.9874,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.026755852842809364,
98
+ "grad_norm": 1.8558588027954102,
99
+ "learning_rate": 2.680412371134021e-06,
100
+ "loss": 2.8608,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.028813995369179314,
105
+ "grad_norm": 1.9658265113830566,
106
+ "learning_rate": 2.8865979381443297e-06,
107
+ "loss": 2.8596,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.030872137895549268,
112
+ "grad_norm": 1.872044563293457,
113
+ "learning_rate": 3.0927835051546395e-06,
114
+ "loss": 2.8836,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.03293028042191922,
119
+ "grad_norm": 1.8884096145629883,
120
+ "learning_rate": 3.298969072164949e-06,
121
+ "loss": 2.9383,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.03498842294828917,
126
+ "grad_norm": 1.8795744180679321,
127
+ "learning_rate": 3.5051546391752577e-06,
128
+ "loss": 2.883,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.03704656547465912,
133
+ "grad_norm": 1.783678412437439,
134
+ "learning_rate": 3.7113402061855674e-06,
135
+ "loss": 2.8019,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.039104708001029075,
140
+ "grad_norm": 1.820617914199829,
141
+ "learning_rate": 3.917525773195877e-06,
142
+ "loss": 2.8813,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.04116285052739902,
147
+ "grad_norm": 1.8188731670379639,
148
+ "learning_rate": 4.123711340206186e-06,
149
+ "loss": 2.8401,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.043220993053768975,
154
+ "grad_norm": 1.7305251359939575,
155
+ "learning_rate": 4.329896907216495e-06,
156
+ "loss": 2.7478,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.04527913558013893,
161
+ "grad_norm": 1.7014551162719727,
162
+ "learning_rate": 4.536082474226804e-06,
163
+ "loss": 2.7356,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.047337278106508875,
168
+ "grad_norm": 1.677381157875061,
169
+ "learning_rate": 4.742268041237113e-06,
170
+ "loss": 2.7593,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.04939542063287883,
175
+ "grad_norm": 1.628554344177246,
176
+ "learning_rate": 4.948453608247423e-06,
177
+ "loss": 2.7689,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.051453563159248775,
182
+ "grad_norm": 1.4968128204345703,
183
+ "learning_rate": 5.154639175257732e-06,
184
+ "loss": 2.6613,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.05351170568561873,
189
+ "grad_norm": 1.4734832048416138,
190
+ "learning_rate": 5.360824742268042e-06,
191
+ "loss": 2.7095,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.05556984821198868,
196
+ "grad_norm": 1.3745571374893188,
197
+ "learning_rate": 5.567010309278351e-06,
198
+ "loss": 2.655,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.05762799073835863,
203
+ "grad_norm": 1.3381729125976562,
204
+ "learning_rate": 5.7731958762886594e-06,
205
+ "loss": 2.55,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.05968613326472858,
210
+ "grad_norm": 1.3388073444366455,
211
+ "learning_rate": 5.979381443298969e-06,
212
+ "loss": 2.5219,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.061744275791098535,
217
+ "grad_norm": 1.317008376121521,
218
+ "learning_rate": 6.185567010309279e-06,
219
+ "loss": 2.4491,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.06380241831746848,
224
+ "grad_norm": 1.3210794925689697,
225
+ "learning_rate": 6.391752577319588e-06,
226
+ "loss": 2.4358,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.06586056084383844,
231
+ "grad_norm": 1.182519555091858,
232
+ "learning_rate": 6.597938144329898e-06,
233
+ "loss": 2.4514,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.06791870337020839,
238
+ "grad_norm": 1.2238099575042725,
239
+ "learning_rate": 6.804123711340207e-06,
240
+ "loss": 2.442,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.06997684589657834,
245
+ "grad_norm": 1.1793314218521118,
246
+ "learning_rate": 7.010309278350515e-06,
247
+ "loss": 2.3864,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.0720349884229483,
252
+ "grad_norm": 1.1983020305633545,
253
+ "learning_rate": 7.216494845360825e-06,
254
+ "loss": 2.3796,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.07409313094931824,
259
+ "grad_norm": 1.2189652919769287,
260
+ "learning_rate": 7.422680412371135e-06,
261
+ "loss": 2.4152,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.07615127347568819,
266
+ "grad_norm": 1.14923095703125,
267
+ "learning_rate": 7.628865979381444e-06,
268
+ "loss": 2.3298,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.07820941600205815,
273
+ "grad_norm": 1.147013545036316,
274
+ "learning_rate": 7.835051546391754e-06,
275
+ "loss": 2.2488,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.0802675585284281,
280
+ "grad_norm": 1.133981466293335,
281
+ "learning_rate": 8.041237113402063e-06,
282
+ "loss": 2.1825,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.08232570105479804,
287
+ "grad_norm": 1.1686867475509644,
288
+ "learning_rate": 8.247422680412371e-06,
289
+ "loss": 2.2282,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.084383843581168,
294
+ "grad_norm": 1.131690502166748,
295
+ "learning_rate": 8.453608247422681e-06,
296
+ "loss": 2.0962,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.08644198610753795,
301
+ "grad_norm": 1.1626195907592773,
302
+ "learning_rate": 8.65979381443299e-06,
303
+ "loss": 2.1161,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.0885001286339079,
308
+ "grad_norm": 1.1508581638336182,
309
+ "learning_rate": 8.865979381443299e-06,
310
+ "loss": 1.9856,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.09055827116027786,
315
+ "grad_norm": 1.2286733388900757,
316
+ "learning_rate": 9.072164948453609e-06,
317
+ "loss": 2.076,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.0926164136866478,
322
+ "grad_norm": 1.82068932056427,
323
+ "learning_rate": 9.278350515463918e-06,
324
+ "loss": 1.9995,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.09467455621301775,
329
+ "grad_norm": 2.079101324081421,
330
+ "learning_rate": 9.484536082474226e-06,
331
+ "loss": 1.9601,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.0967326987393877,
336
+ "grad_norm": 1.1209226846694946,
337
+ "learning_rate": 9.690721649484536e-06,
338
+ "loss": 1.9346,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.09879084126575766,
343
+ "grad_norm": 1.0579711198806763,
344
+ "learning_rate": 9.896907216494846e-06,
345
+ "loss": 1.8764,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.1008489837921276,
350
+ "grad_norm": 1.0434011220932007,
351
+ "learning_rate": 1.0103092783505156e-05,
352
+ "loss": 1.8483,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.10290712631849755,
357
+ "grad_norm": 1.0089991092681885,
358
+ "learning_rate": 1.0309278350515464e-05,
359
+ "loss": 1.8018,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.10496526884486751,
364
+ "grad_norm": 1.0117324590682983,
365
+ "learning_rate": 1.0515463917525775e-05,
366
+ "loss": 1.8003,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.10702341137123746,
371
+ "grad_norm": 1.0006697177886963,
372
+ "learning_rate": 1.0721649484536083e-05,
373
+ "loss": 1.7482,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.1090815538976074,
378
+ "grad_norm": 2.1164329051971436,
379
+ "learning_rate": 1.0927835051546391e-05,
380
+ "loss": 1.7363,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.11113969642397736,
385
+ "grad_norm": 0.9573502540588379,
386
+ "learning_rate": 1.1134020618556703e-05,
387
+ "loss": 1.661,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.11319783895034731,
392
+ "grad_norm": 1.0059764385223389,
393
+ "learning_rate": 1.134020618556701e-05,
394
+ "loss": 1.6979,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.11525598147671726,
399
+ "grad_norm": 0.9719656109809875,
400
+ "learning_rate": 1.1546391752577319e-05,
401
+ "loss": 1.6318,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.11731412400308722,
406
+ "grad_norm": 1.0024539232254028,
407
+ "learning_rate": 1.175257731958763e-05,
408
+ "loss": 1.6283,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.11937226652945716,
413
+ "grad_norm": 0.9772456288337708,
414
+ "learning_rate": 1.1958762886597938e-05,
415
+ "loss": 1.5611,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.12143040905582711,
420
+ "grad_norm": 0.9947625994682312,
421
+ "learning_rate": 1.2164948453608248e-05,
422
+ "loss": 1.6073,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.12348855158219707,
427
+ "grad_norm": 2.112889051437378,
428
+ "learning_rate": 1.2371134020618558e-05,
429
+ "loss": 1.6208,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.12554669410856703,
434
+ "grad_norm": 1.0515345335006714,
435
+ "learning_rate": 1.2577319587628866e-05,
436
+ "loss": 1.569,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.12760483663493696,
441
+ "grad_norm": 1.0782145261764526,
442
+ "learning_rate": 1.2783505154639176e-05,
443
+ "loss": 1.5097,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.12966297916130692,
448
+ "grad_norm": 1.154104232788086,
449
+ "learning_rate": 1.2989690721649485e-05,
450
+ "loss": 1.5472,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.13172112168767688,
455
+ "grad_norm": 1.1614656448364258,
456
+ "learning_rate": 1.3195876288659795e-05,
457
+ "loss": 1.4833,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.13377926421404682,
462
+ "grad_norm": 1.1720911264419556,
463
+ "learning_rate": 1.3402061855670103e-05,
464
+ "loss": 1.4644,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.13583740674041678,
469
+ "grad_norm": 1.8903896808624268,
470
+ "learning_rate": 1.3608247422680415e-05,
471
+ "loss": 1.4286,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.13789554926678674,
476
+ "grad_norm": 1.2675013542175293,
477
+ "learning_rate": 1.3814432989690723e-05,
478
+ "loss": 1.416,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.13995369179315667,
483
+ "grad_norm": 1.266434907913208,
484
+ "learning_rate": 1.402061855670103e-05,
485
+ "loss": 1.3171,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.14201183431952663,
490
+ "grad_norm": 1.3408889770507812,
491
+ "learning_rate": 1.4226804123711342e-05,
492
+ "loss": 1.3396,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.1440699768458966,
497
+ "grad_norm": 1.3862446546554565,
498
+ "learning_rate": 1.443298969072165e-05,
499
+ "loss": 1.2642,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.14612811937226652,
504
+ "grad_norm": 2.110553026199341,
505
+ "learning_rate": 1.4639175257731958e-05,
506
+ "loss": 1.2593,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.14818626189863648,
511
+ "grad_norm": 1.7017499208450317,
512
+ "learning_rate": 1.484536082474227e-05,
513
+ "loss": 1.24,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.15024440442500644,
518
+ "grad_norm": 1.9851700067520142,
519
+ "learning_rate": 1.5051546391752578e-05,
520
+ "loss": 1.2313,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.15230254695137638,
525
+ "grad_norm": 2.009608030319214,
526
+ "learning_rate": 1.5257731958762888e-05,
527
+ "loss": 1.1281,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.15436068947774634,
532
+ "grad_norm": 2.7587485313415527,
533
+ "learning_rate": 1.5463917525773197e-05,
534
+ "loss": 1.1248,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.1564188320041163,
539
+ "grad_norm": 2.780954599380493,
540
+ "learning_rate": 1.5670103092783507e-05,
541
+ "loss": 1.0797,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.15847697453048623,
546
+ "grad_norm": 3.1470866203308105,
547
+ "learning_rate": 1.5876288659793813e-05,
548
+ "loss": 1.0064,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.1605351170568562,
553
+ "grad_norm": 4.653595447540283,
554
+ "learning_rate": 1.6082474226804127e-05,
555
+ "loss": 0.9219,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.16259325958322615,
560
+ "grad_norm": 4.157363414764404,
561
+ "learning_rate": 1.6288659793814433e-05,
562
+ "loss": 0.8709,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.16465140210959608,
567
+ "grad_norm": 4.5814924240112305,
568
+ "learning_rate": 1.6494845360824743e-05,
569
+ "loss": 0.7693,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.16670954463596604,
574
+ "grad_norm": 5.096139907836914,
575
+ "learning_rate": 1.6701030927835052e-05,
576
+ "loss": 0.6868,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.168767687162336,
581
+ "grad_norm": 4.858880519866943,
582
+ "learning_rate": 1.6907216494845362e-05,
583
+ "loss": 0.5971,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.17082582968870594,
588
+ "grad_norm": 4.42564582824707,
589
+ "learning_rate": 1.7113402061855672e-05,
590
+ "loss": 0.4719,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.1728839722150759,
595
+ "grad_norm": 7.720851421356201,
596
+ "learning_rate": 1.731958762886598e-05,
597
+ "loss": 0.3943,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.17494211474144586,
602
+ "grad_norm": 0.41923192143440247,
603
+ "learning_rate": 1.752577319587629e-05,
604
+ "loss": 0.3635,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.1770002572678158,
609
+ "grad_norm": 0.2771846354007721,
610
+ "learning_rate": 1.7731958762886598e-05,
611
+ "loss": 0.3597,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.17905839979418575,
616
+ "grad_norm": 0.24761857092380524,
617
+ "learning_rate": 1.793814432989691e-05,
618
+ "loss": 0.3735,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.1811165423205557,
623
+ "grad_norm": 0.23277048766613007,
624
+ "learning_rate": 1.8144329896907217e-05,
625
+ "loss": 0.3643,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.18317468484692565,
630
+ "grad_norm": 0.22931228578090668,
631
+ "learning_rate": 1.8350515463917527e-05,
632
+ "loss": 0.3519,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.1852328273732956,
637
+ "grad_norm": 0.20750615000724792,
638
+ "learning_rate": 1.8556701030927837e-05,
639
+ "loss": 0.3431,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.18729096989966554,
644
+ "grad_norm": 0.2080322951078415,
645
+ "learning_rate": 1.8762886597938147e-05,
646
+ "loss": 0.3632,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.1893491124260355,
651
+ "grad_norm": 0.20186181366443634,
652
+ "learning_rate": 1.8969072164948453e-05,
653
+ "loss": 0.3492,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.19140725495240546,
658
+ "grad_norm": 0.19172786176204681,
659
+ "learning_rate": 1.9175257731958766e-05,
660
+ "loss": 0.3552,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.1934653974787754,
665
+ "grad_norm": 0.1747850626707077,
666
+ "learning_rate": 1.9381443298969072e-05,
667
+ "loss": 0.3355,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.19552354000514535,
672
+ "grad_norm": 0.196411594748497,
673
+ "learning_rate": 1.9587628865979382e-05,
674
+ "loss": 0.3271,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.1975816825315153,
679
+ "grad_norm": 0.20063228905200958,
680
+ "learning_rate": 1.9793814432989692e-05,
681
+ "loss": 0.3351,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.19963982505788525,
686
+ "grad_norm": 0.19240939617156982,
687
+ "learning_rate": 2e-05,
688
+ "loss": 0.3266,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.2016979675842552,
693
+ "grad_norm": 0.18206572532653809,
694
+ "learning_rate": 1.997709049255441e-05,
695
+ "loss": 0.3393,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.20375611011062517,
700
+ "grad_norm": 0.20384562015533447,
701
+ "learning_rate": 1.9954180985108823e-05,
702
+ "loss": 0.3395,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.2058142526369951,
707
+ "grad_norm": 0.19944581389427185,
708
+ "learning_rate": 1.9931271477663232e-05,
709
+ "loss": 0.3268,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.2058142526369951,
714
+ "eval_loss": 0.3456890285015106,
715
+ "eval_runtime": 2114.0178,
716
+ "eval_samples_per_second": 3.677,
717
+ "eval_steps_per_second": 0.92,
718
+ "step": 100
719
+ },
720
+ {
721
+ "epoch": 0.20787239516336506,
722
+ "grad_norm": 0.17743557691574097,
723
+ "learning_rate": 1.990836197021764e-05,
724
+ "loss": 0.3439,
725
+ "step": 101
726
+ },
727
+ {
728
+ "epoch": 0.20993053768973502,
729
+ "grad_norm": 0.18746449053287506,
730
+ "learning_rate": 1.9885452462772053e-05,
731
+ "loss": 0.326,
732
+ "step": 102
733
+ },
734
+ {
735
+ "epoch": 0.21198868021610495,
736
+ "grad_norm": 0.18555815517902374,
737
+ "learning_rate": 1.9862542955326462e-05,
738
+ "loss": 0.3337,
739
+ "step": 103
740
+ },
741
+ {
742
+ "epoch": 0.2140468227424749,
743
+ "grad_norm": 0.16591575741767883,
744
+ "learning_rate": 1.9839633447880874e-05,
745
+ "loss": 0.3121,
746
+ "step": 104
747
+ },
748
+ {
749
+ "epoch": 0.21610496526884487,
750
+ "grad_norm": 0.1621987372636795,
751
+ "learning_rate": 1.9816723940435283e-05,
752
+ "loss": 0.3287,
753
+ "step": 105
754
+ },
755
+ {
756
+ "epoch": 0.2181631077952148,
757
+ "grad_norm": 0.1614532470703125,
758
+ "learning_rate": 1.9793814432989692e-05,
759
+ "loss": 0.3306,
760
+ "step": 106
761
+ },
762
+ {
763
+ "epoch": 0.22022125032158477,
764
+ "grad_norm": 0.17993387579917908,
765
+ "learning_rate": 1.9770904925544104e-05,
766
+ "loss": 0.3341,
767
+ "step": 107
768
+ },
769
+ {
770
+ "epoch": 0.22227939284795473,
771
+ "grad_norm": 0.1550011783838272,
772
+ "learning_rate": 1.9747995418098513e-05,
773
+ "loss": 0.3197,
774
+ "step": 108
775
+ },
776
+ {
777
+ "epoch": 0.22433753537432466,
778
+ "grad_norm": 0.18471524119377136,
779
+ "learning_rate": 1.9725085910652922e-05,
780
+ "loss": 0.3285,
781
+ "step": 109
782
+ },
783
+ {
784
+ "epoch": 0.22639567790069462,
785
+ "grad_norm": 0.15604373812675476,
786
+ "learning_rate": 1.9702176403207334e-05,
787
+ "loss": 0.3298,
788
+ "step": 110
789
+ },
790
+ {
791
+ "epoch": 0.22845382042706458,
792
+ "grad_norm": 0.1682298630475998,
793
+ "learning_rate": 1.9679266895761743e-05,
794
+ "loss": 0.3343,
795
+ "step": 111
796
+ },
797
+ {
798
+ "epoch": 0.2305119629534345,
799
+ "grad_norm": 0.14933635294437408,
800
+ "learning_rate": 1.9656357388316152e-05,
801
+ "loss": 0.3134,
802
+ "step": 112
803
+ },
804
+ {
805
+ "epoch": 0.23257010547980447,
806
+ "grad_norm": 0.14892347157001495,
807
+ "learning_rate": 1.963344788087056e-05,
808
+ "loss": 0.3154,
809
+ "step": 113
810
+ },
811
+ {
812
+ "epoch": 0.23462824800617443,
813
+ "grad_norm": 0.1577889323234558,
814
+ "learning_rate": 1.9610538373424973e-05,
815
+ "loss": 0.3122,
816
+ "step": 114
817
+ },
818
+ {
819
+ "epoch": 0.23668639053254437,
820
+ "grad_norm": 0.16482344269752502,
821
+ "learning_rate": 1.9587628865979382e-05,
822
+ "loss": 0.3193,
823
+ "step": 115
824
+ },
825
+ {
826
+ "epoch": 0.23874453305891433,
827
+ "grad_norm": 0.15328913927078247,
828
+ "learning_rate": 1.956471935853379e-05,
829
+ "loss": 0.3217,
830
+ "step": 116
831
+ },
832
+ {
833
+ "epoch": 0.2408026755852843,
834
+ "grad_norm": 0.16140656173229218,
835
+ "learning_rate": 1.9541809851088203e-05,
836
+ "loss": 0.318,
837
+ "step": 117
838
+ },
839
+ {
840
+ "epoch": 0.24286081811165422,
841
+ "grad_norm": 0.15448373556137085,
842
+ "learning_rate": 1.9518900343642612e-05,
843
+ "loss": 0.3205,
844
+ "step": 118
845
+ },
846
+ {
847
+ "epoch": 0.24491896063802418,
848
+ "grad_norm": 0.14716887474060059,
849
+ "learning_rate": 1.9495990836197025e-05,
850
+ "loss": 0.3164,
851
+ "step": 119
852
+ },
853
+ {
854
+ "epoch": 0.24697710316439414,
855
+ "grad_norm": 0.16582027077674866,
856
+ "learning_rate": 1.9473081328751433e-05,
857
+ "loss": 0.3191,
858
+ "step": 120
859
+ },
860
+ {
861
+ "epoch": 0.24903524569076407,
862
+ "grad_norm": 0.15213699638843536,
863
+ "learning_rate": 1.9450171821305842e-05,
864
+ "loss": 0.304,
865
+ "step": 121
866
+ },
867
+ {
868
+ "epoch": 0.25109338821713406,
869
+ "grad_norm": 0.1659238487482071,
870
+ "learning_rate": 1.9427262313860255e-05,
871
+ "loss": 0.3184,
872
+ "step": 122
873
+ },
874
+ {
875
+ "epoch": 0.253151530743504,
876
+ "grad_norm": 0.15596656501293182,
877
+ "learning_rate": 1.9404352806414663e-05,
878
+ "loss": 0.3092,
879
+ "step": 123
880
+ },
881
+ {
882
+ "epoch": 0.2552096732698739,
883
+ "grad_norm": 0.15868476033210754,
884
+ "learning_rate": 1.9381443298969072e-05,
885
+ "loss": 0.3163,
886
+ "step": 124
887
+ },
888
+ {
889
+ "epoch": 0.2572678157962439,
890
+ "grad_norm": 0.15386095643043518,
891
+ "learning_rate": 1.9358533791523485e-05,
892
+ "loss": 0.3049,
893
+ "step": 125
894
+ },
895
+ {
896
+ "epoch": 0.25932595832261385,
897
+ "grad_norm": 0.15179213881492615,
898
+ "learning_rate": 1.9335624284077894e-05,
899
+ "loss": 0.3131,
900
+ "step": 126
901
+ },
902
+ {
903
+ "epoch": 0.2613841008489838,
904
+ "grad_norm": 0.1595134735107422,
905
+ "learning_rate": 1.9312714776632306e-05,
906
+ "loss": 0.3069,
907
+ "step": 127
908
+ },
909
+ {
910
+ "epoch": 0.26344224337535377,
911
+ "grad_norm": 0.16989803314208984,
912
+ "learning_rate": 1.9289805269186715e-05,
913
+ "loss": 0.3052,
914
+ "step": 128
915
+ },
916
+ {
917
+ "epoch": 0.2655003859017237,
918
+ "grad_norm": 0.14803892374038696,
919
+ "learning_rate": 1.9266895761741124e-05,
920
+ "loss": 0.3065,
921
+ "step": 129
922
+ },
923
+ {
924
+ "epoch": 0.26755852842809363,
925
+ "grad_norm": 0.16676583886146545,
926
+ "learning_rate": 1.9243986254295536e-05,
927
+ "loss": 0.2962,
928
+ "step": 130
929
+ },
930
+ {
931
+ "epoch": 0.2696166709544636,
932
+ "grad_norm": 0.15694552659988403,
933
+ "learning_rate": 1.9221076746849945e-05,
934
+ "loss": 0.3096,
935
+ "step": 131
936
+ },
937
+ {
938
+ "epoch": 0.27167481348083355,
939
+ "grad_norm": 0.17696696519851685,
940
+ "learning_rate": 1.9198167239404354e-05,
941
+ "loss": 0.3145,
942
+ "step": 132
943
+ },
944
+ {
945
+ "epoch": 0.2737329560072035,
946
+ "grad_norm": 0.17204038798809052,
947
+ "learning_rate": 1.9175257731958766e-05,
948
+ "loss": 0.3248,
949
+ "step": 133
950
+ },
951
+ {
952
+ "epoch": 0.2757910985335735,
953
+ "grad_norm": 0.15630359947681427,
954
+ "learning_rate": 1.9152348224513175e-05,
955
+ "loss": 0.3117,
956
+ "step": 134
957
+ },
958
+ {
959
+ "epoch": 0.2778492410599434,
960
+ "grad_norm": 0.15757997334003448,
961
+ "learning_rate": 1.9129438717067584e-05,
962
+ "loss": 0.3145,
963
+ "step": 135
964
+ },
965
+ {
966
+ "epoch": 0.27990738358631334,
967
+ "grad_norm": 0.16273653507232666,
968
+ "learning_rate": 1.9106529209621996e-05,
969
+ "loss": 0.3159,
970
+ "step": 136
971
+ },
972
+ {
973
+ "epoch": 0.28196552611268333,
974
+ "grad_norm": 0.16213104128837585,
975
+ "learning_rate": 1.9083619702176405e-05,
976
+ "loss": 0.2949,
977
+ "step": 137
978
+ },
979
+ {
980
+ "epoch": 0.28402366863905326,
981
+ "grad_norm": 0.15377865731716156,
982
+ "learning_rate": 1.9060710194730814e-05,
983
+ "loss": 0.306,
984
+ "step": 138
985
+ },
986
+ {
987
+ "epoch": 0.2860818111654232,
988
+ "grad_norm": 0.1545962244272232,
989
+ "learning_rate": 1.9037800687285223e-05,
990
+ "loss": 0.2966,
991
+ "step": 139
992
+ },
993
+ {
994
+ "epoch": 0.2881399536917932,
995
+ "grad_norm": 0.15516617894172668,
996
+ "learning_rate": 1.9014891179839635e-05,
997
+ "loss": 0.3122,
998
+ "step": 140
999
+ },
1000
+ {
1001
+ "epoch": 0.2901980962181631,
1002
+ "grad_norm": 0.14734458923339844,
1003
+ "learning_rate": 1.8991981672394044e-05,
1004
+ "loss": 0.3118,
1005
+ "step": 141
1006
+ },
1007
+ {
1008
+ "epoch": 0.29225623874453305,
1009
+ "grad_norm": 0.1644304096698761,
1010
+ "learning_rate": 1.8969072164948453e-05,
1011
+ "loss": 0.3027,
1012
+ "step": 142
1013
+ },
1014
+ {
1015
+ "epoch": 0.29431438127090304,
1016
+ "grad_norm": 0.14632569253444672,
1017
+ "learning_rate": 1.8946162657502865e-05,
1018
+ "loss": 0.3023,
1019
+ "step": 143
1020
+ },
1021
+ {
1022
+ "epoch": 0.29637252379727297,
1023
+ "grad_norm": 0.1573137789964676,
1024
+ "learning_rate": 1.8923253150057274e-05,
1025
+ "loss": 0.3102,
1026
+ "step": 144
1027
+ },
1028
+ {
1029
+ "epoch": 0.2984306663236429,
1030
+ "grad_norm": 0.16423144936561584,
1031
+ "learning_rate": 1.8900343642611686e-05,
1032
+ "loss": 0.3033,
1033
+ "step": 145
1034
+ },
1035
+ {
1036
+ "epoch": 0.3004888088500129,
1037
+ "grad_norm": 0.15420907735824585,
1038
+ "learning_rate": 1.8877434135166095e-05,
1039
+ "loss": 0.3089,
1040
+ "step": 146
1041
+ },
1042
+ {
1043
+ "epoch": 0.3025469513763828,
1044
+ "grad_norm": 0.1579178273677826,
1045
+ "learning_rate": 1.8854524627720504e-05,
1046
+ "loss": 0.3071,
1047
+ "step": 147
1048
+ },
1049
+ {
1050
+ "epoch": 0.30460509390275275,
1051
+ "grad_norm": 0.15866397321224213,
1052
+ "learning_rate": 1.8831615120274916e-05,
1053
+ "loss": 0.3083,
1054
+ "step": 148
1055
+ },
1056
+ {
1057
+ "epoch": 0.30666323642912274,
1058
+ "grad_norm": 0.16651487350463867,
1059
+ "learning_rate": 1.8808705612829325e-05,
1060
+ "loss": 0.3099,
1061
+ "step": 149
1062
+ },
1063
+ {
1064
+ "epoch": 0.3087213789554927,
1065
+ "grad_norm": 0.16281908750534058,
1066
+ "learning_rate": 1.8785796105383734e-05,
1067
+ "loss": 0.3034,
1068
+ "step": 150
1069
+ },
1070
+ {
1071
+ "epoch": 0.3107795214818626,
1072
+ "grad_norm": 0.17449837923049927,
1073
+ "learning_rate": 1.8762886597938147e-05,
1074
+ "loss": 0.3054,
1075
+ "step": 151
1076
+ },
1077
+ {
1078
+ "epoch": 0.3128376640082326,
1079
+ "grad_norm": 0.15403546392917633,
1080
+ "learning_rate": 1.8739977090492555e-05,
1081
+ "loss": 0.297,
1082
+ "step": 152
1083
+ },
1084
+ {
1085
+ "epoch": 0.31489580653460253,
1086
+ "grad_norm": 0.1472466140985489,
1087
+ "learning_rate": 1.8717067583046968e-05,
1088
+ "loss": 0.2973,
1089
+ "step": 153
1090
+ },
1091
+ {
1092
+ "epoch": 0.31695394906097246,
1093
+ "grad_norm": 0.16027937829494476,
1094
+ "learning_rate": 1.8694158075601377e-05,
1095
+ "loss": 0.3054,
1096
+ "step": 154
1097
+ },
1098
+ {
1099
+ "epoch": 0.31901209158734245,
1100
+ "grad_norm": 0.17086225748062134,
1101
+ "learning_rate": 1.8671248568155786e-05,
1102
+ "loss": 0.307,
1103
+ "step": 155
1104
+ },
1105
+ {
1106
+ "epoch": 0.3210702341137124,
1107
+ "grad_norm": 0.15930697321891785,
1108
+ "learning_rate": 1.8648339060710198e-05,
1109
+ "loss": 0.293,
1110
+ "step": 156
1111
+ },
1112
+ {
1113
+ "epoch": 0.3231283766400823,
1114
+ "grad_norm": 0.17086376249790192,
1115
+ "learning_rate": 1.8625429553264607e-05,
1116
+ "loss": 0.293,
1117
+ "step": 157
1118
+ },
1119
+ {
1120
+ "epoch": 0.3251865191664523,
1121
+ "grad_norm": 0.15970875322818756,
1122
+ "learning_rate": 1.8602520045819016e-05,
1123
+ "loss": 0.3083,
1124
+ "step": 158
1125
+ },
1126
+ {
1127
+ "epoch": 0.32724466169282224,
1128
+ "grad_norm": 0.16355909407138824,
1129
+ "learning_rate": 1.8579610538373428e-05,
1130
+ "loss": 0.3139,
1131
+ "step": 159
1132
+ },
1133
+ {
1134
+ "epoch": 0.32930280421919217,
1135
+ "grad_norm": 0.15183711051940918,
1136
+ "learning_rate": 1.8556701030927837e-05,
1137
+ "loss": 0.2953,
1138
+ "step": 160
1139
+ },
1140
+ {
1141
+ "epoch": 0.33136094674556216,
1142
+ "grad_norm": 0.15123715996742249,
1143
+ "learning_rate": 1.853379152348225e-05,
1144
+ "loss": 0.3025,
1145
+ "step": 161
1146
+ },
1147
+ {
1148
+ "epoch": 0.3334190892719321,
1149
+ "grad_norm": 0.1576143503189087,
1150
+ "learning_rate": 1.8510882016036658e-05,
1151
+ "loss": 0.2904,
1152
+ "step": 162
1153
+ },
1154
+ {
1155
+ "epoch": 0.335477231798302,
1156
+ "grad_norm": 0.1457504779100418,
1157
+ "learning_rate": 1.8487972508591067e-05,
1158
+ "loss": 0.2909,
1159
+ "step": 163
1160
+ },
1161
+ {
1162
+ "epoch": 0.337535374324672,
1163
+ "grad_norm": 0.1557442992925644,
1164
+ "learning_rate": 1.846506300114548e-05,
1165
+ "loss": 0.3027,
1166
+ "step": 164
1167
+ },
1168
+ {
1169
+ "epoch": 0.33959351685104194,
1170
+ "grad_norm": 0.15662318468093872,
1171
+ "learning_rate": 1.8442153493699888e-05,
1172
+ "loss": 0.311,
1173
+ "step": 165
1174
+ },
1175
+ {
1176
+ "epoch": 0.3416516593774119,
1177
+ "grad_norm": 0.16177058219909668,
1178
+ "learning_rate": 1.8419243986254297e-05,
1179
+ "loss": 0.2944,
1180
+ "step": 166
1181
+ },
1182
+ {
1183
+ "epoch": 0.34370980190378186,
1184
+ "grad_norm": 0.16406729817390442,
1185
+ "learning_rate": 1.8396334478808706e-05,
1186
+ "loss": 0.2927,
1187
+ "step": 167
1188
+ },
1189
+ {
1190
+ "epoch": 0.3457679444301518,
1191
+ "grad_norm": 0.16642791032791138,
1192
+ "learning_rate": 1.8373424971363115e-05,
1193
+ "loss": 0.3063,
1194
+ "step": 168
1195
+ },
1196
+ {
1197
+ "epoch": 0.34782608695652173,
1198
+ "grad_norm": 0.1650693714618683,
1199
+ "learning_rate": 1.8350515463917527e-05,
1200
+ "loss": 0.2957,
1201
+ "step": 169
1202
+ },
1203
+ {
1204
+ "epoch": 0.3498842294828917,
1205
+ "grad_norm": 0.15349675714969635,
1206
+ "learning_rate": 1.8327605956471936e-05,
1207
+ "loss": 0.297,
1208
+ "step": 170
1209
+ },
1210
+ {
1211
+ "epoch": 0.35194237200926165,
1212
+ "grad_norm": 0.17770209908485413,
1213
+ "learning_rate": 1.8304696449026348e-05,
1214
+ "loss": 0.3011,
1215
+ "step": 171
1216
+ },
1217
+ {
1218
+ "epoch": 0.3540005145356316,
1219
+ "grad_norm": 0.1647631675004959,
1220
+ "learning_rate": 1.8281786941580757e-05,
1221
+ "loss": 0.2962,
1222
+ "step": 172
1223
+ },
1224
+ {
1225
+ "epoch": 0.35605865706200157,
1226
+ "grad_norm": 0.1603834480047226,
1227
+ "learning_rate": 1.8258877434135166e-05,
1228
+ "loss": 0.2937,
1229
+ "step": 173
1230
+ },
1231
+ {
1232
+ "epoch": 0.3581167995883715,
1233
+ "grad_norm": 0.16780880093574524,
1234
+ "learning_rate": 1.8235967926689578e-05,
1235
+ "loss": 0.2997,
1236
+ "step": 174
1237
+ },
1238
+ {
1239
+ "epoch": 0.36017494211474144,
1240
+ "grad_norm": 0.15976767241954803,
1241
+ "learning_rate": 1.8213058419243987e-05,
1242
+ "loss": 0.3043,
1243
+ "step": 175
1244
+ },
1245
+ {
1246
+ "epoch": 0.3622330846411114,
1247
+ "grad_norm": 0.16236485540866852,
1248
+ "learning_rate": 1.8190148911798396e-05,
1249
+ "loss": 0.3069,
1250
+ "step": 176
1251
+ },
1252
+ {
1253
+ "epoch": 0.36429122716748136,
1254
+ "grad_norm": 0.16391968727111816,
1255
+ "learning_rate": 1.816723940435281e-05,
1256
+ "loss": 0.2923,
1257
+ "step": 177
1258
+ },
1259
+ {
1260
+ "epoch": 0.3663493696938513,
1261
+ "grad_norm": 0.15806889533996582,
1262
+ "learning_rate": 1.8144329896907217e-05,
1263
+ "loss": 0.2872,
1264
+ "step": 178
1265
+ },
1266
+ {
1267
+ "epoch": 0.3684075122202212,
1268
+ "grad_norm": 0.1627352088689804,
1269
+ "learning_rate": 1.812142038946163e-05,
1270
+ "loss": 0.3032,
1271
+ "step": 179
1272
+ },
1273
+ {
1274
+ "epoch": 0.3704656547465912,
1275
+ "grad_norm": 0.15103371441364288,
1276
+ "learning_rate": 1.809851088201604e-05,
1277
+ "loss": 0.2847,
1278
+ "step": 180
1279
+ },
1280
+ {
1281
+ "epoch": 0.37252379727296114,
1282
+ "grad_norm": 0.15178488194942474,
1283
+ "learning_rate": 1.8075601374570447e-05,
1284
+ "loss": 0.3017,
1285
+ "step": 181
1286
+ },
1287
+ {
1288
+ "epoch": 0.3745819397993311,
1289
+ "grad_norm": 0.15493899583816528,
1290
+ "learning_rate": 1.805269186712486e-05,
1291
+ "loss": 0.2901,
1292
+ "step": 182
1293
+ },
1294
+ {
1295
+ "epoch": 0.37664008232570106,
1296
+ "grad_norm": 0.15990686416625977,
1297
+ "learning_rate": 1.802978235967927e-05,
1298
+ "loss": 0.2861,
1299
+ "step": 183
1300
+ },
1301
+ {
1302
+ "epoch": 0.378698224852071,
1303
+ "grad_norm": 0.15824148058891296,
1304
+ "learning_rate": 1.8006872852233677e-05,
1305
+ "loss": 0.2885,
1306
+ "step": 184
1307
+ },
1308
+ {
1309
+ "epoch": 0.38075636737844093,
1310
+ "grad_norm": 0.15690775215625763,
1311
+ "learning_rate": 1.798396334478809e-05,
1312
+ "loss": 0.2814,
1313
+ "step": 185
1314
+ },
1315
+ {
1316
+ "epoch": 0.3828145099048109,
1317
+ "grad_norm": 0.15833796560764313,
1318
+ "learning_rate": 1.79610538373425e-05,
1319
+ "loss": 0.2847,
1320
+ "step": 186
1321
+ },
1322
+ {
1323
+ "epoch": 0.38487265243118085,
1324
+ "grad_norm": 0.16560044884681702,
1325
+ "learning_rate": 1.793814432989691e-05,
1326
+ "loss": 0.3061,
1327
+ "step": 187
1328
+ },
1329
+ {
1330
+ "epoch": 0.3869307949575508,
1331
+ "grad_norm": 0.16240179538726807,
1332
+ "learning_rate": 1.791523482245132e-05,
1333
+ "loss": 0.2943,
1334
+ "step": 188
1335
+ },
1336
+ {
1337
+ "epoch": 0.38898893748392077,
1338
+ "grad_norm": 0.15825721621513367,
1339
+ "learning_rate": 1.789232531500573e-05,
1340
+ "loss": 0.2934,
1341
+ "step": 189
1342
+ },
1343
+ {
1344
+ "epoch": 0.3910470800102907,
1345
+ "grad_norm": 0.16665388643741608,
1346
+ "learning_rate": 1.786941580756014e-05,
1347
+ "loss": 0.291,
1348
+ "step": 190
1349
+ },
1350
+ {
1351
+ "epoch": 0.39310522253666064,
1352
+ "grad_norm": 0.16581200063228607,
1353
+ "learning_rate": 1.784650630011455e-05,
1354
+ "loss": 0.2849,
1355
+ "step": 191
1356
+ },
1357
+ {
1358
+ "epoch": 0.3951633650630306,
1359
+ "grad_norm": 0.1604345291852951,
1360
+ "learning_rate": 1.782359679266896e-05,
1361
+ "loss": 0.3,
1362
+ "step": 192
1363
+ },
1364
+ {
1365
+ "epoch": 0.39722150758940056,
1366
+ "grad_norm": 0.16107915341854095,
1367
+ "learning_rate": 1.7800687285223368e-05,
1368
+ "loss": 0.2847,
1369
+ "step": 193
1370
+ },
1371
+ {
1372
+ "epoch": 0.3992796501157705,
1373
+ "grad_norm": 0.1571730375289917,
1374
+ "learning_rate": 1.7777777777777777e-05,
1375
+ "loss": 0.2863,
1376
+ "step": 194
1377
+ },
1378
+ {
1379
+ "epoch": 0.4013377926421405,
1380
+ "grad_norm": 0.1656399518251419,
1381
+ "learning_rate": 1.775486827033219e-05,
1382
+ "loss": 0.2878,
1383
+ "step": 195
1384
+ },
1385
+ {
1386
+ "epoch": 0.4033959351685104,
1387
+ "grad_norm": 0.16738460958003998,
1388
+ "learning_rate": 1.7731958762886598e-05,
1389
+ "loss": 0.286,
1390
+ "step": 196
1391
+ },
1392
+ {
1393
+ "epoch": 0.40545407769488034,
1394
+ "grad_norm": 0.16704292595386505,
1395
+ "learning_rate": 1.770904925544101e-05,
1396
+ "loss": 0.2919,
1397
+ "step": 197
1398
+ },
1399
+ {
1400
+ "epoch": 0.40751222022125033,
1401
+ "grad_norm": 0.16215579211711884,
1402
+ "learning_rate": 1.768613974799542e-05,
1403
+ "loss": 0.2874,
1404
+ "step": 198
1405
+ },
1406
+ {
1407
+ "epoch": 0.40957036274762026,
1408
+ "grad_norm": 0.15573479235172272,
1409
+ "learning_rate": 1.7663230240549828e-05,
1410
+ "loss": 0.2904,
1411
+ "step": 199
1412
+ },
1413
+ {
1414
+ "epoch": 0.4116285052739902,
1415
+ "grad_norm": 0.1707623153924942,
1416
+ "learning_rate": 1.764032073310424e-05,
1417
+ "loss": 0.289,
1418
+ "step": 200
1419
+ },
1420
+ {
1421
+ "epoch": 0.4116285052739902,
1422
+ "eval_loss": 0.3214050829410553,
1423
+ "eval_runtime": 2449.7742,
1424
+ "eval_samples_per_second": 3.173,
1425
+ "eval_steps_per_second": 0.794,
1426
+ "step": 200
1427
+ }
1428
+ ],
1429
+ "logging_steps": 1,
1430
+ "max_steps": 970,
1431
+ "num_input_tokens_seen": 0,
1432
+ "num_train_epochs": 2,
1433
+ "save_steps": 100,
1434
+ "stateful_callbacks": {
1435
+ "TrainerControl": {
1436
+ "args": {
1437
+ "should_epoch_stop": false,
1438
+ "should_evaluate": false,
1439
+ "should_log": false,
1440
+ "should_save": true,
1441
+ "should_training_stop": false
1442
+ },
1443
+ "attributes": {}
1444
+ }
1445
+ },
1446
+ "total_flos": 6.615055995939963e+17,
1447
+ "train_batch_size": 4,
1448
+ "trial_name": null,
1449
+ "trial_params": null
1450
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee55a11f5a306eb7c39b536fdfe2459bc279e468da50f6adda478c4deffcb812
3
+ size 5688
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/codegemma-7b-it
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 0.15.0
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/codegemma-7b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4904f256bc0d01bcdb1e0e13e3ffde750efe2e272e6acbcc661481ab3b7afccd
3
+ size 800116456
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65cc37f7b35b81a9c19fbda436234ae27b3e7ffe674a3420cf814c7f38a722b
3
+ size 406743860
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36f846e18f654c3cfee105cea70c9e74df15bfcb4fc79f4b82ed01c58b83ae3
3
+ size 14244
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c92157e090687c4e3d6cd57a32a0d42e6f559fd56b8e5771861e40841b6ea7c3
3
+ size 1064
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d964a2c8346d40f95791533eae48730d5f163c2e65fd16333560fd3e661df318
3
+ size 34362915
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583f2ebd2a1936009b7da991ea255504db68c7a9713a78673d1335a87098966c
3
+ size 4241023
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,2011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<|fim_prefix|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<|fim_middle|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<|fim_suffix|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<|file_separator|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": false
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": false
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "bos_token": "<bos>",
1999
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
2000
+ "clean_up_tokenization_spaces": false,
2001
+ "eos_token": "<eos>",
2002
+ "extra_special_tokens": {},
2003
+ "model_max_length": 1000000000000000019884624838656,
2004
+ "pad_token": "<pad>",
2005
+ "padding_side": "left",
2006
+ "sp_model_kwargs": {},
2007
+ "spaces_between_special_tokens": false,
2008
+ "tokenizer_class": "GemmaTokenizer",
2009
+ "unk_token": "<unk>",
2010
+ "use_default_system_prompt": false
2011
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,2158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.6174427579109854,
6
+ "eval_steps": 100,
7
+ "global_step": 300,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0020581425263699513,
14
+ "grad_norm": 11.994463920593262,
15
+ "learning_rate": 2.061855670103093e-07,
16
+ "loss": 2.91,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.004116285052739903,
21
+ "grad_norm": 11.769092559814453,
22
+ "learning_rate": 4.123711340206186e-07,
23
+ "loss": 2.8686,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0061744275791098535,
28
+ "grad_norm": 13.05551815032959,
29
+ "learning_rate": 6.185567010309279e-07,
30
+ "loss": 3.0286,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.008232570105479805,
35
+ "grad_norm": 12.334521293640137,
36
+ "learning_rate": 8.247422680412372e-07,
37
+ "loss": 2.904,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.010290712631849755,
42
+ "grad_norm": 12.075353622436523,
43
+ "learning_rate": 1.0309278350515464e-06,
44
+ "loss": 2.8991,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.012348855158219707,
49
+ "grad_norm": 11.86032485961914,
50
+ "learning_rate": 1.2371134020618557e-06,
51
+ "loss": 3.0007,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.014406997684589657,
56
+ "grad_norm": 10.10457992553711,
57
+ "learning_rate": 1.4432989690721649e-06,
58
+ "loss": 2.8493,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.01646514021095961,
63
+ "grad_norm": 8.56408405303955,
64
+ "learning_rate": 1.6494845360824744e-06,
65
+ "loss": 2.9573,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.01852328273732956,
70
+ "grad_norm": 6.307392120361328,
71
+ "learning_rate": 1.8556701030927837e-06,
72
+ "loss": 2.9507,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.02058142526369951,
77
+ "grad_norm": 4.276430130004883,
78
+ "learning_rate": 2.061855670103093e-06,
79
+ "loss": 2.8988,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.022639567790069464,
84
+ "grad_norm": 2.5912015438079834,
85
+ "learning_rate": 2.268041237113402e-06,
86
+ "loss": 2.9926,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.024697710316439414,
91
+ "grad_norm": 2.018446207046509,
92
+ "learning_rate": 2.4742268041237115e-06,
93
+ "loss": 2.9874,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.026755852842809364,
98
+ "grad_norm": 1.8558588027954102,
99
+ "learning_rate": 2.680412371134021e-06,
100
+ "loss": 2.8608,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.028813995369179314,
105
+ "grad_norm": 1.9658265113830566,
106
+ "learning_rate": 2.8865979381443297e-06,
107
+ "loss": 2.8596,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.030872137895549268,
112
+ "grad_norm": 1.872044563293457,
113
+ "learning_rate": 3.0927835051546395e-06,
114
+ "loss": 2.8836,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.03293028042191922,
119
+ "grad_norm": 1.8884096145629883,
120
+ "learning_rate": 3.298969072164949e-06,
121
+ "loss": 2.9383,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.03498842294828917,
126
+ "grad_norm": 1.8795744180679321,
127
+ "learning_rate": 3.5051546391752577e-06,
128
+ "loss": 2.883,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.03704656547465912,
133
+ "grad_norm": 1.783678412437439,
134
+ "learning_rate": 3.7113402061855674e-06,
135
+ "loss": 2.8019,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.039104708001029075,
140
+ "grad_norm": 1.820617914199829,
141
+ "learning_rate": 3.917525773195877e-06,
142
+ "loss": 2.8813,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.04116285052739902,
147
+ "grad_norm": 1.8188731670379639,
148
+ "learning_rate": 4.123711340206186e-06,
149
+ "loss": 2.8401,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.043220993053768975,
154
+ "grad_norm": 1.7305251359939575,
155
+ "learning_rate": 4.329896907216495e-06,
156
+ "loss": 2.7478,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.04527913558013893,
161
+ "grad_norm": 1.7014551162719727,
162
+ "learning_rate": 4.536082474226804e-06,
163
+ "loss": 2.7356,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.047337278106508875,
168
+ "grad_norm": 1.677381157875061,
169
+ "learning_rate": 4.742268041237113e-06,
170
+ "loss": 2.7593,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.04939542063287883,
175
+ "grad_norm": 1.628554344177246,
176
+ "learning_rate": 4.948453608247423e-06,
177
+ "loss": 2.7689,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.051453563159248775,
182
+ "grad_norm": 1.4968128204345703,
183
+ "learning_rate": 5.154639175257732e-06,
184
+ "loss": 2.6613,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.05351170568561873,
189
+ "grad_norm": 1.4734832048416138,
190
+ "learning_rate": 5.360824742268042e-06,
191
+ "loss": 2.7095,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.05556984821198868,
196
+ "grad_norm": 1.3745571374893188,
197
+ "learning_rate": 5.567010309278351e-06,
198
+ "loss": 2.655,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.05762799073835863,
203
+ "grad_norm": 1.3381729125976562,
204
+ "learning_rate": 5.7731958762886594e-06,
205
+ "loss": 2.55,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.05968613326472858,
210
+ "grad_norm": 1.3388073444366455,
211
+ "learning_rate": 5.979381443298969e-06,
212
+ "loss": 2.5219,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.061744275791098535,
217
+ "grad_norm": 1.317008376121521,
218
+ "learning_rate": 6.185567010309279e-06,
219
+ "loss": 2.4491,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.06380241831746848,
224
+ "grad_norm": 1.3210794925689697,
225
+ "learning_rate": 6.391752577319588e-06,
226
+ "loss": 2.4358,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.06586056084383844,
231
+ "grad_norm": 1.182519555091858,
232
+ "learning_rate": 6.597938144329898e-06,
233
+ "loss": 2.4514,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.06791870337020839,
238
+ "grad_norm": 1.2238099575042725,
239
+ "learning_rate": 6.804123711340207e-06,
240
+ "loss": 2.442,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.06997684589657834,
245
+ "grad_norm": 1.1793314218521118,
246
+ "learning_rate": 7.010309278350515e-06,
247
+ "loss": 2.3864,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.0720349884229483,
252
+ "grad_norm": 1.1983020305633545,
253
+ "learning_rate": 7.216494845360825e-06,
254
+ "loss": 2.3796,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.07409313094931824,
259
+ "grad_norm": 1.2189652919769287,
260
+ "learning_rate": 7.422680412371135e-06,
261
+ "loss": 2.4152,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.07615127347568819,
266
+ "grad_norm": 1.14923095703125,
267
+ "learning_rate": 7.628865979381444e-06,
268
+ "loss": 2.3298,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.07820941600205815,
273
+ "grad_norm": 1.147013545036316,
274
+ "learning_rate": 7.835051546391754e-06,
275
+ "loss": 2.2488,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.0802675585284281,
280
+ "grad_norm": 1.133981466293335,
281
+ "learning_rate": 8.041237113402063e-06,
282
+ "loss": 2.1825,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.08232570105479804,
287
+ "grad_norm": 1.1686867475509644,
288
+ "learning_rate": 8.247422680412371e-06,
289
+ "loss": 2.2282,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.084383843581168,
294
+ "grad_norm": 1.131690502166748,
295
+ "learning_rate": 8.453608247422681e-06,
296
+ "loss": 2.0962,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.08644198610753795,
301
+ "grad_norm": 1.1626195907592773,
302
+ "learning_rate": 8.65979381443299e-06,
303
+ "loss": 2.1161,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.0885001286339079,
308
+ "grad_norm": 1.1508581638336182,
309
+ "learning_rate": 8.865979381443299e-06,
310
+ "loss": 1.9856,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.09055827116027786,
315
+ "grad_norm": 1.2286733388900757,
316
+ "learning_rate": 9.072164948453609e-06,
317
+ "loss": 2.076,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.0926164136866478,
322
+ "grad_norm": 1.82068932056427,
323
+ "learning_rate": 9.278350515463918e-06,
324
+ "loss": 1.9995,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.09467455621301775,
329
+ "grad_norm": 2.079101324081421,
330
+ "learning_rate": 9.484536082474226e-06,
331
+ "loss": 1.9601,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.0967326987393877,
336
+ "grad_norm": 1.1209226846694946,
337
+ "learning_rate": 9.690721649484536e-06,
338
+ "loss": 1.9346,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.09879084126575766,
343
+ "grad_norm": 1.0579711198806763,
344
+ "learning_rate": 9.896907216494846e-06,
345
+ "loss": 1.8764,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.1008489837921276,
350
+ "grad_norm": 1.0434011220932007,
351
+ "learning_rate": 1.0103092783505156e-05,
352
+ "loss": 1.8483,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.10290712631849755,
357
+ "grad_norm": 1.0089991092681885,
358
+ "learning_rate": 1.0309278350515464e-05,
359
+ "loss": 1.8018,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.10496526884486751,
364
+ "grad_norm": 1.0117324590682983,
365
+ "learning_rate": 1.0515463917525775e-05,
366
+ "loss": 1.8003,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.10702341137123746,
371
+ "grad_norm": 1.0006697177886963,
372
+ "learning_rate": 1.0721649484536083e-05,
373
+ "loss": 1.7482,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.1090815538976074,
378
+ "grad_norm": 2.1164329051971436,
379
+ "learning_rate": 1.0927835051546391e-05,
380
+ "loss": 1.7363,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.11113969642397736,
385
+ "grad_norm": 0.9573502540588379,
386
+ "learning_rate": 1.1134020618556703e-05,
387
+ "loss": 1.661,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.11319783895034731,
392
+ "grad_norm": 1.0059764385223389,
393
+ "learning_rate": 1.134020618556701e-05,
394
+ "loss": 1.6979,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.11525598147671726,
399
+ "grad_norm": 0.9719656109809875,
400
+ "learning_rate": 1.1546391752577319e-05,
401
+ "loss": 1.6318,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.11731412400308722,
406
+ "grad_norm": 1.0024539232254028,
407
+ "learning_rate": 1.175257731958763e-05,
408
+ "loss": 1.6283,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.11937226652945716,
413
+ "grad_norm": 0.9772456288337708,
414
+ "learning_rate": 1.1958762886597938e-05,
415
+ "loss": 1.5611,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.12143040905582711,
420
+ "grad_norm": 0.9947625994682312,
421
+ "learning_rate": 1.2164948453608248e-05,
422
+ "loss": 1.6073,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.12348855158219707,
427
+ "grad_norm": 2.112889051437378,
428
+ "learning_rate": 1.2371134020618558e-05,
429
+ "loss": 1.6208,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.12554669410856703,
434
+ "grad_norm": 1.0515345335006714,
435
+ "learning_rate": 1.2577319587628866e-05,
436
+ "loss": 1.569,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.12760483663493696,
441
+ "grad_norm": 1.0782145261764526,
442
+ "learning_rate": 1.2783505154639176e-05,
443
+ "loss": 1.5097,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.12966297916130692,
448
+ "grad_norm": 1.154104232788086,
449
+ "learning_rate": 1.2989690721649485e-05,
450
+ "loss": 1.5472,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.13172112168767688,
455
+ "grad_norm": 1.1614656448364258,
456
+ "learning_rate": 1.3195876288659795e-05,
457
+ "loss": 1.4833,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.13377926421404682,
462
+ "grad_norm": 1.1720911264419556,
463
+ "learning_rate": 1.3402061855670103e-05,
464
+ "loss": 1.4644,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.13583740674041678,
469
+ "grad_norm": 1.8903896808624268,
470
+ "learning_rate": 1.3608247422680415e-05,
471
+ "loss": 1.4286,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.13789554926678674,
476
+ "grad_norm": 1.2675013542175293,
477
+ "learning_rate": 1.3814432989690723e-05,
478
+ "loss": 1.416,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.13995369179315667,
483
+ "grad_norm": 1.266434907913208,
484
+ "learning_rate": 1.402061855670103e-05,
485
+ "loss": 1.3171,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.14201183431952663,
490
+ "grad_norm": 1.3408889770507812,
491
+ "learning_rate": 1.4226804123711342e-05,
492
+ "loss": 1.3396,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.1440699768458966,
497
+ "grad_norm": 1.3862446546554565,
498
+ "learning_rate": 1.443298969072165e-05,
499
+ "loss": 1.2642,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.14612811937226652,
504
+ "grad_norm": 2.110553026199341,
505
+ "learning_rate": 1.4639175257731958e-05,
506
+ "loss": 1.2593,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.14818626189863648,
511
+ "grad_norm": 1.7017499208450317,
512
+ "learning_rate": 1.484536082474227e-05,
513
+ "loss": 1.24,
514
+ "step": 72
515
+ },
516
+ {
517
+ "epoch": 0.15024440442500644,
518
+ "grad_norm": 1.9851700067520142,
519
+ "learning_rate": 1.5051546391752578e-05,
520
+ "loss": 1.2313,
521
+ "step": 73
522
+ },
523
+ {
524
+ "epoch": 0.15230254695137638,
525
+ "grad_norm": 2.009608030319214,
526
+ "learning_rate": 1.5257731958762888e-05,
527
+ "loss": 1.1281,
528
+ "step": 74
529
+ },
530
+ {
531
+ "epoch": 0.15436068947774634,
532
+ "grad_norm": 2.7587485313415527,
533
+ "learning_rate": 1.5463917525773197e-05,
534
+ "loss": 1.1248,
535
+ "step": 75
536
+ },
537
+ {
538
+ "epoch": 0.1564188320041163,
539
+ "grad_norm": 2.780954599380493,
540
+ "learning_rate": 1.5670103092783507e-05,
541
+ "loss": 1.0797,
542
+ "step": 76
543
+ },
544
+ {
545
+ "epoch": 0.15847697453048623,
546
+ "grad_norm": 3.1470866203308105,
547
+ "learning_rate": 1.5876288659793813e-05,
548
+ "loss": 1.0064,
549
+ "step": 77
550
+ },
551
+ {
552
+ "epoch": 0.1605351170568562,
553
+ "grad_norm": 4.653595447540283,
554
+ "learning_rate": 1.6082474226804127e-05,
555
+ "loss": 0.9219,
556
+ "step": 78
557
+ },
558
+ {
559
+ "epoch": 0.16259325958322615,
560
+ "grad_norm": 4.157363414764404,
561
+ "learning_rate": 1.6288659793814433e-05,
562
+ "loss": 0.8709,
563
+ "step": 79
564
+ },
565
+ {
566
+ "epoch": 0.16465140210959608,
567
+ "grad_norm": 4.5814924240112305,
568
+ "learning_rate": 1.6494845360824743e-05,
569
+ "loss": 0.7693,
570
+ "step": 80
571
+ },
572
+ {
573
+ "epoch": 0.16670954463596604,
574
+ "grad_norm": 5.096139907836914,
575
+ "learning_rate": 1.6701030927835052e-05,
576
+ "loss": 0.6868,
577
+ "step": 81
578
+ },
579
+ {
580
+ "epoch": 0.168767687162336,
581
+ "grad_norm": 4.858880519866943,
582
+ "learning_rate": 1.6907216494845362e-05,
583
+ "loss": 0.5971,
584
+ "step": 82
585
+ },
586
+ {
587
+ "epoch": 0.17082582968870594,
588
+ "grad_norm": 4.42564582824707,
589
+ "learning_rate": 1.7113402061855672e-05,
590
+ "loss": 0.4719,
591
+ "step": 83
592
+ },
593
+ {
594
+ "epoch": 0.1728839722150759,
595
+ "grad_norm": 7.720851421356201,
596
+ "learning_rate": 1.731958762886598e-05,
597
+ "loss": 0.3943,
598
+ "step": 84
599
+ },
600
+ {
601
+ "epoch": 0.17494211474144586,
602
+ "grad_norm": 0.41923192143440247,
603
+ "learning_rate": 1.752577319587629e-05,
604
+ "loss": 0.3635,
605
+ "step": 85
606
+ },
607
+ {
608
+ "epoch": 0.1770002572678158,
609
+ "grad_norm": 0.2771846354007721,
610
+ "learning_rate": 1.7731958762886598e-05,
611
+ "loss": 0.3597,
612
+ "step": 86
613
+ },
614
+ {
615
+ "epoch": 0.17905839979418575,
616
+ "grad_norm": 0.24761857092380524,
617
+ "learning_rate": 1.793814432989691e-05,
618
+ "loss": 0.3735,
619
+ "step": 87
620
+ },
621
+ {
622
+ "epoch": 0.1811165423205557,
623
+ "grad_norm": 0.23277048766613007,
624
+ "learning_rate": 1.8144329896907217e-05,
625
+ "loss": 0.3643,
626
+ "step": 88
627
+ },
628
+ {
629
+ "epoch": 0.18317468484692565,
630
+ "grad_norm": 0.22931228578090668,
631
+ "learning_rate": 1.8350515463917527e-05,
632
+ "loss": 0.3519,
633
+ "step": 89
634
+ },
635
+ {
636
+ "epoch": 0.1852328273732956,
637
+ "grad_norm": 0.20750615000724792,
638
+ "learning_rate": 1.8556701030927837e-05,
639
+ "loss": 0.3431,
640
+ "step": 90
641
+ },
642
+ {
643
+ "epoch": 0.18729096989966554,
644
+ "grad_norm": 0.2080322951078415,
645
+ "learning_rate": 1.8762886597938147e-05,
646
+ "loss": 0.3632,
647
+ "step": 91
648
+ },
649
+ {
650
+ "epoch": 0.1893491124260355,
651
+ "grad_norm": 0.20186181366443634,
652
+ "learning_rate": 1.8969072164948453e-05,
653
+ "loss": 0.3492,
654
+ "step": 92
655
+ },
656
+ {
657
+ "epoch": 0.19140725495240546,
658
+ "grad_norm": 0.19172786176204681,
659
+ "learning_rate": 1.9175257731958766e-05,
660
+ "loss": 0.3552,
661
+ "step": 93
662
+ },
663
+ {
664
+ "epoch": 0.1934653974787754,
665
+ "grad_norm": 0.1747850626707077,
666
+ "learning_rate": 1.9381443298969072e-05,
667
+ "loss": 0.3355,
668
+ "step": 94
669
+ },
670
+ {
671
+ "epoch": 0.19552354000514535,
672
+ "grad_norm": 0.196411594748497,
673
+ "learning_rate": 1.9587628865979382e-05,
674
+ "loss": 0.3271,
675
+ "step": 95
676
+ },
677
+ {
678
+ "epoch": 0.1975816825315153,
679
+ "grad_norm": 0.20063228905200958,
680
+ "learning_rate": 1.9793814432989692e-05,
681
+ "loss": 0.3351,
682
+ "step": 96
683
+ },
684
+ {
685
+ "epoch": 0.19963982505788525,
686
+ "grad_norm": 0.19240939617156982,
687
+ "learning_rate": 2e-05,
688
+ "loss": 0.3266,
689
+ "step": 97
690
+ },
691
+ {
692
+ "epoch": 0.2016979675842552,
693
+ "grad_norm": 0.18206572532653809,
694
+ "learning_rate": 1.997709049255441e-05,
695
+ "loss": 0.3393,
696
+ "step": 98
697
+ },
698
+ {
699
+ "epoch": 0.20375611011062517,
700
+ "grad_norm": 0.20384562015533447,
701
+ "learning_rate": 1.9954180985108823e-05,
702
+ "loss": 0.3395,
703
+ "step": 99
704
+ },
705
+ {
706
+ "epoch": 0.2058142526369951,
707
+ "grad_norm": 0.19944581389427185,
708
+ "learning_rate": 1.9931271477663232e-05,
709
+ "loss": 0.3268,
710
+ "step": 100
711
+ },
712
+ {
713
+ "epoch": 0.2058142526369951,
714
+ "eval_loss": 0.3456890285015106,
715
+ "eval_runtime": 2114.0178,
716
+ "eval_samples_per_second": 3.677,
717
+ "eval_steps_per_second": 0.92,
718
+ "step": 100
719
+ },
720
+ {
721
+ "epoch": 0.20787239516336506,
722
+ "grad_norm": 0.17743557691574097,
723
+ "learning_rate": 1.990836197021764e-05,
724
+ "loss": 0.3439,
725
+ "step": 101
726
+ },
727
+ {
728
+ "epoch": 0.20993053768973502,
729
+ "grad_norm": 0.18746449053287506,
730
+ "learning_rate": 1.9885452462772053e-05,
731
+ "loss": 0.326,
732
+ "step": 102
733
+ },
734
+ {
735
+ "epoch": 0.21198868021610495,
736
+ "grad_norm": 0.18555815517902374,
737
+ "learning_rate": 1.9862542955326462e-05,
738
+ "loss": 0.3337,
739
+ "step": 103
740
+ },
741
+ {
742
+ "epoch": 0.2140468227424749,
743
+ "grad_norm": 0.16591575741767883,
744
+ "learning_rate": 1.9839633447880874e-05,
745
+ "loss": 0.3121,
746
+ "step": 104
747
+ },
748
+ {
749
+ "epoch": 0.21610496526884487,
750
+ "grad_norm": 0.1621987372636795,
751
+ "learning_rate": 1.9816723940435283e-05,
752
+ "loss": 0.3287,
753
+ "step": 105
754
+ },
755
+ {
756
+ "epoch": 0.2181631077952148,
757
+ "grad_norm": 0.1614532470703125,
758
+ "learning_rate": 1.9793814432989692e-05,
759
+ "loss": 0.3306,
760
+ "step": 106
761
+ },
762
+ {
763
+ "epoch": 0.22022125032158477,
764
+ "grad_norm": 0.17993387579917908,
765
+ "learning_rate": 1.9770904925544104e-05,
766
+ "loss": 0.3341,
767
+ "step": 107
768
+ },
769
+ {
770
+ "epoch": 0.22227939284795473,
771
+ "grad_norm": 0.1550011783838272,
772
+ "learning_rate": 1.9747995418098513e-05,
773
+ "loss": 0.3197,
774
+ "step": 108
775
+ },
776
+ {
777
+ "epoch": 0.22433753537432466,
778
+ "grad_norm": 0.18471524119377136,
779
+ "learning_rate": 1.9725085910652922e-05,
780
+ "loss": 0.3285,
781
+ "step": 109
782
+ },
783
+ {
784
+ "epoch": 0.22639567790069462,
785
+ "grad_norm": 0.15604373812675476,
786
+ "learning_rate": 1.9702176403207334e-05,
787
+ "loss": 0.3298,
788
+ "step": 110
789
+ },
790
+ {
791
+ "epoch": 0.22845382042706458,
792
+ "grad_norm": 0.1682298630475998,
793
+ "learning_rate": 1.9679266895761743e-05,
794
+ "loss": 0.3343,
795
+ "step": 111
796
+ },
797
+ {
798
+ "epoch": 0.2305119629534345,
799
+ "grad_norm": 0.14933635294437408,
800
+ "learning_rate": 1.9656357388316152e-05,
801
+ "loss": 0.3134,
802
+ "step": 112
803
+ },
804
+ {
805
+ "epoch": 0.23257010547980447,
806
+ "grad_norm": 0.14892347157001495,
807
+ "learning_rate": 1.963344788087056e-05,
808
+ "loss": 0.3154,
809
+ "step": 113
810
+ },
811
+ {
812
+ "epoch": 0.23462824800617443,
813
+ "grad_norm": 0.1577889323234558,
814
+ "learning_rate": 1.9610538373424973e-05,
815
+ "loss": 0.3122,
816
+ "step": 114
817
+ },
818
+ {
819
+ "epoch": 0.23668639053254437,
820
+ "grad_norm": 0.16482344269752502,
821
+ "learning_rate": 1.9587628865979382e-05,
822
+ "loss": 0.3193,
823
+ "step": 115
824
+ },
825
+ {
826
+ "epoch": 0.23874453305891433,
827
+ "grad_norm": 0.15328913927078247,
828
+ "learning_rate": 1.956471935853379e-05,
829
+ "loss": 0.3217,
830
+ "step": 116
831
+ },
832
+ {
833
+ "epoch": 0.2408026755852843,
834
+ "grad_norm": 0.16140656173229218,
835
+ "learning_rate": 1.9541809851088203e-05,
836
+ "loss": 0.318,
837
+ "step": 117
838
+ },
839
+ {
840
+ "epoch": 0.24286081811165422,
841
+ "grad_norm": 0.15448373556137085,
842
+ "learning_rate": 1.9518900343642612e-05,
843
+ "loss": 0.3205,
844
+ "step": 118
845
+ },
846
+ {
847
+ "epoch": 0.24491896063802418,
848
+ "grad_norm": 0.14716887474060059,
849
+ "learning_rate": 1.9495990836197025e-05,
850
+ "loss": 0.3164,
851
+ "step": 119
852
+ },
853
+ {
854
+ "epoch": 0.24697710316439414,
855
+ "grad_norm": 0.16582027077674866,
856
+ "learning_rate": 1.9473081328751433e-05,
857
+ "loss": 0.3191,
858
+ "step": 120
859
+ },
860
+ {
861
+ "epoch": 0.24903524569076407,
862
+ "grad_norm": 0.15213699638843536,
863
+ "learning_rate": 1.9450171821305842e-05,
864
+ "loss": 0.304,
865
+ "step": 121
866
+ },
867
+ {
868
+ "epoch": 0.25109338821713406,
869
+ "grad_norm": 0.1659238487482071,
870
+ "learning_rate": 1.9427262313860255e-05,
871
+ "loss": 0.3184,
872
+ "step": 122
873
+ },
874
+ {
875
+ "epoch": 0.253151530743504,
876
+ "grad_norm": 0.15596656501293182,
877
+ "learning_rate": 1.9404352806414663e-05,
878
+ "loss": 0.3092,
879
+ "step": 123
880
+ },
881
+ {
882
+ "epoch": 0.2552096732698739,
883
+ "grad_norm": 0.15868476033210754,
884
+ "learning_rate": 1.9381443298969072e-05,
885
+ "loss": 0.3163,
886
+ "step": 124
887
+ },
888
+ {
889
+ "epoch": 0.2572678157962439,
890
+ "grad_norm": 0.15386095643043518,
891
+ "learning_rate": 1.9358533791523485e-05,
892
+ "loss": 0.3049,
893
+ "step": 125
894
+ },
895
+ {
896
+ "epoch": 0.25932595832261385,
897
+ "grad_norm": 0.15179213881492615,
898
+ "learning_rate": 1.9335624284077894e-05,
899
+ "loss": 0.3131,
900
+ "step": 126
901
+ },
902
+ {
903
+ "epoch": 0.2613841008489838,
904
+ "grad_norm": 0.1595134735107422,
905
+ "learning_rate": 1.9312714776632306e-05,
906
+ "loss": 0.3069,
907
+ "step": 127
908
+ },
909
+ {
910
+ "epoch": 0.26344224337535377,
911
+ "grad_norm": 0.16989803314208984,
912
+ "learning_rate": 1.9289805269186715e-05,
913
+ "loss": 0.3052,
914
+ "step": 128
915
+ },
916
+ {
917
+ "epoch": 0.2655003859017237,
918
+ "grad_norm": 0.14803892374038696,
919
+ "learning_rate": 1.9266895761741124e-05,
920
+ "loss": 0.3065,
921
+ "step": 129
922
+ },
923
+ {
924
+ "epoch": 0.26755852842809363,
925
+ "grad_norm": 0.16676583886146545,
926
+ "learning_rate": 1.9243986254295536e-05,
927
+ "loss": 0.2962,
928
+ "step": 130
929
+ },
930
+ {
931
+ "epoch": 0.2696166709544636,
932
+ "grad_norm": 0.15694552659988403,
933
+ "learning_rate": 1.9221076746849945e-05,
934
+ "loss": 0.3096,
935
+ "step": 131
936
+ },
937
+ {
938
+ "epoch": 0.27167481348083355,
939
+ "grad_norm": 0.17696696519851685,
940
+ "learning_rate": 1.9198167239404354e-05,
941
+ "loss": 0.3145,
942
+ "step": 132
943
+ },
944
+ {
945
+ "epoch": 0.2737329560072035,
946
+ "grad_norm": 0.17204038798809052,
947
+ "learning_rate": 1.9175257731958766e-05,
948
+ "loss": 0.3248,
949
+ "step": 133
950
+ },
951
+ {
952
+ "epoch": 0.2757910985335735,
953
+ "grad_norm": 0.15630359947681427,
954
+ "learning_rate": 1.9152348224513175e-05,
955
+ "loss": 0.3117,
956
+ "step": 134
957
+ },
958
+ {
959
+ "epoch": 0.2778492410599434,
960
+ "grad_norm": 0.15757997334003448,
961
+ "learning_rate": 1.9129438717067584e-05,
962
+ "loss": 0.3145,
963
+ "step": 135
964
+ },
965
+ {
966
+ "epoch": 0.27990738358631334,
967
+ "grad_norm": 0.16273653507232666,
968
+ "learning_rate": 1.9106529209621996e-05,
969
+ "loss": 0.3159,
970
+ "step": 136
971
+ },
972
+ {
973
+ "epoch": 0.28196552611268333,
974
+ "grad_norm": 0.16213104128837585,
975
+ "learning_rate": 1.9083619702176405e-05,
976
+ "loss": 0.2949,
977
+ "step": 137
978
+ },
979
+ {
980
+ "epoch": 0.28402366863905326,
981
+ "grad_norm": 0.15377865731716156,
982
+ "learning_rate": 1.9060710194730814e-05,
983
+ "loss": 0.306,
984
+ "step": 138
985
+ },
986
+ {
987
+ "epoch": 0.2860818111654232,
988
+ "grad_norm": 0.1545962244272232,
989
+ "learning_rate": 1.9037800687285223e-05,
990
+ "loss": 0.2966,
991
+ "step": 139
992
+ },
993
+ {
994
+ "epoch": 0.2881399536917932,
995
+ "grad_norm": 0.15516617894172668,
996
+ "learning_rate": 1.9014891179839635e-05,
997
+ "loss": 0.3122,
998
+ "step": 140
999
+ },
1000
+ {
1001
+ "epoch": 0.2901980962181631,
1002
+ "grad_norm": 0.14734458923339844,
1003
+ "learning_rate": 1.8991981672394044e-05,
1004
+ "loss": 0.3118,
1005
+ "step": 141
1006
+ },
1007
+ {
1008
+ "epoch": 0.29225623874453305,
1009
+ "grad_norm": 0.1644304096698761,
1010
+ "learning_rate": 1.8969072164948453e-05,
1011
+ "loss": 0.3027,
1012
+ "step": 142
1013
+ },
1014
+ {
1015
+ "epoch": 0.29431438127090304,
1016
+ "grad_norm": 0.14632569253444672,
1017
+ "learning_rate": 1.8946162657502865e-05,
1018
+ "loss": 0.3023,
1019
+ "step": 143
1020
+ },
1021
+ {
1022
+ "epoch": 0.29637252379727297,
1023
+ "grad_norm": 0.1573137789964676,
1024
+ "learning_rate": 1.8923253150057274e-05,
1025
+ "loss": 0.3102,
1026
+ "step": 144
1027
+ },
1028
+ {
1029
+ "epoch": 0.2984306663236429,
1030
+ "grad_norm": 0.16423144936561584,
1031
+ "learning_rate": 1.8900343642611686e-05,
1032
+ "loss": 0.3033,
1033
+ "step": 145
1034
+ },
1035
+ {
1036
+ "epoch": 0.3004888088500129,
1037
+ "grad_norm": 0.15420907735824585,
1038
+ "learning_rate": 1.8877434135166095e-05,
1039
+ "loss": 0.3089,
1040
+ "step": 146
1041
+ },
1042
+ {
1043
+ "epoch": 0.3025469513763828,
1044
+ "grad_norm": 0.1579178273677826,
1045
+ "learning_rate": 1.8854524627720504e-05,
1046
+ "loss": 0.3071,
1047
+ "step": 147
1048
+ },
1049
+ {
1050
+ "epoch": 0.30460509390275275,
1051
+ "grad_norm": 0.15866397321224213,
1052
+ "learning_rate": 1.8831615120274916e-05,
1053
+ "loss": 0.3083,
1054
+ "step": 148
1055
+ },
1056
+ {
1057
+ "epoch": 0.30666323642912274,
1058
+ "grad_norm": 0.16651487350463867,
1059
+ "learning_rate": 1.8808705612829325e-05,
1060
+ "loss": 0.3099,
1061
+ "step": 149
1062
+ },
1063
+ {
1064
+ "epoch": 0.3087213789554927,
1065
+ "grad_norm": 0.16281908750534058,
1066
+ "learning_rate": 1.8785796105383734e-05,
1067
+ "loss": 0.3034,
1068
+ "step": 150
1069
+ },
1070
+ {
1071
+ "epoch": 0.3107795214818626,
1072
+ "grad_norm": 0.17449837923049927,
1073
+ "learning_rate": 1.8762886597938147e-05,
1074
+ "loss": 0.3054,
1075
+ "step": 151
1076
+ },
1077
+ {
1078
+ "epoch": 0.3128376640082326,
1079
+ "grad_norm": 0.15403546392917633,
1080
+ "learning_rate": 1.8739977090492555e-05,
1081
+ "loss": 0.297,
1082
+ "step": 152
1083
+ },
1084
+ {
1085
+ "epoch": 0.31489580653460253,
1086
+ "grad_norm": 0.1472466140985489,
1087
+ "learning_rate": 1.8717067583046968e-05,
1088
+ "loss": 0.2973,
1089
+ "step": 153
1090
+ },
1091
+ {
1092
+ "epoch": 0.31695394906097246,
1093
+ "grad_norm": 0.16027937829494476,
1094
+ "learning_rate": 1.8694158075601377e-05,
1095
+ "loss": 0.3054,
1096
+ "step": 154
1097
+ },
1098
+ {
1099
+ "epoch": 0.31901209158734245,
1100
+ "grad_norm": 0.17086225748062134,
1101
+ "learning_rate": 1.8671248568155786e-05,
1102
+ "loss": 0.307,
1103
+ "step": 155
1104
+ },
1105
+ {
1106
+ "epoch": 0.3210702341137124,
1107
+ "grad_norm": 0.15930697321891785,
1108
+ "learning_rate": 1.8648339060710198e-05,
1109
+ "loss": 0.293,
1110
+ "step": 156
1111
+ },
1112
+ {
1113
+ "epoch": 0.3231283766400823,
1114
+ "grad_norm": 0.17086376249790192,
1115
+ "learning_rate": 1.8625429553264607e-05,
1116
+ "loss": 0.293,
1117
+ "step": 157
1118
+ },
1119
+ {
1120
+ "epoch": 0.3251865191664523,
1121
+ "grad_norm": 0.15970875322818756,
1122
+ "learning_rate": 1.8602520045819016e-05,
1123
+ "loss": 0.3083,
1124
+ "step": 158
1125
+ },
1126
+ {
1127
+ "epoch": 0.32724466169282224,
1128
+ "grad_norm": 0.16355909407138824,
1129
+ "learning_rate": 1.8579610538373428e-05,
1130
+ "loss": 0.3139,
1131
+ "step": 159
1132
+ },
1133
+ {
1134
+ "epoch": 0.32930280421919217,
1135
+ "grad_norm": 0.15183711051940918,
1136
+ "learning_rate": 1.8556701030927837e-05,
1137
+ "loss": 0.2953,
1138
+ "step": 160
1139
+ },
1140
+ {
1141
+ "epoch": 0.33136094674556216,
1142
+ "grad_norm": 0.15123715996742249,
1143
+ "learning_rate": 1.853379152348225e-05,
1144
+ "loss": 0.3025,
1145
+ "step": 161
1146
+ },
1147
+ {
1148
+ "epoch": 0.3334190892719321,
1149
+ "grad_norm": 0.1576143503189087,
1150
+ "learning_rate": 1.8510882016036658e-05,
1151
+ "loss": 0.2904,
1152
+ "step": 162
1153
+ },
1154
+ {
1155
+ "epoch": 0.335477231798302,
1156
+ "grad_norm": 0.1457504779100418,
1157
+ "learning_rate": 1.8487972508591067e-05,
1158
+ "loss": 0.2909,
1159
+ "step": 163
1160
+ },
1161
+ {
1162
+ "epoch": 0.337535374324672,
1163
+ "grad_norm": 0.1557442992925644,
1164
+ "learning_rate": 1.846506300114548e-05,
1165
+ "loss": 0.3027,
1166
+ "step": 164
1167
+ },
1168
+ {
1169
+ "epoch": 0.33959351685104194,
1170
+ "grad_norm": 0.15662318468093872,
1171
+ "learning_rate": 1.8442153493699888e-05,
1172
+ "loss": 0.311,
1173
+ "step": 165
1174
+ },
1175
+ {
1176
+ "epoch": 0.3416516593774119,
1177
+ "grad_norm": 0.16177058219909668,
1178
+ "learning_rate": 1.8419243986254297e-05,
1179
+ "loss": 0.2944,
1180
+ "step": 166
1181
+ },
1182
+ {
1183
+ "epoch": 0.34370980190378186,
1184
+ "grad_norm": 0.16406729817390442,
1185
+ "learning_rate": 1.8396334478808706e-05,
1186
+ "loss": 0.2927,
1187
+ "step": 167
1188
+ },
1189
+ {
1190
+ "epoch": 0.3457679444301518,
1191
+ "grad_norm": 0.16642791032791138,
1192
+ "learning_rate": 1.8373424971363115e-05,
1193
+ "loss": 0.3063,
1194
+ "step": 168
1195
+ },
1196
+ {
1197
+ "epoch": 0.34782608695652173,
1198
+ "grad_norm": 0.1650693714618683,
1199
+ "learning_rate": 1.8350515463917527e-05,
1200
+ "loss": 0.2957,
1201
+ "step": 169
1202
+ },
1203
+ {
1204
+ "epoch": 0.3498842294828917,
1205
+ "grad_norm": 0.15349675714969635,
1206
+ "learning_rate": 1.8327605956471936e-05,
1207
+ "loss": 0.297,
1208
+ "step": 170
1209
+ },
1210
+ {
1211
+ "epoch": 0.35194237200926165,
1212
+ "grad_norm": 0.17770209908485413,
1213
+ "learning_rate": 1.8304696449026348e-05,
1214
+ "loss": 0.3011,
1215
+ "step": 171
1216
+ },
1217
+ {
1218
+ "epoch": 0.3540005145356316,
1219
+ "grad_norm": 0.1647631675004959,
1220
+ "learning_rate": 1.8281786941580757e-05,
1221
+ "loss": 0.2962,
1222
+ "step": 172
1223
+ },
1224
+ {
1225
+ "epoch": 0.35605865706200157,
1226
+ "grad_norm": 0.1603834480047226,
1227
+ "learning_rate": 1.8258877434135166e-05,
1228
+ "loss": 0.2937,
1229
+ "step": 173
1230
+ },
1231
+ {
1232
+ "epoch": 0.3581167995883715,
1233
+ "grad_norm": 0.16780880093574524,
1234
+ "learning_rate": 1.8235967926689578e-05,
1235
+ "loss": 0.2997,
1236
+ "step": 174
1237
+ },
1238
+ {
1239
+ "epoch": 0.36017494211474144,
1240
+ "grad_norm": 0.15976767241954803,
1241
+ "learning_rate": 1.8213058419243987e-05,
1242
+ "loss": 0.3043,
1243
+ "step": 175
1244
+ },
1245
+ {
1246
+ "epoch": 0.3622330846411114,
1247
+ "grad_norm": 0.16236485540866852,
1248
+ "learning_rate": 1.8190148911798396e-05,
1249
+ "loss": 0.3069,
1250
+ "step": 176
1251
+ },
1252
+ {
1253
+ "epoch": 0.36429122716748136,
1254
+ "grad_norm": 0.16391968727111816,
1255
+ "learning_rate": 1.816723940435281e-05,
1256
+ "loss": 0.2923,
1257
+ "step": 177
1258
+ },
1259
+ {
1260
+ "epoch": 0.3663493696938513,
1261
+ "grad_norm": 0.15806889533996582,
1262
+ "learning_rate": 1.8144329896907217e-05,
1263
+ "loss": 0.2872,
1264
+ "step": 178
1265
+ },
1266
+ {
1267
+ "epoch": 0.3684075122202212,
1268
+ "grad_norm": 0.1627352088689804,
1269
+ "learning_rate": 1.812142038946163e-05,
1270
+ "loss": 0.3032,
1271
+ "step": 179
1272
+ },
1273
+ {
1274
+ "epoch": 0.3704656547465912,
1275
+ "grad_norm": 0.15103371441364288,
1276
+ "learning_rate": 1.809851088201604e-05,
1277
+ "loss": 0.2847,
1278
+ "step": 180
1279
+ },
1280
+ {
1281
+ "epoch": 0.37252379727296114,
1282
+ "grad_norm": 0.15178488194942474,
1283
+ "learning_rate": 1.8075601374570447e-05,
1284
+ "loss": 0.3017,
1285
+ "step": 181
1286
+ },
1287
+ {
1288
+ "epoch": 0.3745819397993311,
1289
+ "grad_norm": 0.15493899583816528,
1290
+ "learning_rate": 1.805269186712486e-05,
1291
+ "loss": 0.2901,
1292
+ "step": 182
1293
+ },
1294
+ {
1295
+ "epoch": 0.37664008232570106,
1296
+ "grad_norm": 0.15990686416625977,
1297
+ "learning_rate": 1.802978235967927e-05,
1298
+ "loss": 0.2861,
1299
+ "step": 183
1300
+ },
1301
+ {
1302
+ "epoch": 0.378698224852071,
1303
+ "grad_norm": 0.15824148058891296,
1304
+ "learning_rate": 1.8006872852233677e-05,
1305
+ "loss": 0.2885,
1306
+ "step": 184
1307
+ },
1308
+ {
1309
+ "epoch": 0.38075636737844093,
1310
+ "grad_norm": 0.15690775215625763,
1311
+ "learning_rate": 1.798396334478809e-05,
1312
+ "loss": 0.2814,
1313
+ "step": 185
1314
+ },
1315
+ {
1316
+ "epoch": 0.3828145099048109,
1317
+ "grad_norm": 0.15833796560764313,
1318
+ "learning_rate": 1.79610538373425e-05,
1319
+ "loss": 0.2847,
1320
+ "step": 186
1321
+ },
1322
+ {
1323
+ "epoch": 0.38487265243118085,
1324
+ "grad_norm": 0.16560044884681702,
1325
+ "learning_rate": 1.793814432989691e-05,
1326
+ "loss": 0.3061,
1327
+ "step": 187
1328
+ },
1329
+ {
1330
+ "epoch": 0.3869307949575508,
1331
+ "grad_norm": 0.16240179538726807,
1332
+ "learning_rate": 1.791523482245132e-05,
1333
+ "loss": 0.2943,
1334
+ "step": 188
1335
+ },
1336
+ {
1337
+ "epoch": 0.38898893748392077,
1338
+ "grad_norm": 0.15825721621513367,
1339
+ "learning_rate": 1.789232531500573e-05,
1340
+ "loss": 0.2934,
1341
+ "step": 189
1342
+ },
1343
+ {
1344
+ "epoch": 0.3910470800102907,
1345
+ "grad_norm": 0.16665388643741608,
1346
+ "learning_rate": 1.786941580756014e-05,
1347
+ "loss": 0.291,
1348
+ "step": 190
1349
+ },
1350
+ {
1351
+ "epoch": 0.39310522253666064,
1352
+ "grad_norm": 0.16581200063228607,
1353
+ "learning_rate": 1.784650630011455e-05,
1354
+ "loss": 0.2849,
1355
+ "step": 191
1356
+ },
1357
+ {
1358
+ "epoch": 0.3951633650630306,
1359
+ "grad_norm": 0.1604345291852951,
1360
+ "learning_rate": 1.782359679266896e-05,
1361
+ "loss": 0.3,
1362
+ "step": 192
1363
+ },
1364
+ {
1365
+ "epoch": 0.39722150758940056,
1366
+ "grad_norm": 0.16107915341854095,
1367
+ "learning_rate": 1.7800687285223368e-05,
1368
+ "loss": 0.2847,
1369
+ "step": 193
1370
+ },
1371
+ {
1372
+ "epoch": 0.3992796501157705,
1373
+ "grad_norm": 0.1571730375289917,
1374
+ "learning_rate": 1.7777777777777777e-05,
1375
+ "loss": 0.2863,
1376
+ "step": 194
1377
+ },
1378
+ {
1379
+ "epoch": 0.4013377926421405,
1380
+ "grad_norm": 0.1656399518251419,
1381
+ "learning_rate": 1.775486827033219e-05,
1382
+ "loss": 0.2878,
1383
+ "step": 195
1384
+ },
1385
+ {
1386
+ "epoch": 0.4033959351685104,
1387
+ "grad_norm": 0.16738460958003998,
1388
+ "learning_rate": 1.7731958762886598e-05,
1389
+ "loss": 0.286,
1390
+ "step": 196
1391
+ },
1392
+ {
1393
+ "epoch": 0.40545407769488034,
1394
+ "grad_norm": 0.16704292595386505,
1395
+ "learning_rate": 1.770904925544101e-05,
1396
+ "loss": 0.2919,
1397
+ "step": 197
1398
+ },
1399
+ {
1400
+ "epoch": 0.40751222022125033,
1401
+ "grad_norm": 0.16215579211711884,
1402
+ "learning_rate": 1.768613974799542e-05,
1403
+ "loss": 0.2874,
1404
+ "step": 198
1405
+ },
1406
+ {
1407
+ "epoch": 0.40957036274762026,
1408
+ "grad_norm": 0.15573479235172272,
1409
+ "learning_rate": 1.7663230240549828e-05,
1410
+ "loss": 0.2904,
1411
+ "step": 199
1412
+ },
1413
+ {
1414
+ "epoch": 0.4116285052739902,
1415
+ "grad_norm": 0.1707623153924942,
1416
+ "learning_rate": 1.764032073310424e-05,
1417
+ "loss": 0.289,
1418
+ "step": 200
1419
+ },
1420
+ {
1421
+ "epoch": 0.4116285052739902,
1422
+ "eval_loss": 0.3214050829410553,
1423
+ "eval_runtime": 2449.7742,
1424
+ "eval_samples_per_second": 3.173,
1425
+ "eval_steps_per_second": 0.794,
1426
+ "step": 200
1427
+ },
1428
+ {
1429
+ "epoch": 0.4136866478003602,
1430
+ "grad_norm": 0.1699172556400299,
1431
+ "learning_rate": 1.761741122565865e-05,
1432
+ "loss": 0.2852,
1433
+ "step": 201
1434
+ },
1435
+ {
1436
+ "epoch": 0.4157447903267301,
1437
+ "grad_norm": 0.19150058925151825,
1438
+ "learning_rate": 1.7594501718213058e-05,
1439
+ "loss": 0.29,
1440
+ "step": 202
1441
+ },
1442
+ {
1443
+ "epoch": 0.41780293285310005,
1444
+ "grad_norm": 0.15794627368450165,
1445
+ "learning_rate": 1.757159221076747e-05,
1446
+ "loss": 0.2746,
1447
+ "step": 203
1448
+ },
1449
+ {
1450
+ "epoch": 0.41986107537947004,
1451
+ "grad_norm": 0.17305190861225128,
1452
+ "learning_rate": 1.754868270332188e-05,
1453
+ "loss": 0.3003,
1454
+ "step": 204
1455
+ },
1456
+ {
1457
+ "epoch": 0.42191921790583997,
1458
+ "grad_norm": 0.16257523000240326,
1459
+ "learning_rate": 1.752577319587629e-05,
1460
+ "loss": 0.2789,
1461
+ "step": 205
1462
+ },
1463
+ {
1464
+ "epoch": 0.4239773604322099,
1465
+ "grad_norm": 0.17273619771003723,
1466
+ "learning_rate": 1.75028636884307e-05,
1467
+ "loss": 0.2917,
1468
+ "step": 206
1469
+ },
1470
+ {
1471
+ "epoch": 0.4260355029585799,
1472
+ "grad_norm": 0.17502790689468384,
1473
+ "learning_rate": 1.747995418098511e-05,
1474
+ "loss": 0.2992,
1475
+ "step": 207
1476
+ },
1477
+ {
1478
+ "epoch": 0.4280936454849498,
1479
+ "grad_norm": 0.16464050114154816,
1480
+ "learning_rate": 1.745704467353952e-05,
1481
+ "loss": 0.2873,
1482
+ "step": 208
1483
+ },
1484
+ {
1485
+ "epoch": 0.43015178801131976,
1486
+ "grad_norm": 0.1681668758392334,
1487
+ "learning_rate": 1.743413516609393e-05,
1488
+ "loss": 0.2991,
1489
+ "step": 209
1490
+ },
1491
+ {
1492
+ "epoch": 0.43220993053768975,
1493
+ "grad_norm": 0.16957956552505493,
1494
+ "learning_rate": 1.741122565864834e-05,
1495
+ "loss": 0.2868,
1496
+ "step": 210
1497
+ },
1498
+ {
1499
+ "epoch": 0.4342680730640597,
1500
+ "grad_norm": 0.15875883400440216,
1501
+ "learning_rate": 1.738831615120275e-05,
1502
+ "loss": 0.2946,
1503
+ "step": 211
1504
+ },
1505
+ {
1506
+ "epoch": 0.4363262155904296,
1507
+ "grad_norm": 0.18127889931201935,
1508
+ "learning_rate": 1.736540664375716e-05,
1509
+ "loss": 0.2835,
1510
+ "step": 212
1511
+ },
1512
+ {
1513
+ "epoch": 0.4383843581167996,
1514
+ "grad_norm": 0.17822811007499695,
1515
+ "learning_rate": 1.7342497136311573e-05,
1516
+ "loss": 0.2944,
1517
+ "step": 213
1518
+ },
1519
+ {
1520
+ "epoch": 0.44044250064316953,
1521
+ "grad_norm": 0.17555806040763855,
1522
+ "learning_rate": 1.731958762886598e-05,
1523
+ "loss": 0.3001,
1524
+ "step": 214
1525
+ },
1526
+ {
1527
+ "epoch": 0.44250064316953946,
1528
+ "grad_norm": 0.18709121644496918,
1529
+ "learning_rate": 1.729667812142039e-05,
1530
+ "loss": 0.282,
1531
+ "step": 215
1532
+ },
1533
+ {
1534
+ "epoch": 0.44455878569590945,
1535
+ "grad_norm": 0.16322475671768188,
1536
+ "learning_rate": 1.7273768613974803e-05,
1537
+ "loss": 0.2883,
1538
+ "step": 216
1539
+ },
1540
+ {
1541
+ "epoch": 0.4466169282222794,
1542
+ "grad_norm": 0.1677054911851883,
1543
+ "learning_rate": 1.7250859106529212e-05,
1544
+ "loss": 0.28,
1545
+ "step": 217
1546
+ },
1547
+ {
1548
+ "epoch": 0.4486750707486493,
1549
+ "grad_norm": 0.15764063596725464,
1550
+ "learning_rate": 1.722794959908362e-05,
1551
+ "loss": 0.2768,
1552
+ "step": 218
1553
+ },
1554
+ {
1555
+ "epoch": 0.4507332132750193,
1556
+ "grad_norm": 0.16166841983795166,
1557
+ "learning_rate": 1.7205040091638033e-05,
1558
+ "loss": 0.2868,
1559
+ "step": 219
1560
+ },
1561
+ {
1562
+ "epoch": 0.45279135580138924,
1563
+ "grad_norm": 0.1799350380897522,
1564
+ "learning_rate": 1.7182130584192442e-05,
1565
+ "loss": 0.2891,
1566
+ "step": 220
1567
+ },
1568
+ {
1569
+ "epoch": 0.45484949832775917,
1570
+ "grad_norm": 0.18119174242019653,
1571
+ "learning_rate": 1.715922107674685e-05,
1572
+ "loss": 0.2841,
1573
+ "step": 221
1574
+ },
1575
+ {
1576
+ "epoch": 0.45690764085412916,
1577
+ "grad_norm": 0.17725548148155212,
1578
+ "learning_rate": 1.713631156930126e-05,
1579
+ "loss": 0.3038,
1580
+ "step": 222
1581
+ },
1582
+ {
1583
+ "epoch": 0.4589657833804991,
1584
+ "grad_norm": 0.1628233790397644,
1585
+ "learning_rate": 1.7113402061855672e-05,
1586
+ "loss": 0.2868,
1587
+ "step": 223
1588
+ },
1589
+ {
1590
+ "epoch": 0.461023925906869,
1591
+ "grad_norm": 0.1745166927576065,
1592
+ "learning_rate": 1.709049255441008e-05,
1593
+ "loss": 0.3033,
1594
+ "step": 224
1595
+ },
1596
+ {
1597
+ "epoch": 0.463082068433239,
1598
+ "grad_norm": 0.17708267271518707,
1599
+ "learning_rate": 1.706758304696449e-05,
1600
+ "loss": 0.2842,
1601
+ "step": 225
1602
+ },
1603
+ {
1604
+ "epoch": 0.46514021095960895,
1605
+ "grad_norm": 0.1738453358411789,
1606
+ "learning_rate": 1.7044673539518902e-05,
1607
+ "loss": 0.3005,
1608
+ "step": 226
1609
+ },
1610
+ {
1611
+ "epoch": 0.4671983534859789,
1612
+ "grad_norm": 0.1706874966621399,
1613
+ "learning_rate": 1.702176403207331e-05,
1614
+ "loss": 0.2924,
1615
+ "step": 227
1616
+ },
1617
+ {
1618
+ "epoch": 0.46925649601234887,
1619
+ "grad_norm": 0.1697423756122589,
1620
+ "learning_rate": 1.699885452462772e-05,
1621
+ "loss": 0.2783,
1622
+ "step": 228
1623
+ },
1624
+ {
1625
+ "epoch": 0.4713146385387188,
1626
+ "grad_norm": 0.1783403754234314,
1627
+ "learning_rate": 1.6975945017182132e-05,
1628
+ "loss": 0.2924,
1629
+ "step": 229
1630
+ },
1631
+ {
1632
+ "epoch": 0.47337278106508873,
1633
+ "grad_norm": 0.17431536316871643,
1634
+ "learning_rate": 1.695303550973654e-05,
1635
+ "loss": 0.2792,
1636
+ "step": 230
1637
+ },
1638
+ {
1639
+ "epoch": 0.4754309235914587,
1640
+ "grad_norm": 0.164026141166687,
1641
+ "learning_rate": 1.6930126002290953e-05,
1642
+ "loss": 0.2825,
1643
+ "step": 231
1644
+ },
1645
+ {
1646
+ "epoch": 0.47748906611782865,
1647
+ "grad_norm": 0.16449657082557678,
1648
+ "learning_rate": 1.6907216494845362e-05,
1649
+ "loss": 0.2831,
1650
+ "step": 232
1651
+ },
1652
+ {
1653
+ "epoch": 0.4795472086441986,
1654
+ "grad_norm": 0.1812741607427597,
1655
+ "learning_rate": 1.688430698739977e-05,
1656
+ "loss": 0.2849,
1657
+ "step": 233
1658
+ },
1659
+ {
1660
+ "epoch": 0.4816053511705686,
1661
+ "grad_norm": 0.18431834876537323,
1662
+ "learning_rate": 1.6861397479954183e-05,
1663
+ "loss": 0.2802,
1664
+ "step": 234
1665
+ },
1666
+ {
1667
+ "epoch": 0.4836634936969385,
1668
+ "grad_norm": 0.18349015712738037,
1669
+ "learning_rate": 1.6838487972508592e-05,
1670
+ "loss": 0.2804,
1671
+ "step": 235
1672
+ },
1673
+ {
1674
+ "epoch": 0.48572163622330844,
1675
+ "grad_norm": 0.1769968420267105,
1676
+ "learning_rate": 1.6815578465063e-05,
1677
+ "loss": 0.2777,
1678
+ "step": 236
1679
+ },
1680
+ {
1681
+ "epoch": 0.4877797787496784,
1682
+ "grad_norm": 0.17207500338554382,
1683
+ "learning_rate": 1.6792668957617413e-05,
1684
+ "loss": 0.2883,
1685
+ "step": 237
1686
+ },
1687
+ {
1688
+ "epoch": 0.48983792127604836,
1689
+ "grad_norm": 0.1729692667722702,
1690
+ "learning_rate": 1.6769759450171822e-05,
1691
+ "loss": 0.2784,
1692
+ "step": 238
1693
+ },
1694
+ {
1695
+ "epoch": 0.4918960638024183,
1696
+ "grad_norm": 0.17234881222248077,
1697
+ "learning_rate": 1.6746849942726235e-05,
1698
+ "loss": 0.2816,
1699
+ "step": 239
1700
+ },
1701
+ {
1702
+ "epoch": 0.4939542063287883,
1703
+ "grad_norm": 0.17132551968097687,
1704
+ "learning_rate": 1.6723940435280644e-05,
1705
+ "loss": 0.2812,
1706
+ "step": 240
1707
+ },
1708
+ {
1709
+ "epoch": 0.4960123488551582,
1710
+ "grad_norm": 0.1752254068851471,
1711
+ "learning_rate": 1.6701030927835052e-05,
1712
+ "loss": 0.2799,
1713
+ "step": 241
1714
+ },
1715
+ {
1716
+ "epoch": 0.49807049138152815,
1717
+ "grad_norm": 0.1768665313720703,
1718
+ "learning_rate": 1.6678121420389465e-05,
1719
+ "loss": 0.2966,
1720
+ "step": 242
1721
+ },
1722
+ {
1723
+ "epoch": 0.5001286339078981,
1724
+ "grad_norm": 0.18139514327049255,
1725
+ "learning_rate": 1.6655211912943874e-05,
1726
+ "loss": 0.2816,
1727
+ "step": 243
1728
+ },
1729
+ {
1730
+ "epoch": 0.5021867764342681,
1731
+ "grad_norm": 0.17312943935394287,
1732
+ "learning_rate": 1.6632302405498283e-05,
1733
+ "loss": 0.2845,
1734
+ "step": 244
1735
+ },
1736
+ {
1737
+ "epoch": 0.5042449189606381,
1738
+ "grad_norm": 0.17966389656066895,
1739
+ "learning_rate": 1.6609392898052695e-05,
1740
+ "loss": 0.2864,
1741
+ "step": 245
1742
+ },
1743
+ {
1744
+ "epoch": 0.506303061487008,
1745
+ "grad_norm": 0.16653811931610107,
1746
+ "learning_rate": 1.6586483390607104e-05,
1747
+ "loss": 0.2759,
1748
+ "step": 246
1749
+ },
1750
+ {
1751
+ "epoch": 0.5083612040133779,
1752
+ "grad_norm": 0.1634613424539566,
1753
+ "learning_rate": 1.6563573883161516e-05,
1754
+ "loss": 0.2728,
1755
+ "step": 247
1756
+ },
1757
+ {
1758
+ "epoch": 0.5104193465397479,
1759
+ "grad_norm": 0.17358507215976715,
1760
+ "learning_rate": 1.654066437571592e-05,
1761
+ "loss": 0.2706,
1762
+ "step": 248
1763
+ },
1764
+ {
1765
+ "epoch": 0.5124774890661178,
1766
+ "grad_norm": 0.17524316906929016,
1767
+ "learning_rate": 1.6517754868270334e-05,
1768
+ "loss": 0.2805,
1769
+ "step": 249
1770
+ },
1771
+ {
1772
+ "epoch": 0.5145356315924878,
1773
+ "grad_norm": 0.18134094774723053,
1774
+ "learning_rate": 1.6494845360824743e-05,
1775
+ "loss": 0.2909,
1776
+ "step": 250
1777
+ },
1778
+ {
1779
+ "epoch": 0.5165937741188578,
1780
+ "grad_norm": 0.17795510590076447,
1781
+ "learning_rate": 1.647193585337915e-05,
1782
+ "loss": 0.2889,
1783
+ "step": 251
1784
+ },
1785
+ {
1786
+ "epoch": 0.5186519166452277,
1787
+ "grad_norm": 0.16782547533512115,
1788
+ "learning_rate": 1.6449026345933564e-05,
1789
+ "loss": 0.2842,
1790
+ "step": 252
1791
+ },
1792
+ {
1793
+ "epoch": 0.5207100591715976,
1794
+ "grad_norm": 0.17360062897205353,
1795
+ "learning_rate": 1.6426116838487973e-05,
1796
+ "loss": 0.2763,
1797
+ "step": 253
1798
+ },
1799
+ {
1800
+ "epoch": 0.5227682016979676,
1801
+ "grad_norm": 0.17241406440734863,
1802
+ "learning_rate": 1.6403207331042385e-05,
1803
+ "loss": 0.2753,
1804
+ "step": 254
1805
+ },
1806
+ {
1807
+ "epoch": 0.5248263442243375,
1808
+ "grad_norm": 0.1709229201078415,
1809
+ "learning_rate": 1.6380297823596794e-05,
1810
+ "loss": 0.2732,
1811
+ "step": 255
1812
+ },
1813
+ {
1814
+ "epoch": 0.5268844867507075,
1815
+ "grad_norm": 0.1807374209165573,
1816
+ "learning_rate": 1.6357388316151203e-05,
1817
+ "loss": 0.2856,
1818
+ "step": 256
1819
+ },
1820
+ {
1821
+ "epoch": 0.5289426292770775,
1822
+ "grad_norm": 0.1749904304742813,
1823
+ "learning_rate": 1.6334478808705615e-05,
1824
+ "loss": 0.285,
1825
+ "step": 257
1826
+ },
1827
+ {
1828
+ "epoch": 0.5310007718034474,
1829
+ "grad_norm": 0.16673170030117035,
1830
+ "learning_rate": 1.6311569301260024e-05,
1831
+ "loss": 0.2825,
1832
+ "step": 258
1833
+ },
1834
+ {
1835
+ "epoch": 0.5330589143298173,
1836
+ "grad_norm": 0.17239685356616974,
1837
+ "learning_rate": 1.6288659793814433e-05,
1838
+ "loss": 0.2845,
1839
+ "step": 259
1840
+ },
1841
+ {
1842
+ "epoch": 0.5351170568561873,
1843
+ "grad_norm": 0.1831504851579666,
1844
+ "learning_rate": 1.6265750286368845e-05,
1845
+ "loss": 0.2859,
1846
+ "step": 260
1847
+ },
1848
+ {
1849
+ "epoch": 0.5371751993825572,
1850
+ "grad_norm": 0.18507827818393707,
1851
+ "learning_rate": 1.6242840778923254e-05,
1852
+ "loss": 0.293,
1853
+ "step": 261
1854
+ },
1855
+ {
1856
+ "epoch": 0.5392333419089272,
1857
+ "grad_norm": 0.16738134622573853,
1858
+ "learning_rate": 1.6219931271477663e-05,
1859
+ "loss": 0.2853,
1860
+ "step": 262
1861
+ },
1862
+ {
1863
+ "epoch": 0.5412914844352972,
1864
+ "grad_norm": 0.1701226830482483,
1865
+ "learning_rate": 1.6197021764032075e-05,
1866
+ "loss": 0.2763,
1867
+ "step": 263
1868
+ },
1869
+ {
1870
+ "epoch": 0.5433496269616671,
1871
+ "grad_norm": 0.18195705115795135,
1872
+ "learning_rate": 1.6174112256586484e-05,
1873
+ "loss": 0.2797,
1874
+ "step": 264
1875
+ },
1876
+ {
1877
+ "epoch": 0.545407769488037,
1878
+ "grad_norm": 0.1832309514284134,
1879
+ "learning_rate": 1.6151202749140896e-05,
1880
+ "loss": 0.2885,
1881
+ "step": 265
1882
+ },
1883
+ {
1884
+ "epoch": 0.547465912014407,
1885
+ "grad_norm": 0.1773810088634491,
1886
+ "learning_rate": 1.6128293241695305e-05,
1887
+ "loss": 0.2682,
1888
+ "step": 266
1889
+ },
1890
+ {
1891
+ "epoch": 0.5495240545407769,
1892
+ "grad_norm": 0.16989603638648987,
1893
+ "learning_rate": 1.6105383734249714e-05,
1894
+ "loss": 0.2821,
1895
+ "step": 267
1896
+ },
1897
+ {
1898
+ "epoch": 0.551582197067147,
1899
+ "grad_norm": 0.17835170030593872,
1900
+ "learning_rate": 1.6082474226804127e-05,
1901
+ "loss": 0.2774,
1902
+ "step": 268
1903
+ },
1904
+ {
1905
+ "epoch": 0.5536403395935169,
1906
+ "grad_norm": 0.1777082234621048,
1907
+ "learning_rate": 1.6059564719358535e-05,
1908
+ "loss": 0.2726,
1909
+ "step": 269
1910
+ },
1911
+ {
1912
+ "epoch": 0.5556984821198868,
1913
+ "grad_norm": 0.18766450881958008,
1914
+ "learning_rate": 1.6036655211912944e-05,
1915
+ "loss": 0.2879,
1916
+ "step": 270
1917
+ },
1918
+ {
1919
+ "epoch": 0.5577566246462567,
1920
+ "grad_norm": 0.1868186593055725,
1921
+ "learning_rate": 1.6013745704467357e-05,
1922
+ "loss": 0.2808,
1923
+ "step": 271
1924
+ },
1925
+ {
1926
+ "epoch": 0.5598147671726267,
1927
+ "grad_norm": 0.16695882380008698,
1928
+ "learning_rate": 1.5990836197021766e-05,
1929
+ "loss": 0.2668,
1930
+ "step": 272
1931
+ },
1932
+ {
1933
+ "epoch": 0.5618729096989966,
1934
+ "grad_norm": 0.17224495112895966,
1935
+ "learning_rate": 1.5967926689576178e-05,
1936
+ "loss": 0.2682,
1937
+ "step": 273
1938
+ },
1939
+ {
1940
+ "epoch": 0.5639310522253667,
1941
+ "grad_norm": 0.20116423070430756,
1942
+ "learning_rate": 1.5945017182130587e-05,
1943
+ "loss": 0.276,
1944
+ "step": 274
1945
+ },
1946
+ {
1947
+ "epoch": 0.5659891947517366,
1948
+ "grad_norm": 0.19478343427181244,
1949
+ "learning_rate": 1.5922107674684996e-05,
1950
+ "loss": 0.2854,
1951
+ "step": 275
1952
+ },
1953
+ {
1954
+ "epoch": 0.5680473372781065,
1955
+ "grad_norm": 0.20242950320243835,
1956
+ "learning_rate": 1.5899198167239405e-05,
1957
+ "loss": 0.2854,
1958
+ "step": 276
1959
+ },
1960
+ {
1961
+ "epoch": 0.5701054798044765,
1962
+ "grad_norm": 0.19146093726158142,
1963
+ "learning_rate": 1.5876288659793813e-05,
1964
+ "loss": 0.2817,
1965
+ "step": 277
1966
+ },
1967
+ {
1968
+ "epoch": 0.5721636223308464,
1969
+ "grad_norm": 0.1804896742105484,
1970
+ "learning_rate": 1.5853379152348226e-05,
1971
+ "loss": 0.2714,
1972
+ "step": 278
1973
+ },
1974
+ {
1975
+ "epoch": 0.5742217648572163,
1976
+ "grad_norm": 0.19315646588802338,
1977
+ "learning_rate": 1.5830469644902635e-05,
1978
+ "loss": 0.2703,
1979
+ "step": 279
1980
+ },
1981
+ {
1982
+ "epoch": 0.5762799073835864,
1983
+ "grad_norm": 0.1910266876220703,
1984
+ "learning_rate": 1.5807560137457047e-05,
1985
+ "loss": 0.2728,
1986
+ "step": 280
1987
+ },
1988
+ {
1989
+ "epoch": 0.5783380499099563,
1990
+ "grad_norm": 0.20330773293972015,
1991
+ "learning_rate": 1.5784650630011456e-05,
1992
+ "loss": 0.2717,
1993
+ "step": 281
1994
+ },
1995
+ {
1996
+ "epoch": 0.5803961924363262,
1997
+ "grad_norm": 0.19080683588981628,
1998
+ "learning_rate": 1.5761741122565865e-05,
1999
+ "loss": 0.2679,
2000
+ "step": 282
2001
+ },
2002
+ {
2003
+ "epoch": 0.5824543349626962,
2004
+ "grad_norm": 0.18052135407924652,
2005
+ "learning_rate": 1.5738831615120277e-05,
2006
+ "loss": 0.2815,
2007
+ "step": 283
2008
+ },
2009
+ {
2010
+ "epoch": 0.5845124774890661,
2011
+ "grad_norm": 0.1998361051082611,
2012
+ "learning_rate": 1.5715922107674686e-05,
2013
+ "loss": 0.2888,
2014
+ "step": 284
2015
+ },
2016
+ {
2017
+ "epoch": 0.586570620015436,
2018
+ "grad_norm": 0.1978764683008194,
2019
+ "learning_rate": 1.5693012600229095e-05,
2020
+ "loss": 0.2926,
2021
+ "step": 285
2022
+ },
2023
+ {
2024
+ "epoch": 0.5886287625418061,
2025
+ "grad_norm": 0.17189203202724457,
2026
+ "learning_rate": 1.5670103092783507e-05,
2027
+ "loss": 0.2674,
2028
+ "step": 286
2029
+ },
2030
+ {
2031
+ "epoch": 0.590686905068176,
2032
+ "grad_norm": 0.1937166303396225,
2033
+ "learning_rate": 1.5647193585337916e-05,
2034
+ "loss": 0.2838,
2035
+ "step": 287
2036
+ },
2037
+ {
2038
+ "epoch": 0.5927450475945459,
2039
+ "grad_norm": 0.18978627026081085,
2040
+ "learning_rate": 1.5624284077892328e-05,
2041
+ "loss": 0.273,
2042
+ "step": 288
2043
+ },
2044
+ {
2045
+ "epoch": 0.5948031901209159,
2046
+ "grad_norm": 0.17718705534934998,
2047
+ "learning_rate": 1.5601374570446737e-05,
2048
+ "loss": 0.2842,
2049
+ "step": 289
2050
+ },
2051
+ {
2052
+ "epoch": 0.5968613326472858,
2053
+ "grad_norm": 0.1912536770105362,
2054
+ "learning_rate": 1.5578465063001146e-05,
2055
+ "loss": 0.2736,
2056
+ "step": 290
2057
+ },
2058
+ {
2059
+ "epoch": 0.5989194751736557,
2060
+ "grad_norm": 0.18104907870292664,
2061
+ "learning_rate": 1.555555555555556e-05,
2062
+ "loss": 0.274,
2063
+ "step": 291
2064
+ },
2065
+ {
2066
+ "epoch": 0.6009776177000258,
2067
+ "grad_norm": 0.1620381772518158,
2068
+ "learning_rate": 1.5532646048109967e-05,
2069
+ "loss": 0.2663,
2070
+ "step": 292
2071
+ },
2072
+ {
2073
+ "epoch": 0.6030357602263957,
2074
+ "grad_norm": 0.17973916232585907,
2075
+ "learning_rate": 1.5509736540664376e-05,
2076
+ "loss": 0.2791,
2077
+ "step": 293
2078
+ },
2079
+ {
2080
+ "epoch": 0.6050939027527656,
2081
+ "grad_norm": 0.16821186244487762,
2082
+ "learning_rate": 1.548682703321879e-05,
2083
+ "loss": 0.2787,
2084
+ "step": 294
2085
+ },
2086
+ {
2087
+ "epoch": 0.6071520452791356,
2088
+ "grad_norm": 0.18426693975925446,
2089
+ "learning_rate": 1.5463917525773197e-05,
2090
+ "loss": 0.2886,
2091
+ "step": 295
2092
+ },
2093
+ {
2094
+ "epoch": 0.6092101878055055,
2095
+ "grad_norm": 0.19796033203601837,
2096
+ "learning_rate": 1.5441008018327606e-05,
2097
+ "loss": 0.268,
2098
+ "step": 296
2099
+ },
2100
+ {
2101
+ "epoch": 0.6112683303318754,
2102
+ "grad_norm": 0.1971343755722046,
2103
+ "learning_rate": 1.541809851088202e-05,
2104
+ "loss": 0.2761,
2105
+ "step": 297
2106
+ },
2107
+ {
2108
+ "epoch": 0.6133264728582455,
2109
+ "grad_norm": 0.17458567023277283,
2110
+ "learning_rate": 1.5395189003436427e-05,
2111
+ "loss": 0.2831,
2112
+ "step": 298
2113
+ },
2114
+ {
2115
+ "epoch": 0.6153846153846154,
2116
+ "grad_norm": 0.17610400915145874,
2117
+ "learning_rate": 1.537227949599084e-05,
2118
+ "loss": 0.2691,
2119
+ "step": 299
2120
+ },
2121
+ {
2122
+ "epoch": 0.6174427579109854,
2123
+ "grad_norm": 0.1929042488336563,
2124
+ "learning_rate": 1.534936998854525e-05,
2125
+ "loss": 0.2847,
2126
+ "step": 300
2127
+ },
2128
+ {
2129
+ "epoch": 0.6174427579109854,
2130
+ "eval_loss": 0.2959522604942322,
2131
+ "eval_runtime": 2428.6339,
2132
+ "eval_samples_per_second": 3.201,
2133
+ "eval_steps_per_second": 0.8,
2134
+ "step": 300
2135
+ }
2136
+ ],
2137
+ "logging_steps": 1,
2138
+ "max_steps": 970,
2139
+ "num_input_tokens_seen": 0,
2140
+ "num_train_epochs": 2,
2141
+ "save_steps": 100,
2142
+ "stateful_callbacks": {
2143
+ "TrainerControl": {
2144
+ "args": {
2145
+ "should_epoch_stop": false,
2146
+ "should_evaluate": false,
2147
+ "should_log": false,
2148
+ "should_save": true,
2149
+ "should_training_stop": false
2150
+ },
2151
+ "attributes": {}
2152
+ }
2153
+ },
2154
+ "total_flos": 9.916186406277612e+17,
2155
+ "train_batch_size": 4,
2156
+ "trial_name": null,
2157
+ "trial_params": null
2158
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee55a11f5a306eb7c39b536fdfe2459bc279e468da50f6adda478c4deffcb812
3
+ size 5688
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/codegemma-7b-it
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 0.15.0
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/codegemma-7b-it",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 64,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "gate_proj",
32
+ "k_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28d1150755988379f75a873814aff4bb698c6bfe61017321740de287540011d
3
+ size 800116456
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eaaabccd9eef6be0dbad53b8764bdb248322edd314f59dc0c08eeaa8b6aaea0
3
+ size 406743860
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d4fbb4eb2a12b17b73babfa38b90bdafc73a682a0af60498a1e002b1fd5b3a
3
+ size 14244
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4268342c3fe77dd38c7543ef5b2cdacbd82e8a3bb5c5cae6fb040e599526f0e
3
+ size 1064
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<bos>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<eos>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d964a2c8346d40f95791533eae48730d5f163c2e65fd16333560fd3e661df318
3
+ size 34362915
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583f2ebd2a1936009b7da991ea255504db68c7a9713a78673d1335a87098966c
3
+ size 4241023
codegemma_instruct_cot_ft_lora_r64_alpha64/checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,2011 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<eos>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<bos>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "5": {
46
+ "content": "<2mass>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "7": {
62
+ "content": "<unused0>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "8": {
70
+ "content": "<unused1>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "9": {
78
+ "content": "<unused2>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "10": {
86
+ "content": "<unused3>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "11": {
94
+ "content": "<unused4>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "12": {
102
+ "content": "<unused5>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "13": {
110
+ "content": "<unused6>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "14": {
118
+ "content": "<unused7>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "15": {
126
+ "content": "<unused8>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "16": {
134
+ "content": "<unused9>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "17": {
142
+ "content": "<unused10>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "18": {
150
+ "content": "<unused11>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "19": {
158
+ "content": "<unused12>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "20": {
166
+ "content": "<unused13>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "21": {
174
+ "content": "<unused14>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "22": {
182
+ "content": "<unused15>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "23": {
190
+ "content": "<unused16>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "24": {
198
+ "content": "<unused17>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "25": {
206
+ "content": "<unused18>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "26": {
214
+ "content": "<unused19>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "27": {
222
+ "content": "<unused20>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "28": {
230
+ "content": "<unused21>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "29": {
238
+ "content": "<unused22>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "30": {
246
+ "content": "<unused23>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "31": {
254
+ "content": "<unused24>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "32": {
262
+ "content": "<unused25>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "33": {
270
+ "content": "<unused26>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "34": {
278
+ "content": "<unused27>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "35": {
286
+ "content": "<unused28>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "36": {
294
+ "content": "<unused29>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "37": {
302
+ "content": "<unused30>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "38": {
310
+ "content": "<unused31>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ },
317
+ "39": {
318
+ "content": "<unused32>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": false
324
+ },
325
+ "40": {
326
+ "content": "<unused33>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": false
332
+ },
333
+ "41": {
334
+ "content": "<unused34>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": false
340
+ },
341
+ "42": {
342
+ "content": "<unused35>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": false
348
+ },
349
+ "43": {
350
+ "content": "<unused36>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": false
356
+ },
357
+ "44": {
358
+ "content": "<unused37>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": false
364
+ },
365
+ "45": {
366
+ "content": "<unused38>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": false
372
+ },
373
+ "46": {
374
+ "content": "<unused39>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": false
380
+ },
381
+ "47": {
382
+ "content": "<unused40>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": false
388
+ },
389
+ "48": {
390
+ "content": "<unused41>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": false
396
+ },
397
+ "49": {
398
+ "content": "<unused42>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": false
404
+ },
405
+ "50": {
406
+ "content": "<unused43>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "51": {
414
+ "content": "<unused44>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "52": {
422
+ "content": "<unused45>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "53": {
430
+ "content": "<unused46>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ },
437
+ "54": {
438
+ "content": "<unused47>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": false
444
+ },
445
+ "55": {
446
+ "content": "<unused48>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": false
452
+ },
453
+ "56": {
454
+ "content": "<unused49>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": false
460
+ },
461
+ "57": {
462
+ "content": "<unused50>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": false
468
+ },
469
+ "58": {
470
+ "content": "<unused51>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": false
476
+ },
477
+ "59": {
478
+ "content": "<unused52>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": false
484
+ },
485
+ "60": {
486
+ "content": "<unused53>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": false
492
+ },
493
+ "61": {
494
+ "content": "<unused54>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": false
500
+ },
501
+ "62": {
502
+ "content": "<unused55>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": false
508
+ },
509
+ "63": {
510
+ "content": "<unused56>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": false
516
+ },
517
+ "64": {
518
+ "content": "<unused57>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": false
524
+ },
525
+ "65": {
526
+ "content": "<unused58>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": false
532
+ },
533
+ "66": {
534
+ "content": "<unused59>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": false
540
+ },
541
+ "67": {
542
+ "content": "<|fim_prefix|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": false
548
+ },
549
+ "68": {
550
+ "content": "<|fim_middle|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": false
556
+ },
557
+ "69": {
558
+ "content": "<|fim_suffix|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": false
564
+ },
565
+ "70": {
566
+ "content": "<|file_separator|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": false
572
+ },
573
+ "71": {
574
+ "content": "<unused64>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": false
580
+ },
581
+ "72": {
582
+ "content": "<unused65>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": false
588
+ },
589
+ "73": {
590
+ "content": "<unused66>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": false
596
+ },
597
+ "74": {
598
+ "content": "<unused67>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": false
604
+ },
605
+ "75": {
606
+ "content": "<unused68>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": false
612
+ },
613
+ "76": {
614
+ "content": "<unused69>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": false
620
+ },
621
+ "77": {
622
+ "content": "<unused70>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": false
628
+ },
629
+ "78": {
630
+ "content": "<unused71>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": false
636
+ },
637
+ "79": {
638
+ "content": "<unused72>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": false
644
+ },
645
+ "80": {
646
+ "content": "<unused73>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": false
652
+ },
653
+ "81": {
654
+ "content": "<unused74>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": false
660
+ },
661
+ "82": {
662
+ "content": "<unused75>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": false
668
+ },
669
+ "83": {
670
+ "content": "<unused76>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": false
676
+ },
677
+ "84": {
678
+ "content": "<unused77>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": false
684
+ },
685
+ "85": {
686
+ "content": "<unused78>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": false
692
+ },
693
+ "86": {
694
+ "content": "<unused79>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": false
700
+ },
701
+ "87": {
702
+ "content": "<unused80>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": false
708
+ },
709
+ "88": {
710
+ "content": "<unused81>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": false
716
+ },
717
+ "89": {
718
+ "content": "<unused82>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": false
724
+ },
725
+ "90": {
726
+ "content": "<unused83>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": false
732
+ },
733
+ "91": {
734
+ "content": "<unused84>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": false
740
+ },
741
+ "92": {
742
+ "content": "<unused85>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": false
748
+ },
749
+ "93": {
750
+ "content": "<unused86>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": false
756
+ },
757
+ "94": {
758
+ "content": "<unused87>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": false
764
+ },
765
+ "95": {
766
+ "content": "<unused88>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": false
772
+ },
773
+ "96": {
774
+ "content": "<unused89>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": false
780
+ },
781
+ "97": {
782
+ "content": "<unused90>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": false
788
+ },
789
+ "98": {
790
+ "content": "<unused91>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": false
796
+ },
797
+ "99": {
798
+ "content": "<unused92>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": false
804
+ },
805
+ "100": {
806
+ "content": "<unused93>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": false
812
+ },
813
+ "101": {
814
+ "content": "<unused94>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": false
820
+ },
821
+ "102": {
822
+ "content": "<unused95>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": false
828
+ },
829
+ "103": {
830
+ "content": "<unused96>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": false
836
+ },
837
+ "104": {
838
+ "content": "<unused97>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": false
844
+ },
845
+ "105": {
846
+ "content": "<unused98>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": false
852
+ },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": false
860
+ },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": false
868
+ },
869
+ "108": {
870
+ "content": "\n",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": false
876
+ },
877
+ "109": {
878
+ "content": "\n\n",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": false
884
+ },
885
+ "110": {
886
+ "content": "\n\n\n",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": false
892
+ },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": false
900
+ },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": false
908
+ },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": false
916
+ },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": false
924
+ },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": false
932
+ },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": false
940
+ },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": false
948
+ },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": false
956
+ },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": false
964
+ },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": false
972
+ },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": false
980
+ },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": false
988
+ },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": false
996
+ },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": false
1004
+ },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": false
1012
+ },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": false
1020
+ },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": false
1028
+ },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": false
1036
+ },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": false
1044
+ },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": false
1052
+ },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": false
1060
+ },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": false
1068
+ },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": false
1076
+ },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": false
1084
+ },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": false
1092
+ },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": false
1100
+ },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": false
1108
+ },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": false
1116
+ },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": false
1124
+ },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": false
1132
+ },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": false
1140
+ },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": false
1148
+ },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": false
1156
+ },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": false
1164
+ },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": false
1172
+ },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": false
1180
+ },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": false
1188
+ },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": false
1196
+ },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": false
1204
+ },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": false
1212
+ },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": false
1220
+ },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": false
1228
+ },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": false
1236
+ },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": false
1244
+ },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": false
1252
+ },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": false
1260
+ },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": false
1268
+ },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": false
1276
+ },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": false
1284
+ },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": false
1292
+ },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": false
1300
+ },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": false
1308
+ },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": false
1316
+ },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": false
1324
+ },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": false
1332
+ },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": false
1340
+ },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": false
1348
+ },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": false
1356
+ },
1357
+ "169": {
1358
+ "content": "<table>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": false
1364
+ },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": false
1372
+ },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": false
1380
+ },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": false
1388
+ },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": false
1396
+ },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": false
1404
+ },
1405
+ "175": {
1406
+ "content": "<th>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": false
1412
+ },
1413
+ "176": {
1414
+ "content": "<td>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": false
1420
+ },
1421
+ "177": {
1422
+ "content": "</table>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": false
1428
+ },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": false
1436
+ },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": false
1444
+ },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": false
1452
+ },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": false
1460
+ },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": false
1468
+ },
1469
+ "183": {
1470
+ "content": "</th>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": false
1476
+ },
1477
+ "184": {
1478
+ "content": "</td>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": false
1484
+ },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": false
1492
+ },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": false
1500
+ },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": false
1508
+ },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": false
1516
+ },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": false
1524
+ },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": false
1532
+ },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": false
1540
+ },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": false
1548
+ },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": false
1556
+ },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": false
1564
+ },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": false
1572
+ },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": false
1580
+ },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": false
1588
+ },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": false
1596
+ },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": false
1604
+ },
1605
+ "200": {
1606
+ "content": "<em>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": false
1612
+ },
1613
+ "201": {
1614
+ "content": "<b>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": false
1620
+ },
1621
+ "202": {
1622
+ "content": "<i>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": false
1628
+ },
1629
+ "203": {
1630
+ "content": "<u>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": false
1636
+ },
1637
+ "204": {
1638
+ "content": "<s>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": false
1644
+ },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": false
1652
+ },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": false
1660
+ },
1661
+ "207": {
1662
+ "content": "<code>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": false
1668
+ },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": false
1676
+ },
1677
+ "209": {
1678
+ "content": "</em>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": false
1684
+ },
1685
+ "210": {
1686
+ "content": "</b>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": false
1692
+ },
1693
+ "211": {
1694
+ "content": "</i>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": false
1700
+ },
1701
+ "212": {
1702
+ "content": "</u>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": false
1708
+ },
1709
+ "213": {
1710
+ "content": "</s>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": false
1716
+ },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": false
1724
+ },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": false
1732
+ },
1733
+ "216": {
1734
+ "content": "</code>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": false
1740
+ },
1741
+ "255968": {
1742
+ "content": "[toxicity=0]",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": false
1748
+ },
1749
+ "255969": {
1750
+ "content": "\t\t",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": false
1756
+ },
1757
+ "255970": {
1758
+ "content": "\t\t\t",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": false
1764
+ },
1765
+ "255971": {
1766
+ "content": "\t\t\t\t",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": false
1772
+ },
1773
+ "255972": {
1774
+ "content": "\t\t\t\t\t",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": false
1780
+ },
1781
+ "255973": {
1782
+ "content": "\t\t\t\t\t\t",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": false
1788
+ },
1789
+ "255974": {
1790
+ "content": "\t\t\t\t\t\t\t",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": false
1796
+ },
1797
+ "255975": {
1798
+ "content": "\t\t\t\t\t\t\t\t",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": false
1804
+ },
1805
+ "255976": {
1806
+ "content": "\t\t\t\t\t\t\t\t\t",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": false
1812
+ },
1813
+ "255977": {
1814
+ "content": "\t\t\t\t\t\t\t\t\t\t",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": false
1820
+ },
1821
+ "255978": {
1822
+ "content": "\t\t\t\t\t\t\t\t\t\t\t",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": false
1828
+ },
1829
+ "255979": {
1830
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": false
1836
+ },
1837
+ "255980": {
1838
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": false
1844
+ },
1845
+ "255981": {
1846
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": false
1852
+ },
1853
+ "255982": {
1854
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": false
1860
+ },
1861
+ "255983": {
1862
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": false
1868
+ },
1869
+ "255984": {
1870
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": false
1876
+ },
1877
+ "255985": {
1878
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": false
1884
+ },
1885
+ "255986": {
1886
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": false
1892
+ },
1893
+ "255987": {
1894
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": false
1900
+ },
1901
+ "255988": {
1902
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": false
1908
+ },
1909
+ "255989": {
1910
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": false
1916
+ },
1917
+ "255990": {
1918
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": false
1924
+ },
1925
+ "255991": {
1926
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": false
1932
+ },
1933
+ "255992": {
1934
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": false
1940
+ },
1941
+ "255993": {
1942
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": false
1948
+ },
1949
+ "255994": {
1950
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": false
1956
+ },
1957
+ "255995": {
1958
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": false
1964
+ },
1965
+ "255996": {
1966
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": false
1972
+ },
1973
+ "255997": {
1974
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": false
1980
+ },
1981
+ "255998": {
1982
+ "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": false
1988
+ },
1989
+ "255999": {
1990
+ "content": "<unused99>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": false
1996
+ }
1997
+ },
1998
+ "bos_token": "<bos>",
1999
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
2000
+ "clean_up_tokenization_spaces": false,
2001
+ "eos_token": "<eos>",
2002
+ "extra_special_tokens": {},
2003
+ "model_max_length": 1000000000000000019884624838656,
2004
+ "pad_token": "<pad>",
2005
+ "padding_side": "left",
2006
+ "sp_model_kwargs": {},
2007
+ "spaces_between_special_tokens": false,
2008
+ "tokenizer_class": "GemmaTokenizer",
2009
+ "unk_token": "<unk>",
2010
+ "use_default_system_prompt": false
2011
+ }