miike-ai commited on
Commit
8dd2cf5
·
verified ·
1 Parent(s): 5a67331

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ 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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
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 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 64,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "up_proj",
28
+ "v_proj",
29
+ "o_proj",
30
+ "gate_proj",
31
+ "down_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be3c003d101e3692c4c6b25ec855eb4bff0e846171a67fa2acb6fe08ae81c81e
3
+ size 671149168
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0686860aa0a7b428472d5de9b8c0e6b0f7c542f824a396c9e29fa4ee5e0c4652
3
+ size 341323540
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8385a6e317599a86e0fe5738b39c6c65992d426bb9409a73fead1bd5a6b053e2
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4444096202171fe5c4d56c7d31e49feb755bbc38619a4d7e773f643fddfdece1
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin▁of▁sentence|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end▁of▁sentence|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f68c30a4056f2e5d53416b382e328409a81cfd495e74b7f8a5a14722c5df71
3
+ size 17209709
tokenizer_config.json ADDED
@@ -0,0 +1,2068 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "128000": {
7
+ "content": "<|begin▁of▁sentence|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "128001": {
15
+ "content": "<|end▁of▁sentence|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "128002": {
23
+ "content": "<|reserved_special_token_0|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "128003": {
31
+ "content": "<|reserved_special_token_1|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "128004": {
39
+ "content": "<|finetune_right_pad_id|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "128005": {
47
+ "content": "<|reserved_special_token_2|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "128006": {
55
+ "content": "<|start_header_id|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "128007": {
63
+ "content": "<|end_header_id|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "128008": {
71
+ "content": "<|eom_id|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "128009": {
79
+ "content": "<|eot_id|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "128010": {
87
+ "content": "<|python_tag|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "128011": {
95
+ "content": "<|User|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "128012": {
103
+ "content": "<|Assistant|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "128013": {
111
+ "content": "<think>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "128014": {
119
+ "content": "</think>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "128015": {
127
+ "content": "<|▁pad▁|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "128016": {
135
+ "content": "<|reserved_special_token_8|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "128017": {
143
+ "content": "<|reserved_special_token_9|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "128018": {
151
+ "content": "<|reserved_special_token_10|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "128019": {
159
+ "content": "<|reserved_special_token_11|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "128020": {
167
+ "content": "<|reserved_special_token_12|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "128021": {
175
+ "content": "<|reserved_special_token_13|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "128022": {
183
+ "content": "<|reserved_special_token_14|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "128023": {
191
+ "content": "<|reserved_special_token_15|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "128024": {
199
+ "content": "<|reserved_special_token_16|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "128025": {
207
+ "content": "<|reserved_special_token_17|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "128026": {
215
+ "content": "<|reserved_special_token_18|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "128027": {
223
+ "content": "<|reserved_special_token_19|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "128028": {
231
+ "content": "<|reserved_special_token_20|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "128029": {
239
+ "content": "<|reserved_special_token_21|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "128030": {
247
+ "content": "<|reserved_special_token_22|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "128031": {
255
+ "content": "<|reserved_special_token_23|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "128032": {
263
+ "content": "<|reserved_special_token_24|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "128033": {
271
+ "content": "<|reserved_special_token_25|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "128034": {
279
+ "content": "<|reserved_special_token_26|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "128035": {
287
+ "content": "<|reserved_special_token_27|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "128036": {
295
+ "content": "<|reserved_special_token_28|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "128037": {
303
+ "content": "<|reserved_special_token_29|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "128038": {
311
+ "content": "<|reserved_special_token_30|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "128039": {
319
+ "content": "<|reserved_special_token_31|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "128040": {
327
+ "content": "<|reserved_special_token_32|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "128041": {
335
+ "content": "<|reserved_special_token_33|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "128042": {
343
+ "content": "<|reserved_special_token_34|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "128043": {
351
+ "content": "<|reserved_special_token_35|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "128044": {
359
+ "content": "<|reserved_special_token_36|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "128045": {
367
+ "content": "<|reserved_special_token_37|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "128046": {
375
+ "content": "<|reserved_special_token_38|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "128047": {
383
+ "content": "<|reserved_special_token_39|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "128048": {
391
+ "content": "<|reserved_special_token_40|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "128049": {
399
+ "content": "<|reserved_special_token_41|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "128050": {
407
+ "content": "<|reserved_special_token_42|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "128051": {
415
+ "content": "<|reserved_special_token_43|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "128052": {
423
+ "content": "<|reserved_special_token_44|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "128053": {
431
+ "content": "<|reserved_special_token_45|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "128054": {
439
+ "content": "<|reserved_special_token_46|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "128055": {
447
+ "content": "<|reserved_special_token_47|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "128056": {
455
+ "content": "<|reserved_special_token_48|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "128057": {
463
+ "content": "<|reserved_special_token_49|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "128058": {
471
+ "content": "<|reserved_special_token_50|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "128059": {
479
+ "content": "<|reserved_special_token_51|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "128060": {
487
+ "content": "<|reserved_special_token_52|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "128061": {
495
+ "content": "<|reserved_special_token_53|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "128062": {
503
+ "content": "<|reserved_special_token_54|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "128063": {
511
+ "content": "<|reserved_special_token_55|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "128064": {
519
+ "content": "<|reserved_special_token_56|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "128065": {
527
+ "content": "<|reserved_special_token_57|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "128066": {
535
+ "content": "<|reserved_special_token_58|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ },
542
+ "128067": {
543
+ "content": "<|reserved_special_token_59|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false,
548
+ "special": true
549
+ },
550
+ "128068": {
551
+ "content": "<|reserved_special_token_60|>",
552
+ "lstrip": false,
553
+ "normalized": false,
554
+ "rstrip": false,
555
+ "single_word": false,
556
+ "special": true
557
+ },
558
+ "128069": {
559
+ "content": "<|reserved_special_token_61|>",
560
+ "lstrip": false,
561
+ "normalized": false,
562
+ "rstrip": false,
563
+ "single_word": false,
564
+ "special": true
565
+ },
566
+ "128070": {
567
+ "content": "<|reserved_special_token_62|>",
568
+ "lstrip": false,
569
+ "normalized": false,
570
+ "rstrip": false,
571
+ "single_word": false,
572
+ "special": true
573
+ },
574
+ "128071": {
575
+ "content": "<|reserved_special_token_63|>",
576
+ "lstrip": false,
577
+ "normalized": false,
578
+ "rstrip": false,
579
+ "single_word": false,
580
+ "special": true
581
+ },
582
+ "128072": {
583
+ "content": "<|reserved_special_token_64|>",
584
+ "lstrip": false,
585
+ "normalized": false,
586
+ "rstrip": false,
587
+ "single_word": false,
588
+ "special": true
589
+ },
590
+ "128073": {
591
+ "content": "<|reserved_special_token_65|>",
592
+ "lstrip": false,
593
+ "normalized": false,
594
+ "rstrip": false,
595
+ "single_word": false,
596
+ "special": true
597
+ },
598
+ "128074": {
599
+ "content": "<|reserved_special_token_66|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false,
604
+ "special": true
605
+ },
606
+ "128075": {
607
+ "content": "<|reserved_special_token_67|>",
608
+ "lstrip": false,
609
+ "normalized": false,
610
+ "rstrip": false,
611
+ "single_word": false,
612
+ "special": true
613
+ },
614
+ "128076": {
615
+ "content": "<|reserved_special_token_68|>",
616
+ "lstrip": false,
617
+ "normalized": false,
618
+ "rstrip": false,
619
+ "single_word": false,
620
+ "special": true
621
+ },
622
+ "128077": {
623
+ "content": "<|reserved_special_token_69|>",
624
+ "lstrip": false,
625
+ "normalized": false,
626
+ "rstrip": false,
627
+ "single_word": false,
628
+ "special": true
629
+ },
630
+ "128078": {
631
+ "content": "<|reserved_special_token_70|>",
632
+ "lstrip": false,
633
+ "normalized": false,
634
+ "rstrip": false,
635
+ "single_word": false,
636
+ "special": true
637
+ },
638
+ "128079": {
639
+ "content": "<|reserved_special_token_71|>",
640
+ "lstrip": false,
641
+ "normalized": false,
642
+ "rstrip": false,
643
+ "single_word": false,
644
+ "special": true
645
+ },
646
+ "128080": {
647
+ "content": "<|reserved_special_token_72|>",
648
+ "lstrip": false,
649
+ "normalized": false,
650
+ "rstrip": false,
651
+ "single_word": false,
652
+ "special": true
653
+ },
654
+ "128081": {
655
+ "content": "<|reserved_special_token_73|>",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false,
660
+ "special": true
661
+ },
662
+ "128082": {
663
+ "content": "<|reserved_special_token_74|>",
664
+ "lstrip": false,
665
+ "normalized": false,
666
+ "rstrip": false,
667
+ "single_word": false,
668
+ "special": true
669
+ },
670
+ "128083": {
671
+ "content": "<|reserved_special_token_75|>",
672
+ "lstrip": false,
673
+ "normalized": false,
674
+ "rstrip": false,
675
+ "single_word": false,
676
+ "special": true
677
+ },
678
+ "128084": {
679
+ "content": "<|reserved_special_token_76|>",
680
+ "lstrip": false,
681
+ "normalized": false,
682
+ "rstrip": false,
683
+ "single_word": false,
684
+ "special": true
685
+ },
686
+ "128085": {
687
+ "content": "<|reserved_special_token_77|>",
688
+ "lstrip": false,
689
+ "normalized": false,
690
+ "rstrip": false,
691
+ "single_word": false,
692
+ "special": true
693
+ },
694
+ "128086": {
695
+ "content": "<|reserved_special_token_78|>",
696
+ "lstrip": false,
697
+ "normalized": false,
698
+ "rstrip": false,
699
+ "single_word": false,
700
+ "special": true
701
+ },
702
+ "128087": {
703
+ "content": "<|reserved_special_token_79|>",
704
+ "lstrip": false,
705
+ "normalized": false,
706
+ "rstrip": false,
707
+ "single_word": false,
708
+ "special": true
709
+ },
710
+ "128088": {
711
+ "content": "<|reserved_special_token_80|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false,
716
+ "special": true
717
+ },
718
+ "128089": {
719
+ "content": "<|reserved_special_token_81|>",
720
+ "lstrip": false,
721
+ "normalized": false,
722
+ "rstrip": false,
723
+ "single_word": false,
724
+ "special": true
725
+ },
726
+ "128090": {
727
+ "content": "<|reserved_special_token_82|>",
728
+ "lstrip": false,
729
+ "normalized": false,
730
+ "rstrip": false,
731
+ "single_word": false,
732
+ "special": true
733
+ },
734
+ "128091": {
735
+ "content": "<|reserved_special_token_83|>",
736
+ "lstrip": false,
737
+ "normalized": false,
738
+ "rstrip": false,
739
+ "single_word": false,
740
+ "special": true
741
+ },
742
+ "128092": {
743
+ "content": "<|reserved_special_token_84|>",
744
+ "lstrip": false,
745
+ "normalized": false,
746
+ "rstrip": false,
747
+ "single_word": false,
748
+ "special": true
749
+ },
750
+ "128093": {
751
+ "content": "<|reserved_special_token_85|>",
752
+ "lstrip": false,
753
+ "normalized": false,
754
+ "rstrip": false,
755
+ "single_word": false,
756
+ "special": true
757
+ },
758
+ "128094": {
759
+ "content": "<|reserved_special_token_86|>",
760
+ "lstrip": false,
761
+ "normalized": false,
762
+ "rstrip": false,
763
+ "single_word": false,
764
+ "special": true
765
+ },
766
+ "128095": {
767
+ "content": "<|reserved_special_token_87|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false,
772
+ "special": true
773
+ },
774
+ "128096": {
775
+ "content": "<|reserved_special_token_88|>",
776
+ "lstrip": false,
777
+ "normalized": false,
778
+ "rstrip": false,
779
+ "single_word": false,
780
+ "special": true
781
+ },
782
+ "128097": {
783
+ "content": "<|reserved_special_token_89|>",
784
+ "lstrip": false,
785
+ "normalized": false,
786
+ "rstrip": false,
787
+ "single_word": false,
788
+ "special": true
789
+ },
790
+ "128098": {
791
+ "content": "<|reserved_special_token_90|>",
792
+ "lstrip": false,
793
+ "normalized": false,
794
+ "rstrip": false,
795
+ "single_word": false,
796
+ "special": true
797
+ },
798
+ "128099": {
799
+ "content": "<|reserved_special_token_91|>",
800
+ "lstrip": false,
801
+ "normalized": false,
802
+ "rstrip": false,
803
+ "single_word": false,
804
+ "special": true
805
+ },
806
+ "128100": {
807
+ "content": "<|reserved_special_token_92|>",
808
+ "lstrip": false,
809
+ "normalized": false,
810
+ "rstrip": false,
811
+ "single_word": false,
812
+ "special": true
813
+ },
814
+ "128101": {
815
+ "content": "<|reserved_special_token_93|>",
816
+ "lstrip": false,
817
+ "normalized": false,
818
+ "rstrip": false,
819
+ "single_word": false,
820
+ "special": true
821
+ },
822
+ "128102": {
823
+ "content": "<|reserved_special_token_94|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false,
828
+ "special": true
829
+ },
830
+ "128103": {
831
+ "content": "<|reserved_special_token_95|>",
832
+ "lstrip": false,
833
+ "normalized": false,
834
+ "rstrip": false,
835
+ "single_word": false,
836
+ "special": true
837
+ },
838
+ "128104": {
839
+ "content": "<|reserved_special_token_96|>",
840
+ "lstrip": false,
841
+ "normalized": false,
842
+ "rstrip": false,
843
+ "single_word": false,
844
+ "special": true
845
+ },
846
+ "128105": {
847
+ "content": "<|reserved_special_token_97|>",
848
+ "lstrip": false,
849
+ "normalized": false,
850
+ "rstrip": false,
851
+ "single_word": false,
852
+ "special": true
853
+ },
854
+ "128106": {
855
+ "content": "<|reserved_special_token_98|>",
856
+ "lstrip": false,
857
+ "normalized": false,
858
+ "rstrip": false,
859
+ "single_word": false,
860
+ "special": true
861
+ },
862
+ "128107": {
863
+ "content": "<|reserved_special_token_99|>",
864
+ "lstrip": false,
865
+ "normalized": false,
866
+ "rstrip": false,
867
+ "single_word": false,
868
+ "special": true
869
+ },
870
+ "128108": {
871
+ "content": "<|reserved_special_token_100|>",
872
+ "lstrip": false,
873
+ "normalized": false,
874
+ "rstrip": false,
875
+ "single_word": false,
876
+ "special": true
877
+ },
878
+ "128109": {
879
+ "content": "<|reserved_special_token_101|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false,
884
+ "special": true
885
+ },
886
+ "128110": {
887
+ "content": "<|reserved_special_token_102|>",
888
+ "lstrip": false,
889
+ "normalized": false,
890
+ "rstrip": false,
891
+ "single_word": false,
892
+ "special": true
893
+ },
894
+ "128111": {
895
+ "content": "<|reserved_special_token_103|>",
896
+ "lstrip": false,
897
+ "normalized": false,
898
+ "rstrip": false,
899
+ "single_word": false,
900
+ "special": true
901
+ },
902
+ "128112": {
903
+ "content": "<|reserved_special_token_104|>",
904
+ "lstrip": false,
905
+ "normalized": false,
906
+ "rstrip": false,
907
+ "single_word": false,
908
+ "special": true
909
+ },
910
+ "128113": {
911
+ "content": "<|reserved_special_token_105|>",
912
+ "lstrip": false,
913
+ "normalized": false,
914
+ "rstrip": false,
915
+ "single_word": false,
916
+ "special": true
917
+ },
918
+ "128114": {
919
+ "content": "<|reserved_special_token_106|>",
920
+ "lstrip": false,
921
+ "normalized": false,
922
+ "rstrip": false,
923
+ "single_word": false,
924
+ "special": true
925
+ },
926
+ "128115": {
927
+ "content": "<|reserved_special_token_107|>",
928
+ "lstrip": false,
929
+ "normalized": false,
930
+ "rstrip": false,
931
+ "single_word": false,
932
+ "special": true
933
+ },
934
+ "128116": {
935
+ "content": "<|reserved_special_token_108|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false,
940
+ "special": true
941
+ },
942
+ "128117": {
943
+ "content": "<|reserved_special_token_109|>",
944
+ "lstrip": false,
945
+ "normalized": false,
946
+ "rstrip": false,
947
+ "single_word": false,
948
+ "special": true
949
+ },
950
+ "128118": {
951
+ "content": "<|reserved_special_token_110|>",
952
+ "lstrip": false,
953
+ "normalized": false,
954
+ "rstrip": false,
955
+ "single_word": false,
956
+ "special": true
957
+ },
958
+ "128119": {
959
+ "content": "<|reserved_special_token_111|>",
960
+ "lstrip": false,
961
+ "normalized": false,
962
+ "rstrip": false,
963
+ "single_word": false,
964
+ "special": true
965
+ },
966
+ "128120": {
967
+ "content": "<|reserved_special_token_112|>",
968
+ "lstrip": false,
969
+ "normalized": false,
970
+ "rstrip": false,
971
+ "single_word": false,
972
+ "special": true
973
+ },
974
+ "128121": {
975
+ "content": "<|reserved_special_token_113|>",
976
+ "lstrip": false,
977
+ "normalized": false,
978
+ "rstrip": false,
979
+ "single_word": false,
980
+ "special": true
981
+ },
982
+ "128122": {
983
+ "content": "<|reserved_special_token_114|>",
984
+ "lstrip": false,
985
+ "normalized": false,
986
+ "rstrip": false,
987
+ "single_word": false,
988
+ "special": true
989
+ },
990
+ "128123": {
991
+ "content": "<|reserved_special_token_115|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false,
996
+ "special": true
997
+ },
998
+ "128124": {
999
+ "content": "<|reserved_special_token_116|>",
1000
+ "lstrip": false,
1001
+ "normalized": false,
1002
+ "rstrip": false,
1003
+ "single_word": false,
1004
+ "special": true
1005
+ },
1006
+ "128125": {
1007
+ "content": "<|reserved_special_token_117|>",
1008
+ "lstrip": false,
1009
+ "normalized": false,
1010
+ "rstrip": false,
1011
+ "single_word": false,
1012
+ "special": true
1013
+ },
1014
+ "128126": {
1015
+ "content": "<|reserved_special_token_118|>",
1016
+ "lstrip": false,
1017
+ "normalized": false,
1018
+ "rstrip": false,
1019
+ "single_word": false,
1020
+ "special": true
1021
+ },
1022
+ "128127": {
1023
+ "content": "<|reserved_special_token_119|>",
1024
+ "lstrip": false,
1025
+ "normalized": false,
1026
+ "rstrip": false,
1027
+ "single_word": false,
1028
+ "special": true
1029
+ },
1030
+ "128128": {
1031
+ "content": "<|reserved_special_token_120|>",
1032
+ "lstrip": false,
1033
+ "normalized": false,
1034
+ "rstrip": false,
1035
+ "single_word": false,
1036
+ "special": true
1037
+ },
1038
+ "128129": {
1039
+ "content": "<|reserved_special_token_121|>",
1040
+ "lstrip": false,
1041
+ "normalized": false,
1042
+ "rstrip": false,
1043
+ "single_word": false,
1044
+ "special": true
1045
+ },
1046
+ "128130": {
1047
+ "content": "<|reserved_special_token_122|>",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false,
1052
+ "special": true
1053
+ },
1054
+ "128131": {
1055
+ "content": "<|reserved_special_token_123|>",
1056
+ "lstrip": false,
1057
+ "normalized": false,
1058
+ "rstrip": false,
1059
+ "single_word": false,
1060
+ "special": true
1061
+ },
1062
+ "128132": {
1063
+ "content": "<|reserved_special_token_124|>",
1064
+ "lstrip": false,
1065
+ "normalized": false,
1066
+ "rstrip": false,
1067
+ "single_word": false,
1068
+ "special": true
1069
+ },
1070
+ "128133": {
1071
+ "content": "<|reserved_special_token_125|>",
1072
+ "lstrip": false,
1073
+ "normalized": false,
1074
+ "rstrip": false,
1075
+ "single_word": false,
1076
+ "special": true
1077
+ },
1078
+ "128134": {
1079
+ "content": "<|reserved_special_token_126|>",
1080
+ "lstrip": false,
1081
+ "normalized": false,
1082
+ "rstrip": false,
1083
+ "single_word": false,
1084
+ "special": true
1085
+ },
1086
+ "128135": {
1087
+ "content": "<|reserved_special_token_127|>",
1088
+ "lstrip": false,
1089
+ "normalized": false,
1090
+ "rstrip": false,
1091
+ "single_word": false,
1092
+ "special": true
1093
+ },
1094
+ "128136": {
1095
+ "content": "<|reserved_special_token_128|>",
1096
+ "lstrip": false,
1097
+ "normalized": false,
1098
+ "rstrip": false,
1099
+ "single_word": false,
1100
+ "special": true
1101
+ },
1102
+ "128137": {
1103
+ "content": "<|reserved_special_token_129|>",
1104
+ "lstrip": false,
1105
+ "normalized": false,
1106
+ "rstrip": false,
1107
+ "single_word": false,
1108
+ "special": true
1109
+ },
1110
+ "128138": {
1111
+ "content": "<|reserved_special_token_130|>",
1112
+ "lstrip": false,
1113
+ "normalized": false,
1114
+ "rstrip": false,
1115
+ "single_word": false,
1116
+ "special": true
1117
+ },
1118
+ "128139": {
1119
+ "content": "<|reserved_special_token_131|>",
1120
+ "lstrip": false,
1121
+ "normalized": false,
1122
+ "rstrip": false,
1123
+ "single_word": false,
1124
+ "special": true
1125
+ },
1126
+ "128140": {
1127
+ "content": "<|reserved_special_token_132|>",
1128
+ "lstrip": false,
1129
+ "normalized": false,
1130
+ "rstrip": false,
1131
+ "single_word": false,
1132
+ "special": true
1133
+ },
1134
+ "128141": {
1135
+ "content": "<|reserved_special_token_133|>",
1136
+ "lstrip": false,
1137
+ "normalized": false,
1138
+ "rstrip": false,
1139
+ "single_word": false,
1140
+ "special": true
1141
+ },
1142
+ "128142": {
1143
+ "content": "<|reserved_special_token_134|>",
1144
+ "lstrip": false,
1145
+ "normalized": false,
1146
+ "rstrip": false,
1147
+ "single_word": false,
1148
+ "special": true
1149
+ },
1150
+ "128143": {
1151
+ "content": "<|reserved_special_token_135|>",
1152
+ "lstrip": false,
1153
+ "normalized": false,
1154
+ "rstrip": false,
1155
+ "single_word": false,
1156
+ "special": true
1157
+ },
1158
+ "128144": {
1159
+ "content": "<|reserved_special_token_136|>",
1160
+ "lstrip": false,
1161
+ "normalized": false,
1162
+ "rstrip": false,
1163
+ "single_word": false,
1164
+ "special": true
1165
+ },
1166
+ "128145": {
1167
+ "content": "<|reserved_special_token_137|>",
1168
+ "lstrip": false,
1169
+ "normalized": false,
1170
+ "rstrip": false,
1171
+ "single_word": false,
1172
+ "special": true
1173
+ },
1174
+ "128146": {
1175
+ "content": "<|reserved_special_token_138|>",
1176
+ "lstrip": false,
1177
+ "normalized": false,
1178
+ "rstrip": false,
1179
+ "single_word": false,
1180
+ "special": true
1181
+ },
1182
+ "128147": {
1183
+ "content": "<|reserved_special_token_139|>",
1184
+ "lstrip": false,
1185
+ "normalized": false,
1186
+ "rstrip": false,
1187
+ "single_word": false,
1188
+ "special": true
1189
+ },
1190
+ "128148": {
1191
+ "content": "<|reserved_special_token_140|>",
1192
+ "lstrip": false,
1193
+ "normalized": false,
1194
+ "rstrip": false,
1195
+ "single_word": false,
1196
+ "special": true
1197
+ },
1198
+ "128149": {
1199
+ "content": "<|reserved_special_token_141|>",
1200
+ "lstrip": false,
1201
+ "normalized": false,
1202
+ "rstrip": false,
1203
+ "single_word": false,
1204
+ "special": true
1205
+ },
1206
+ "128150": {
1207
+ "content": "<|reserved_special_token_142|>",
1208
+ "lstrip": false,
1209
+ "normalized": false,
1210
+ "rstrip": false,
1211
+ "single_word": false,
1212
+ "special": true
1213
+ },
1214
+ "128151": {
1215
+ "content": "<|reserved_special_token_143|>",
1216
+ "lstrip": false,
1217
+ "normalized": false,
1218
+ "rstrip": false,
1219
+ "single_word": false,
1220
+ "special": true
1221
+ },
1222
+ "128152": {
1223
+ "content": "<|reserved_special_token_144|>",
1224
+ "lstrip": false,
1225
+ "normalized": false,
1226
+ "rstrip": false,
1227
+ "single_word": false,
1228
+ "special": true
1229
+ },
1230
+ "128153": {
1231
+ "content": "<|reserved_special_token_145|>",
1232
+ "lstrip": false,
1233
+ "normalized": false,
1234
+ "rstrip": false,
1235
+ "single_word": false,
1236
+ "special": true
1237
+ },
1238
+ "128154": {
1239
+ "content": "<|reserved_special_token_146|>",
1240
+ "lstrip": false,
1241
+ "normalized": false,
1242
+ "rstrip": false,
1243
+ "single_word": false,
1244
+ "special": true
1245
+ },
1246
+ "128155": {
1247
+ "content": "<|reserved_special_token_147|>",
1248
+ "lstrip": false,
1249
+ "normalized": false,
1250
+ "rstrip": false,
1251
+ "single_word": false,
1252
+ "special": true
1253
+ },
1254
+ "128156": {
1255
+ "content": "<|reserved_special_token_148|>",
1256
+ "lstrip": false,
1257
+ "normalized": false,
1258
+ "rstrip": false,
1259
+ "single_word": false,
1260
+ "special": true
1261
+ },
1262
+ "128157": {
1263
+ "content": "<|reserved_special_token_149|>",
1264
+ "lstrip": false,
1265
+ "normalized": false,
1266
+ "rstrip": false,
1267
+ "single_word": false,
1268
+ "special": true
1269
+ },
1270
+ "128158": {
1271
+ "content": "<|reserved_special_token_150|>",
1272
+ "lstrip": false,
1273
+ "normalized": false,
1274
+ "rstrip": false,
1275
+ "single_word": false,
1276
+ "special": true
1277
+ },
1278
+ "128159": {
1279
+ "content": "<|reserved_special_token_151|>",
1280
+ "lstrip": false,
1281
+ "normalized": false,
1282
+ "rstrip": false,
1283
+ "single_word": false,
1284
+ "special": true
1285
+ },
1286
+ "128160": {
1287
+ "content": "<|reserved_special_token_152|>",
1288
+ "lstrip": false,
1289
+ "normalized": false,
1290
+ "rstrip": false,
1291
+ "single_word": false,
1292
+ "special": true
1293
+ },
1294
+ "128161": {
1295
+ "content": "<|reserved_special_token_153|>",
1296
+ "lstrip": false,
1297
+ "normalized": false,
1298
+ "rstrip": false,
1299
+ "single_word": false,
1300
+ "special": true
1301
+ },
1302
+ "128162": {
1303
+ "content": "<|reserved_special_token_154|>",
1304
+ "lstrip": false,
1305
+ "normalized": false,
1306
+ "rstrip": false,
1307
+ "single_word": false,
1308
+ "special": true
1309
+ },
1310
+ "128163": {
1311
+ "content": "<|reserved_special_token_155|>",
1312
+ "lstrip": false,
1313
+ "normalized": false,
1314
+ "rstrip": false,
1315
+ "single_word": false,
1316
+ "special": true
1317
+ },
1318
+ "128164": {
1319
+ "content": "<|reserved_special_token_156|>",
1320
+ "lstrip": false,
1321
+ "normalized": false,
1322
+ "rstrip": false,
1323
+ "single_word": false,
1324
+ "special": true
1325
+ },
1326
+ "128165": {
1327
+ "content": "<|reserved_special_token_157|>",
1328
+ "lstrip": false,
1329
+ "normalized": false,
1330
+ "rstrip": false,
1331
+ "single_word": false,
1332
+ "special": true
1333
+ },
1334
+ "128166": {
1335
+ "content": "<|reserved_special_token_158|>",
1336
+ "lstrip": false,
1337
+ "normalized": false,
1338
+ "rstrip": false,
1339
+ "single_word": false,
1340
+ "special": true
1341
+ },
1342
+ "128167": {
1343
+ "content": "<|reserved_special_token_159|>",
1344
+ "lstrip": false,
1345
+ "normalized": false,
1346
+ "rstrip": false,
1347
+ "single_word": false,
1348
+ "special": true
1349
+ },
1350
+ "128168": {
1351
+ "content": "<|reserved_special_token_160|>",
1352
+ "lstrip": false,
1353
+ "normalized": false,
1354
+ "rstrip": false,
1355
+ "single_word": false,
1356
+ "special": true
1357
+ },
1358
+ "128169": {
1359
+ "content": "<|reserved_special_token_161|>",
1360
+ "lstrip": false,
1361
+ "normalized": false,
1362
+ "rstrip": false,
1363
+ "single_word": false,
1364
+ "special": true
1365
+ },
1366
+ "128170": {
1367
+ "content": "<|reserved_special_token_162|>",
1368
+ "lstrip": false,
1369
+ "normalized": false,
1370
+ "rstrip": false,
1371
+ "single_word": false,
1372
+ "special": true
1373
+ },
1374
+ "128171": {
1375
+ "content": "<|reserved_special_token_163|>",
1376
+ "lstrip": false,
1377
+ "normalized": false,
1378
+ "rstrip": false,
1379
+ "single_word": false,
1380
+ "special": true
1381
+ },
1382
+ "128172": {
1383
+ "content": "<|reserved_special_token_164|>",
1384
+ "lstrip": false,
1385
+ "normalized": false,
1386
+ "rstrip": false,
1387
+ "single_word": false,
1388
+ "special": true
1389
+ },
1390
+ "128173": {
1391
+ "content": "<|reserved_special_token_165|>",
1392
+ "lstrip": false,
1393
+ "normalized": false,
1394
+ "rstrip": false,
1395
+ "single_word": false,
1396
+ "special": true
1397
+ },
1398
+ "128174": {
1399
+ "content": "<|reserved_special_token_166|>",
1400
+ "lstrip": false,
1401
+ "normalized": false,
1402
+ "rstrip": false,
1403
+ "single_word": false,
1404
+ "special": true
1405
+ },
1406
+ "128175": {
1407
+ "content": "<|reserved_special_token_167|>",
1408
+ "lstrip": false,
1409
+ "normalized": false,
1410
+ "rstrip": false,
1411
+ "single_word": false,
1412
+ "special": true
1413
+ },
1414
+ "128176": {
1415
+ "content": "<|reserved_special_token_168|>",
1416
+ "lstrip": false,
1417
+ "normalized": false,
1418
+ "rstrip": false,
1419
+ "single_word": false,
1420
+ "special": true
1421
+ },
1422
+ "128177": {
1423
+ "content": "<|reserved_special_token_169|>",
1424
+ "lstrip": false,
1425
+ "normalized": false,
1426
+ "rstrip": false,
1427
+ "single_word": false,
1428
+ "special": true
1429
+ },
1430
+ "128178": {
1431
+ "content": "<|reserved_special_token_170|>",
1432
+ "lstrip": false,
1433
+ "normalized": false,
1434
+ "rstrip": false,
1435
+ "single_word": false,
1436
+ "special": true
1437
+ },
1438
+ "128179": {
1439
+ "content": "<|reserved_special_token_171|>",
1440
+ "lstrip": false,
1441
+ "normalized": false,
1442
+ "rstrip": false,
1443
+ "single_word": false,
1444
+ "special": true
1445
+ },
1446
+ "128180": {
1447
+ "content": "<|reserved_special_token_172|>",
1448
+ "lstrip": false,
1449
+ "normalized": false,
1450
+ "rstrip": false,
1451
+ "single_word": false,
1452
+ "special": true
1453
+ },
1454
+ "128181": {
1455
+ "content": "<|reserved_special_token_173|>",
1456
+ "lstrip": false,
1457
+ "normalized": false,
1458
+ "rstrip": false,
1459
+ "single_word": false,
1460
+ "special": true
1461
+ },
1462
+ "128182": {
1463
+ "content": "<|reserved_special_token_174|>",
1464
+ "lstrip": false,
1465
+ "normalized": false,
1466
+ "rstrip": false,
1467
+ "single_word": false,
1468
+ "special": true
1469
+ },
1470
+ "128183": {
1471
+ "content": "<|reserved_special_token_175|>",
1472
+ "lstrip": false,
1473
+ "normalized": false,
1474
+ "rstrip": false,
1475
+ "single_word": false,
1476
+ "special": true
1477
+ },
1478
+ "128184": {
1479
+ "content": "<|reserved_special_token_176|>",
1480
+ "lstrip": false,
1481
+ "normalized": false,
1482
+ "rstrip": false,
1483
+ "single_word": false,
1484
+ "special": true
1485
+ },
1486
+ "128185": {
1487
+ "content": "<|reserved_special_token_177|>",
1488
+ "lstrip": false,
1489
+ "normalized": false,
1490
+ "rstrip": false,
1491
+ "single_word": false,
1492
+ "special": true
1493
+ },
1494
+ "128186": {
1495
+ "content": "<|reserved_special_token_178|>",
1496
+ "lstrip": false,
1497
+ "normalized": false,
1498
+ "rstrip": false,
1499
+ "single_word": false,
1500
+ "special": true
1501
+ },
1502
+ "128187": {
1503
+ "content": "<|reserved_special_token_179|>",
1504
+ "lstrip": false,
1505
+ "normalized": false,
1506
+ "rstrip": false,
1507
+ "single_word": false,
1508
+ "special": true
1509
+ },
1510
+ "128188": {
1511
+ "content": "<|reserved_special_token_180|>",
1512
+ "lstrip": false,
1513
+ "normalized": false,
1514
+ "rstrip": false,
1515
+ "single_word": false,
1516
+ "special": true
1517
+ },
1518
+ "128189": {
1519
+ "content": "<|reserved_special_token_181|>",
1520
+ "lstrip": false,
1521
+ "normalized": false,
1522
+ "rstrip": false,
1523
+ "single_word": false,
1524
+ "special": true
1525
+ },
1526
+ "128190": {
1527
+ "content": "<|reserved_special_token_182|>",
1528
+ "lstrip": false,
1529
+ "normalized": false,
1530
+ "rstrip": false,
1531
+ "single_word": false,
1532
+ "special": true
1533
+ },
1534
+ "128191": {
1535
+ "content": "<|reserved_special_token_183|>",
1536
+ "lstrip": false,
1537
+ "normalized": false,
1538
+ "rstrip": false,
1539
+ "single_word": false,
1540
+ "special": true
1541
+ },
1542
+ "128192": {
1543
+ "content": "<|reserved_special_token_184|>",
1544
+ "lstrip": false,
1545
+ "normalized": false,
1546
+ "rstrip": false,
1547
+ "single_word": false,
1548
+ "special": true
1549
+ },
1550
+ "128193": {
1551
+ "content": "<|reserved_special_token_185|>",
1552
+ "lstrip": false,
1553
+ "normalized": false,
1554
+ "rstrip": false,
1555
+ "single_word": false,
1556
+ "special": true
1557
+ },
1558
+ "128194": {
1559
+ "content": "<|reserved_special_token_186|>",
1560
+ "lstrip": false,
1561
+ "normalized": false,
1562
+ "rstrip": false,
1563
+ "single_word": false,
1564
+ "special": true
1565
+ },
1566
+ "128195": {
1567
+ "content": "<|reserved_special_token_187|>",
1568
+ "lstrip": false,
1569
+ "normalized": false,
1570
+ "rstrip": false,
1571
+ "single_word": false,
1572
+ "special": true
1573
+ },
1574
+ "128196": {
1575
+ "content": "<|reserved_special_token_188|>",
1576
+ "lstrip": false,
1577
+ "normalized": false,
1578
+ "rstrip": false,
1579
+ "single_word": false,
1580
+ "special": true
1581
+ },
1582
+ "128197": {
1583
+ "content": "<|reserved_special_token_189|>",
1584
+ "lstrip": false,
1585
+ "normalized": false,
1586
+ "rstrip": false,
1587
+ "single_word": false,
1588
+ "special": true
1589
+ },
1590
+ "128198": {
1591
+ "content": "<|reserved_special_token_190|>",
1592
+ "lstrip": false,
1593
+ "normalized": false,
1594
+ "rstrip": false,
1595
+ "single_word": false,
1596
+ "special": true
1597
+ },
1598
+ "128199": {
1599
+ "content": "<|reserved_special_token_191|>",
1600
+ "lstrip": false,
1601
+ "normalized": false,
1602
+ "rstrip": false,
1603
+ "single_word": false,
1604
+ "special": true
1605
+ },
1606
+ "128200": {
1607
+ "content": "<|reserved_special_token_192|>",
1608
+ "lstrip": false,
1609
+ "normalized": false,
1610
+ "rstrip": false,
1611
+ "single_word": false,
1612
+ "special": true
1613
+ },
1614
+ "128201": {
1615
+ "content": "<|reserved_special_token_193|>",
1616
+ "lstrip": false,
1617
+ "normalized": false,
1618
+ "rstrip": false,
1619
+ "single_word": false,
1620
+ "special": true
1621
+ },
1622
+ "128202": {
1623
+ "content": "<|reserved_special_token_194|>",
1624
+ "lstrip": false,
1625
+ "normalized": false,
1626
+ "rstrip": false,
1627
+ "single_word": false,
1628
+ "special": true
1629
+ },
1630
+ "128203": {
1631
+ "content": "<|reserved_special_token_195|>",
1632
+ "lstrip": false,
1633
+ "normalized": false,
1634
+ "rstrip": false,
1635
+ "single_word": false,
1636
+ "special": true
1637
+ },
1638
+ "128204": {
1639
+ "content": "<|reserved_special_token_196|>",
1640
+ "lstrip": false,
1641
+ "normalized": false,
1642
+ "rstrip": false,
1643
+ "single_word": false,
1644
+ "special": true
1645
+ },
1646
+ "128205": {
1647
+ "content": "<|reserved_special_token_197|>",
1648
+ "lstrip": false,
1649
+ "normalized": false,
1650
+ "rstrip": false,
1651
+ "single_word": false,
1652
+ "special": true
1653
+ },
1654
+ "128206": {
1655
+ "content": "<|reserved_special_token_198|>",
1656
+ "lstrip": false,
1657
+ "normalized": false,
1658
+ "rstrip": false,
1659
+ "single_word": false,
1660
+ "special": true
1661
+ },
1662
+ "128207": {
1663
+ "content": "<|reserved_special_token_199|>",
1664
+ "lstrip": false,
1665
+ "normalized": false,
1666
+ "rstrip": false,
1667
+ "single_word": false,
1668
+ "special": true
1669
+ },
1670
+ "128208": {
1671
+ "content": "<|reserved_special_token_200|>",
1672
+ "lstrip": false,
1673
+ "normalized": false,
1674
+ "rstrip": false,
1675
+ "single_word": false,
1676
+ "special": true
1677
+ },
1678
+ "128209": {
1679
+ "content": "<|reserved_special_token_201|>",
1680
+ "lstrip": false,
1681
+ "normalized": false,
1682
+ "rstrip": false,
1683
+ "single_word": false,
1684
+ "special": true
1685
+ },
1686
+ "128210": {
1687
+ "content": "<|reserved_special_token_202|>",
1688
+ "lstrip": false,
1689
+ "normalized": false,
1690
+ "rstrip": false,
1691
+ "single_word": false,
1692
+ "special": true
1693
+ },
1694
+ "128211": {
1695
+ "content": "<|reserved_special_token_203|>",
1696
+ "lstrip": false,
1697
+ "normalized": false,
1698
+ "rstrip": false,
1699
+ "single_word": false,
1700
+ "special": true
1701
+ },
1702
+ "128212": {
1703
+ "content": "<|reserved_special_token_204|>",
1704
+ "lstrip": false,
1705
+ "normalized": false,
1706
+ "rstrip": false,
1707
+ "single_word": false,
1708
+ "special": true
1709
+ },
1710
+ "128213": {
1711
+ "content": "<|reserved_special_token_205|>",
1712
+ "lstrip": false,
1713
+ "normalized": false,
1714
+ "rstrip": false,
1715
+ "single_word": false,
1716
+ "special": true
1717
+ },
1718
+ "128214": {
1719
+ "content": "<|reserved_special_token_206|>",
1720
+ "lstrip": false,
1721
+ "normalized": false,
1722
+ "rstrip": false,
1723
+ "single_word": false,
1724
+ "special": true
1725
+ },
1726
+ "128215": {
1727
+ "content": "<|reserved_special_token_207|>",
1728
+ "lstrip": false,
1729
+ "normalized": false,
1730
+ "rstrip": false,
1731
+ "single_word": false,
1732
+ "special": true
1733
+ },
1734
+ "128216": {
1735
+ "content": "<|reserved_special_token_208|>",
1736
+ "lstrip": false,
1737
+ "normalized": false,
1738
+ "rstrip": false,
1739
+ "single_word": false,
1740
+ "special": true
1741
+ },
1742
+ "128217": {
1743
+ "content": "<|reserved_special_token_209|>",
1744
+ "lstrip": false,
1745
+ "normalized": false,
1746
+ "rstrip": false,
1747
+ "single_word": false,
1748
+ "special": true
1749
+ },
1750
+ "128218": {
1751
+ "content": "<|reserved_special_token_210|>",
1752
+ "lstrip": false,
1753
+ "normalized": false,
1754
+ "rstrip": false,
1755
+ "single_word": false,
1756
+ "special": true
1757
+ },
1758
+ "128219": {
1759
+ "content": "<|reserved_special_token_211|>",
1760
+ "lstrip": false,
1761
+ "normalized": false,
1762
+ "rstrip": false,
1763
+ "single_word": false,
1764
+ "special": true
1765
+ },
1766
+ "128220": {
1767
+ "content": "<|reserved_special_token_212|>",
1768
+ "lstrip": false,
1769
+ "normalized": false,
1770
+ "rstrip": false,
1771
+ "single_word": false,
1772
+ "special": true
1773
+ },
1774
+ "128221": {
1775
+ "content": "<|reserved_special_token_213|>",
1776
+ "lstrip": false,
1777
+ "normalized": false,
1778
+ "rstrip": false,
1779
+ "single_word": false,
1780
+ "special": true
1781
+ },
1782
+ "128222": {
1783
+ "content": "<|reserved_special_token_214|>",
1784
+ "lstrip": false,
1785
+ "normalized": false,
1786
+ "rstrip": false,
1787
+ "single_word": false,
1788
+ "special": true
1789
+ },
1790
+ "128223": {
1791
+ "content": "<|reserved_special_token_215|>",
1792
+ "lstrip": false,
1793
+ "normalized": false,
1794
+ "rstrip": false,
1795
+ "single_word": false,
1796
+ "special": true
1797
+ },
1798
+ "128224": {
1799
+ "content": "<|reserved_special_token_216|>",
1800
+ "lstrip": false,
1801
+ "normalized": false,
1802
+ "rstrip": false,
1803
+ "single_word": false,
1804
+ "special": true
1805
+ },
1806
+ "128225": {
1807
+ "content": "<|reserved_special_token_217|>",
1808
+ "lstrip": false,
1809
+ "normalized": false,
1810
+ "rstrip": false,
1811
+ "single_word": false,
1812
+ "special": true
1813
+ },
1814
+ "128226": {
1815
+ "content": "<|reserved_special_token_218|>",
1816
+ "lstrip": false,
1817
+ "normalized": false,
1818
+ "rstrip": false,
1819
+ "single_word": false,
1820
+ "special": true
1821
+ },
1822
+ "128227": {
1823
+ "content": "<|reserved_special_token_219|>",
1824
+ "lstrip": false,
1825
+ "normalized": false,
1826
+ "rstrip": false,
1827
+ "single_word": false,
1828
+ "special": true
1829
+ },
1830
+ "128228": {
1831
+ "content": "<|reserved_special_token_220|>",
1832
+ "lstrip": false,
1833
+ "normalized": false,
1834
+ "rstrip": false,
1835
+ "single_word": false,
1836
+ "special": true
1837
+ },
1838
+ "128229": {
1839
+ "content": "<|reserved_special_token_221|>",
1840
+ "lstrip": false,
1841
+ "normalized": false,
1842
+ "rstrip": false,
1843
+ "single_word": false,
1844
+ "special": true
1845
+ },
1846
+ "128230": {
1847
+ "content": "<|reserved_special_token_222|>",
1848
+ "lstrip": false,
1849
+ "normalized": false,
1850
+ "rstrip": false,
1851
+ "single_word": false,
1852
+ "special": true
1853
+ },
1854
+ "128231": {
1855
+ "content": "<|reserved_special_token_223|>",
1856
+ "lstrip": false,
1857
+ "normalized": false,
1858
+ "rstrip": false,
1859
+ "single_word": false,
1860
+ "special": true
1861
+ },
1862
+ "128232": {
1863
+ "content": "<|reserved_special_token_224|>",
1864
+ "lstrip": false,
1865
+ "normalized": false,
1866
+ "rstrip": false,
1867
+ "single_word": false,
1868
+ "special": true
1869
+ },
1870
+ "128233": {
1871
+ "content": "<|reserved_special_token_225|>",
1872
+ "lstrip": false,
1873
+ "normalized": false,
1874
+ "rstrip": false,
1875
+ "single_word": false,
1876
+ "special": true
1877
+ },
1878
+ "128234": {
1879
+ "content": "<|reserved_special_token_226|>",
1880
+ "lstrip": false,
1881
+ "normalized": false,
1882
+ "rstrip": false,
1883
+ "single_word": false,
1884
+ "special": true
1885
+ },
1886
+ "128235": {
1887
+ "content": "<|reserved_special_token_227|>",
1888
+ "lstrip": false,
1889
+ "normalized": false,
1890
+ "rstrip": false,
1891
+ "single_word": false,
1892
+ "special": true
1893
+ },
1894
+ "128236": {
1895
+ "content": "<|reserved_special_token_228|>",
1896
+ "lstrip": false,
1897
+ "normalized": false,
1898
+ "rstrip": false,
1899
+ "single_word": false,
1900
+ "special": true
1901
+ },
1902
+ "128237": {
1903
+ "content": "<|reserved_special_token_229|>",
1904
+ "lstrip": false,
1905
+ "normalized": false,
1906
+ "rstrip": false,
1907
+ "single_word": false,
1908
+ "special": true
1909
+ },
1910
+ "128238": {
1911
+ "content": "<|reserved_special_token_230|>",
1912
+ "lstrip": false,
1913
+ "normalized": false,
1914
+ "rstrip": false,
1915
+ "single_word": false,
1916
+ "special": true
1917
+ },
1918
+ "128239": {
1919
+ "content": "<|reserved_special_token_231|>",
1920
+ "lstrip": false,
1921
+ "normalized": false,
1922
+ "rstrip": false,
1923
+ "single_word": false,
1924
+ "special": true
1925
+ },
1926
+ "128240": {
1927
+ "content": "<|reserved_special_token_232|>",
1928
+ "lstrip": false,
1929
+ "normalized": false,
1930
+ "rstrip": false,
1931
+ "single_word": false,
1932
+ "special": true
1933
+ },
1934
+ "128241": {
1935
+ "content": "<|reserved_special_token_233|>",
1936
+ "lstrip": false,
1937
+ "normalized": false,
1938
+ "rstrip": false,
1939
+ "single_word": false,
1940
+ "special": true
1941
+ },
1942
+ "128242": {
1943
+ "content": "<|reserved_special_token_234|>",
1944
+ "lstrip": false,
1945
+ "normalized": false,
1946
+ "rstrip": false,
1947
+ "single_word": false,
1948
+ "special": true
1949
+ },
1950
+ "128243": {
1951
+ "content": "<|reserved_special_token_235|>",
1952
+ "lstrip": false,
1953
+ "normalized": false,
1954
+ "rstrip": false,
1955
+ "single_word": false,
1956
+ "special": true
1957
+ },
1958
+ "128244": {
1959
+ "content": "<|reserved_special_token_236|>",
1960
+ "lstrip": false,
1961
+ "normalized": false,
1962
+ "rstrip": false,
1963
+ "single_word": false,
1964
+ "special": true
1965
+ },
1966
+ "128245": {
1967
+ "content": "<|reserved_special_token_237|>",
1968
+ "lstrip": false,
1969
+ "normalized": false,
1970
+ "rstrip": false,
1971
+ "single_word": false,
1972
+ "special": true
1973
+ },
1974
+ "128246": {
1975
+ "content": "<|reserved_special_token_238|>",
1976
+ "lstrip": false,
1977
+ "normalized": false,
1978
+ "rstrip": false,
1979
+ "single_word": false,
1980
+ "special": true
1981
+ },
1982
+ "128247": {
1983
+ "content": "<|reserved_special_token_239|>",
1984
+ "lstrip": false,
1985
+ "normalized": false,
1986
+ "rstrip": false,
1987
+ "single_word": false,
1988
+ "special": true
1989
+ },
1990
+ "128248": {
1991
+ "content": "<|reserved_special_token_240|>",
1992
+ "lstrip": false,
1993
+ "normalized": false,
1994
+ "rstrip": false,
1995
+ "single_word": false,
1996
+ "special": true
1997
+ },
1998
+ "128249": {
1999
+ "content": "<|reserved_special_token_241|>",
2000
+ "lstrip": false,
2001
+ "normalized": false,
2002
+ "rstrip": false,
2003
+ "single_word": false,
2004
+ "special": true
2005
+ },
2006
+ "128250": {
2007
+ "content": "<|reserved_special_token_242|>",
2008
+ "lstrip": false,
2009
+ "normalized": false,
2010
+ "rstrip": false,
2011
+ "single_word": false,
2012
+ "special": true
2013
+ },
2014
+ "128251": {
2015
+ "content": "<|reserved_special_token_243|>",
2016
+ "lstrip": false,
2017
+ "normalized": false,
2018
+ "rstrip": false,
2019
+ "single_word": false,
2020
+ "special": true
2021
+ },
2022
+ "128252": {
2023
+ "content": "<|reserved_special_token_244|>",
2024
+ "lstrip": false,
2025
+ "normalized": false,
2026
+ "rstrip": false,
2027
+ "single_word": false,
2028
+ "special": true
2029
+ },
2030
+ "128253": {
2031
+ "content": "<|reserved_special_token_245|>",
2032
+ "lstrip": false,
2033
+ "normalized": false,
2034
+ "rstrip": false,
2035
+ "single_word": false,
2036
+ "special": true
2037
+ },
2038
+ "128254": {
2039
+ "content": "<|reserved_special_token_246|>",
2040
+ "lstrip": false,
2041
+ "normalized": false,
2042
+ "rstrip": false,
2043
+ "single_word": false,
2044
+ "special": true
2045
+ },
2046
+ "128255": {
2047
+ "content": "<|reserved_special_token_247|>",
2048
+ "lstrip": false,
2049
+ "normalized": false,
2050
+ "rstrip": false,
2051
+ "single_word": false,
2052
+ "special": true
2053
+ }
2054
+ },
2055
+ "bos_token": "<|begin▁of▁sentence|>",
2056
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}",
2057
+ "clean_up_tokenization_spaces": false,
2058
+ "eos_token": "<|end▁of▁sentence|>",
2059
+ "extra_special_tokens": {},
2060
+ "legacy": true,
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "right",
2064
+ "sp_model_kwargs": {},
2065
+ "tokenizer_class": "LlamaTokenizer",
2066
+ "unk_token": null,
2067
+ "use_default_system_prompt": false
2068
+ }
trainer_state.json ADDED
@@ -0,0 +1,1633 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8403361344537815,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "completion_length": 208.0,
13
+ "epoch": 0.008403361344537815,
14
+ "grad_norm": 0.0,
15
+ "kl": 0.0,
16
+ "learning_rate": 5.0000000000000004e-08,
17
+ "loss": 0.0,
18
+ "reward": 0.25,
19
+ "reward_std": 0.0,
20
+ "rewards/correctness_reward_func": 0.0,
21
+ "rewards/int_reward_func": 0.0,
22
+ "rewards/soft_format_reward_func": 0.0,
23
+ "rewards/strict_format_reward_func": 0.0,
24
+ "rewards/xmlcount_reward_func": 0.25,
25
+ "step": 1
26
+ },
27
+ {
28
+ "completion_length": 256.0,
29
+ "epoch": 0.01680672268907563,
30
+ "grad_norm": 0.0,
31
+ "kl": 0.0,
32
+ "learning_rate": 1.0000000000000001e-07,
33
+ "loss": 0.0,
34
+ "reward": 0.125,
35
+ "reward_std": 0.0,
36
+ "rewards/correctness_reward_func": 0.0,
37
+ "rewards/int_reward_func": 0.0,
38
+ "rewards/soft_format_reward_func": 0.0,
39
+ "rewards/strict_format_reward_func": 0.0,
40
+ "rewards/xmlcount_reward_func": 0.125,
41
+ "step": 2
42
+ },
43
+ {
44
+ "completion_length": 256.0,
45
+ "epoch": 0.025210084033613446,
46
+ "grad_norm": 0.0,
47
+ "kl": 0.0,
48
+ "learning_rate": 1.5000000000000002e-07,
49
+ "loss": 0.0,
50
+ "reward": 0.25,
51
+ "reward_std": 0.0,
52
+ "rewards/correctness_reward_func": 0.0,
53
+ "rewards/int_reward_func": 0.0,
54
+ "rewards/soft_format_reward_func": 0.0,
55
+ "rewards/strict_format_reward_func": 0.0,
56
+ "rewards/xmlcount_reward_func": 0.25,
57
+ "step": 3
58
+ },
59
+ {
60
+ "completion_length": 256.0,
61
+ "epoch": 0.03361344537815126,
62
+ "grad_norm": 0.8838915228843689,
63
+ "kl": 0.0,
64
+ "learning_rate": 2.0000000000000002e-07,
65
+ "loss": 0.0,
66
+ "reward": 0.1875,
67
+ "reward_std": 0.0883883461356163,
68
+ "rewards/correctness_reward_func": 0.0,
69
+ "rewards/int_reward_func": 0.0,
70
+ "rewards/soft_format_reward_func": 0.0,
71
+ "rewards/strict_format_reward_func": 0.0,
72
+ "rewards/xmlcount_reward_func": 0.1875,
73
+ "step": 4
74
+ },
75
+ {
76
+ "completion_length": 256.0,
77
+ "epoch": 0.04201680672268908,
78
+ "grad_norm": 0.8301438093185425,
79
+ "kl": 0.0009573494317010045,
80
+ "learning_rate": 2.5000000000000004e-07,
81
+ "loss": 0.0,
82
+ "reward": 0.1875,
83
+ "reward_std": 0.0883883461356163,
84
+ "rewards/correctness_reward_func": 0.0,
85
+ "rewards/int_reward_func": 0.0,
86
+ "rewards/soft_format_reward_func": 0.0,
87
+ "rewards/strict_format_reward_func": 0.0,
88
+ "rewards/xmlcount_reward_func": 0.1875,
89
+ "step": 5
90
+ },
91
+ {
92
+ "completion_length": 256.0,
93
+ "epoch": 0.05042016806722689,
94
+ "grad_norm": 1.043217658996582,
95
+ "kl": 0.0007592927431687713,
96
+ "learning_rate": 3.0000000000000004e-07,
97
+ "loss": 0.0,
98
+ "reward": 0.1875,
99
+ "reward_std": 0.0883883461356163,
100
+ "rewards/correctness_reward_func": 0.0,
101
+ "rewards/int_reward_func": 0.0,
102
+ "rewards/soft_format_reward_func": 0.0,
103
+ "rewards/strict_format_reward_func": 0.0,
104
+ "rewards/xmlcount_reward_func": 0.1875,
105
+ "step": 6
106
+ },
107
+ {
108
+ "completion_length": 235.5,
109
+ "epoch": 0.058823529411764705,
110
+ "grad_norm": 1.012459635734558,
111
+ "kl": 0.0005637629656121135,
112
+ "learning_rate": 3.5000000000000004e-07,
113
+ "loss": 0.0,
114
+ "reward": 0.1875,
115
+ "reward_std": 0.0883883461356163,
116
+ "rewards/correctness_reward_func": 0.0,
117
+ "rewards/int_reward_func": 0.0,
118
+ "rewards/soft_format_reward_func": 0.0,
119
+ "rewards/strict_format_reward_func": 0.0,
120
+ "rewards/xmlcount_reward_func": 0.1875,
121
+ "step": 7
122
+ },
123
+ {
124
+ "completion_length": 256.0,
125
+ "epoch": 0.06722689075630252,
126
+ "grad_norm": 0.005794348195195198,
127
+ "kl": 0.0007739531574770808,
128
+ "learning_rate": 4.0000000000000003e-07,
129
+ "loss": 0.0,
130
+ "reward": 0.125,
131
+ "reward_std": 0.0,
132
+ "rewards/correctness_reward_func": 0.0,
133
+ "rewards/int_reward_func": 0.0,
134
+ "rewards/soft_format_reward_func": 0.0,
135
+ "rewards/strict_format_reward_func": 0.0,
136
+ "rewards/xmlcount_reward_func": 0.125,
137
+ "step": 8
138
+ },
139
+ {
140
+ "completion_length": 256.0,
141
+ "epoch": 0.07563025210084033,
142
+ "grad_norm": 0.0030261946376413107,
143
+ "kl": 0.00047754880506545305,
144
+ "learning_rate": 4.5000000000000003e-07,
145
+ "loss": 0.0,
146
+ "reward": 0.125,
147
+ "reward_std": 0.0,
148
+ "rewards/correctness_reward_func": 0.0,
149
+ "rewards/int_reward_func": 0.0,
150
+ "rewards/soft_format_reward_func": 0.0,
151
+ "rewards/strict_format_reward_func": 0.0,
152
+ "rewards/xmlcount_reward_func": 0.125,
153
+ "step": 9
154
+ },
155
+ {
156
+ "completion_length": 154.0,
157
+ "epoch": 0.08403361344537816,
158
+ "grad_norm": 1.6739884614944458,
159
+ "kl": 0.0011951741762459278,
160
+ "learning_rate": 5.000000000000001e-07,
161
+ "loss": 0.0,
162
+ "reward": 0.1875,
163
+ "reward_std": 0.0883883461356163,
164
+ "rewards/correctness_reward_func": 0.0,
165
+ "rewards/int_reward_func": 0.0,
166
+ "rewards/soft_format_reward_func": 0.0,
167
+ "rewards/strict_format_reward_func": 0.0,
168
+ "rewards/xmlcount_reward_func": 0.1875,
169
+ "step": 10
170
+ },
171
+ {
172
+ "completion_length": 216.0,
173
+ "epoch": 0.09243697478991597,
174
+ "grad_norm": 1.0617121458053589,
175
+ "kl": 0.0005866724532097578,
176
+ "learning_rate": 5.5e-07,
177
+ "loss": 0.0,
178
+ "reward": 0.1875,
179
+ "reward_std": 0.0883883461356163,
180
+ "rewards/correctness_reward_func": 0.0,
181
+ "rewards/int_reward_func": 0.0,
182
+ "rewards/soft_format_reward_func": 0.0,
183
+ "rewards/strict_format_reward_func": 0.0,
184
+ "rewards/xmlcount_reward_func": 0.1875,
185
+ "step": 11
186
+ },
187
+ {
188
+ "completion_length": 256.0,
189
+ "epoch": 0.10084033613445378,
190
+ "grad_norm": 0.9380314350128174,
191
+ "kl": 0.0006365124136209488,
192
+ "learning_rate": 6.000000000000001e-07,
193
+ "loss": 0.0,
194
+ "reward": 0.1875,
195
+ "reward_std": 0.0883883461356163,
196
+ "rewards/correctness_reward_func": 0.0,
197
+ "rewards/int_reward_func": 0.0,
198
+ "rewards/soft_format_reward_func": 0.0,
199
+ "rewards/strict_format_reward_func": 0.0,
200
+ "rewards/xmlcount_reward_func": 0.1875,
201
+ "step": 12
202
+ },
203
+ {
204
+ "completion_length": 256.0,
205
+ "epoch": 0.1092436974789916,
206
+ "grad_norm": 0.004214159213006496,
207
+ "kl": 0.0007441662019118667,
208
+ "learning_rate": 6.5e-07,
209
+ "loss": 0.0,
210
+ "reward": 0.125,
211
+ "reward_std": 0.0,
212
+ "rewards/correctness_reward_func": 0.0,
213
+ "rewards/int_reward_func": 0.0,
214
+ "rewards/soft_format_reward_func": 0.0,
215
+ "rewards/strict_format_reward_func": 0.0,
216
+ "rewards/xmlcount_reward_func": 0.125,
217
+ "step": 13
218
+ },
219
+ {
220
+ "completion_length": 182.0,
221
+ "epoch": 0.11764705882352941,
222
+ "grad_norm": 1.2295690774917603,
223
+ "kl": 0.0007082950905896723,
224
+ "learning_rate": 7.000000000000001e-07,
225
+ "loss": 0.0,
226
+ "reward": 0.1875,
227
+ "reward_std": 0.0883883461356163,
228
+ "rewards/correctness_reward_func": 0.0,
229
+ "rewards/int_reward_func": 0.0,
230
+ "rewards/soft_format_reward_func": 0.0,
231
+ "rewards/strict_format_reward_func": 0.0,
232
+ "rewards/xmlcount_reward_func": 0.1875,
233
+ "step": 14
234
+ },
235
+ {
236
+ "completion_length": 256.0,
237
+ "epoch": 0.12605042016806722,
238
+ "grad_norm": 0.004315641708672047,
239
+ "kl": 0.0006666813278570771,
240
+ "learning_rate": 7.5e-07,
241
+ "loss": 0.0,
242
+ "reward": 0.125,
243
+ "reward_std": 0.0,
244
+ "rewards/correctness_reward_func": 0.0,
245
+ "rewards/int_reward_func": 0.0,
246
+ "rewards/soft_format_reward_func": 0.0,
247
+ "rewards/strict_format_reward_func": 0.0,
248
+ "rewards/xmlcount_reward_func": 0.125,
249
+ "step": 15
250
+ },
251
+ {
252
+ "completion_length": 256.0,
253
+ "epoch": 0.13445378151260504,
254
+ "grad_norm": 0.8514454364776611,
255
+ "kl": 0.0004808601224794984,
256
+ "learning_rate": 8.000000000000001e-07,
257
+ "loss": 0.0,
258
+ "reward": 0.1875,
259
+ "reward_std": 0.0883883461356163,
260
+ "rewards/correctness_reward_func": 0.0,
261
+ "rewards/int_reward_func": 0.0,
262
+ "rewards/soft_format_reward_func": 0.0,
263
+ "rewards/strict_format_reward_func": 0.0,
264
+ "rewards/xmlcount_reward_func": 0.1875,
265
+ "step": 16
266
+ },
267
+ {
268
+ "completion_length": 256.0,
269
+ "epoch": 0.14285714285714285,
270
+ "grad_norm": 0.0051048225723207,
271
+ "kl": 0.0006351690972223878,
272
+ "learning_rate": 8.500000000000001e-07,
273
+ "loss": 0.0,
274
+ "reward": 0.125,
275
+ "reward_std": 0.0,
276
+ "rewards/correctness_reward_func": 0.0,
277
+ "rewards/int_reward_func": 0.0,
278
+ "rewards/soft_format_reward_func": 0.0,
279
+ "rewards/strict_format_reward_func": 0.0,
280
+ "rewards/xmlcount_reward_func": 0.125,
281
+ "step": 17
282
+ },
283
+ {
284
+ "completion_length": 256.0,
285
+ "epoch": 0.15126050420168066,
286
+ "grad_norm": 0.004074061755090952,
287
+ "kl": 0.0006499768933281302,
288
+ "learning_rate": 9.000000000000001e-07,
289
+ "loss": 0.0,
290
+ "reward": 0.125,
291
+ "reward_std": 0.0,
292
+ "rewards/correctness_reward_func": 0.0,
293
+ "rewards/int_reward_func": 0.0,
294
+ "rewards/soft_format_reward_func": 0.0,
295
+ "rewards/strict_format_reward_func": 0.0,
296
+ "rewards/xmlcount_reward_func": 0.125,
297
+ "step": 18
298
+ },
299
+ {
300
+ "completion_length": 256.0,
301
+ "epoch": 0.15966386554621848,
302
+ "grad_norm": 0.004084853455424309,
303
+ "kl": 0.0006889225915074348,
304
+ "learning_rate": 9.500000000000001e-07,
305
+ "loss": 0.0,
306
+ "reward": 0.125,
307
+ "reward_std": 0.0,
308
+ "rewards/correctness_reward_func": 0.0,
309
+ "rewards/int_reward_func": 0.0,
310
+ "rewards/soft_format_reward_func": 0.0,
311
+ "rewards/strict_format_reward_func": 0.0,
312
+ "rewards/xmlcount_reward_func": 0.125,
313
+ "step": 19
314
+ },
315
+ {
316
+ "completion_length": 148.0,
317
+ "epoch": 0.16806722689075632,
318
+ "grad_norm": 1.7451705932617188,
319
+ "kl": 0.0006731421453878284,
320
+ "learning_rate": 1.0000000000000002e-06,
321
+ "loss": 0.0,
322
+ "reward": 0.1875,
323
+ "reward_std": 0.0883883461356163,
324
+ "rewards/correctness_reward_func": 0.0,
325
+ "rewards/int_reward_func": 0.0,
326
+ "rewards/soft_format_reward_func": 0.0,
327
+ "rewards/strict_format_reward_func": 0.0,
328
+ "rewards/xmlcount_reward_func": 0.1875,
329
+ "step": 20
330
+ },
331
+ {
332
+ "completion_length": 229.5,
333
+ "epoch": 0.17647058823529413,
334
+ "grad_norm": 1.0134456157684326,
335
+ "kl": 0.0008167714113369584,
336
+ "learning_rate": 1.0500000000000001e-06,
337
+ "loss": 0.0,
338
+ "reward": 0.1875,
339
+ "reward_std": 0.0883883461356163,
340
+ "rewards/correctness_reward_func": 0.0,
341
+ "rewards/int_reward_func": 0.0,
342
+ "rewards/soft_format_reward_func": 0.0,
343
+ "rewards/strict_format_reward_func": 0.0,
344
+ "rewards/xmlcount_reward_func": 0.1875,
345
+ "step": 21
346
+ },
347
+ {
348
+ "completion_length": 95.0,
349
+ "epoch": 0.18487394957983194,
350
+ "grad_norm": 1.4376728534698486,
351
+ "kl": 0.0003571448614820838,
352
+ "learning_rate": 1.1e-06,
353
+ "loss": 0.0,
354
+ "reward": 0.2175000011920929,
355
+ "reward_std": 0.2241528332233429,
356
+ "rewards/correctness_reward_func": 0.0,
357
+ "rewards/int_reward_func": 0.0,
358
+ "rewards/soft_format_reward_func": 0.0,
359
+ "rewards/strict_format_reward_func": 0.0,
360
+ "rewards/xmlcount_reward_func": 0.2175000011920929,
361
+ "step": 22
362
+ },
363
+ {
364
+ "completion_length": 256.0,
365
+ "epoch": 0.19327731092436976,
366
+ "grad_norm": 0.9212502241134644,
367
+ "kl": 0.0007788074435666203,
368
+ "learning_rate": 1.1500000000000002e-06,
369
+ "loss": 0.0,
370
+ "reward": 0.1875,
371
+ "reward_std": 0.0883883461356163,
372
+ "rewards/correctness_reward_func": 0.0,
373
+ "rewards/int_reward_func": 0.0,
374
+ "rewards/soft_format_reward_func": 0.0,
375
+ "rewards/strict_format_reward_func": 0.0,
376
+ "rewards/xmlcount_reward_func": 0.1875,
377
+ "step": 23
378
+ },
379
+ {
380
+ "completion_length": 256.0,
381
+ "epoch": 0.20168067226890757,
382
+ "grad_norm": 0.0038035286124795675,
383
+ "kl": 0.0007109848083928227,
384
+ "learning_rate": 1.2000000000000002e-06,
385
+ "loss": 0.0,
386
+ "reward": 0.125,
387
+ "reward_std": 0.0,
388
+ "rewards/correctness_reward_func": 0.0,
389
+ "rewards/int_reward_func": 0.0,
390
+ "rewards/soft_format_reward_func": 0.0,
391
+ "rewards/strict_format_reward_func": 0.0,
392
+ "rewards/xmlcount_reward_func": 0.125,
393
+ "step": 24
394
+ },
395
+ {
396
+ "completion_length": 191.0,
397
+ "epoch": 0.21008403361344538,
398
+ "grad_norm": 0.006888057105243206,
399
+ "kl": 0.0004465555539354682,
400
+ "learning_rate": 1.25e-06,
401
+ "loss": 0.0,
402
+ "reward": 0.25,
403
+ "reward_std": 0.0,
404
+ "rewards/correctness_reward_func": 0.0,
405
+ "rewards/int_reward_func": 0.0,
406
+ "rewards/soft_format_reward_func": 0.0,
407
+ "rewards/strict_format_reward_func": 0.0,
408
+ "rewards/xmlcount_reward_func": 0.25,
409
+ "step": 25
410
+ },
411
+ {
412
+ "completion_length": 158.0,
413
+ "epoch": 0.2184873949579832,
414
+ "grad_norm": 1.6241445541381836,
415
+ "kl": 0.0006565352086909115,
416
+ "learning_rate": 1.3e-06,
417
+ "loss": 0.0,
418
+ "reward": 0.1875,
419
+ "reward_std": 0.0883883461356163,
420
+ "rewards/correctness_reward_func": 0.0,
421
+ "rewards/int_reward_func": 0.0,
422
+ "rewards/soft_format_reward_func": 0.0,
423
+ "rewards/strict_format_reward_func": 0.0,
424
+ "rewards/xmlcount_reward_func": 0.1875,
425
+ "step": 26
426
+ },
427
+ {
428
+ "completion_length": 256.0,
429
+ "epoch": 0.226890756302521,
430
+ "grad_norm": 0.0034175037872046232,
431
+ "kl": 0.000486561912111938,
432
+ "learning_rate": 1.3500000000000002e-06,
433
+ "loss": 0.0,
434
+ "reward": 0.25,
435
+ "reward_std": 0.0,
436
+ "rewards/correctness_reward_func": 0.0,
437
+ "rewards/int_reward_func": 0.0,
438
+ "rewards/soft_format_reward_func": 0.0,
439
+ "rewards/strict_format_reward_func": 0.0,
440
+ "rewards/xmlcount_reward_func": 0.25,
441
+ "step": 27
442
+ },
443
+ {
444
+ "completion_length": 256.0,
445
+ "epoch": 0.23529411764705882,
446
+ "grad_norm": 0.0036285840906202793,
447
+ "kl": 0.0006047994829714298,
448
+ "learning_rate": 1.4000000000000001e-06,
449
+ "loss": 0.0,
450
+ "reward": 0.125,
451
+ "reward_std": 0.0,
452
+ "rewards/correctness_reward_func": 0.0,
453
+ "rewards/int_reward_func": 0.0,
454
+ "rewards/soft_format_reward_func": 0.0,
455
+ "rewards/strict_format_reward_func": 0.0,
456
+ "rewards/xmlcount_reward_func": 0.125,
457
+ "step": 28
458
+ },
459
+ {
460
+ "completion_length": 256.0,
461
+ "epoch": 0.24369747899159663,
462
+ "grad_norm": 0.0032581069972366095,
463
+ "kl": 0.00038483343087136745,
464
+ "learning_rate": 1.45e-06,
465
+ "loss": 0.0,
466
+ "reward": 0.125,
467
+ "reward_std": 0.0,
468
+ "rewards/correctness_reward_func": 0.0,
469
+ "rewards/int_reward_func": 0.0,
470
+ "rewards/soft_format_reward_func": 0.0,
471
+ "rewards/strict_format_reward_func": 0.0,
472
+ "rewards/xmlcount_reward_func": 0.125,
473
+ "step": 29
474
+ },
475
+ {
476
+ "completion_length": 256.0,
477
+ "epoch": 0.25210084033613445,
478
+ "grad_norm": 0.007449345197528601,
479
+ "kl": 0.000766490469686687,
480
+ "learning_rate": 1.5e-06,
481
+ "loss": 0.0,
482
+ "reward": 0.25,
483
+ "reward_std": 0.0,
484
+ "rewards/correctness_reward_func": 0.0,
485
+ "rewards/int_reward_func": 0.0,
486
+ "rewards/soft_format_reward_func": 0.0,
487
+ "rewards/strict_format_reward_func": 0.0,
488
+ "rewards/xmlcount_reward_func": 0.25,
489
+ "step": 30
490
+ },
491
+ {
492
+ "completion_length": 256.0,
493
+ "epoch": 0.2605042016806723,
494
+ "grad_norm": 0.004598978906869888,
495
+ "kl": 0.0005899533862248063,
496
+ "learning_rate": 1.5500000000000002e-06,
497
+ "loss": 0.0,
498
+ "reward": 0.125,
499
+ "reward_std": 0.0,
500
+ "rewards/correctness_reward_func": 0.0,
501
+ "rewards/int_reward_func": 0.0,
502
+ "rewards/soft_format_reward_func": 0.0,
503
+ "rewards/strict_format_reward_func": 0.0,
504
+ "rewards/xmlcount_reward_func": 0.125,
505
+ "step": 31
506
+ },
507
+ {
508
+ "completion_length": 256.0,
509
+ "epoch": 0.2689075630252101,
510
+ "grad_norm": 0.9563409090042114,
511
+ "kl": 0.0007002416532486677,
512
+ "learning_rate": 1.6000000000000001e-06,
513
+ "loss": 0.0,
514
+ "reward": 0.1875,
515
+ "reward_std": 0.0883883461356163,
516
+ "rewards/correctness_reward_func": 0.0,
517
+ "rewards/int_reward_func": 0.0,
518
+ "rewards/soft_format_reward_func": 0.0,
519
+ "rewards/strict_format_reward_func": 0.0,
520
+ "rewards/xmlcount_reward_func": 0.1875,
521
+ "step": 32
522
+ },
523
+ {
524
+ "completion_length": 256.0,
525
+ "epoch": 0.2773109243697479,
526
+ "grad_norm": 0.0032359708566218615,
527
+ "kl": 0.0004646314773708582,
528
+ "learning_rate": 1.6500000000000003e-06,
529
+ "loss": 0.0,
530
+ "reward": 0.125,
531
+ "reward_std": 0.0,
532
+ "rewards/correctness_reward_func": 0.0,
533
+ "rewards/int_reward_func": 0.0,
534
+ "rewards/soft_format_reward_func": 0.0,
535
+ "rewards/strict_format_reward_func": 0.0,
536
+ "rewards/xmlcount_reward_func": 0.125,
537
+ "step": 33
538
+ },
539
+ {
540
+ "completion_length": 256.0,
541
+ "epoch": 0.2857142857142857,
542
+ "grad_norm": 0.00397283211350441,
543
+ "kl": 0.0006836783140897751,
544
+ "learning_rate": 1.7000000000000002e-06,
545
+ "loss": 0.0,
546
+ "reward": 0.125,
547
+ "reward_std": 0.0,
548
+ "rewards/correctness_reward_func": 0.0,
549
+ "rewards/int_reward_func": 0.0,
550
+ "rewards/soft_format_reward_func": 0.0,
551
+ "rewards/strict_format_reward_func": 0.0,
552
+ "rewards/xmlcount_reward_func": 0.125,
553
+ "step": 34
554
+ },
555
+ {
556
+ "completion_length": 238.0,
557
+ "epoch": 0.29411764705882354,
558
+ "grad_norm": 0.00816441886126995,
559
+ "kl": 0.0009063881007023156,
560
+ "learning_rate": 1.75e-06,
561
+ "loss": 0.0,
562
+ "reward": 0.25,
563
+ "reward_std": 0.0,
564
+ "rewards/correctness_reward_func": 0.0,
565
+ "rewards/int_reward_func": 0.0,
566
+ "rewards/soft_format_reward_func": 0.0,
567
+ "rewards/strict_format_reward_func": 0.0,
568
+ "rewards/xmlcount_reward_func": 0.25,
569
+ "step": 35
570
+ },
571
+ {
572
+ "completion_length": 256.0,
573
+ "epoch": 0.3025210084033613,
574
+ "grad_norm": 0.9932153224945068,
575
+ "kl": 0.000791319995187223,
576
+ "learning_rate": 1.8000000000000001e-06,
577
+ "loss": 0.0,
578
+ "reward": 0.1875,
579
+ "reward_std": 0.0883883461356163,
580
+ "rewards/correctness_reward_func": 0.0,
581
+ "rewards/int_reward_func": 0.0,
582
+ "rewards/soft_format_reward_func": 0.0,
583
+ "rewards/strict_format_reward_func": 0.0,
584
+ "rewards/xmlcount_reward_func": 0.1875,
585
+ "step": 36
586
+ },
587
+ {
588
+ "completion_length": 256.0,
589
+ "epoch": 0.31092436974789917,
590
+ "grad_norm": 0.004532299004495144,
591
+ "kl": 0.0007765735499560833,
592
+ "learning_rate": 1.85e-06,
593
+ "loss": 0.0,
594
+ "reward": 0.125,
595
+ "reward_std": 0.0,
596
+ "rewards/correctness_reward_func": 0.0,
597
+ "rewards/int_reward_func": 0.0,
598
+ "rewards/soft_format_reward_func": 0.0,
599
+ "rewards/strict_format_reward_func": 0.0,
600
+ "rewards/xmlcount_reward_func": 0.125,
601
+ "step": 37
602
+ },
603
+ {
604
+ "completion_length": 256.0,
605
+ "epoch": 0.31932773109243695,
606
+ "grad_norm": 0.004246938973665237,
607
+ "kl": 0.0007269444176927209,
608
+ "learning_rate": 1.9000000000000002e-06,
609
+ "loss": 0.0,
610
+ "reward": 0.125,
611
+ "reward_std": 0.0,
612
+ "rewards/correctness_reward_func": 0.0,
613
+ "rewards/int_reward_func": 0.0,
614
+ "rewards/soft_format_reward_func": 0.0,
615
+ "rewards/strict_format_reward_func": 0.0,
616
+ "rewards/xmlcount_reward_func": 0.125,
617
+ "step": 38
618
+ },
619
+ {
620
+ "completion_length": 161.5,
621
+ "epoch": 0.3277310924369748,
622
+ "grad_norm": 1.6179838180541992,
623
+ "kl": 0.0008333936566486955,
624
+ "learning_rate": 1.9500000000000004e-06,
625
+ "loss": 0.0,
626
+ "reward": 0.1875,
627
+ "reward_std": 0.0883883461356163,
628
+ "rewards/correctness_reward_func": 0.0,
629
+ "rewards/int_reward_func": 0.0,
630
+ "rewards/soft_format_reward_func": 0.0,
631
+ "rewards/strict_format_reward_func": 0.0,
632
+ "rewards/xmlcount_reward_func": 0.1875,
633
+ "step": 39
634
+ },
635
+ {
636
+ "completion_length": 256.0,
637
+ "epoch": 0.33613445378151263,
638
+ "grad_norm": 0.003035498782992363,
639
+ "kl": 0.0005902517586946487,
640
+ "learning_rate": 2.0000000000000003e-06,
641
+ "loss": 0.0,
642
+ "reward": 0.125,
643
+ "reward_std": 0.0,
644
+ "rewards/correctness_reward_func": 0.0,
645
+ "rewards/int_reward_func": 0.0,
646
+ "rewards/soft_format_reward_func": 0.0,
647
+ "rewards/strict_format_reward_func": 0.0,
648
+ "rewards/xmlcount_reward_func": 0.125,
649
+ "step": 40
650
+ },
651
+ {
652
+ "completion_length": 256.0,
653
+ "epoch": 0.3445378151260504,
654
+ "grad_norm": 0.0025484724901616573,
655
+ "kl": 0.0004038845654577017,
656
+ "learning_rate": 2.05e-06,
657
+ "loss": 0.0,
658
+ "reward": 0.125,
659
+ "reward_std": 0.0,
660
+ "rewards/correctness_reward_func": 0.0,
661
+ "rewards/int_reward_func": 0.0,
662
+ "rewards/soft_format_reward_func": 0.0,
663
+ "rewards/strict_format_reward_func": 0.0,
664
+ "rewards/xmlcount_reward_func": 0.125,
665
+ "step": 41
666
+ },
667
+ {
668
+ "completion_length": 256.0,
669
+ "epoch": 0.35294117647058826,
670
+ "grad_norm": 0.003505554748699069,
671
+ "kl": 0.0006591258570551872,
672
+ "learning_rate": 2.1000000000000002e-06,
673
+ "loss": 0.0,
674
+ "reward": 0.125,
675
+ "reward_std": 0.0,
676
+ "rewards/correctness_reward_func": 0.0,
677
+ "rewards/int_reward_func": 0.0,
678
+ "rewards/soft_format_reward_func": 0.0,
679
+ "rewards/strict_format_reward_func": 0.0,
680
+ "rewards/xmlcount_reward_func": 0.125,
681
+ "step": 42
682
+ },
683
+ {
684
+ "completion_length": 231.5,
685
+ "epoch": 0.36134453781512604,
686
+ "grad_norm": 0.0046354010701179504,
687
+ "kl": 0.0007136644562706351,
688
+ "learning_rate": 2.15e-06,
689
+ "loss": 0.0,
690
+ "reward": 0.25,
691
+ "reward_std": 0.0,
692
+ "rewards/correctness_reward_func": 0.0,
693
+ "rewards/int_reward_func": 0.0,
694
+ "rewards/soft_format_reward_func": 0.0,
695
+ "rewards/strict_format_reward_func": 0.0,
696
+ "rewards/xmlcount_reward_func": 0.25,
697
+ "step": 43
698
+ },
699
+ {
700
+ "completion_length": 256.0,
701
+ "epoch": 0.3697478991596639,
702
+ "grad_norm": 0.0032716356217861176,
703
+ "kl": 0.0006846879841759801,
704
+ "learning_rate": 2.2e-06,
705
+ "loss": 0.0,
706
+ "reward": 0.125,
707
+ "reward_std": 0.0,
708
+ "rewards/correctness_reward_func": 0.0,
709
+ "rewards/int_reward_func": 0.0,
710
+ "rewards/soft_format_reward_func": 0.0,
711
+ "rewards/strict_format_reward_func": 0.0,
712
+ "rewards/xmlcount_reward_func": 0.125,
713
+ "step": 44
714
+ },
715
+ {
716
+ "completion_length": 256.0,
717
+ "epoch": 0.37815126050420167,
718
+ "grad_norm": 0.004479558672755957,
719
+ "kl": 0.0007645890582352877,
720
+ "learning_rate": 2.25e-06,
721
+ "loss": 0.0,
722
+ "reward": 0.125,
723
+ "reward_std": 0.0,
724
+ "rewards/correctness_reward_func": 0.0,
725
+ "rewards/int_reward_func": 0.0,
726
+ "rewards/soft_format_reward_func": 0.0,
727
+ "rewards/strict_format_reward_func": 0.0,
728
+ "rewards/xmlcount_reward_func": 0.125,
729
+ "step": 45
730
+ },
731
+ {
732
+ "completion_length": 256.0,
733
+ "epoch": 0.3865546218487395,
734
+ "grad_norm": 0.003661304945126176,
735
+ "kl": 0.0005422246176749468,
736
+ "learning_rate": 2.3000000000000004e-06,
737
+ "loss": 0.0,
738
+ "reward": 0.125,
739
+ "reward_std": 0.0,
740
+ "rewards/correctness_reward_func": 0.0,
741
+ "rewards/int_reward_func": 0.0,
742
+ "rewards/soft_format_reward_func": 0.0,
743
+ "rewards/strict_format_reward_func": 0.0,
744
+ "rewards/xmlcount_reward_func": 0.125,
745
+ "step": 46
746
+ },
747
+ {
748
+ "completion_length": 256.0,
749
+ "epoch": 0.3949579831932773,
750
+ "grad_norm": 0.8428875803947449,
751
+ "kl": 0.0007787372451275587,
752
+ "learning_rate": 2.35e-06,
753
+ "loss": 0.0,
754
+ "reward": 0.1875,
755
+ "reward_std": 0.0883883461356163,
756
+ "rewards/correctness_reward_func": 0.0,
757
+ "rewards/int_reward_func": 0.0,
758
+ "rewards/soft_format_reward_func": 0.0,
759
+ "rewards/strict_format_reward_func": 0.0,
760
+ "rewards/xmlcount_reward_func": 0.1875,
761
+ "step": 47
762
+ },
763
+ {
764
+ "completion_length": 100.5,
765
+ "epoch": 0.40336134453781514,
766
+ "grad_norm": 0.00735253794118762,
767
+ "kl": 0.0009225605172105134,
768
+ "learning_rate": 2.4000000000000003e-06,
769
+ "loss": 0.0,
770
+ "reward": 0.25,
771
+ "reward_std": 0.0,
772
+ "rewards/correctness_reward_func": 0.0,
773
+ "rewards/int_reward_func": 0.0,
774
+ "rewards/soft_format_reward_func": 0.0,
775
+ "rewards/strict_format_reward_func": 0.0,
776
+ "rewards/xmlcount_reward_func": 0.25,
777
+ "step": 48
778
+ },
779
+ {
780
+ "completion_length": 256.0,
781
+ "epoch": 0.4117647058823529,
782
+ "grad_norm": 0.8739237785339355,
783
+ "kl": 0.0006543750641867518,
784
+ "learning_rate": 2.4500000000000003e-06,
785
+ "loss": 0.0,
786
+ "reward": 0.1875,
787
+ "reward_std": 0.0883883461356163,
788
+ "rewards/correctness_reward_func": 0.0,
789
+ "rewards/int_reward_func": 0.0,
790
+ "rewards/soft_format_reward_func": 0.0,
791
+ "rewards/strict_format_reward_func": 0.0,
792
+ "rewards/xmlcount_reward_func": 0.1875,
793
+ "step": 49
794
+ },
795
+ {
796
+ "completion_length": 256.0,
797
+ "epoch": 0.42016806722689076,
798
+ "grad_norm": 0.0060773007571697235,
799
+ "kl": 0.000822792062535882,
800
+ "learning_rate": 2.5e-06,
801
+ "loss": 0.0,
802
+ "reward": 0.125,
803
+ "reward_std": 0.0,
804
+ "rewards/correctness_reward_func": 0.0,
805
+ "rewards/int_reward_func": 0.0,
806
+ "rewards/soft_format_reward_func": 0.0,
807
+ "rewards/strict_format_reward_func": 0.0,
808
+ "rewards/xmlcount_reward_func": 0.125,
809
+ "step": 50
810
+ },
811
+ {
812
+ "completion_length": 256.0,
813
+ "epoch": 0.42857142857142855,
814
+ "grad_norm": 0.010451748967170715,
815
+ "kl": 0.0012671941658481956,
816
+ "learning_rate": 2.55e-06,
817
+ "loss": 0.0001,
818
+ "reward": 0.25,
819
+ "reward_std": 0.0,
820
+ "rewards/correctness_reward_func": 0.0,
821
+ "rewards/int_reward_func": 0.0,
822
+ "rewards/soft_format_reward_func": 0.0,
823
+ "rewards/strict_format_reward_func": 0.0,
824
+ "rewards/xmlcount_reward_func": 0.25,
825
+ "step": 51
826
+ },
827
+ {
828
+ "completion_length": 99.5,
829
+ "epoch": 0.4369747899159664,
830
+ "grad_norm": 0.006612293887883425,
831
+ "kl": 0.0008995666867122054,
832
+ "learning_rate": 2.6e-06,
833
+ "loss": 0.0,
834
+ "reward": 0.25,
835
+ "reward_std": 0.0,
836
+ "rewards/correctness_reward_func": 0.0,
837
+ "rewards/int_reward_func": 0.0,
838
+ "rewards/soft_format_reward_func": 0.0,
839
+ "rewards/strict_format_reward_func": 0.0,
840
+ "rewards/xmlcount_reward_func": 0.25,
841
+ "step": 52
842
+ },
843
+ {
844
+ "completion_length": 256.0,
845
+ "epoch": 0.44537815126050423,
846
+ "grad_norm": 0.9036616086959839,
847
+ "kl": 0.0008495927322655916,
848
+ "learning_rate": 2.6500000000000005e-06,
849
+ "loss": 0.0,
850
+ "reward": 0.1875,
851
+ "reward_std": 0.0883883461356163,
852
+ "rewards/correctness_reward_func": 0.0,
853
+ "rewards/int_reward_func": 0.0,
854
+ "rewards/soft_format_reward_func": 0.0,
855
+ "rewards/strict_format_reward_func": 0.0,
856
+ "rewards/xmlcount_reward_func": 0.1875,
857
+ "step": 53
858
+ },
859
+ {
860
+ "completion_length": 195.0,
861
+ "epoch": 0.453781512605042,
862
+ "grad_norm": 1.3959556818008423,
863
+ "kl": 0.0010955859906971455,
864
+ "learning_rate": 2.7000000000000004e-06,
865
+ "loss": 0.0,
866
+ "reward": 0.1875,
867
+ "reward_std": 0.0883883461356163,
868
+ "rewards/correctness_reward_func": 0.0,
869
+ "rewards/int_reward_func": 0.0,
870
+ "rewards/soft_format_reward_func": 0.0,
871
+ "rewards/strict_format_reward_func": 0.0,
872
+ "rewards/xmlcount_reward_func": 0.1875,
873
+ "step": 54
874
+ },
875
+ {
876
+ "completion_length": 256.0,
877
+ "epoch": 0.46218487394957986,
878
+ "grad_norm": 0.849948525428772,
879
+ "kl": 0.0007333974353969097,
880
+ "learning_rate": 2.7500000000000004e-06,
881
+ "loss": 0.0,
882
+ "reward": 0.1875,
883
+ "reward_std": 0.0883883461356163,
884
+ "rewards/correctness_reward_func": 0.0,
885
+ "rewards/int_reward_func": 0.0,
886
+ "rewards/soft_format_reward_func": 0.0,
887
+ "rewards/strict_format_reward_func": 0.0,
888
+ "rewards/xmlcount_reward_func": 0.1875,
889
+ "step": 55
890
+ },
891
+ {
892
+ "completion_length": 225.0,
893
+ "epoch": 0.47058823529411764,
894
+ "grad_norm": 0.870661199092865,
895
+ "kl": 0.000870745861902833,
896
+ "learning_rate": 2.8000000000000003e-06,
897
+ "loss": 0.0,
898
+ "reward": 0.1875,
899
+ "reward_std": 0.0883883461356163,
900
+ "rewards/correctness_reward_func": 0.0,
901
+ "rewards/int_reward_func": 0.0,
902
+ "rewards/soft_format_reward_func": 0.0,
903
+ "rewards/strict_format_reward_func": 0.0,
904
+ "rewards/xmlcount_reward_func": 0.1875,
905
+ "step": 56
906
+ },
907
+ {
908
+ "completion_length": 256.0,
909
+ "epoch": 0.4789915966386555,
910
+ "grad_norm": 0.0075195119716227055,
911
+ "kl": 0.0012707834830507636,
912
+ "learning_rate": 2.85e-06,
913
+ "loss": 0.0001,
914
+ "reward": 0.25,
915
+ "reward_std": 0.0,
916
+ "rewards/correctness_reward_func": 0.0,
917
+ "rewards/int_reward_func": 0.0,
918
+ "rewards/soft_format_reward_func": 0.0,
919
+ "rewards/strict_format_reward_func": 0.0,
920
+ "rewards/xmlcount_reward_func": 0.25,
921
+ "step": 57
922
+ },
923
+ {
924
+ "completion_length": 256.0,
925
+ "epoch": 0.48739495798319327,
926
+ "grad_norm": 0.0033428138121962547,
927
+ "kl": 0.0005659679882228374,
928
+ "learning_rate": 2.9e-06,
929
+ "loss": 0.0,
930
+ "reward": 0.125,
931
+ "reward_std": 0.0,
932
+ "rewards/correctness_reward_func": 0.0,
933
+ "rewards/int_reward_func": 0.0,
934
+ "rewards/soft_format_reward_func": 0.0,
935
+ "rewards/strict_format_reward_func": 0.0,
936
+ "rewards/xmlcount_reward_func": 0.125,
937
+ "step": 58
938
+ },
939
+ {
940
+ "completion_length": 217.0,
941
+ "epoch": 0.4957983193277311,
942
+ "grad_norm": 0.010066932067275047,
943
+ "kl": 0.001386146410368383,
944
+ "learning_rate": 2.95e-06,
945
+ "loss": 0.0001,
946
+ "reward": 0.25,
947
+ "reward_std": 0.0,
948
+ "rewards/correctness_reward_func": 0.0,
949
+ "rewards/int_reward_func": 0.0,
950
+ "rewards/soft_format_reward_func": 0.0,
951
+ "rewards/strict_format_reward_func": 0.0,
952
+ "rewards/xmlcount_reward_func": 0.25,
953
+ "step": 59
954
+ },
955
+ {
956
+ "completion_length": 256.0,
957
+ "epoch": 0.5042016806722689,
958
+ "grad_norm": 0.005329888314008713,
959
+ "kl": 0.000831706216558814,
960
+ "learning_rate": 3e-06,
961
+ "loss": 0.0,
962
+ "reward": 0.125,
963
+ "reward_std": 0.0,
964
+ "rewards/correctness_reward_func": 0.0,
965
+ "rewards/int_reward_func": 0.0,
966
+ "rewards/soft_format_reward_func": 0.0,
967
+ "rewards/strict_format_reward_func": 0.0,
968
+ "rewards/xmlcount_reward_func": 0.125,
969
+ "step": 60
970
+ },
971
+ {
972
+ "completion_length": 256.0,
973
+ "epoch": 0.5126050420168067,
974
+ "grad_norm": 0.01864616759121418,
975
+ "kl": 0.002434937749058008,
976
+ "learning_rate": 3.05e-06,
977
+ "loss": 0.0001,
978
+ "reward": 0.25,
979
+ "reward_std": 0.0,
980
+ "rewards/correctness_reward_func": 0.0,
981
+ "rewards/int_reward_func": 0.0,
982
+ "rewards/soft_format_reward_func": 0.0,
983
+ "rewards/strict_format_reward_func": 0.0,
984
+ "rewards/xmlcount_reward_func": 0.25,
985
+ "step": 61
986
+ },
987
+ {
988
+ "completion_length": 253.5,
989
+ "epoch": 0.5210084033613446,
990
+ "grad_norm": 0.950167715549469,
991
+ "kl": 0.0012768663000315428,
992
+ "learning_rate": 3.1000000000000004e-06,
993
+ "loss": 0.0001,
994
+ "reward": 0.1875,
995
+ "reward_std": 0.0883883461356163,
996
+ "rewards/correctness_reward_func": 0.0,
997
+ "rewards/int_reward_func": 0.0,
998
+ "rewards/soft_format_reward_func": 0.0,
999
+ "rewards/strict_format_reward_func": 0.0,
1000
+ "rewards/xmlcount_reward_func": 0.1875,
1001
+ "step": 62
1002
+ },
1003
+ {
1004
+ "completion_length": 256.0,
1005
+ "epoch": 0.5294117647058824,
1006
+ "grad_norm": 0.008330680429935455,
1007
+ "kl": 0.0012756225187331438,
1008
+ "learning_rate": 3.1500000000000003e-06,
1009
+ "loss": 0.0001,
1010
+ "reward": 0.25,
1011
+ "reward_std": 0.0,
1012
+ "rewards/correctness_reward_func": 0.0,
1013
+ "rewards/int_reward_func": 0.0,
1014
+ "rewards/soft_format_reward_func": 0.0,
1015
+ "rewards/strict_format_reward_func": 0.0,
1016
+ "rewards/xmlcount_reward_func": 0.25,
1017
+ "step": 63
1018
+ },
1019
+ {
1020
+ "completion_length": 140.5,
1021
+ "epoch": 0.5378151260504201,
1022
+ "grad_norm": 0.014831366017460823,
1023
+ "kl": 0.0031117983162403107,
1024
+ "learning_rate": 3.2000000000000003e-06,
1025
+ "loss": 0.0001,
1026
+ "reward": 0.25,
1027
+ "reward_std": 0.0,
1028
+ "rewards/correctness_reward_func": 0.0,
1029
+ "rewards/int_reward_func": 0.0,
1030
+ "rewards/soft_format_reward_func": 0.0,
1031
+ "rewards/strict_format_reward_func": 0.0,
1032
+ "rewards/xmlcount_reward_func": 0.25,
1033
+ "step": 64
1034
+ },
1035
+ {
1036
+ "completion_length": 256.0,
1037
+ "epoch": 0.5462184873949579,
1038
+ "grad_norm": 0.9908618927001953,
1039
+ "kl": 0.0014188946224749088,
1040
+ "learning_rate": 3.2500000000000002e-06,
1041
+ "loss": 0.0001,
1042
+ "reward": 0.1875,
1043
+ "reward_std": 0.0883883461356163,
1044
+ "rewards/correctness_reward_func": 0.0,
1045
+ "rewards/int_reward_func": 0.0,
1046
+ "rewards/soft_format_reward_func": 0.0,
1047
+ "rewards/strict_format_reward_func": 0.0,
1048
+ "rewards/xmlcount_reward_func": 0.1875,
1049
+ "step": 65
1050
+ },
1051
+ {
1052
+ "completion_length": 256.0,
1053
+ "epoch": 0.5546218487394958,
1054
+ "grad_norm": 0.7165637016296387,
1055
+ "kl": 0.0006240149959921837,
1056
+ "learning_rate": 3.3000000000000006e-06,
1057
+ "loss": 0.0,
1058
+ "reward": 0.1875,
1059
+ "reward_std": 0.0883883461356163,
1060
+ "rewards/correctness_reward_func": 0.0,
1061
+ "rewards/int_reward_func": 0.0,
1062
+ "rewards/soft_format_reward_func": 0.0,
1063
+ "rewards/strict_format_reward_func": 0.0,
1064
+ "rewards/xmlcount_reward_func": 0.1875,
1065
+ "step": 66
1066
+ },
1067
+ {
1068
+ "completion_length": 91.5,
1069
+ "epoch": 0.5630252100840336,
1070
+ "grad_norm": 0.018771149218082428,
1071
+ "kl": 0.0030818600207567215,
1072
+ "learning_rate": 3.3500000000000005e-06,
1073
+ "loss": 0.0001,
1074
+ "reward": 0.25,
1075
+ "reward_std": 0.0,
1076
+ "rewards/correctness_reward_func": 0.0,
1077
+ "rewards/int_reward_func": 0.0,
1078
+ "rewards/soft_format_reward_func": 0.0,
1079
+ "rewards/strict_format_reward_func": 0.0,
1080
+ "rewards/xmlcount_reward_func": 0.25,
1081
+ "step": 67
1082
+ },
1083
+ {
1084
+ "completion_length": 169.5,
1085
+ "epoch": 0.5714285714285714,
1086
+ "grad_norm": 1.1422396898269653,
1087
+ "kl": 0.001963505521416664,
1088
+ "learning_rate": 3.4000000000000005e-06,
1089
+ "loss": 0.0001,
1090
+ "reward": 0.1875,
1091
+ "reward_std": 0.0883883461356163,
1092
+ "rewards/correctness_reward_func": 0.0,
1093
+ "rewards/int_reward_func": 0.0,
1094
+ "rewards/soft_format_reward_func": 0.0,
1095
+ "rewards/strict_format_reward_func": 0.0,
1096
+ "rewards/xmlcount_reward_func": 0.1875,
1097
+ "step": 68
1098
+ },
1099
+ {
1100
+ "completion_length": 225.5,
1101
+ "epoch": 0.5798319327731093,
1102
+ "grad_norm": 0.014802279882133007,
1103
+ "kl": 0.0021320898085832596,
1104
+ "learning_rate": 3.45e-06,
1105
+ "loss": 0.0001,
1106
+ "reward": 0.25,
1107
+ "reward_std": 0.0,
1108
+ "rewards/correctness_reward_func": 0.0,
1109
+ "rewards/int_reward_func": 0.0,
1110
+ "rewards/soft_format_reward_func": 0.0,
1111
+ "rewards/strict_format_reward_func": 0.0,
1112
+ "rewards/xmlcount_reward_func": 0.25,
1113
+ "step": 69
1114
+ },
1115
+ {
1116
+ "completion_length": 256.0,
1117
+ "epoch": 0.5882352941176471,
1118
+ "grad_norm": 0.9517803192138672,
1119
+ "kl": 0.0013911720598116517,
1120
+ "learning_rate": 3.5e-06,
1121
+ "loss": 0.0001,
1122
+ "reward": 0.1875,
1123
+ "reward_std": 0.0883883461356163,
1124
+ "rewards/correctness_reward_func": 0.0,
1125
+ "rewards/int_reward_func": 0.0,
1126
+ "rewards/soft_format_reward_func": 0.0,
1127
+ "rewards/strict_format_reward_func": 0.0,
1128
+ "rewards/xmlcount_reward_func": 0.1875,
1129
+ "step": 70
1130
+ },
1131
+ {
1132
+ "completion_length": 256.0,
1133
+ "epoch": 0.5966386554621849,
1134
+ "grad_norm": 1.2495174407958984,
1135
+ "kl": 0.001323533128015697,
1136
+ "learning_rate": 3.5500000000000003e-06,
1137
+ "loss": 0.0001,
1138
+ "reward": 0.1875,
1139
+ "reward_std": 0.0883883461356163,
1140
+ "rewards/correctness_reward_func": 0.0,
1141
+ "rewards/int_reward_func": 0.0,
1142
+ "rewards/soft_format_reward_func": 0.0,
1143
+ "rewards/strict_format_reward_func": 0.0,
1144
+ "rewards/xmlcount_reward_func": 0.1875,
1145
+ "step": 71
1146
+ },
1147
+ {
1148
+ "completion_length": 188.0,
1149
+ "epoch": 0.6050420168067226,
1150
+ "grad_norm": 1.1743896007537842,
1151
+ "kl": 0.002660756465047598,
1152
+ "learning_rate": 3.6000000000000003e-06,
1153
+ "loss": 0.0001,
1154
+ "reward": 0.1875,
1155
+ "reward_std": 0.0883883461356163,
1156
+ "rewards/correctness_reward_func": 0.0,
1157
+ "rewards/int_reward_func": 0.0,
1158
+ "rewards/soft_format_reward_func": 0.0,
1159
+ "rewards/strict_format_reward_func": 0.0,
1160
+ "rewards/xmlcount_reward_func": 0.1875,
1161
+ "step": 72
1162
+ },
1163
+ {
1164
+ "completion_length": 256.0,
1165
+ "epoch": 0.6134453781512605,
1166
+ "grad_norm": 0.003697387408465147,
1167
+ "kl": 0.0006548548117280006,
1168
+ "learning_rate": 3.65e-06,
1169
+ "loss": 0.0,
1170
+ "reward": 0.125,
1171
+ "reward_std": 0.0,
1172
+ "rewards/correctness_reward_func": 0.0,
1173
+ "rewards/int_reward_func": 0.0,
1174
+ "rewards/soft_format_reward_func": 0.0,
1175
+ "rewards/strict_format_reward_func": 0.0,
1176
+ "rewards/xmlcount_reward_func": 0.125,
1177
+ "step": 73
1178
+ },
1179
+ {
1180
+ "completion_length": 256.0,
1181
+ "epoch": 0.6218487394957983,
1182
+ "grad_norm": 0.8471294045448303,
1183
+ "kl": 0.0012757513904944062,
1184
+ "learning_rate": 3.7e-06,
1185
+ "loss": 0.0001,
1186
+ "reward": 0.1875,
1187
+ "reward_std": 0.0883883461356163,
1188
+ "rewards/correctness_reward_func": 0.0,
1189
+ "rewards/int_reward_func": 0.0,
1190
+ "rewards/soft_format_reward_func": 0.0,
1191
+ "rewards/strict_format_reward_func": 0.0,
1192
+ "rewards/xmlcount_reward_func": 0.1875,
1193
+ "step": 74
1194
+ },
1195
+ {
1196
+ "completion_length": 256.0,
1197
+ "epoch": 0.6302521008403361,
1198
+ "grad_norm": 0.009078427217900753,
1199
+ "kl": 0.0013090419815853238,
1200
+ "learning_rate": 3.7500000000000005e-06,
1201
+ "loss": 0.0001,
1202
+ "reward": 0.25,
1203
+ "reward_std": 0.0,
1204
+ "rewards/correctness_reward_func": 0.0,
1205
+ "rewards/int_reward_func": 0.0,
1206
+ "rewards/soft_format_reward_func": 0.0,
1207
+ "rewards/strict_format_reward_func": 0.0,
1208
+ "rewards/xmlcount_reward_func": 0.25,
1209
+ "step": 75
1210
+ },
1211
+ {
1212
+ "completion_length": 256.0,
1213
+ "epoch": 0.6386554621848739,
1214
+ "grad_norm": 0.9492903351783752,
1215
+ "kl": 0.002218120265752077,
1216
+ "learning_rate": 3.8000000000000005e-06,
1217
+ "loss": 0.0001,
1218
+ "reward": 0.1875,
1219
+ "reward_std": 0.0883883461356163,
1220
+ "rewards/correctness_reward_func": 0.0,
1221
+ "rewards/int_reward_func": 0.0,
1222
+ "rewards/soft_format_reward_func": 0.0,
1223
+ "rewards/strict_format_reward_func": 0.0,
1224
+ "rewards/xmlcount_reward_func": 0.1875,
1225
+ "step": 76
1226
+ },
1227
+ {
1228
+ "completion_length": 256.0,
1229
+ "epoch": 0.6470588235294118,
1230
+ "grad_norm": 0.0035131191834807396,
1231
+ "kl": 0.000702213728800416,
1232
+ "learning_rate": 3.85e-06,
1233
+ "loss": 0.0,
1234
+ "reward": 0.125,
1235
+ "reward_std": 0.0,
1236
+ "rewards/correctness_reward_func": 0.0,
1237
+ "rewards/int_reward_func": 0.0,
1238
+ "rewards/soft_format_reward_func": 0.0,
1239
+ "rewards/strict_format_reward_func": 0.0,
1240
+ "rewards/xmlcount_reward_func": 0.125,
1241
+ "step": 77
1242
+ },
1243
+ {
1244
+ "completion_length": 228.5,
1245
+ "epoch": 0.6554621848739496,
1246
+ "grad_norm": 0.005907819140702486,
1247
+ "kl": 0.0012794373324140906,
1248
+ "learning_rate": 3.900000000000001e-06,
1249
+ "loss": 0.0001,
1250
+ "reward": 0.25,
1251
+ "reward_std": 0.0,
1252
+ "rewards/correctness_reward_func": 0.0,
1253
+ "rewards/int_reward_func": 0.0,
1254
+ "rewards/soft_format_reward_func": 0.0,
1255
+ "rewards/strict_format_reward_func": 0.0,
1256
+ "rewards/xmlcount_reward_func": 0.25,
1257
+ "step": 78
1258
+ },
1259
+ {
1260
+ "completion_length": 256.0,
1261
+ "epoch": 0.6638655462184874,
1262
+ "grad_norm": 0.9454696178436279,
1263
+ "kl": 0.0018798538949340582,
1264
+ "learning_rate": 3.95e-06,
1265
+ "loss": 0.0001,
1266
+ "reward": 0.1875,
1267
+ "reward_std": 0.0883883461356163,
1268
+ "rewards/correctness_reward_func": 0.0,
1269
+ "rewards/int_reward_func": 0.0,
1270
+ "rewards/soft_format_reward_func": 0.0,
1271
+ "rewards/strict_format_reward_func": 0.0,
1272
+ "rewards/xmlcount_reward_func": 0.1875,
1273
+ "step": 79
1274
+ },
1275
+ {
1276
+ "completion_length": 256.0,
1277
+ "epoch": 0.6722689075630253,
1278
+ "grad_norm": 0.011725543066859245,
1279
+ "kl": 0.0036349850706756115,
1280
+ "learning_rate": 4.000000000000001e-06,
1281
+ "loss": 0.0001,
1282
+ "reward": 0.25,
1283
+ "reward_std": 0.0,
1284
+ "rewards/correctness_reward_func": 0.0,
1285
+ "rewards/int_reward_func": 0.0,
1286
+ "rewards/soft_format_reward_func": 0.0,
1287
+ "rewards/strict_format_reward_func": 0.0,
1288
+ "rewards/xmlcount_reward_func": 0.25,
1289
+ "step": 80
1290
+ },
1291
+ {
1292
+ "completion_length": 182.0,
1293
+ "epoch": 0.680672268907563,
1294
+ "grad_norm": 0.0036761611700057983,
1295
+ "kl": 0.0005937532987445593,
1296
+ "learning_rate": 4.05e-06,
1297
+ "loss": 0.0,
1298
+ "reward": 0.25,
1299
+ "reward_std": 0.0,
1300
+ "rewards/correctness_reward_func": 0.0,
1301
+ "rewards/int_reward_func": 0.0,
1302
+ "rewards/soft_format_reward_func": 0.0,
1303
+ "rewards/strict_format_reward_func": 0.0,
1304
+ "rewards/xmlcount_reward_func": 0.25,
1305
+ "step": 81
1306
+ },
1307
+ {
1308
+ "completion_length": 238.5,
1309
+ "epoch": 0.6890756302521008,
1310
+ "grad_norm": 0.00544555252417922,
1311
+ "kl": 0.0012453272938728333,
1312
+ "learning_rate": 4.1e-06,
1313
+ "loss": 0.0,
1314
+ "reward": 0.25,
1315
+ "reward_std": 0.0,
1316
+ "rewards/correctness_reward_func": 0.0,
1317
+ "rewards/int_reward_func": 0.0,
1318
+ "rewards/soft_format_reward_func": 0.0,
1319
+ "rewards/strict_format_reward_func": 0.0,
1320
+ "rewards/xmlcount_reward_func": 0.25,
1321
+ "step": 82
1322
+ },
1323
+ {
1324
+ "completion_length": 256.0,
1325
+ "epoch": 0.6974789915966386,
1326
+ "grad_norm": 0.002836729632690549,
1327
+ "kl": 0.0004919321509078145,
1328
+ "learning_rate": 4.15e-06,
1329
+ "loss": 0.0,
1330
+ "reward": 0.125,
1331
+ "reward_std": 0.0,
1332
+ "rewards/correctness_reward_func": 0.0,
1333
+ "rewards/int_reward_func": 0.0,
1334
+ "rewards/soft_format_reward_func": 0.0,
1335
+ "rewards/strict_format_reward_func": 0.0,
1336
+ "rewards/xmlcount_reward_func": 0.125,
1337
+ "step": 83
1338
+ },
1339
+ {
1340
+ "completion_length": 256.0,
1341
+ "epoch": 0.7058823529411765,
1342
+ "grad_norm": 0.002849327167496085,
1343
+ "kl": 0.00048355443868786097,
1344
+ "learning_rate": 4.2000000000000004e-06,
1345
+ "loss": 0.0,
1346
+ "reward": 0.125,
1347
+ "reward_std": 0.0,
1348
+ "rewards/correctness_reward_func": 0.0,
1349
+ "rewards/int_reward_func": 0.0,
1350
+ "rewards/soft_format_reward_func": 0.0,
1351
+ "rewards/strict_format_reward_func": 0.0,
1352
+ "rewards/xmlcount_reward_func": 0.125,
1353
+ "step": 84
1354
+ },
1355
+ {
1356
+ "completion_length": 163.0,
1357
+ "epoch": 0.7142857142857143,
1358
+ "grad_norm": 0.023407526314258575,
1359
+ "kl": 0.008791845291852951,
1360
+ "learning_rate": 4.25e-06,
1361
+ "loss": 0.0004,
1362
+ "reward": 0.25,
1363
+ "reward_std": 0.0,
1364
+ "rewards/correctness_reward_func": 0.0,
1365
+ "rewards/int_reward_func": 0.0,
1366
+ "rewards/soft_format_reward_func": 0.0,
1367
+ "rewards/strict_format_reward_func": 0.0,
1368
+ "rewards/xmlcount_reward_func": 0.25,
1369
+ "step": 85
1370
+ },
1371
+ {
1372
+ "completion_length": 256.0,
1373
+ "epoch": 0.7226890756302521,
1374
+ "grad_norm": 0.003463078523054719,
1375
+ "kl": 0.0007299153367057443,
1376
+ "learning_rate": 4.3e-06,
1377
+ "loss": 0.0,
1378
+ "reward": 0.125,
1379
+ "reward_std": 0.0,
1380
+ "rewards/correctness_reward_func": 0.0,
1381
+ "rewards/int_reward_func": 0.0,
1382
+ "rewards/soft_format_reward_func": 0.0,
1383
+ "rewards/strict_format_reward_func": 0.0,
1384
+ "rewards/xmlcount_reward_func": 0.125,
1385
+ "step": 86
1386
+ },
1387
+ {
1388
+ "completion_length": 256.0,
1389
+ "epoch": 0.7310924369747899,
1390
+ "grad_norm": 0.007253331132233143,
1391
+ "kl": 0.004142088815569878,
1392
+ "learning_rate": 4.350000000000001e-06,
1393
+ "loss": 0.0002,
1394
+ "reward": 0.25,
1395
+ "reward_std": 0.0,
1396
+ "rewards/correctness_reward_func": 0.0,
1397
+ "rewards/int_reward_func": 0.0,
1398
+ "rewards/soft_format_reward_func": 0.0,
1399
+ "rewards/strict_format_reward_func": 0.0,
1400
+ "rewards/xmlcount_reward_func": 0.25,
1401
+ "step": 87
1402
+ },
1403
+ {
1404
+ "completion_length": 256.0,
1405
+ "epoch": 0.7394957983193278,
1406
+ "grad_norm": 0.5496742129325867,
1407
+ "kl": 0.010586329735815525,
1408
+ "learning_rate": 4.4e-06,
1409
+ "loss": 0.0004,
1410
+ "reward": 0.25,
1411
+ "reward_std": 0.0,
1412
+ "rewards/correctness_reward_func": 0.0,
1413
+ "rewards/int_reward_func": 0.0,
1414
+ "rewards/soft_format_reward_func": 0.0,
1415
+ "rewards/strict_format_reward_func": 0.0,
1416
+ "rewards/xmlcount_reward_func": 0.25,
1417
+ "step": 88
1418
+ },
1419
+ {
1420
+ "completion_length": 256.0,
1421
+ "epoch": 0.7478991596638656,
1422
+ "grad_norm": 0.964024543762207,
1423
+ "kl": 0.0029028397984802723,
1424
+ "learning_rate": 4.450000000000001e-06,
1425
+ "loss": 0.0001,
1426
+ "reward": 0.1875,
1427
+ "reward_std": 0.0883883461356163,
1428
+ "rewards/correctness_reward_func": 0.0,
1429
+ "rewards/int_reward_func": 0.0,
1430
+ "rewards/soft_format_reward_func": 0.0,
1431
+ "rewards/strict_format_reward_func": 0.0,
1432
+ "rewards/xmlcount_reward_func": 0.1875,
1433
+ "step": 89
1434
+ },
1435
+ {
1436
+ "completion_length": 83.0,
1437
+ "epoch": 0.7563025210084033,
1438
+ "grad_norm": 0.0122342174872756,
1439
+ "kl": 0.0071075791493058205,
1440
+ "learning_rate": 4.5e-06,
1441
+ "loss": 0.0003,
1442
+ "reward": 0.25,
1443
+ "reward_std": 0.0,
1444
+ "rewards/correctness_reward_func": 0.0,
1445
+ "rewards/int_reward_func": 0.0,
1446
+ "rewards/soft_format_reward_func": 0.0,
1447
+ "rewards/strict_format_reward_func": 0.0,
1448
+ "rewards/xmlcount_reward_func": 0.25,
1449
+ "step": 90
1450
+ },
1451
+ {
1452
+ "completion_length": 136.5,
1453
+ "epoch": 0.7647058823529411,
1454
+ "grad_norm": 0.004309786017984152,
1455
+ "kl": 0.002355900825932622,
1456
+ "learning_rate": 4.5500000000000005e-06,
1457
+ "loss": 0.0001,
1458
+ "reward": 0.25,
1459
+ "reward_std": 0.0,
1460
+ "rewards/correctness_reward_func": 0.0,
1461
+ "rewards/int_reward_func": 0.0,
1462
+ "rewards/soft_format_reward_func": 0.0,
1463
+ "rewards/strict_format_reward_func": 0.0,
1464
+ "rewards/xmlcount_reward_func": 0.25,
1465
+ "step": 91
1466
+ },
1467
+ {
1468
+ "completion_length": 256.0,
1469
+ "epoch": 0.773109243697479,
1470
+ "grad_norm": 0.009771923534572124,
1471
+ "kl": 0.000915266340598464,
1472
+ "learning_rate": 4.600000000000001e-06,
1473
+ "loss": 0.0,
1474
+ "reward": 0.125,
1475
+ "reward_std": 0.0,
1476
+ "rewards/correctness_reward_func": 0.0,
1477
+ "rewards/int_reward_func": 0.0,
1478
+ "rewards/soft_format_reward_func": 0.0,
1479
+ "rewards/strict_format_reward_func": 0.0,
1480
+ "rewards/xmlcount_reward_func": 0.125,
1481
+ "step": 92
1482
+ },
1483
+ {
1484
+ "completion_length": 220.0,
1485
+ "epoch": 0.7815126050420168,
1486
+ "grad_norm": 0.004257082939147949,
1487
+ "kl": 0.00190926983486861,
1488
+ "learning_rate": 4.65e-06,
1489
+ "loss": 0.0001,
1490
+ "reward": 0.25,
1491
+ "reward_std": 0.0,
1492
+ "rewards/correctness_reward_func": 0.0,
1493
+ "rewards/int_reward_func": 0.0,
1494
+ "rewards/soft_format_reward_func": 0.0,
1495
+ "rewards/strict_format_reward_func": 0.0,
1496
+ "rewards/xmlcount_reward_func": 0.25,
1497
+ "step": 93
1498
+ },
1499
+ {
1500
+ "completion_length": 179.0,
1501
+ "epoch": 0.7899159663865546,
1502
+ "grad_norm": 0.9655229449272156,
1503
+ "kl": 0.005708057899028063,
1504
+ "learning_rate": 4.7e-06,
1505
+ "loss": 0.0002,
1506
+ "reward": 0.1875,
1507
+ "reward_std": 0.0883883461356163,
1508
+ "rewards/correctness_reward_func": 0.0,
1509
+ "rewards/int_reward_func": 0.0,
1510
+ "rewards/soft_format_reward_func": 0.0,
1511
+ "rewards/strict_format_reward_func": 0.0,
1512
+ "rewards/xmlcount_reward_func": 0.1875,
1513
+ "step": 94
1514
+ },
1515
+ {
1516
+ "completion_length": 256.0,
1517
+ "epoch": 0.7983193277310925,
1518
+ "grad_norm": 0.006459425203502178,
1519
+ "kl": 0.0011771931312978268,
1520
+ "learning_rate": 4.75e-06,
1521
+ "loss": 0.0,
1522
+ "reward": 0.125,
1523
+ "reward_std": 0.0,
1524
+ "rewards/correctness_reward_func": 0.0,
1525
+ "rewards/int_reward_func": 0.0,
1526
+ "rewards/soft_format_reward_func": 0.0,
1527
+ "rewards/strict_format_reward_func": 0.0,
1528
+ "rewards/xmlcount_reward_func": 0.125,
1529
+ "step": 95
1530
+ },
1531
+ {
1532
+ "completion_length": 225.5,
1533
+ "epoch": 0.8067226890756303,
1534
+ "grad_norm": 0.017570044845342636,
1535
+ "kl": 0.004837444052100182,
1536
+ "learning_rate": 4.800000000000001e-06,
1537
+ "loss": 0.0002,
1538
+ "reward": 0.125,
1539
+ "reward_std": 0.0,
1540
+ "rewards/correctness_reward_func": 0.0,
1541
+ "rewards/int_reward_func": 0.0,
1542
+ "rewards/soft_format_reward_func": 0.0,
1543
+ "rewards/strict_format_reward_func": 0.0,
1544
+ "rewards/xmlcount_reward_func": 0.125,
1545
+ "step": 96
1546
+ },
1547
+ {
1548
+ "completion_length": 256.0,
1549
+ "epoch": 0.8151260504201681,
1550
+ "grad_norm": 0.004950360860675573,
1551
+ "kl": 0.0007728399941697717,
1552
+ "learning_rate": 4.85e-06,
1553
+ "loss": 0.0,
1554
+ "reward": 0.125,
1555
+ "reward_std": 0.0,
1556
+ "rewards/correctness_reward_func": 0.0,
1557
+ "rewards/int_reward_func": 0.0,
1558
+ "rewards/soft_format_reward_func": 0.0,
1559
+ "rewards/strict_format_reward_func": 0.0,
1560
+ "rewards/xmlcount_reward_func": 0.125,
1561
+ "step": 97
1562
+ },
1563
+ {
1564
+ "completion_length": 256.0,
1565
+ "epoch": 0.8235294117647058,
1566
+ "grad_norm": 0.005911249667406082,
1567
+ "kl": 0.001108302385546267,
1568
+ "learning_rate": 4.9000000000000005e-06,
1569
+ "loss": 0.0,
1570
+ "reward": 0.125,
1571
+ "reward_std": 0.0,
1572
+ "rewards/correctness_reward_func": 0.0,
1573
+ "rewards/int_reward_func": 0.0,
1574
+ "rewards/soft_format_reward_func": 0.0,
1575
+ "rewards/strict_format_reward_func": 0.0,
1576
+ "rewards/xmlcount_reward_func": 0.125,
1577
+ "step": 98
1578
+ },
1579
+ {
1580
+ "completion_length": 256.0,
1581
+ "epoch": 0.8319327731092437,
1582
+ "grad_norm": 0.0036189311649650335,
1583
+ "kl": 0.000541006913408637,
1584
+ "learning_rate": 4.95e-06,
1585
+ "loss": 0.0,
1586
+ "reward": 0.125,
1587
+ "reward_std": 0.0,
1588
+ "rewards/correctness_reward_func": 0.0,
1589
+ "rewards/int_reward_func": 0.0,
1590
+ "rewards/soft_format_reward_func": 0.0,
1591
+ "rewards/strict_format_reward_func": 0.0,
1592
+ "rewards/xmlcount_reward_func": 0.125,
1593
+ "step": 99
1594
+ },
1595
+ {
1596
+ "completion_length": 256.0,
1597
+ "epoch": 0.8403361344537815,
1598
+ "grad_norm": 0.007687319535762072,
1599
+ "kl": 0.0007422353373840451,
1600
+ "learning_rate": 5e-06,
1601
+ "loss": 0.0,
1602
+ "reward": 0.125,
1603
+ "reward_std": 0.0,
1604
+ "rewards/correctness_reward_func": 0.0,
1605
+ "rewards/int_reward_func": 0.0,
1606
+ "rewards/soft_format_reward_func": 0.0,
1607
+ "rewards/strict_format_reward_func": 0.0,
1608
+ "rewards/xmlcount_reward_func": 0.125,
1609
+ "step": 100
1610
+ }
1611
+ ],
1612
+ "logging_steps": 1,
1613
+ "max_steps": 1000,
1614
+ "num_input_tokens_seen": 0,
1615
+ "num_train_epochs": 9,
1616
+ "save_steps": 100,
1617
+ "stateful_callbacks": {
1618
+ "TrainerControl": {
1619
+ "args": {
1620
+ "should_epoch_stop": false,
1621
+ "should_evaluate": false,
1622
+ "should_log": false,
1623
+ "should_save": true,
1624
+ "should_training_stop": false
1625
+ },
1626
+ "attributes": {}
1627
+ }
1628
+ },
1629
+ "total_flos": 0.0,
1630
+ "train_batch_size": 1,
1631
+ "trial_name": null,
1632
+ "trial_params": null
1633
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5d8444388982636e18dbb1d85ec0d386361c636956a1318c9174105f56a371
3
+ size 5496