Hugging Face's logo

janhq
/
250409-llama-3.2-3b-instruct-grpo-01-no-retry

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
thinhlpg commited on
Commit
ad8d419
·
verified ·
1 Parent(s): c219507

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. .gitattributes +4 -0
  2. checkpoint-100/README.md +202 -0
  3. checkpoint-100/adapter_config.json +39 -0
  4. checkpoint-100/adapter_model.safetensors +3 -0
  5. checkpoint-100/optimizer.pt +3 -0
  6. checkpoint-100/rng_state.pth +3 -0
  7. checkpoint-100/scheduler.pt +3 -0
  8. checkpoint-100/special_tokens_map.json +23 -0
  9. checkpoint-100/tokenizer.json +3 -0
  10. checkpoint-100/tokenizer_config.json +2067 -0
  11. checkpoint-100/trainer_state.json +1633 -0
  12. checkpoint-100/training_args.bin +3 -0
  13. checkpoint-150/README.md +202 -0
  14. checkpoint-150/adapter_config.json +39 -0
  15. checkpoint-150/adapter_model.safetensors +3 -0
  16. checkpoint-150/optimizer.pt +3 -0
  17. checkpoint-150/rng_state.pth +3 -0
  18. checkpoint-150/scheduler.pt +3 -0
  19. checkpoint-150/special_tokens_map.json +23 -0
  20. checkpoint-150/tokenizer.json +3 -0
  21. checkpoint-150/tokenizer_config.json +2067 -0
  22. checkpoint-150/trainer_state.json +2433 -0
  23. checkpoint-150/training_args.bin +3 -0
  24. checkpoint-50/README.md +202 -0
  25. checkpoint-50/adapter_config.json +39 -0
  26. checkpoint-50/adapter_model.safetensors +3 -0
  27. checkpoint-50/optimizer.pt +3 -0
  28. checkpoint-50/rng_state.pth +3 -0
  29. checkpoint-50/scheduler.pt +3 -0
  30. checkpoint-50/special_tokens_map.json +23 -0
  31. checkpoint-50/tokenizer.json +3 -0
  32. checkpoint-50/tokenizer_config.json +2067 -0
  33. checkpoint-50/trainer_state.json +833 -0
  34. checkpoint-50/training_args.bin +3 -0
  35. logs/app.log +0 -0
  36. runs/Apr09_02-14-09_879c0348b78a/events.out.tfevents.1744164850.879c0348b78a.920.0 +2 -2
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ logs/app.log filter=lfs diff=lfs merge=lfs -text
checkpoint-100/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-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 0.15.1
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "down_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "q_proj",
31
+ "k_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-100/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a9b0d8a28046e6b95755471d1f321d37ab140b2833659665d63a72b940cdc7
3
+ size 778096664
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635d64bb60ec94e24d5f8674da67e602f4d1ead55a3d6bd79ae5dfbb19d3b3fc
3
+ size 395570868
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989c38bcf60c16007b8259a15692e4a9261a54452fd4f7b454d8fc752387f7fa
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4444096202171fe5c4d56c7d31e49feb755bbc38619a4d7e773f643fddfdece1
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,2067 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|finetune_right_pad_id|>",
2064
+ "padding_side": "right",
2065
+ "tokenizer_class": "PreTrainedTokenizer",
2066
+ "unk_token": null
2067
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,1633 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.34965034965034963,
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": 145.875,
13
+ "epoch": 0.0034965034965034965,
14
+ "grad_norm": 8.602514266967773,
15
+ "kl": 0.0,
16
+ "learning_rate": 5.0000000000000004e-08,
17
+ "loss": 0.0,
18
+ "reward": 0.7051772475242615,
19
+ "reward_std": 0.8263505697250366,
20
+ "rewards/reward_correctness": 0.0,
21
+ "rewards/reward_em_chunk": 0.375,
22
+ "rewards/reward_format": 0.0,
23
+ "rewards/reward_search_diversity": 0.3301772475242615,
24
+ "rewards/reward_search_strategy": 0.0,
25
+ "step": 1
26
+ },
27
+ {
28
+ "completion_length": 88.125,
29
+ "epoch": 0.006993006993006993,
30
+ "grad_norm": 1.4985997676849365,
31
+ "kl": 0.0,
32
+ "learning_rate": 1.0000000000000001e-07,
33
+ "loss": -0.0,
34
+ "reward": 1.8388628959655762,
35
+ "reward_std": 2.5329272747039795,
36
+ "rewards/reward_correctness": 0.25,
37
+ "rewards/reward_em_chunk": 0.5,
38
+ "rewards/reward_format": 0.0,
39
+ "rewards/reward_search_diversity": 0.2388630509376526,
40
+ "rewards/reward_search_strategy": 0.10000000149011612,
41
+ "step": 2
42
+ },
43
+ {
44
+ "completion_length": 296.5,
45
+ "epoch": 0.01048951048951049,
46
+ "grad_norm": 0.7674520611763,
47
+ "kl": 0.0006381775019690394,
48
+ "learning_rate": 1.5000000000000002e-07,
49
+ "loss": 0.0,
50
+ "reward": 1.654070258140564,
51
+ "reward_std": 2.827007532119751,
52
+ "rewards/reward_correctness": 0.125,
53
+ "rewards/reward_em_chunk": 0.5,
54
+ "rewards/reward_format": 0.125,
55
+ "rewards/reward_search_diversity": 0.17907029390335083,
56
+ "rewards/reward_search_strategy": 0.22499999403953552,
57
+ "step": 3
58
+ },
59
+ {
60
+ "completion_length": 290.125,
61
+ "epoch": 0.013986013986013986,
62
+ "grad_norm": 1.0457236766815186,
63
+ "kl": 0.0007995082996785641,
64
+ "learning_rate": 2.0000000000000002e-07,
65
+ "loss": 0.0,
66
+ "reward": 3.421433448791504,
67
+ "reward_std": 2.9866631031036377,
68
+ "rewards/reward_correctness": 0.5,
69
+ "rewards/reward_em_chunk": 0.0,
70
+ "rewards/reward_format": 0.375,
71
+ "rewards/reward_search_diversity": 0.396433562040329,
72
+ "rewards/reward_search_strategy": 0.2750000059604645,
73
+ "step": 4
74
+ },
75
+ {
76
+ "completion_length": 259.125,
77
+ "epoch": 0.017482517482517484,
78
+ "grad_norm": 1.3121755123138428,
79
+ "kl": 0.000728036102373153,
80
+ "learning_rate": 2.5000000000000004e-07,
81
+ "loss": 0.0,
82
+ "reward": 0.9268761873245239,
83
+ "reward_std": 0.7560767531394958,
84
+ "rewards/reward_correctness": 0.0,
85
+ "rewards/reward_em_chunk": 0.625,
86
+ "rewards/reward_format": 0.0,
87
+ "rewards/reward_search_diversity": 0.2268761545419693,
88
+ "rewards/reward_search_strategy": 0.07500000298023224,
89
+ "step": 5
90
+ },
91
+ {
92
+ "completion_length": 383.5,
93
+ "epoch": 0.02097902097902098,
94
+ "grad_norm": 0.9658453464508057,
95
+ "kl": 0.0007470359560102224,
96
+ "learning_rate": 3.0000000000000004e-07,
97
+ "loss": 0.0,
98
+ "reward": 1.4594597816467285,
99
+ "reward_std": 2.2520837783813477,
100
+ "rewards/reward_correctness": 0.25,
101
+ "rewards/reward_em_chunk": 0.125,
102
+ "rewards/reward_format": 0.0,
103
+ "rewards/reward_search_diversity": 0.25945988297462463,
104
+ "rewards/reward_search_strategy": 0.07500000298023224,
105
+ "step": 6
106
+ },
107
+ {
108
+ "completion_length": 144.375,
109
+ "epoch": 0.024475524475524476,
110
+ "grad_norm": 1.1642646789550781,
111
+ "kl": 0.0009361266857013106,
112
+ "learning_rate": 3.5000000000000004e-07,
113
+ "loss": 0.0,
114
+ "reward": 1.378964900970459,
115
+ "reward_std": 2.0963218212127686,
116
+ "rewards/reward_correctness": 0.25,
117
+ "rewards/reward_em_chunk": 0.0,
118
+ "rewards/reward_format": 0.0,
119
+ "rewards/reward_search_diversity": 0.30396491289138794,
120
+ "rewards/reward_search_strategy": 0.07500000298023224,
121
+ "step": 7
122
+ },
123
+ {
124
+ "completion_length": 314.375,
125
+ "epoch": 0.027972027972027972,
126
+ "grad_norm": 5.21930456161499,
127
+ "kl": 0.0008346753311343491,
128
+ "learning_rate": 4.0000000000000003e-07,
129
+ "loss": 0.0,
130
+ "reward": 1.181166410446167,
131
+ "reward_std": 1.6016024351119995,
132
+ "rewards/reward_correctness": 0.125,
133
+ "rewards/reward_em_chunk": 0.0,
134
+ "rewards/reward_format": 0.125,
135
+ "rewards/reward_search_diversity": 0.3561664819717407,
136
+ "rewards/reward_search_strategy": 0.07500000298023224,
137
+ "step": 8
138
+ },
139
+ {
140
+ "completion_length": 98.375,
141
+ "epoch": 0.03146853146853147,
142
+ "grad_norm": 1.6168773174285889,
143
+ "kl": 0.0009058149298653007,
144
+ "learning_rate": 4.5000000000000003e-07,
145
+ "loss": 0.0,
146
+ "reward": 1.141206979751587,
147
+ "reward_std": 2.1089890003204346,
148
+ "rewards/reward_correctness": 0.125,
149
+ "rewards/reward_em_chunk": 0.375,
150
+ "rewards/reward_format": 0.0,
151
+ "rewards/reward_search_diversity": 0.16620691120624542,
152
+ "rewards/reward_search_strategy": 0.10000000149011612,
153
+ "step": 9
154
+ },
155
+ {
156
+ "completion_length": 269.625,
157
+ "epoch": 0.03496503496503497,
158
+ "grad_norm": 1.310072660446167,
159
+ "kl": 0.000750248203985393,
160
+ "learning_rate": 5.000000000000001e-07,
161
+ "loss": 0.0,
162
+ "reward": 1.901651382446289,
163
+ "reward_std": 3.08128023147583,
164
+ "rewards/reward_correctness": 0.25,
165
+ "rewards/reward_em_chunk": 0.25,
166
+ "rewards/reward_format": 0.125,
167
+ "rewards/reward_search_diversity": 0.27665144205093384,
168
+ "rewards/reward_search_strategy": 0.125,
169
+ "step": 10
170
+ },
171
+ {
172
+ "completion_length": 311.125,
173
+ "epoch": 0.038461538461538464,
174
+ "grad_norm": 1.1051065921783447,
175
+ "kl": 0.000834438658785075,
176
+ "learning_rate": 5.5e-07,
177
+ "loss": 0.0,
178
+ "reward": 2.1270594596862793,
179
+ "reward_std": 2.309929132461548,
180
+ "rewards/reward_correctness": 0.25,
181
+ "rewards/reward_em_chunk": 0.625,
182
+ "rewards/reward_format": 0.0,
183
+ "rewards/reward_search_diversity": 0.377059668302536,
184
+ "rewards/reward_search_strategy": 0.125,
185
+ "step": 11
186
+ },
187
+ {
188
+ "completion_length": 182.375,
189
+ "epoch": 0.04195804195804196,
190
+ "grad_norm": 1.3039528131484985,
191
+ "kl": 0.0007587745785713196,
192
+ "learning_rate": 6.000000000000001e-07,
193
+ "loss": 0.0,
194
+ "reward": 0.24762853980064392,
195
+ "reward_std": 0.28513866662979126,
196
+ "rewards/reward_correctness": 0.0,
197
+ "rewards/reward_em_chunk": 0.0,
198
+ "rewards/reward_format": 0.0,
199
+ "rewards/reward_search_diversity": 0.17262855172157288,
200
+ "rewards/reward_search_strategy": 0.07500000298023224,
201
+ "step": 12
202
+ },
203
+ {
204
+ "completion_length": 198.5,
205
+ "epoch": 0.045454545454545456,
206
+ "grad_norm": 1.176461935043335,
207
+ "kl": 0.0008510244661010802,
208
+ "learning_rate": 6.5e-07,
209
+ "loss": 0.0,
210
+ "reward": 2.0060770511627197,
211
+ "reward_std": 2.2957346439361572,
212
+ "rewards/reward_correctness": 0.25,
213
+ "rewards/reward_em_chunk": 0.625,
214
+ "rewards/reward_format": 0.0,
215
+ "rewards/reward_search_diversity": 0.3060770034790039,
216
+ "rewards/reward_search_strategy": 0.07500000298023224,
217
+ "step": 13
218
+ },
219
+ {
220
+ "completion_length": 158.25,
221
+ "epoch": 0.04895104895104895,
222
+ "grad_norm": 1.1484898328781128,
223
+ "kl": 0.0009028888889588416,
224
+ "learning_rate": 7.000000000000001e-07,
225
+ "loss": 0.0,
226
+ "reward": 0.2598831355571747,
227
+ "reward_std": 0.4156216084957123,
228
+ "rewards/reward_correctness": 0.0,
229
+ "rewards/reward_em_chunk": 0.125,
230
+ "rewards/reward_format": 0.0,
231
+ "rewards/reward_search_diversity": 0.1348831057548523,
232
+ "rewards/reward_search_strategy": 0.0,
233
+ "step": 14
234
+ },
235
+ {
236
+ "completion_length": 321.125,
237
+ "epoch": 0.05244755244755245,
238
+ "grad_norm": 1.08210027217865,
239
+ "kl": 0.0007499511120840907,
240
+ "learning_rate": 7.5e-07,
241
+ "loss": 0.0,
242
+ "reward": 2.711674213409424,
243
+ "reward_std": 3.2537524700164795,
244
+ "rewards/reward_correctness": 0.375,
245
+ "rewards/reward_em_chunk": 0.375,
246
+ "rewards/reward_format": 0.125,
247
+ "rewards/reward_search_diversity": 0.3866744041442871,
248
+ "rewards/reward_search_strategy": 0.20000000298023224,
249
+ "step": 15
250
+ },
251
+ {
252
+ "completion_length": 176.0,
253
+ "epoch": 0.055944055944055944,
254
+ "grad_norm": 1.007460117340088,
255
+ "kl": 0.0008281145128421485,
256
+ "learning_rate": 8.000000000000001e-07,
257
+ "loss": 0.0,
258
+ "reward": 1.6642776727676392,
259
+ "reward_std": 3.1836605072021484,
260
+ "rewards/reward_correctness": 0.25,
261
+ "rewards/reward_em_chunk": 0.125,
262
+ "rewards/reward_format": 0.125,
263
+ "rewards/reward_search_diversity": 0.1892777681350708,
264
+ "rewards/reward_search_strategy": 0.10000000149011612,
265
+ "step": 16
266
+ },
267
+ {
268
+ "completion_length": 299.0,
269
+ "epoch": 0.05944055944055944,
270
+ "grad_norm": 0.9308914542198181,
271
+ "kl": 0.0006533896084874868,
272
+ "learning_rate": 8.500000000000001e-07,
273
+ "loss": 0.0,
274
+ "reward": 2.9600870609283447,
275
+ "reward_std": 3.002318859100342,
276
+ "rewards/reward_correctness": 0.375,
277
+ "rewards/reward_em_chunk": 0.75,
278
+ "rewards/reward_format": 0.125,
279
+ "rewards/reward_search_diversity": 0.38508710265159607,
280
+ "rewards/reward_search_strategy": 0.07500000298023224,
281
+ "step": 17
282
+ },
283
+ {
284
+ "completion_length": 170.125,
285
+ "epoch": 0.06293706293706294,
286
+ "grad_norm": 1.6546720266342163,
287
+ "kl": 0.0009436010150238872,
288
+ "learning_rate": 9.000000000000001e-07,
289
+ "loss": 0.0,
290
+ "reward": 1.807711124420166,
291
+ "reward_std": 2.873779773712158,
292
+ "rewards/reward_correctness": 0.25,
293
+ "rewards/reward_em_chunk": 0.0,
294
+ "rewards/reward_format": 0.125,
295
+ "rewards/reward_search_diversity": 0.33271118998527527,
296
+ "rewards/reward_search_strategy": 0.22499999403953552,
297
+ "step": 18
298
+ },
299
+ {
300
+ "completion_length": 377.125,
301
+ "epoch": 0.06643356643356643,
302
+ "grad_norm": 0.7977221608161926,
303
+ "kl": 0.0008231342071667314,
304
+ "learning_rate": 9.500000000000001e-07,
305
+ "loss": 0.0,
306
+ "reward": 0.7038719058036804,
307
+ "reward_std": 1.2563936710357666,
308
+ "rewards/reward_correctness": 0.0,
309
+ "rewards/reward_em_chunk": 0.125,
310
+ "rewards/reward_format": 0.125,
311
+ "rewards/reward_search_diversity": 0.22887186706066132,
312
+ "rewards/reward_search_strategy": 0.10000000149011612,
313
+ "step": 19
314
+ },
315
+ {
316
+ "completion_length": 161.625,
317
+ "epoch": 0.06993006993006994,
318
+ "grad_norm": 1.5974496603012085,
319
+ "kl": 0.000790413178037852,
320
+ "learning_rate": 1.0000000000000002e-06,
321
+ "loss": 0.0,
322
+ "reward": 2.404862880706787,
323
+ "reward_std": 2.712550163269043,
324
+ "rewards/reward_correctness": 0.375,
325
+ "rewards/reward_em_chunk": 0.625,
326
+ "rewards/reward_format": 0.0,
327
+ "rewards/reward_search_diversity": 0.179862841963768,
328
+ "rewards/reward_search_strategy": 0.10000000149011612,
329
+ "step": 20
330
+ },
331
+ {
332
+ "completion_length": 298.875,
333
+ "epoch": 0.07342657342657342,
334
+ "grad_norm": 0.8817616105079651,
335
+ "kl": 0.0007674504304304719,
336
+ "learning_rate": 1.0500000000000001e-06,
337
+ "loss": 0.0,
338
+ "reward": 2.6999998092651367,
339
+ "reward_std": 3.122270345687866,
340
+ "rewards/reward_correctness": 0.375,
341
+ "rewards/reward_em_chunk": 0.125,
342
+ "rewards/reward_format": 0.375,
343
+ "rewards/reward_search_diversity": 0.05000000074505806,
344
+ "rewards/reward_search_strategy": 0.2750000059604645,
345
+ "step": 21
346
+ },
347
+ {
348
+ "completion_length": 150.125,
349
+ "epoch": 0.07692307692307693,
350
+ "grad_norm": 1.345902919769287,
351
+ "kl": 0.0010101046646013856,
352
+ "learning_rate": 1.1e-06,
353
+ "loss": 0.0,
354
+ "reward": 1.2625212669372559,
355
+ "reward_std": 1.9802589416503906,
356
+ "rewards/reward_correctness": 0.25,
357
+ "rewards/reward_em_chunk": 0.125,
358
+ "rewards/reward_format": 0.0,
359
+ "rewards/reward_search_diversity": 0.13752126693725586,
360
+ "rewards/reward_search_strategy": 0.0,
361
+ "step": 22
362
+ },
363
+ {
364
+ "completion_length": 156.625,
365
+ "epoch": 0.08041958041958042,
366
+ "grad_norm": 3.1841650009155273,
367
+ "kl": 0.0009282200480811298,
368
+ "learning_rate": 1.1500000000000002e-06,
369
+ "loss": 0.0,
370
+ "reward": 2.532832145690918,
371
+ "reward_std": 3.623222827911377,
372
+ "rewards/reward_correctness": 0.375,
373
+ "rewards/reward_em_chunk": 0.375,
374
+ "rewards/reward_format": 0.125,
375
+ "rewards/reward_search_diversity": 0.18283231556415558,
376
+ "rewards/reward_search_strategy": 0.22500000894069672,
377
+ "step": 23
378
+ },
379
+ {
380
+ "completion_length": 230.625,
381
+ "epoch": 0.08391608391608392,
382
+ "grad_norm": 0.560590922832489,
383
+ "kl": 0.0008200581069104373,
384
+ "learning_rate": 1.2000000000000002e-06,
385
+ "loss": 0.0,
386
+ "reward": 0.7196725606918335,
387
+ "reward_std": 1.5131947994232178,
388
+ "rewards/reward_correctness": 0.125,
389
+ "rewards/reward_em_chunk": 0.0,
390
+ "rewards/reward_format": 0.0,
391
+ "rewards/reward_search_diversity": 0.1946725845336914,
392
+ "rewards/reward_search_strategy": 0.02500000037252903,
393
+ "step": 24
394
+ },
395
+ {
396
+ "completion_length": 232.5,
397
+ "epoch": 0.08741258741258741,
398
+ "grad_norm": 5.627699375152588,
399
+ "kl": 0.0007359281880781054,
400
+ "learning_rate": 1.25e-06,
401
+ "loss": 0.0,
402
+ "reward": 2.3161444664001465,
403
+ "reward_std": 2.266465425491333,
404
+ "rewards/reward_correctness": 0.5,
405
+ "rewards/reward_em_chunk": 0.0,
406
+ "rewards/reward_format": 0.0,
407
+ "rewards/reward_search_diversity": 0.31614452600479126,
408
+ "rewards/reward_search_strategy": 0.0,
409
+ "step": 25
410
+ },
411
+ {
412
+ "completion_length": 256.625,
413
+ "epoch": 0.09090909090909091,
414
+ "grad_norm": 1.243622064590454,
415
+ "kl": 0.0009776452789083123,
416
+ "learning_rate": 1.3e-06,
417
+ "loss": 0.0,
418
+ "reward": 1.8542793989181519,
419
+ "reward_std": 2.3880927562713623,
420
+ "rewards/reward_correctness": 0.25,
421
+ "rewards/reward_em_chunk": 0.625,
422
+ "rewards/reward_format": 0.0,
423
+ "rewards/reward_search_diversity": 0.22927939891815186,
424
+ "rewards/reward_search_strategy": 0.0,
425
+ "step": 26
426
+ },
427
+ {
428
+ "completion_length": 221.625,
429
+ "epoch": 0.0944055944055944,
430
+ "grad_norm": 2.455430030822754,
431
+ "kl": 0.0014260835014283657,
432
+ "learning_rate": 1.3500000000000002e-06,
433
+ "loss": 0.0001,
434
+ "reward": 1.0012282133102417,
435
+ "reward_std": 1.7000349760055542,
436
+ "rewards/reward_correctness": 0.125,
437
+ "rewards/reward_em_chunk": 0.0,
438
+ "rewards/reward_format": 0.125,
439
+ "rewards/reward_search_diversity": 0.15122826397418976,
440
+ "rewards/reward_search_strategy": 0.10000000149011612,
441
+ "step": 27
442
+ },
443
+ {
444
+ "completion_length": 185.75,
445
+ "epoch": 0.0979020979020979,
446
+ "grad_norm": 1.199497938156128,
447
+ "kl": 0.0007826727814972401,
448
+ "learning_rate": 1.4000000000000001e-06,
449
+ "loss": 0.0,
450
+ "reward": 2.173332691192627,
451
+ "reward_std": 2.801347255706787,
452
+ "rewards/reward_correctness": 0.375,
453
+ "rewards/reward_em_chunk": 0.0,
454
+ "rewards/reward_format": 0.125,
455
+ "rewards/reward_search_diversity": 0.32333269715309143,
456
+ "rewards/reward_search_strategy": 0.10000000149011612,
457
+ "step": 28
458
+ },
459
+ {
460
+ "completion_length": 243.125,
461
+ "epoch": 0.10139860139860139,
462
+ "grad_norm": 0.8430306315422058,
463
+ "kl": 0.0008962135761976242,
464
+ "learning_rate": 1.45e-06,
465
+ "loss": 0.0,
466
+ "reward": 1.0625323057174683,
467
+ "reward_std": 1.898645043373108,
468
+ "rewards/reward_correctness": 0.125,
469
+ "rewards/reward_em_chunk": 0.375,
470
+ "rewards/reward_format": 0.0,
471
+ "rewards/reward_search_diversity": 0.18753226101398468,
472
+ "rewards/reward_search_strategy": 0.0,
473
+ "step": 29
474
+ },
475
+ {
476
+ "completion_length": 334.875,
477
+ "epoch": 0.1048951048951049,
478
+ "grad_norm": 0.8412113785743713,
479
+ "kl": 0.001170428702607751,
480
+ "learning_rate": 1.5e-06,
481
+ "loss": 0.0,
482
+ "reward": 1.303612232208252,
483
+ "reward_std": 2.1826775074005127,
484
+ "rewards/reward_correctness": 0.25,
485
+ "rewards/reward_em_chunk": 0.0,
486
+ "rewards/reward_format": 0.0,
487
+ "rewards/reward_search_diversity": 0.27861225605010986,
488
+ "rewards/reward_search_strategy": 0.02500000037252903,
489
+ "step": 30
490
+ },
491
+ {
492
+ "completion_length": 165.75,
493
+ "epoch": 0.10839160839160839,
494
+ "grad_norm": 1.9105679988861084,
495
+ "kl": 0.0031302073039114475,
496
+ "learning_rate": 1.5500000000000002e-06,
497
+ "loss": 0.0001,
498
+ "reward": 1.0198408365249634,
499
+ "reward_std": 2.1316380500793457,
500
+ "rewards/reward_correctness": 0.125,
501
+ "rewards/reward_em_chunk": 0.25,
502
+ "rewards/reward_format": 0.0,
503
+ "rewards/reward_search_diversity": 0.16984085738658905,
504
+ "rewards/reward_search_strategy": 0.10000000149011612,
505
+ "step": 31
506
+ },
507
+ {
508
+ "completion_length": 174.625,
509
+ "epoch": 0.11188811188811189,
510
+ "grad_norm": 2.309382915496826,
511
+ "kl": 0.0032356895972043276,
512
+ "learning_rate": 1.6000000000000001e-06,
513
+ "loss": 0.0001,
514
+ "reward": 0.9216341376304626,
515
+ "reward_std": 1.8671420812606812,
516
+ "rewards/reward_correctness": 0.125,
517
+ "rewards/reward_em_chunk": 0.25,
518
+ "rewards/reward_format": 0.0,
519
+ "rewards/reward_search_diversity": 0.14663413166999817,
520
+ "rewards/reward_search_strategy": 0.02500000037252903,
521
+ "step": 32
522
+ },
523
+ {
524
+ "completion_length": 85.75,
525
+ "epoch": 0.11538461538461539,
526
+ "grad_norm": 1.4122040271759033,
527
+ "kl": 0.0017049856251105666,
528
+ "learning_rate": 1.6500000000000003e-06,
529
+ "loss": 0.0001,
530
+ "reward": 1.524999976158142,
531
+ "reward_std": 2.2926902770996094,
532
+ "rewards/reward_correctness": 0.25,
533
+ "rewards/reward_em_chunk": 0.125,
534
+ "rewards/reward_format": 0.125,
535
+ "rewards/reward_search_diversity": 0.10000000149011612,
536
+ "rewards/reward_search_strategy": 0.05000000074505806,
537
+ "step": 33
538
+ },
539
+ {
540
+ "completion_length": 173.5,
541
+ "epoch": 0.11888111888111888,
542
+ "grad_norm": 0.9712541699409485,
543
+ "kl": 0.0014842856908217072,
544
+ "learning_rate": 1.7000000000000002e-06,
545
+ "loss": 0.0001,
546
+ "reward": 3.4844837188720703,
547
+ "reward_std": 3.1145381927490234,
548
+ "rewards/reward_correctness": 0.5,
549
+ "rewards/reward_em_chunk": 0.75,
550
+ "rewards/reward_format": 0.125,
551
+ "rewards/reward_search_diversity": 0.3094840347766876,
552
+ "rewards/reward_search_strategy": 0.17499999701976776,
553
+ "step": 34
554
+ },
555
+ {
556
+ "completion_length": 268.25,
557
+ "epoch": 0.12237762237762238,
558
+ "grad_norm": 1.1684075593948364,
559
+ "kl": 0.0012478481512516737,
560
+ "learning_rate": 1.75e-06,
561
+ "loss": 0.0,
562
+ "reward": 2.8716678619384766,
563
+ "reward_std": 2.387646198272705,
564
+ "rewards/reward_correctness": 0.5,
565
+ "rewards/reward_em_chunk": 0.375,
566
+ "rewards/reward_format": 0.0,
567
+ "rewards/reward_search_diversity": 0.3716679811477661,
568
+ "rewards/reward_search_strategy": 0.125,
569
+ "step": 35
570
+ },
571
+ {
572
+ "completion_length": 235.125,
573
+ "epoch": 0.1258741258741259,
574
+ "grad_norm": 1.2749513387680054,
575
+ "kl": 0.004472827073186636,
576
+ "learning_rate": 1.8000000000000001e-06,
577
+ "loss": 0.0002,
578
+ "reward": 1.8775699138641357,
579
+ "reward_std": 2.413510322570801,
580
+ "rewards/reward_correctness": 0.375,
581
+ "rewards/reward_em_chunk": 0.0,
582
+ "rewards/reward_format": 0.0,
583
+ "rewards/reward_search_diversity": 0.30256983637809753,
584
+ "rewards/reward_search_strategy": 0.07500000298023224,
585
+ "step": 36
586
+ },
587
+ {
588
+ "completion_length": 175.5,
589
+ "epoch": 0.12937062937062938,
590
+ "grad_norm": 0.8929537534713745,
591
+ "kl": 0.0037049425300210714,
592
+ "learning_rate": 1.85e-06,
593
+ "loss": 0.0001,
594
+ "reward": 0.6821428537368774,
595
+ "reward_std": 1.4377206563949585,
596
+ "rewards/reward_correctness": 0.125,
597
+ "rewards/reward_em_chunk": 0.0,
598
+ "rewards/reward_format": 0.0,
599
+ "rewards/reward_search_diversity": 0.18214285373687744,
600
+ "rewards/reward_search_strategy": 0.0,
601
+ "step": 37
602
+ },
603
+ {
604
+ "completion_length": 290.125,
605
+ "epoch": 0.13286713286713286,
606
+ "grad_norm": 2.52665114402771,
607
+ "kl": 0.005157872103154659,
608
+ "learning_rate": 1.9000000000000002e-06,
609
+ "loss": 0.0002,
610
+ "reward": 2.574741840362549,
611
+ "reward_std": 2.5146002769470215,
612
+ "rewards/reward_correctness": 0.375,
613
+ "rewards/reward_em_chunk": 0.75,
614
+ "rewards/reward_format": 0.0,
615
+ "rewards/reward_search_diversity": 0.14974190294742584,
616
+ "rewards/reward_search_strategy": 0.17500001192092896,
617
+ "step": 38
618
+ },
619
+ {
620
+ "completion_length": 344.125,
621
+ "epoch": 0.13636363636363635,
622
+ "grad_norm": 0.8259175419807434,
623
+ "kl": 0.002582128159701824,
624
+ "learning_rate": 1.9500000000000004e-06,
625
+ "loss": 0.0001,
626
+ "reward": 2.376612901687622,
627
+ "reward_std": 2.9910624027252197,
628
+ "rewards/reward_correctness": 0.375,
629
+ "rewards/reward_em_chunk": 0.125,
630
+ "rewards/reward_format": 0.125,
631
+ "rewards/reward_search_diversity": 0.4266127943992615,
632
+ "rewards/reward_search_strategy": 0.07500000298023224,
633
+ "step": 39
634
+ },
635
+ {
636
+ "completion_length": 243.125,
637
+ "epoch": 0.13986013986013987,
638
+ "grad_norm": 1.0021271705627441,
639
+ "kl": 0.004831339232623577,
640
+ "learning_rate": 2.0000000000000003e-06,
641
+ "loss": 0.0002,
642
+ "reward": 2.04349946975708,
643
+ "reward_std": 2.3903656005859375,
644
+ "rewards/reward_correctness": 0.25,
645
+ "rewards/reward_em_chunk": 0.625,
646
+ "rewards/reward_format": 0.0,
647
+ "rewards/reward_search_diversity": 0.34349945187568665,
648
+ "rewards/reward_search_strategy": 0.07500000298023224,
649
+ "step": 40
650
+ },
651
+ {
652
+ "completion_length": 207.375,
653
+ "epoch": 0.14335664335664336,
654
+ "grad_norm": 1.2446260452270508,
655
+ "kl": 0.005710378754884005,
656
+ "learning_rate": 2.05e-06,
657
+ "loss": 0.0002,
658
+ "reward": 2.8324475288391113,
659
+ "reward_std": 3.167931079864502,
660
+ "rewards/reward_correctness": 0.375,
661
+ "rewards/reward_em_chunk": 0.625,
662
+ "rewards/reward_format": 0.125,
663
+ "rewards/reward_search_diversity": 0.25744765996932983,
664
+ "rewards/reward_search_strategy": 0.20000000298023224,
665
+ "step": 41
666
+ },
667
+ {
668
+ "completion_length": 441.125,
669
+ "epoch": 0.14685314685314685,
670
+ "grad_norm": 0.8263920545578003,
671
+ "kl": 0.0030913222581148148,
672
+ "learning_rate": 2.1000000000000002e-06,
673
+ "loss": 0.0001,
674
+ "reward": 2.5794529914855957,
675
+ "reward_std": 2.6344144344329834,
676
+ "rewards/reward_correctness": 0.375,
677
+ "rewards/reward_em_chunk": 0.125,
678
+ "rewards/reward_format": 0.25,
679
+ "rewards/reward_search_diversity": 0.30445292592048645,
680
+ "rewards/reward_search_strategy": 0.15000000596046448,
681
+ "step": 42
682
+ },
683
+ {
684
+ "completion_length": 226.375,
685
+ "epoch": 0.15034965034965034,
686
+ "grad_norm": 1.141964316368103,
687
+ "kl": 0.008909309282898903,
688
+ "learning_rate": 2.15e-06,
689
+ "loss": 0.0004,
690
+ "reward": 1.8603672981262207,
691
+ "reward_std": 2.203197479248047,
692
+ "rewards/reward_correctness": 0.25,
693
+ "rewards/reward_em_chunk": 0.625,
694
+ "rewards/reward_format": 0.0,
695
+ "rewards/reward_search_diversity": 0.21036729216575623,
696
+ "rewards/reward_search_strategy": 0.02500000037252903,
697
+ "step": 43
698
+ },
699
+ {
700
+ "completion_length": 397.75,
701
+ "epoch": 0.15384615384615385,
702
+ "grad_norm": 0.9564006328582764,
703
+ "kl": 0.01092858798801899,
704
+ "learning_rate": 2.2e-06,
705
+ "loss": 0.0004,
706
+ "reward": 2.557056188583374,
707
+ "reward_std": 2.429002046585083,
708
+ "rewards/reward_correctness": 0.375,
709
+ "rewards/reward_em_chunk": 0.75,
710
+ "rewards/reward_format": 0.0,
711
+ "rewards/reward_search_diversity": 0.28205621242523193,
712
+ "rewards/reward_search_strategy": 0.02500000037252903,
713
+ "step": 44
714
+ },
715
+ {
716
+ "completion_length": 307.25,
717
+ "epoch": 0.15734265734265734,
718
+ "grad_norm": 1.0510841608047485,
719
+ "kl": 0.007918575778603554,
720
+ "learning_rate": 2.25e-06,
721
+ "loss": 0.0003,
722
+ "reward": 1.2331278324127197,
723
+ "reward_std": 1.7548075914382935,
724
+ "rewards/reward_correctness": 0.25,
725
+ "rewards/reward_em_chunk": 0.0,
726
+ "rewards/reward_format": 0.0,
727
+ "rewards/reward_search_diversity": 0.15812794864177704,
728
+ "rewards/reward_search_strategy": 0.07500000298023224,
729
+ "step": 45
730
+ },
731
+ {
732
+ "completion_length": 277.0,
733
+ "epoch": 0.16083916083916083,
734
+ "grad_norm": 0.9169591665267944,
735
+ "kl": 0.015062836930155754,
736
+ "learning_rate": 2.3000000000000004e-06,
737
+ "loss": 0.0006,
738
+ "reward": 1.2089338302612305,
739
+ "reward_std": 2.5115318298339844,
740
+ "rewards/reward_correctness": 0.125,
741
+ "rewards/reward_em_chunk": 0.125,
742
+ "rewards/reward_format": 0.125,
743
+ "rewards/reward_search_diversity": 0.1339338719844818,
744
+ "rewards/reward_search_strategy": 0.20000000298023224,
745
+ "step": 46
746
+ },
747
+ {
748
+ "completion_length": 206.25,
749
+ "epoch": 0.16433566433566432,
750
+ "grad_norm": 1.3427180051803589,
751
+ "kl": 0.019624339416623116,
752
+ "learning_rate": 2.35e-06,
753
+ "loss": 0.0008,
754
+ "reward": 4.1133527755737305,
755
+ "reward_std": 3.2583820819854736,
756
+ "rewards/reward_correctness": 0.625,
757
+ "rewards/reward_em_chunk": 0.625,
758
+ "rewards/reward_format": 0.25,
759
+ "rewards/reward_search_diversity": 0.36335283517837524,
760
+ "rewards/reward_search_strategy": 0.125,
761
+ "step": 47
762
+ },
763
+ {
764
+ "completion_length": 252.125,
765
+ "epoch": 0.16783216783216784,
766
+ "grad_norm": 0.7444542050361633,
767
+ "kl": 0.021463895216584206,
768
+ "learning_rate": 2.4000000000000003e-06,
769
+ "loss": 0.0009,
770
+ "reward": 1.631263017654419,
771
+ "reward_std": 2.5925517082214355,
772
+ "rewards/reward_correctness": 0.25,
773
+ "rewards/reward_em_chunk": 0.375,
774
+ "rewards/reward_format": 0.0,
775
+ "rewards/reward_search_diversity": 0.23126289248466492,
776
+ "rewards/reward_search_strategy": 0.02500000037252903,
777
+ "step": 48
778
+ },
779
+ {
780
+ "completion_length": 117.625,
781
+ "epoch": 0.17132867132867133,
782
+ "grad_norm": 1.888673186302185,
783
+ "kl": 0.03609447553753853,
784
+ "learning_rate": 2.4500000000000003e-06,
785
+ "loss": 0.0014,
786
+ "reward": 1.9036250114440918,
787
+ "reward_std": 2.2273151874542236,
788
+ "rewards/reward_correctness": 0.25,
789
+ "rewards/reward_em_chunk": 0.625,
790
+ "rewards/reward_format": 0.0,
791
+ "rewards/reward_search_diversity": 0.20362500846385956,
792
+ "rewards/reward_search_strategy": 0.07500000298023224,
793
+ "step": 49
794
+ },
795
+ {
796
+ "completion_length": 302.75,
797
+ "epoch": 0.17482517482517482,
798
+ "grad_norm": 1.2723031044006348,
799
+ "kl": 0.2012804001569748,
800
+ "learning_rate": 2.5e-06,
801
+ "loss": 0.0081,
802
+ "reward": 0.15956448018550873,
803
+ "reward_std": 0.4513165056705475,
804
+ "rewards/reward_correctness": 0.0,
805
+ "rewards/reward_em_chunk": 0.125,
806
+ "rewards/reward_format": 0.0,
807
+ "rewards/reward_search_diversity": 0.03456447646021843,
808
+ "rewards/reward_search_strategy": 0.0,
809
+ "step": 50
810
+ },
811
+ {
812
+ "completion_length": 222.0,
813
+ "epoch": 0.17832167832167833,
814
+ "grad_norm": 0.8149501085281372,
815
+ "kl": 0.04784020781517029,
816
+ "learning_rate": 2.55e-06,
817
+ "loss": 0.0019,
818
+ "reward": 0.49046826362609863,
819
+ "reward_std": 0.9328532814979553,
820
+ "rewards/reward_correctness": 0.0,
821
+ "rewards/reward_em_chunk": 0.0,
822
+ "rewards/reward_format": 0.125,
823
+ "rewards/reward_search_diversity": 0.1654682457447052,
824
+ "rewards/reward_search_strategy": 0.07500000298023224,
825
+ "step": 51
826
+ },
827
+ {
828
+ "completion_length": 329.75,
829
+ "epoch": 0.18181818181818182,
830
+ "grad_norm": 1.0090314149856567,
831
+ "kl": 0.03431350365281105,
832
+ "learning_rate": 2.6e-06,
833
+ "loss": 0.0014,
834
+ "reward": 1.8717395067214966,
835
+ "reward_std": 2.0185225009918213,
836
+ "rewards/reward_correctness": 0.125,
837
+ "rewards/reward_em_chunk": 0.375,
838
+ "rewards/reward_format": 0.25,
839
+ "rewards/reward_search_diversity": 0.246739462018013,
840
+ "rewards/reward_search_strategy": 0.25,
841
+ "step": 52
842
+ },
843
+ {
844
+ "completion_length": 292.5,
845
+ "epoch": 0.1853146853146853,
846
+ "grad_norm": 0.9738456606864929,
847
+ "kl": 0.03869509696960449,
848
+ "learning_rate": 2.6500000000000005e-06,
849
+ "loss": 0.0015,
850
+ "reward": 3.411203384399414,
851
+ "reward_std": 2.776095390319824,
852
+ "rewards/reward_correctness": 0.625,
853
+ "rewards/reward_em_chunk": 0.625,
854
+ "rewards/reward_format": 0.0,
855
+ "rewards/reward_search_diversity": 0.28620344400405884,
856
+ "rewards/reward_search_strategy": 0.0,
857
+ "step": 53
858
+ },
859
+ {
860
+ "completion_length": 262.25,
861
+ "epoch": 0.1888111888111888,
862
+ "grad_norm": 1.0264172554016113,
863
+ "kl": 0.04221673682332039,
864
+ "learning_rate": 2.7000000000000004e-06,
865
+ "loss": 0.0017,
866
+ "reward": 3.2230210304260254,
867
+ "reward_std": 3.179140329360962,
868
+ "rewards/reward_correctness": 0.5,
869
+ "rewards/reward_em_chunk": 0.125,
870
+ "rewards/reward_format": 0.25,
871
+ "rewards/reward_search_diversity": 0.2730211913585663,
872
+ "rewards/reward_search_strategy": 0.32500001788139343,
873
+ "step": 54
874
+ },
875
+ {
876
+ "completion_length": 278.0,
877
+ "epoch": 0.19230769230769232,
878
+ "grad_norm": 1.219490885734558,
879
+ "kl": 0.07308313995599747,
880
+ "learning_rate": 2.7500000000000004e-06,
881
+ "loss": 0.0029,
882
+ "reward": 2.9714736938476562,
883
+ "reward_std": 3.078878164291382,
884
+ "rewards/reward_correctness": 0.25,
885
+ "rewards/reward_em_chunk": 0.625,
886
+ "rewards/reward_format": 0.375,
887
+ "rewards/reward_search_diversity": 0.32147371768951416,
888
+ "rewards/reward_search_strategy": 0.2750000059604645,
889
+ "step": 55
890
+ },
891
+ {
892
+ "completion_length": 198.125,
893
+ "epoch": 0.1958041958041958,
894
+ "grad_norm": 2.261676788330078,
895
+ "kl": 0.10734312981367111,
896
+ "learning_rate": 2.8000000000000003e-06,
897
+ "loss": 0.0043,
898
+ "reward": 1.751394271850586,
899
+ "reward_std": 2.916086196899414,
900
+ "rewards/reward_correctness": 0.125,
901
+ "rewards/reward_em_chunk": 0.5,
902
+ "rewards/reward_format": 0.125,
903
+ "rewards/reward_search_diversity": 0.35139432549476624,
904
+ "rewards/reward_search_strategy": 0.15000000596046448,
905
+ "step": 56
906
+ },
907
+ {
908
+ "completion_length": 368.25,
909
+ "epoch": 0.1993006993006993,
910
+ "grad_norm": 1.0139119625091553,
911
+ "kl": 0.07945723086595535,
912
+ "learning_rate": 2.85e-06,
913
+ "loss": 0.0032,
914
+ "reward": 2.6666977405548096,
915
+ "reward_std": 3.0744428634643555,
916
+ "rewards/reward_correctness": 0.375,
917
+ "rewards/reward_em_chunk": 0.625,
918
+ "rewards/reward_format": 0.125,
919
+ "rewards/reward_search_diversity": 0.1416977047920227,
920
+ "rewards/reward_search_strategy": 0.15000000596046448,
921
+ "step": 57
922
+ },
923
+ {
924
+ "completion_length": 445.875,
925
+ "epoch": 0.20279720279720279,
926
+ "grad_norm": 1.2591164112091064,
927
+ "kl": 0.0817643404006958,
928
+ "learning_rate": 2.9e-06,
929
+ "loss": 0.0033,
930
+ "reward": 3.105250358581543,
931
+ "reward_std": 2.503899574279785,
932
+ "rewards/reward_correctness": 0.375,
933
+ "rewards/reward_em_chunk": 0.75,
934
+ "rewards/reward_format": 0.125,
935
+ "rewards/reward_search_diversity": 0.4302505850791931,
936
+ "rewards/reward_search_strategy": 0.17499999701976776,
937
+ "step": 58
938
+ },
939
+ {
940
+ "completion_length": 465.875,
941
+ "epoch": 0.2062937062937063,
942
+ "grad_norm": 0.6122844219207764,
943
+ "kl": 0.0703798234462738,
944
+ "learning_rate": 2.95e-06,
945
+ "loss": 0.0028,
946
+ "reward": 1.6243177652359009,
947
+ "reward_std": 1.8378466367721558,
948
+ "rewards/reward_correctness": 0.25,
949
+ "rewards/reward_em_chunk": 0.125,
950
+ "rewards/reward_format": 0.0,
951
+ "rewards/reward_search_diversity": 0.37431782484054565,
952
+ "rewards/reward_search_strategy": 0.125,
953
+ "step": 59
954
+ },
955
+ {
956
+ "completion_length": 256.375,
957
+ "epoch": 0.2097902097902098,
958
+ "grad_norm": 0.9197457432746887,
959
+ "kl": 0.08273329585790634,
960
+ "learning_rate": 3e-06,
961
+ "loss": 0.0033,
962
+ "reward": 2.420247793197632,
963
+ "reward_std": 2.3122122287750244,
964
+ "rewards/reward_correctness": 0.375,
965
+ "rewards/reward_em_chunk": 0.0,
966
+ "rewards/reward_format": 0.125,
967
+ "rewards/reward_search_diversity": 0.4202479422092438,
968
+ "rewards/reward_search_strategy": 0.25,
969
+ "step": 60
970
+ },
971
+ {
972
+ "completion_length": 517.125,
973
+ "epoch": 0.21328671328671328,
974
+ "grad_norm": 0.8799907565116882,
975
+ "kl": 0.20334148406982422,
976
+ "learning_rate": 3.05e-06,
977
+ "loss": 0.0081,
978
+ "reward": 1.377384066581726,
979
+ "reward_std": 1.68935227394104,
980
+ "rewards/reward_correctness": 0.125,
981
+ "rewards/reward_em_chunk": 0.25,
982
+ "rewards/reward_format": 0.125,
983
+ "rewards/reward_search_diversity": 0.3023841083049774,
984
+ "rewards/reward_search_strategy": 0.07500000298023224,
985
+ "step": 61
986
+ },
987
+ {
988
+ "completion_length": 502.5,
989
+ "epoch": 0.21678321678321677,
990
+ "grad_norm": 0.7109338641166687,
991
+ "kl": 0.03114498406648636,
992
+ "learning_rate": 3.1000000000000004e-06,
993
+ "loss": 0.0012,
994
+ "reward": 5.466271877288818,
995
+ "reward_std": 2.7285211086273193,
996
+ "rewards/reward_correctness": 0.75,
997
+ "rewards/reward_em_chunk": 0.625,
998
+ "rewards/reward_format": 0.375,
999
+ "rewards/reward_search_diversity": 0.6912716627120972,
1000
+ "rewards/reward_search_strategy": 0.4000000059604645,
1001
+ "step": 62
1002
+ },
1003
+ {
1004
+ "completion_length": 503.25,
1005
+ "epoch": 0.2202797202797203,
1006
+ "grad_norm": 0.9971331357955933,
1007
+ "kl": 0.20209850370883942,
1008
+ "learning_rate": 3.1500000000000003e-06,
1009
+ "loss": 0.0081,
1010
+ "reward": 1.2392462491989136,
1011
+ "reward_std": 1.4006211757659912,
1012
+ "rewards/reward_correctness": 0.125,
1013
+ "rewards/reward_em_chunk": 0.375,
1014
+ "rewards/reward_format": 0.0,
1015
+ "rewards/reward_search_diversity": 0.189246267080307,
1016
+ "rewards/reward_search_strategy": 0.17500001192092896,
1017
+ "step": 63
1018
+ },
1019
+ {
1020
+ "completion_length": 288.5,
1021
+ "epoch": 0.22377622377622378,
1022
+ "grad_norm": 0.8857221603393555,
1023
+ "kl": 0.10349184274673462,
1024
+ "learning_rate": 3.2000000000000003e-06,
1025
+ "loss": 0.0041,
1026
+ "reward": 1.3573650121688843,
1027
+ "reward_std": 1.9148555994033813,
1028
+ "rewards/reward_correctness": 0.125,
1029
+ "rewards/reward_em_chunk": 0.375,
1030
+ "rewards/reward_format": 0.0,
1031
+ "rewards/reward_search_diversity": 0.40736502408981323,
1032
+ "rewards/reward_search_strategy": 0.07500000298023224,
1033
+ "step": 64
1034
+ },
1035
+ {
1036
+ "completion_length": 445.875,
1037
+ "epoch": 0.22727272727272727,
1038
+ "grad_norm": 2.050611734390259,
1039
+ "kl": 0.9011820554733276,
1040
+ "learning_rate": 3.2500000000000002e-06,
1041
+ "loss": 0.036,
1042
+ "reward": 2.7885334491729736,
1043
+ "reward_std": 2.6393096446990967,
1044
+ "rewards/reward_correctness": 0.375,
1045
+ "rewards/reward_em_chunk": 0.375,
1046
+ "rewards/reward_format": 0.125,
1047
+ "rewards/reward_search_diversity": 0.46353352069854736,
1048
+ "rewards/reward_search_strategy": 0.20000000298023224,
1049
+ "step": 65
1050
+ },
1051
+ {
1052
+ "completion_length": 321.75,
1053
+ "epoch": 0.23076923076923078,
1054
+ "grad_norm": 0.8712911605834961,
1055
+ "kl": 0.11524824798107147,
1056
+ "learning_rate": 3.3000000000000006e-06,
1057
+ "loss": 0.0046,
1058
+ "reward": 2.963777542114258,
1059
+ "reward_std": 2.7310569286346436,
1060
+ "rewards/reward_correctness": 0.5,
1061
+ "rewards/reward_em_chunk": 0.375,
1062
+ "rewards/reward_format": 0.125,
1063
+ "rewards/reward_search_diversity": 0.21377724409103394,
1064
+ "rewards/reward_search_strategy": 0.125,
1065
+ "step": 66
1066
+ },
1067
+ {
1068
+ "completion_length": 579.5,
1069
+ "epoch": 0.23426573426573427,
1070
+ "grad_norm": 0.6312026977539062,
1071
+ "kl": 0.08477935940027237,
1072
+ "learning_rate": 3.3500000000000005e-06,
1073
+ "loss": 0.0034,
1074
+ "reward": 4.128048896789551,
1075
+ "reward_std": 2.959887742996216,
1076
+ "rewards/reward_correctness": 0.625,
1077
+ "rewards/reward_em_chunk": 0.875,
1078
+ "rewards/reward_format": 0.125,
1079
+ "rewards/reward_search_diversity": 0.30304890871047974,
1080
+ "rewards/reward_search_strategy": 0.20000000298023224,
1081
+ "step": 67
1082
+ },
1083
+ {
1084
+ "completion_length": 256.625,
1085
+ "epoch": 0.23776223776223776,
1086
+ "grad_norm": 0.835229218006134,
1087
+ "kl": 0.1031595766544342,
1088
+ "learning_rate": 3.4000000000000005e-06,
1089
+ "loss": 0.0041,
1090
+ "reward": 5.231247425079346,
1091
+ "reward_std": 2.7173686027526855,
1092
+ "rewards/reward_correctness": 0.75,
1093
+ "rewards/reward_em_chunk": 1.0,
1094
+ "rewards/reward_format": 0.25,
1095
+ "rewards/reward_search_diversity": 0.48124733567237854,
1096
+ "rewards/reward_search_strategy": 0.25,
1097
+ "step": 68
1098
+ },
1099
+ {
1100
+ "completion_length": 458.125,
1101
+ "epoch": 0.24125874125874125,
1102
+ "grad_norm": 1.0669630765914917,
1103
+ "kl": 0.050319548696279526,
1104
+ "learning_rate": 3.45e-06,
1105
+ "loss": 0.002,
1106
+ "reward": 2.627213716506958,
1107
+ "reward_std": 2.752366781234741,
1108
+ "rewards/reward_correctness": 0.25,
1109
+ "rewards/reward_em_chunk": 0.875,
1110
+ "rewards/reward_format": 0.125,
1111
+ "rewards/reward_search_diversity": 0.1022137925028801,
1112
+ "rewards/reward_search_strategy": 0.4000000059604645,
1113
+ "step": 69
1114
+ },
1115
+ {
1116
+ "completion_length": 758.125,
1117
+ "epoch": 0.24475524475524477,
1118
+ "grad_norm": 0.4896698594093323,
1119
+ "kl": 0.03787853941321373,
1120
+ "learning_rate": 3.5e-06,
1121
+ "loss": 0.0015,
1122
+ "reward": 3.715177059173584,
1123
+ "reward_std": 2.108518362045288,
1124
+ "rewards/reward_correctness": 0.25,
1125
+ "rewards/reward_em_chunk": 0.875,
1126
+ "rewards/reward_format": 0.5,
1127
+ "rewards/reward_search_diversity": 0.44017714262008667,
1128
+ "rewards/reward_search_strategy": 0.3999999761581421,
1129
+ "step": 70
1130
+ },
1131
+ {
1132
+ "completion_length": 359.625,
1133
+ "epoch": 0.24825174825174826,
1134
+ "grad_norm": 1.1720679998397827,
1135
+ "kl": 0.09393578767776489,
1136
+ "learning_rate": 3.5500000000000003e-06,
1137
+ "loss": 0.0038,
1138
+ "reward": 5.1651530265808105,
1139
+ "reward_std": 2.7064919471740723,
1140
+ "rewards/reward_correctness": 0.625,
1141
+ "rewards/reward_em_chunk": 1.0,
1142
+ "rewards/reward_format": 0.375,
1143
+ "rewards/reward_search_diversity": 0.39015328884124756,
1144
+ "rewards/reward_search_strategy": 0.5249999761581421,
1145
+ "step": 71
1146
+ },
1147
+ {
1148
+ "completion_length": 603.75,
1149
+ "epoch": 0.2517482517482518,
1150
+ "grad_norm": 0.92381352186203,
1151
+ "kl": 0.03434322774410248,
1152
+ "learning_rate": 3.6000000000000003e-06,
1153
+ "loss": 0.0014,
1154
+ "reward": 1.6090435981750488,
1155
+ "reward_std": 1.3871439695358276,
1156
+ "rewards/reward_correctness": 0.125,
1157
+ "rewards/reward_em_chunk": 0.125,
1158
+ "rewards/reward_format": 0.125,
1159
+ "rewards/reward_search_diversity": 0.5090435743331909,
1160
+ "rewards/reward_search_strategy": 0.22500000894069672,
1161
+ "step": 72
1162
+ },
1163
+ {
1164
+ "completion_length": 324.125,
1165
+ "epoch": 0.25524475524475526,
1166
+ "grad_norm": 0.8183465003967285,
1167
+ "kl": 0.09460737556219101,
1168
+ "learning_rate": 3.65e-06,
1169
+ "loss": 0.0038,
1170
+ "reward": 1.5781946182250977,
1171
+ "reward_std": 2.772611618041992,
1172
+ "rewards/reward_correctness": 0.125,
1173
+ "rewards/reward_em_chunk": 0.5,
1174
+ "rewards/reward_format": 0.125,
1175
+ "rewards/reward_search_diversity": 0.25319457054138184,
1176
+ "rewards/reward_search_strategy": 0.07500000298023224,
1177
+ "step": 73
1178
+ },
1179
+ {
1180
+ "completion_length": 479.5,
1181
+ "epoch": 0.25874125874125875,
1182
+ "grad_norm": 0.8604242205619812,
1183
+ "kl": 0.053619399666786194,
1184
+ "learning_rate": 3.7e-06,
1185
+ "loss": 0.0021,
1186
+ "reward": 4.117947578430176,
1187
+ "reward_std": 2.7907135486602783,
1188
+ "rewards/reward_correctness": 0.75,
1189
+ "rewards/reward_em_chunk": 0.0,
1190
+ "rewards/reward_format": 0.25,
1191
+ "rewards/reward_search_diversity": 0.41794782876968384,
1192
+ "rewards/reward_search_strategy": 0.20000000298023224,
1193
+ "step": 74
1194
+ },
1195
+ {
1196
+ "completion_length": 450.25,
1197
+ "epoch": 0.26223776223776224,
1198
+ "grad_norm": 2.1643834114074707,
1199
+ "kl": 0.19324736297130585,
1200
+ "learning_rate": 3.7500000000000005e-06,
1201
+ "loss": 0.0077,
1202
+ "reward": 4.815071105957031,
1203
+ "reward_std": 3.0326616764068604,
1204
+ "rewards/reward_correctness": 0.5,
1205
+ "rewards/reward_em_chunk": 0.75,
1206
+ "rewards/reward_format": 0.625,
1207
+ "rewards/reward_search_diversity": 0.39007121324539185,
1208
+ "rewards/reward_search_strategy": 0.42500001192092896,
1209
+ "step": 75
1210
+ },
1211
+ {
1212
+ "completion_length": 412.25,
1213
+ "epoch": 0.26573426573426573,
1214
+ "grad_norm": 0.8062530159950256,
1215
+ "kl": 0.0793648362159729,
1216
+ "learning_rate": 3.8000000000000005e-06,
1217
+ "loss": 0.0032,
1218
+ "reward": 3.5049312114715576,
1219
+ "reward_std": 2.922109603881836,
1220
+ "rewards/reward_correctness": 0.5,
1221
+ "rewards/reward_em_chunk": 0.25,
1222
+ "rewards/reward_format": 0.25,
1223
+ "rewards/reward_search_diversity": 0.5549312829971313,
1224
+ "rewards/reward_search_strategy": 0.20000000298023224,
1225
+ "step": 76
1226
+ },
1227
+ {
1228
+ "completion_length": 369.75,
1229
+ "epoch": 0.2692307692307692,
1230
+ "grad_norm": 1.467880368232727,
1231
+ "kl": 0.0835878923535347,
1232
+ "learning_rate": 3.85e-06,
1233
+ "loss": 0.0033,
1234
+ "reward": 2.802757978439331,
1235
+ "reward_std": 2.5307087898254395,
1236
+ "rewards/reward_correctness": 0.375,
1237
+ "rewards/reward_em_chunk": 0.0,
1238
+ "rewards/reward_format": 0.375,
1239
+ "rewards/reward_search_diversity": 0.3277580440044403,
1240
+ "rewards/reward_search_strategy": 0.22500000894069672,
1241
+ "step": 77
1242
+ },
1243
+ {
1244
+ "completion_length": 382.375,
1245
+ "epoch": 0.2727272727272727,
1246
+ "grad_norm": 4.771082401275635,
1247
+ "kl": 0.9713490605354309,
1248
+ "learning_rate": 3.900000000000001e-06,
1249
+ "loss": 0.0389,
1250
+ "reward": 2.052755117416382,
1251
+ "reward_std": 3.0059754848480225,
1252
+ "rewards/reward_correctness": 0.25,
1253
+ "rewards/reward_em_chunk": 0.125,
1254
+ "rewards/reward_format": 0.125,
1255
+ "rewards/reward_search_diversity": 0.3777550160884857,
1256
+ "rewards/reward_search_strategy": 0.30000001192092896,
1257
+ "step": 78
1258
+ },
1259
+ {
1260
+ "completion_length": 546.125,
1261
+ "epoch": 0.2762237762237762,
1262
+ "grad_norm": 0.48559486865997314,
1263
+ "kl": 0.037933606654405594,
1264
+ "learning_rate": 3.95e-06,
1265
+ "loss": 0.0015,
1266
+ "reward": 4.67194938659668,
1267
+ "reward_std": 1.9323244094848633,
1268
+ "rewards/reward_correctness": 0.375,
1269
+ "rewards/reward_em_chunk": 1.0,
1270
+ "rewards/reward_format": 0.625,
1271
+ "rewards/reward_search_diversity": 0.5219494700431824,
1272
+ "rewards/reward_search_strategy": 0.3999999761581421,
1273
+ "step": 79
1274
+ },
1275
+ {
1276
+ "completion_length": 677.25,
1277
+ "epoch": 0.27972027972027974,
1278
+ "grad_norm": 0.42382290959358215,
1279
+ "kl": 0.0389033704996109,
1280
+ "learning_rate": 4.000000000000001e-06,
1281
+ "loss": 0.0016,
1282
+ "reward": 1.6928536891937256,
1283
+ "reward_std": 2.6118526458740234,
1284
+ "rewards/reward_correctness": 0.125,
1285
+ "rewards/reward_em_chunk": 0.125,
1286
+ "rewards/reward_format": 0.25,
1287
+ "rewards/reward_search_diversity": 0.367853581905365,
1288
+ "rewards/reward_search_strategy": 0.20000000298023224,
1289
+ "step": 80
1290
+ },
1291
+ {
1292
+ "completion_length": 472.125,
1293
+ "epoch": 0.28321678321678323,
1294
+ "grad_norm": 0.8816371560096741,
1295
+ "kl": 0.07524556666612625,
1296
+ "learning_rate": 4.05e-06,
1297
+ "loss": 0.003,
1298
+ "reward": 3.7551965713500977,
1299
+ "reward_std": 2.652488946914673,
1300
+ "rewards/reward_correctness": 0.375,
1301
+ "rewards/reward_em_chunk": 0.875,
1302
+ "rewards/reward_format": 0.375,
1303
+ "rewards/reward_search_diversity": 0.4801965653896332,
1304
+ "rewards/reward_search_strategy": 0.15000000596046448,
1305
+ "step": 81
1306
+ },
1307
+ {
1308
+ "completion_length": 1057.125,
1309
+ "epoch": 0.2867132867132867,
1310
+ "grad_norm": 0.5135111808776855,
1311
+ "kl": 0.03152136504650116,
1312
+ "learning_rate": 4.1e-06,
1313
+ "loss": 0.0013,
1314
+ "reward": 3.2323527336120605,
1315
+ "reward_std": 1.7208728790283203,
1316
+ "rewards/reward_correctness": 0.125,
1317
+ "rewards/reward_em_chunk": 0.625,
1318
+ "rewards/reward_format": 0.5,
1319
+ "rewards/reward_search_diversity": 0.682352602481842,
1320
+ "rewards/reward_search_strategy": 0.42500001192092896,
1321
+ "step": 82
1322
+ },
1323
+ {
1324
+ "completion_length": 485.375,
1325
+ "epoch": 0.2902097902097902,
1326
+ "grad_norm": 0.9151804447174072,
1327
+ "kl": 0.059312522411346436,
1328
+ "learning_rate": 4.15e-06,
1329
+ "loss": 0.0024,
1330
+ "reward": 1.5200467109680176,
1331
+ "reward_std": 1.384164810180664,
1332
+ "rewards/reward_correctness": 0.0,
1333
+ "rewards/reward_em_chunk": 0.75,
1334
+ "rewards/reward_format": 0.125,
1335
+ "rewards/reward_search_diversity": 0.4450467824935913,
1336
+ "rewards/reward_search_strategy": 0.07500000298023224,
1337
+ "step": 83
1338
+ },
1339
+ {
1340
+ "completion_length": 703.25,
1341
+ "epoch": 0.2937062937062937,
1342
+ "grad_norm": 0.708080530166626,
1343
+ "kl": 0.02395041473209858,
1344
+ "learning_rate": 4.2000000000000004e-06,
1345
+ "loss": 0.001,
1346
+ "reward": 4.584571838378906,
1347
+ "reward_std": 2.8503193855285645,
1348
+ "rewards/reward_correctness": 0.5,
1349
+ "rewards/reward_em_chunk": 0.75,
1350
+ "rewards/reward_format": 0.5,
1351
+ "rewards/reward_search_diversity": 0.4345718026161194,
1352
+ "rewards/reward_search_strategy": 0.4000000059604645,
1353
+ "step": 84
1354
+ },
1355
+ {
1356
+ "completion_length": 507.75,
1357
+ "epoch": 0.2972027972027972,
1358
+ "grad_norm": 0.9842731356620789,
1359
+ "kl": 0.045889340341091156,
1360
+ "learning_rate": 4.25e-06,
1361
+ "loss": 0.0018,
1362
+ "reward": 6.216353893280029,
1363
+ "reward_std": 3.617387056350708,
1364
+ "rewards/reward_correctness": 0.75,
1365
+ "rewards/reward_em_chunk": 0.75,
1366
+ "rewards/reward_format": 0.625,
1367
+ "rewards/reward_search_diversity": 0.4663536846637726,
1368
+ "rewards/reward_search_strategy": 0.75,
1369
+ "step": 85
1370
+ },
1371
+ {
1372
+ "completion_length": 362.75,
1373
+ "epoch": 0.3006993006993007,
1374
+ "grad_norm": 5.553736686706543,
1375
+ "kl": 0.31082066893577576,
1376
+ "learning_rate": 4.3e-06,
1377
+ "loss": 0.0124,
1378
+ "reward": 2.6352591514587402,
1379
+ "reward_std": 3.6418111324310303,
1380
+ "rewards/reward_correctness": 0.25,
1381
+ "rewards/reward_em_chunk": 0.375,
1382
+ "rewards/reward_format": 0.375,
1383
+ "rewards/reward_search_diversity": 0.18525923788547516,
1384
+ "rewards/reward_search_strategy": 0.32499998807907104,
1385
+ "step": 86
1386
+ },
1387
+ {
1388
+ "completion_length": 760.625,
1389
+ "epoch": 0.3041958041958042,
1390
+ "grad_norm": 0.40838149189949036,
1391
+ "kl": 0.03904329240322113,
1392
+ "learning_rate": 4.350000000000001e-06,
1393
+ "loss": 0.0016,
1394
+ "reward": 2.3138082027435303,
1395
+ "reward_std": 2.5393922328948975,
1396
+ "rewards/reward_correctness": 0.125,
1397
+ "rewards/reward_em_chunk": 0.25,
1398
+ "rewards/reward_format": 0.375,
1399
+ "rewards/reward_search_diversity": 0.43880823254585266,
1400
+ "rewards/reward_search_strategy": 0.375,
1401
+ "step": 87
1402
+ },
1403
+ {
1404
+ "completion_length": 233.875,
1405
+ "epoch": 0.3076923076923077,
1406
+ "grad_norm": 1.6991461515426636,
1407
+ "kl": 0.11344132572412491,
1408
+ "learning_rate": 4.4e-06,
1409
+ "loss": 0.0045,
1410
+ "reward": 5.137988090515137,
1411
+ "reward_std": 3.6587538719177246,
1412
+ "rewards/reward_correctness": 0.625,
1413
+ "rewards/reward_em_chunk": 0.875,
1414
+ "rewards/reward_format": 0.5,
1415
+ "rewards/reward_search_diversity": 0.28798776865005493,
1416
+ "rewards/reward_search_strategy": 0.4750000238418579,
1417
+ "step": 88
1418
+ },
1419
+ {
1420
+ "completion_length": 634.0,
1421
+ "epoch": 0.3111888111888112,
1422
+ "grad_norm": 1.008798599243164,
1423
+ "kl": 0.13237585127353668,
1424
+ "learning_rate": 4.450000000000001e-06,
1425
+ "loss": 0.0053,
1426
+ "reward": 2.58494234085083,
1427
+ "reward_std": 3.3475492000579834,
1428
+ "rewards/reward_correctness": 0.25,
1429
+ "rewards/reward_em_chunk": 0.375,
1430
+ "rewards/reward_format": 0.25,
1431
+ "rewards/reward_search_diversity": 0.30994224548339844,
1432
+ "rewards/reward_search_strategy": 0.3999999761581421,
1433
+ "step": 89
1434
+ },
1435
+ {
1436
+ "completion_length": 673.875,
1437
+ "epoch": 0.3146853146853147,
1438
+ "grad_norm": 0.38143813610076904,
1439
+ "kl": 0.04431832954287529,
1440
+ "learning_rate": 4.5e-06,
1441
+ "loss": 0.0018,
1442
+ "reward": 3.379831552505493,
1443
+ "reward_std": 2.6894783973693848,
1444
+ "rewards/reward_correctness": 0.25,
1445
+ "rewards/reward_em_chunk": 1.0,
1446
+ "rewards/reward_format": 0.25,
1447
+ "rewards/reward_search_diversity": 0.5048315525054932,
1448
+ "rewards/reward_search_strategy": 0.375,
1449
+ "step": 90
1450
+ },
1451
+ {
1452
+ "completion_length": 335.5,
1453
+ "epoch": 0.3181818181818182,
1454
+ "grad_norm": 1.326707124710083,
1455
+ "kl": 0.1567000150680542,
1456
+ "learning_rate": 4.5500000000000005e-06,
1457
+ "loss": 0.0063,
1458
+ "reward": 1.540712594985962,
1459
+ "reward_std": 1.9064555168151855,
1460
+ "rewards/reward_correctness": 0.0,
1461
+ "rewards/reward_em_chunk": 0.25,
1462
+ "rewards/reward_format": 0.375,
1463
+ "rewards/reward_search_diversity": 0.24071267247200012,
1464
+ "rewards/reward_search_strategy": 0.30000001192092896,
1465
+ "step": 91
1466
+ },
1467
+ {
1468
+ "completion_length": 479.25,
1469
+ "epoch": 0.32167832167832167,
1470
+ "grad_norm": 0.8233426213264465,
1471
+ "kl": 0.046305958181619644,
1472
+ "learning_rate": 4.600000000000001e-06,
1473
+ "loss": 0.0019,
1474
+ "reward": 4.979320526123047,
1475
+ "reward_std": 2.5221211910247803,
1476
+ "rewards/reward_correctness": 0.5,
1477
+ "rewards/reward_em_chunk": 1.0,
1478
+ "rewards/reward_format": 0.5,
1479
+ "rewards/reward_search_diversity": 0.6293203234672546,
1480
+ "rewards/reward_search_strategy": 0.3500000238418579,
1481
+ "step": 92
1482
+ },
1483
+ {
1484
+ "completion_length": 529.625,
1485
+ "epoch": 0.32517482517482516,
1486
+ "grad_norm": 0.8791444301605225,
1487
+ "kl": 0.049900904297828674,
1488
+ "learning_rate": 4.65e-06,
1489
+ "loss": 0.002,
1490
+ "reward": 4.73832893371582,
1491
+ "reward_std": 2.957406520843506,
1492
+ "rewards/reward_correctness": 0.375,
1493
+ "rewards/reward_em_chunk": 0.875,
1494
+ "rewards/reward_format": 0.625,
1495
+ "rewards/reward_search_diversity": 0.5633291006088257,
1496
+ "rewards/reward_search_strategy": 0.550000011920929,
1497
+ "step": 93
1498
+ },
1499
+ {
1500
+ "completion_length": 566.25,
1501
+ "epoch": 0.32867132867132864,
1502
+ "grad_norm": 0.93157559633255,
1503
+ "kl": 0.10382921993732452,
1504
+ "learning_rate": 4.7e-06,
1505
+ "loss": 0.0042,
1506
+ "reward": 3.921233654022217,
1507
+ "reward_std": 3.259979486465454,
1508
+ "rewards/reward_correctness": 0.25,
1509
+ "rewards/reward_em_chunk": 0.75,
1510
+ "rewards/reward_format": 0.625,
1511
+ "rewards/reward_search_diversity": 0.39623361825942993,
1512
+ "rewards/reward_search_strategy": 0.5249999761581421,
1513
+ "step": 94
1514
+ },
1515
+ {
1516
+ "completion_length": 405.0,
1517
+ "epoch": 0.3321678321678322,
1518
+ "grad_norm": 0.6553046703338623,
1519
+ "kl": 0.05014060437679291,
1520
+ "learning_rate": 4.75e-06,
1521
+ "loss": 0.002,
1522
+ "reward": 4.048189163208008,
1523
+ "reward_std": 3.046299934387207,
1524
+ "rewards/reward_correctness": 0.375,
1525
+ "rewards/reward_em_chunk": 0.375,
1526
+ "rewards/reward_format": 0.625,
1527
+ "rewards/reward_search_diversity": 0.3731893002986908,
1528
+ "rewards/reward_search_strategy": 0.550000011920929,
1529
+ "step": 95
1530
+ },
1531
+ {
1532
+ "completion_length": 559.0,
1533
+ "epoch": 0.3356643356643357,
1534
+ "grad_norm": 0.9019679427146912,
1535
+ "kl": 0.1154535710811615,
1536
+ "learning_rate": 4.800000000000001e-06,
1537
+ "loss": 0.0046,
1538
+ "reward": 3.3237497806549072,
1539
+ "reward_std": 2.755406379699707,
1540
+ "rewards/reward_correctness": 0.375,
1541
+ "rewards/reward_em_chunk": 0.5,
1542
+ "rewards/reward_format": 0.375,
1543
+ "rewards/reward_search_diversity": 0.19874979555606842,
1544
+ "rewards/reward_search_strategy": 0.375,
1545
+ "step": 96
1546
+ },
1547
+ {
1548
+ "completion_length": 513.125,
1549
+ "epoch": 0.33916083916083917,
1550
+ "grad_norm": 1.1792876720428467,
1551
+ "kl": 0.20403671264648438,
1552
+ "learning_rate": 4.85e-06,
1553
+ "loss": 0.0082,
1554
+ "reward": 4.584352970123291,
1555
+ "reward_std": 3.532867908477783,
1556
+ "rewards/reward_correctness": 0.5,
1557
+ "rewards/reward_em_chunk": 0.625,
1558
+ "rewards/reward_format": 0.5,
1559
+ "rewards/reward_search_diversity": 0.4093528091907501,
1560
+ "rewards/reward_search_strategy": 0.550000011920929,
1561
+ "step": 97
1562
+ },
1563
+ {
1564
+ "completion_length": 390.75,
1565
+ "epoch": 0.34265734265734266,
1566
+ "grad_norm": 24.102558135986328,
1567
+ "kl": 1.4576557874679565,
1568
+ "learning_rate": 4.9000000000000005e-06,
1569
+ "loss": 0.0583,
1570
+ "reward": 3.2650551795959473,
1571
+ "reward_std": 1.5778415203094482,
1572
+ "rewards/reward_correctness": 0.125,
1573
+ "rewards/reward_em_chunk": 0.875,
1574
+ "rewards/reward_format": 0.5,
1575
+ "rewards/reward_search_diversity": 0.4150553047657013,
1576
+ "rewards/reward_search_strategy": 0.4749999940395355,
1577
+ "step": 98
1578
+ },
1579
+ {
1580
+ "completion_length": 992.0,
1581
+ "epoch": 0.34615384615384615,
1582
+ "grad_norm": 1.07889723777771,
1583
+ "kl": 0.15134873986244202,
1584
+ "learning_rate": 4.95e-06,
1585
+ "loss": 0.0061,
1586
+ "reward": 3.4669156074523926,
1587
+ "reward_std": 3.278291940689087,
1588
+ "rewards/reward_correctness": 0.375,
1589
+ "rewards/reward_em_chunk": 0.25,
1590
+ "rewards/reward_format": 0.5,
1591
+ "rewards/reward_search_diversity": 0.31691551208496094,
1592
+ "rewards/reward_search_strategy": 0.4000000059604645,
1593
+ "step": 99
1594
+ },
1595
+ {
1596
+ "completion_length": 839.625,
1597
+ "epoch": 0.34965034965034963,
1598
+ "grad_norm": 0.5948315262794495,
1599
+ "kl": 0.03611273318529129,
1600
+ "learning_rate": 5e-06,
1601
+ "loss": 0.0014,
1602
+ "reward": 2.273786783218384,
1603
+ "reward_std": 1.3839948177337646,
1604
+ "rewards/reward_correctness": 0.0,
1605
+ "rewards/reward_em_chunk": 0.0,
1606
+ "rewards/reward_format": 0.625,
1607
+ "rewards/reward_search_diversity": 0.5487868189811707,
1608
+ "rewards/reward_search_strategy": 0.4750000238418579,
1609
+ "step": 100
1610
+ }
1611
+ ],
1612
+ "logging_steps": 1,
1613
+ "max_steps": 1000,
1614
+ "num_input_tokens_seen": 0,
1615
+ "num_train_epochs": 4,
1616
+ "save_steps": 50,
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": 8,
1631
+ "trial_name": null,
1632
+ "trial_params": null
1633
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5bc2ce9fdda7e038f3836e0b24edb51569455f9c88149bdac5d77d744168c8
3
+ size 6072
checkpoint-150/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-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 0.15.1
checkpoint-150/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "down_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "q_proj",
31
+ "k_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-150/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e16e7b93552c381438a5d8e725d8da2430943dbd76f02ab4d47b0f08f4f5a59
3
+ size 778096664
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b11370b34c6ed0db4edf21108eaeea4f7b4ddadd9596c6b1f7e5198a575371
3
+ size 395570868
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d43ffde3d0d01ec0e1f6f034e46ae1a74df18d41a688881204e6dc41c2b8e07e
3
+ size 14244
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4eca0aacad6aa041c8f018144d83552f7abe353238b988693bc0c844bb7803
3
+ size 1064
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-150/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,2067 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|finetune_right_pad_id|>",
2064
+ "padding_side": "right",
2065
+ "tokenizer_class": "PreTrainedTokenizer",
2066
+ "unk_token": null
2067
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,2433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5244755244755245,
5
+ "eval_steps": 500,
6
+ "global_step": 150,
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": 145.875,
13
+ "epoch": 0.0034965034965034965,
14
+ "grad_norm": 8.602514266967773,
15
+ "kl": 0.0,
16
+ "learning_rate": 5.0000000000000004e-08,
17
+ "loss": 0.0,
18
+ "reward": 0.7051772475242615,
19
+ "reward_std": 0.8263505697250366,
20
+ "rewards/reward_correctness": 0.0,
21
+ "rewards/reward_em_chunk": 0.375,
22
+ "rewards/reward_format": 0.0,
23
+ "rewards/reward_search_diversity": 0.3301772475242615,
24
+ "rewards/reward_search_strategy": 0.0,
25
+ "step": 1
26
+ },
27
+ {
28
+ "completion_length": 88.125,
29
+ "epoch": 0.006993006993006993,
30
+ "grad_norm": 1.4985997676849365,
31
+ "kl": 0.0,
32
+ "learning_rate": 1.0000000000000001e-07,
33
+ "loss": -0.0,
34
+ "reward": 1.8388628959655762,
35
+ "reward_std": 2.5329272747039795,
36
+ "rewards/reward_correctness": 0.25,
37
+ "rewards/reward_em_chunk": 0.5,
38
+ "rewards/reward_format": 0.0,
39
+ "rewards/reward_search_diversity": 0.2388630509376526,
40
+ "rewards/reward_search_strategy": 0.10000000149011612,
41
+ "step": 2
42
+ },
43
+ {
44
+ "completion_length": 296.5,
45
+ "epoch": 0.01048951048951049,
46
+ "grad_norm": 0.7674520611763,
47
+ "kl": 0.0006381775019690394,
48
+ "learning_rate": 1.5000000000000002e-07,
49
+ "loss": 0.0,
50
+ "reward": 1.654070258140564,
51
+ "reward_std": 2.827007532119751,
52
+ "rewards/reward_correctness": 0.125,
53
+ "rewards/reward_em_chunk": 0.5,
54
+ "rewards/reward_format": 0.125,
55
+ "rewards/reward_search_diversity": 0.17907029390335083,
56
+ "rewards/reward_search_strategy": 0.22499999403953552,
57
+ "step": 3
58
+ },
59
+ {
60
+ "completion_length": 290.125,
61
+ "epoch": 0.013986013986013986,
62
+ "grad_norm": 1.0457236766815186,
63
+ "kl": 0.0007995082996785641,
64
+ "learning_rate": 2.0000000000000002e-07,
65
+ "loss": 0.0,
66
+ "reward": 3.421433448791504,
67
+ "reward_std": 2.9866631031036377,
68
+ "rewards/reward_correctness": 0.5,
69
+ "rewards/reward_em_chunk": 0.0,
70
+ "rewards/reward_format": 0.375,
71
+ "rewards/reward_search_diversity": 0.396433562040329,
72
+ "rewards/reward_search_strategy": 0.2750000059604645,
73
+ "step": 4
74
+ },
75
+ {
76
+ "completion_length": 259.125,
77
+ "epoch": 0.017482517482517484,
78
+ "grad_norm": 1.3121755123138428,
79
+ "kl": 0.000728036102373153,
80
+ "learning_rate": 2.5000000000000004e-07,
81
+ "loss": 0.0,
82
+ "reward": 0.9268761873245239,
83
+ "reward_std": 0.7560767531394958,
84
+ "rewards/reward_correctness": 0.0,
85
+ "rewards/reward_em_chunk": 0.625,
86
+ "rewards/reward_format": 0.0,
87
+ "rewards/reward_search_diversity": 0.2268761545419693,
88
+ "rewards/reward_search_strategy": 0.07500000298023224,
89
+ "step": 5
90
+ },
91
+ {
92
+ "completion_length": 383.5,
93
+ "epoch": 0.02097902097902098,
94
+ "grad_norm": 0.9658453464508057,
95
+ "kl": 0.0007470359560102224,
96
+ "learning_rate": 3.0000000000000004e-07,
97
+ "loss": 0.0,
98
+ "reward": 1.4594597816467285,
99
+ "reward_std": 2.2520837783813477,
100
+ "rewards/reward_correctness": 0.25,
101
+ "rewards/reward_em_chunk": 0.125,
102
+ "rewards/reward_format": 0.0,
103
+ "rewards/reward_search_diversity": 0.25945988297462463,
104
+ "rewards/reward_search_strategy": 0.07500000298023224,
105
+ "step": 6
106
+ },
107
+ {
108
+ "completion_length": 144.375,
109
+ "epoch": 0.024475524475524476,
110
+ "grad_norm": 1.1642646789550781,
111
+ "kl": 0.0009361266857013106,
112
+ "learning_rate": 3.5000000000000004e-07,
113
+ "loss": 0.0,
114
+ "reward": 1.378964900970459,
115
+ "reward_std": 2.0963218212127686,
116
+ "rewards/reward_correctness": 0.25,
117
+ "rewards/reward_em_chunk": 0.0,
118
+ "rewards/reward_format": 0.0,
119
+ "rewards/reward_search_diversity": 0.30396491289138794,
120
+ "rewards/reward_search_strategy": 0.07500000298023224,
121
+ "step": 7
122
+ },
123
+ {
124
+ "completion_length": 314.375,
125
+ "epoch": 0.027972027972027972,
126
+ "grad_norm": 5.21930456161499,
127
+ "kl": 0.0008346753311343491,
128
+ "learning_rate": 4.0000000000000003e-07,
129
+ "loss": 0.0,
130
+ "reward": 1.181166410446167,
131
+ "reward_std": 1.6016024351119995,
132
+ "rewards/reward_correctness": 0.125,
133
+ "rewards/reward_em_chunk": 0.0,
134
+ "rewards/reward_format": 0.125,
135
+ "rewards/reward_search_diversity": 0.3561664819717407,
136
+ "rewards/reward_search_strategy": 0.07500000298023224,
137
+ "step": 8
138
+ },
139
+ {
140
+ "completion_length": 98.375,
141
+ "epoch": 0.03146853146853147,
142
+ "grad_norm": 1.6168773174285889,
143
+ "kl": 0.0009058149298653007,
144
+ "learning_rate": 4.5000000000000003e-07,
145
+ "loss": 0.0,
146
+ "reward": 1.141206979751587,
147
+ "reward_std": 2.1089890003204346,
148
+ "rewards/reward_correctness": 0.125,
149
+ "rewards/reward_em_chunk": 0.375,
150
+ "rewards/reward_format": 0.0,
151
+ "rewards/reward_search_diversity": 0.16620691120624542,
152
+ "rewards/reward_search_strategy": 0.10000000149011612,
153
+ "step": 9
154
+ },
155
+ {
156
+ "completion_length": 269.625,
157
+ "epoch": 0.03496503496503497,
158
+ "grad_norm": 1.310072660446167,
159
+ "kl": 0.000750248203985393,
160
+ "learning_rate": 5.000000000000001e-07,
161
+ "loss": 0.0,
162
+ "reward": 1.901651382446289,
163
+ "reward_std": 3.08128023147583,
164
+ "rewards/reward_correctness": 0.25,
165
+ "rewards/reward_em_chunk": 0.25,
166
+ "rewards/reward_format": 0.125,
167
+ "rewards/reward_search_diversity": 0.27665144205093384,
168
+ "rewards/reward_search_strategy": 0.125,
169
+ "step": 10
170
+ },
171
+ {
172
+ "completion_length": 311.125,
173
+ "epoch": 0.038461538461538464,
174
+ "grad_norm": 1.1051065921783447,
175
+ "kl": 0.000834438658785075,
176
+ "learning_rate": 5.5e-07,
177
+ "loss": 0.0,
178
+ "reward": 2.1270594596862793,
179
+ "reward_std": 2.309929132461548,
180
+ "rewards/reward_correctness": 0.25,
181
+ "rewards/reward_em_chunk": 0.625,
182
+ "rewards/reward_format": 0.0,
183
+ "rewards/reward_search_diversity": 0.377059668302536,
184
+ "rewards/reward_search_strategy": 0.125,
185
+ "step": 11
186
+ },
187
+ {
188
+ "completion_length": 182.375,
189
+ "epoch": 0.04195804195804196,
190
+ "grad_norm": 1.3039528131484985,
191
+ "kl": 0.0007587745785713196,
192
+ "learning_rate": 6.000000000000001e-07,
193
+ "loss": 0.0,
194
+ "reward": 0.24762853980064392,
195
+ "reward_std": 0.28513866662979126,
196
+ "rewards/reward_correctness": 0.0,
197
+ "rewards/reward_em_chunk": 0.0,
198
+ "rewards/reward_format": 0.0,
199
+ "rewards/reward_search_diversity": 0.17262855172157288,
200
+ "rewards/reward_search_strategy": 0.07500000298023224,
201
+ "step": 12
202
+ },
203
+ {
204
+ "completion_length": 198.5,
205
+ "epoch": 0.045454545454545456,
206
+ "grad_norm": 1.176461935043335,
207
+ "kl": 0.0008510244661010802,
208
+ "learning_rate": 6.5e-07,
209
+ "loss": 0.0,
210
+ "reward": 2.0060770511627197,
211
+ "reward_std": 2.2957346439361572,
212
+ "rewards/reward_correctness": 0.25,
213
+ "rewards/reward_em_chunk": 0.625,
214
+ "rewards/reward_format": 0.0,
215
+ "rewards/reward_search_diversity": 0.3060770034790039,
216
+ "rewards/reward_search_strategy": 0.07500000298023224,
217
+ "step": 13
218
+ },
219
+ {
220
+ "completion_length": 158.25,
221
+ "epoch": 0.04895104895104895,
222
+ "grad_norm": 1.1484898328781128,
223
+ "kl": 0.0009028888889588416,
224
+ "learning_rate": 7.000000000000001e-07,
225
+ "loss": 0.0,
226
+ "reward": 0.2598831355571747,
227
+ "reward_std": 0.4156216084957123,
228
+ "rewards/reward_correctness": 0.0,
229
+ "rewards/reward_em_chunk": 0.125,
230
+ "rewards/reward_format": 0.0,
231
+ "rewards/reward_search_diversity": 0.1348831057548523,
232
+ "rewards/reward_search_strategy": 0.0,
233
+ "step": 14
234
+ },
235
+ {
236
+ "completion_length": 321.125,
237
+ "epoch": 0.05244755244755245,
238
+ "grad_norm": 1.08210027217865,
239
+ "kl": 0.0007499511120840907,
240
+ "learning_rate": 7.5e-07,
241
+ "loss": 0.0,
242
+ "reward": 2.711674213409424,
243
+ "reward_std": 3.2537524700164795,
244
+ "rewards/reward_correctness": 0.375,
245
+ "rewards/reward_em_chunk": 0.375,
246
+ "rewards/reward_format": 0.125,
247
+ "rewards/reward_search_diversity": 0.3866744041442871,
248
+ "rewards/reward_search_strategy": 0.20000000298023224,
249
+ "step": 15
250
+ },
251
+ {
252
+ "completion_length": 176.0,
253
+ "epoch": 0.055944055944055944,
254
+ "grad_norm": 1.007460117340088,
255
+ "kl": 0.0008281145128421485,
256
+ "learning_rate": 8.000000000000001e-07,
257
+ "loss": 0.0,
258
+ "reward": 1.6642776727676392,
259
+ "reward_std": 3.1836605072021484,
260
+ "rewards/reward_correctness": 0.25,
261
+ "rewards/reward_em_chunk": 0.125,
262
+ "rewards/reward_format": 0.125,
263
+ "rewards/reward_search_diversity": 0.1892777681350708,
264
+ "rewards/reward_search_strategy": 0.10000000149011612,
265
+ "step": 16
266
+ },
267
+ {
268
+ "completion_length": 299.0,
269
+ "epoch": 0.05944055944055944,
270
+ "grad_norm": 0.9308914542198181,
271
+ "kl": 0.0006533896084874868,
272
+ "learning_rate": 8.500000000000001e-07,
273
+ "loss": 0.0,
274
+ "reward": 2.9600870609283447,
275
+ "reward_std": 3.002318859100342,
276
+ "rewards/reward_correctness": 0.375,
277
+ "rewards/reward_em_chunk": 0.75,
278
+ "rewards/reward_format": 0.125,
279
+ "rewards/reward_search_diversity": 0.38508710265159607,
280
+ "rewards/reward_search_strategy": 0.07500000298023224,
281
+ "step": 17
282
+ },
283
+ {
284
+ "completion_length": 170.125,
285
+ "epoch": 0.06293706293706294,
286
+ "grad_norm": 1.6546720266342163,
287
+ "kl": 0.0009436010150238872,
288
+ "learning_rate": 9.000000000000001e-07,
289
+ "loss": 0.0,
290
+ "reward": 1.807711124420166,
291
+ "reward_std": 2.873779773712158,
292
+ "rewards/reward_correctness": 0.25,
293
+ "rewards/reward_em_chunk": 0.0,
294
+ "rewards/reward_format": 0.125,
295
+ "rewards/reward_search_diversity": 0.33271118998527527,
296
+ "rewards/reward_search_strategy": 0.22499999403953552,
297
+ "step": 18
298
+ },
299
+ {
300
+ "completion_length": 377.125,
301
+ "epoch": 0.06643356643356643,
302
+ "grad_norm": 0.7977221608161926,
303
+ "kl": 0.0008231342071667314,
304
+ "learning_rate": 9.500000000000001e-07,
305
+ "loss": 0.0,
306
+ "reward": 0.7038719058036804,
307
+ "reward_std": 1.2563936710357666,
308
+ "rewards/reward_correctness": 0.0,
309
+ "rewards/reward_em_chunk": 0.125,
310
+ "rewards/reward_format": 0.125,
311
+ "rewards/reward_search_diversity": 0.22887186706066132,
312
+ "rewards/reward_search_strategy": 0.10000000149011612,
313
+ "step": 19
314
+ },
315
+ {
316
+ "completion_length": 161.625,
317
+ "epoch": 0.06993006993006994,
318
+ "grad_norm": 1.5974496603012085,
319
+ "kl": 0.000790413178037852,
320
+ "learning_rate": 1.0000000000000002e-06,
321
+ "loss": 0.0,
322
+ "reward": 2.404862880706787,
323
+ "reward_std": 2.712550163269043,
324
+ "rewards/reward_correctness": 0.375,
325
+ "rewards/reward_em_chunk": 0.625,
326
+ "rewards/reward_format": 0.0,
327
+ "rewards/reward_search_diversity": 0.179862841963768,
328
+ "rewards/reward_search_strategy": 0.10000000149011612,
329
+ "step": 20
330
+ },
331
+ {
332
+ "completion_length": 298.875,
333
+ "epoch": 0.07342657342657342,
334
+ "grad_norm": 0.8817616105079651,
335
+ "kl": 0.0007674504304304719,
336
+ "learning_rate": 1.0500000000000001e-06,
337
+ "loss": 0.0,
338
+ "reward": 2.6999998092651367,
339
+ "reward_std": 3.122270345687866,
340
+ "rewards/reward_correctness": 0.375,
341
+ "rewards/reward_em_chunk": 0.125,
342
+ "rewards/reward_format": 0.375,
343
+ "rewards/reward_search_diversity": 0.05000000074505806,
344
+ "rewards/reward_search_strategy": 0.2750000059604645,
345
+ "step": 21
346
+ },
347
+ {
348
+ "completion_length": 150.125,
349
+ "epoch": 0.07692307692307693,
350
+ "grad_norm": 1.345902919769287,
351
+ "kl": 0.0010101046646013856,
352
+ "learning_rate": 1.1e-06,
353
+ "loss": 0.0,
354
+ "reward": 1.2625212669372559,
355
+ "reward_std": 1.9802589416503906,
356
+ "rewards/reward_correctness": 0.25,
357
+ "rewards/reward_em_chunk": 0.125,
358
+ "rewards/reward_format": 0.0,
359
+ "rewards/reward_search_diversity": 0.13752126693725586,
360
+ "rewards/reward_search_strategy": 0.0,
361
+ "step": 22
362
+ },
363
+ {
364
+ "completion_length": 156.625,
365
+ "epoch": 0.08041958041958042,
366
+ "grad_norm": 3.1841650009155273,
367
+ "kl": 0.0009282200480811298,
368
+ "learning_rate": 1.1500000000000002e-06,
369
+ "loss": 0.0,
370
+ "reward": 2.532832145690918,
371
+ "reward_std": 3.623222827911377,
372
+ "rewards/reward_correctness": 0.375,
373
+ "rewards/reward_em_chunk": 0.375,
374
+ "rewards/reward_format": 0.125,
375
+ "rewards/reward_search_diversity": 0.18283231556415558,
376
+ "rewards/reward_search_strategy": 0.22500000894069672,
377
+ "step": 23
378
+ },
379
+ {
380
+ "completion_length": 230.625,
381
+ "epoch": 0.08391608391608392,
382
+ "grad_norm": 0.560590922832489,
383
+ "kl": 0.0008200581069104373,
384
+ "learning_rate": 1.2000000000000002e-06,
385
+ "loss": 0.0,
386
+ "reward": 0.7196725606918335,
387
+ "reward_std": 1.5131947994232178,
388
+ "rewards/reward_correctness": 0.125,
389
+ "rewards/reward_em_chunk": 0.0,
390
+ "rewards/reward_format": 0.0,
391
+ "rewards/reward_search_diversity": 0.1946725845336914,
392
+ "rewards/reward_search_strategy": 0.02500000037252903,
393
+ "step": 24
394
+ },
395
+ {
396
+ "completion_length": 232.5,
397
+ "epoch": 0.08741258741258741,
398
+ "grad_norm": 5.627699375152588,
399
+ "kl": 0.0007359281880781054,
400
+ "learning_rate": 1.25e-06,
401
+ "loss": 0.0,
402
+ "reward": 2.3161444664001465,
403
+ "reward_std": 2.266465425491333,
404
+ "rewards/reward_correctness": 0.5,
405
+ "rewards/reward_em_chunk": 0.0,
406
+ "rewards/reward_format": 0.0,
407
+ "rewards/reward_search_diversity": 0.31614452600479126,
408
+ "rewards/reward_search_strategy": 0.0,
409
+ "step": 25
410
+ },
411
+ {
412
+ "completion_length": 256.625,
413
+ "epoch": 0.09090909090909091,
414
+ "grad_norm": 1.243622064590454,
415
+ "kl": 0.0009776452789083123,
416
+ "learning_rate": 1.3e-06,
417
+ "loss": 0.0,
418
+ "reward": 1.8542793989181519,
419
+ "reward_std": 2.3880927562713623,
420
+ "rewards/reward_correctness": 0.25,
421
+ "rewards/reward_em_chunk": 0.625,
422
+ "rewards/reward_format": 0.0,
423
+ "rewards/reward_search_diversity": 0.22927939891815186,
424
+ "rewards/reward_search_strategy": 0.0,
425
+ "step": 26
426
+ },
427
+ {
428
+ "completion_length": 221.625,
429
+ "epoch": 0.0944055944055944,
430
+ "grad_norm": 2.455430030822754,
431
+ "kl": 0.0014260835014283657,
432
+ "learning_rate": 1.3500000000000002e-06,
433
+ "loss": 0.0001,
434
+ "reward": 1.0012282133102417,
435
+ "reward_std": 1.7000349760055542,
436
+ "rewards/reward_correctness": 0.125,
437
+ "rewards/reward_em_chunk": 0.0,
438
+ "rewards/reward_format": 0.125,
439
+ "rewards/reward_search_diversity": 0.15122826397418976,
440
+ "rewards/reward_search_strategy": 0.10000000149011612,
441
+ "step": 27
442
+ },
443
+ {
444
+ "completion_length": 185.75,
445
+ "epoch": 0.0979020979020979,
446
+ "grad_norm": 1.199497938156128,
447
+ "kl": 0.0007826727814972401,
448
+ "learning_rate": 1.4000000000000001e-06,
449
+ "loss": 0.0,
450
+ "reward": 2.173332691192627,
451
+ "reward_std": 2.801347255706787,
452
+ "rewards/reward_correctness": 0.375,
453
+ "rewards/reward_em_chunk": 0.0,
454
+ "rewards/reward_format": 0.125,
455
+ "rewards/reward_search_diversity": 0.32333269715309143,
456
+ "rewards/reward_search_strategy": 0.10000000149011612,
457
+ "step": 28
458
+ },
459
+ {
460
+ "completion_length": 243.125,
461
+ "epoch": 0.10139860139860139,
462
+ "grad_norm": 0.8430306315422058,
463
+ "kl": 0.0008962135761976242,
464
+ "learning_rate": 1.45e-06,
465
+ "loss": 0.0,
466
+ "reward": 1.0625323057174683,
467
+ "reward_std": 1.898645043373108,
468
+ "rewards/reward_correctness": 0.125,
469
+ "rewards/reward_em_chunk": 0.375,
470
+ "rewards/reward_format": 0.0,
471
+ "rewards/reward_search_diversity": 0.18753226101398468,
472
+ "rewards/reward_search_strategy": 0.0,
473
+ "step": 29
474
+ },
475
+ {
476
+ "completion_length": 334.875,
477
+ "epoch": 0.1048951048951049,
478
+ "grad_norm": 0.8412113785743713,
479
+ "kl": 0.001170428702607751,
480
+ "learning_rate": 1.5e-06,
481
+ "loss": 0.0,
482
+ "reward": 1.303612232208252,
483
+ "reward_std": 2.1826775074005127,
484
+ "rewards/reward_correctness": 0.25,
485
+ "rewards/reward_em_chunk": 0.0,
486
+ "rewards/reward_format": 0.0,
487
+ "rewards/reward_search_diversity": 0.27861225605010986,
488
+ "rewards/reward_search_strategy": 0.02500000037252903,
489
+ "step": 30
490
+ },
491
+ {
492
+ "completion_length": 165.75,
493
+ "epoch": 0.10839160839160839,
494
+ "grad_norm": 1.9105679988861084,
495
+ "kl": 0.0031302073039114475,
496
+ "learning_rate": 1.5500000000000002e-06,
497
+ "loss": 0.0001,
498
+ "reward": 1.0198408365249634,
499
+ "reward_std": 2.1316380500793457,
500
+ "rewards/reward_correctness": 0.125,
501
+ "rewards/reward_em_chunk": 0.25,
502
+ "rewards/reward_format": 0.0,
503
+ "rewards/reward_search_diversity": 0.16984085738658905,
504
+ "rewards/reward_search_strategy": 0.10000000149011612,
505
+ "step": 31
506
+ },
507
+ {
508
+ "completion_length": 174.625,
509
+ "epoch": 0.11188811188811189,
510
+ "grad_norm": 2.309382915496826,
511
+ "kl": 0.0032356895972043276,
512
+ "learning_rate": 1.6000000000000001e-06,
513
+ "loss": 0.0001,
514
+ "reward": 0.9216341376304626,
515
+ "reward_std": 1.8671420812606812,
516
+ "rewards/reward_correctness": 0.125,
517
+ "rewards/reward_em_chunk": 0.25,
518
+ "rewards/reward_format": 0.0,
519
+ "rewards/reward_search_diversity": 0.14663413166999817,
520
+ "rewards/reward_search_strategy": 0.02500000037252903,
521
+ "step": 32
522
+ },
523
+ {
524
+ "completion_length": 85.75,
525
+ "epoch": 0.11538461538461539,
526
+ "grad_norm": 1.4122040271759033,
527
+ "kl": 0.0017049856251105666,
528
+ "learning_rate": 1.6500000000000003e-06,
529
+ "loss": 0.0001,
530
+ "reward": 1.524999976158142,
531
+ "reward_std": 2.2926902770996094,
532
+ "rewards/reward_correctness": 0.25,
533
+ "rewards/reward_em_chunk": 0.125,
534
+ "rewards/reward_format": 0.125,
535
+ "rewards/reward_search_diversity": 0.10000000149011612,
536
+ "rewards/reward_search_strategy": 0.05000000074505806,
537
+ "step": 33
538
+ },
539
+ {
540
+ "completion_length": 173.5,
541
+ "epoch": 0.11888111888111888,
542
+ "grad_norm": 0.9712541699409485,
543
+ "kl": 0.0014842856908217072,
544
+ "learning_rate": 1.7000000000000002e-06,
545
+ "loss": 0.0001,
546
+ "reward": 3.4844837188720703,
547
+ "reward_std": 3.1145381927490234,
548
+ "rewards/reward_correctness": 0.5,
549
+ "rewards/reward_em_chunk": 0.75,
550
+ "rewards/reward_format": 0.125,
551
+ "rewards/reward_search_diversity": 0.3094840347766876,
552
+ "rewards/reward_search_strategy": 0.17499999701976776,
553
+ "step": 34
554
+ },
555
+ {
556
+ "completion_length": 268.25,
557
+ "epoch": 0.12237762237762238,
558
+ "grad_norm": 1.1684075593948364,
559
+ "kl": 0.0012478481512516737,
560
+ "learning_rate": 1.75e-06,
561
+ "loss": 0.0,
562
+ "reward": 2.8716678619384766,
563
+ "reward_std": 2.387646198272705,
564
+ "rewards/reward_correctness": 0.5,
565
+ "rewards/reward_em_chunk": 0.375,
566
+ "rewards/reward_format": 0.0,
567
+ "rewards/reward_search_diversity": 0.3716679811477661,
568
+ "rewards/reward_search_strategy": 0.125,
569
+ "step": 35
570
+ },
571
+ {
572
+ "completion_length": 235.125,
573
+ "epoch": 0.1258741258741259,
574
+ "grad_norm": 1.2749513387680054,
575
+ "kl": 0.004472827073186636,
576
+ "learning_rate": 1.8000000000000001e-06,
577
+ "loss": 0.0002,
578
+ "reward": 1.8775699138641357,
579
+ "reward_std": 2.413510322570801,
580
+ "rewards/reward_correctness": 0.375,
581
+ "rewards/reward_em_chunk": 0.0,
582
+ "rewards/reward_format": 0.0,
583
+ "rewards/reward_search_diversity": 0.30256983637809753,
584
+ "rewards/reward_search_strategy": 0.07500000298023224,
585
+ "step": 36
586
+ },
587
+ {
588
+ "completion_length": 175.5,
589
+ "epoch": 0.12937062937062938,
590
+ "grad_norm": 0.8929537534713745,
591
+ "kl": 0.0037049425300210714,
592
+ "learning_rate": 1.85e-06,
593
+ "loss": 0.0001,
594
+ "reward": 0.6821428537368774,
595
+ "reward_std": 1.4377206563949585,
596
+ "rewards/reward_correctness": 0.125,
597
+ "rewards/reward_em_chunk": 0.0,
598
+ "rewards/reward_format": 0.0,
599
+ "rewards/reward_search_diversity": 0.18214285373687744,
600
+ "rewards/reward_search_strategy": 0.0,
601
+ "step": 37
602
+ },
603
+ {
604
+ "completion_length": 290.125,
605
+ "epoch": 0.13286713286713286,
606
+ "grad_norm": 2.52665114402771,
607
+ "kl": 0.005157872103154659,
608
+ "learning_rate": 1.9000000000000002e-06,
609
+ "loss": 0.0002,
610
+ "reward": 2.574741840362549,
611
+ "reward_std": 2.5146002769470215,
612
+ "rewards/reward_correctness": 0.375,
613
+ "rewards/reward_em_chunk": 0.75,
614
+ "rewards/reward_format": 0.0,
615
+ "rewards/reward_search_diversity": 0.14974190294742584,
616
+ "rewards/reward_search_strategy": 0.17500001192092896,
617
+ "step": 38
618
+ },
619
+ {
620
+ "completion_length": 344.125,
621
+ "epoch": 0.13636363636363635,
622
+ "grad_norm": 0.8259175419807434,
623
+ "kl": 0.002582128159701824,
624
+ "learning_rate": 1.9500000000000004e-06,
625
+ "loss": 0.0001,
626
+ "reward": 2.376612901687622,
627
+ "reward_std": 2.9910624027252197,
628
+ "rewards/reward_correctness": 0.375,
629
+ "rewards/reward_em_chunk": 0.125,
630
+ "rewards/reward_format": 0.125,
631
+ "rewards/reward_search_diversity": 0.4266127943992615,
632
+ "rewards/reward_search_strategy": 0.07500000298023224,
633
+ "step": 39
634
+ },
635
+ {
636
+ "completion_length": 243.125,
637
+ "epoch": 0.13986013986013987,
638
+ "grad_norm": 1.0021271705627441,
639
+ "kl": 0.004831339232623577,
640
+ "learning_rate": 2.0000000000000003e-06,
641
+ "loss": 0.0002,
642
+ "reward": 2.04349946975708,
643
+ "reward_std": 2.3903656005859375,
644
+ "rewards/reward_correctness": 0.25,
645
+ "rewards/reward_em_chunk": 0.625,
646
+ "rewards/reward_format": 0.0,
647
+ "rewards/reward_search_diversity": 0.34349945187568665,
648
+ "rewards/reward_search_strategy": 0.07500000298023224,
649
+ "step": 40
650
+ },
651
+ {
652
+ "completion_length": 207.375,
653
+ "epoch": 0.14335664335664336,
654
+ "grad_norm": 1.2446260452270508,
655
+ "kl": 0.005710378754884005,
656
+ "learning_rate": 2.05e-06,
657
+ "loss": 0.0002,
658
+ "reward": 2.8324475288391113,
659
+ "reward_std": 3.167931079864502,
660
+ "rewards/reward_correctness": 0.375,
661
+ "rewards/reward_em_chunk": 0.625,
662
+ "rewards/reward_format": 0.125,
663
+ "rewards/reward_search_diversity": 0.25744765996932983,
664
+ "rewards/reward_search_strategy": 0.20000000298023224,
665
+ "step": 41
666
+ },
667
+ {
668
+ "completion_length": 441.125,
669
+ "epoch": 0.14685314685314685,
670
+ "grad_norm": 0.8263920545578003,
671
+ "kl": 0.0030913222581148148,
672
+ "learning_rate": 2.1000000000000002e-06,
673
+ "loss": 0.0001,
674
+ "reward": 2.5794529914855957,
675
+ "reward_std": 2.6344144344329834,
676
+ "rewards/reward_correctness": 0.375,
677
+ "rewards/reward_em_chunk": 0.125,
678
+ "rewards/reward_format": 0.25,
679
+ "rewards/reward_search_diversity": 0.30445292592048645,
680
+ "rewards/reward_search_strategy": 0.15000000596046448,
681
+ "step": 42
682
+ },
683
+ {
684
+ "completion_length": 226.375,
685
+ "epoch": 0.15034965034965034,
686
+ "grad_norm": 1.141964316368103,
687
+ "kl": 0.008909309282898903,
688
+ "learning_rate": 2.15e-06,
689
+ "loss": 0.0004,
690
+ "reward": 1.8603672981262207,
691
+ "reward_std": 2.203197479248047,
692
+ "rewards/reward_correctness": 0.25,
693
+ "rewards/reward_em_chunk": 0.625,
694
+ "rewards/reward_format": 0.0,
695
+ "rewards/reward_search_diversity": 0.21036729216575623,
696
+ "rewards/reward_search_strategy": 0.02500000037252903,
697
+ "step": 43
698
+ },
699
+ {
700
+ "completion_length": 397.75,
701
+ "epoch": 0.15384615384615385,
702
+ "grad_norm": 0.9564006328582764,
703
+ "kl": 0.01092858798801899,
704
+ "learning_rate": 2.2e-06,
705
+ "loss": 0.0004,
706
+ "reward": 2.557056188583374,
707
+ "reward_std": 2.429002046585083,
708
+ "rewards/reward_correctness": 0.375,
709
+ "rewards/reward_em_chunk": 0.75,
710
+ "rewards/reward_format": 0.0,
711
+ "rewards/reward_search_diversity": 0.28205621242523193,
712
+ "rewards/reward_search_strategy": 0.02500000037252903,
713
+ "step": 44
714
+ },
715
+ {
716
+ "completion_length": 307.25,
717
+ "epoch": 0.15734265734265734,
718
+ "grad_norm": 1.0510841608047485,
719
+ "kl": 0.007918575778603554,
720
+ "learning_rate": 2.25e-06,
721
+ "loss": 0.0003,
722
+ "reward": 1.2331278324127197,
723
+ "reward_std": 1.7548075914382935,
724
+ "rewards/reward_correctness": 0.25,
725
+ "rewards/reward_em_chunk": 0.0,
726
+ "rewards/reward_format": 0.0,
727
+ "rewards/reward_search_diversity": 0.15812794864177704,
728
+ "rewards/reward_search_strategy": 0.07500000298023224,
729
+ "step": 45
730
+ },
731
+ {
732
+ "completion_length": 277.0,
733
+ "epoch": 0.16083916083916083,
734
+ "grad_norm": 0.9169591665267944,
735
+ "kl": 0.015062836930155754,
736
+ "learning_rate": 2.3000000000000004e-06,
737
+ "loss": 0.0006,
738
+ "reward": 1.2089338302612305,
739
+ "reward_std": 2.5115318298339844,
740
+ "rewards/reward_correctness": 0.125,
741
+ "rewards/reward_em_chunk": 0.125,
742
+ "rewards/reward_format": 0.125,
743
+ "rewards/reward_search_diversity": 0.1339338719844818,
744
+ "rewards/reward_search_strategy": 0.20000000298023224,
745
+ "step": 46
746
+ },
747
+ {
748
+ "completion_length": 206.25,
749
+ "epoch": 0.16433566433566432,
750
+ "grad_norm": 1.3427180051803589,
751
+ "kl": 0.019624339416623116,
752
+ "learning_rate": 2.35e-06,
753
+ "loss": 0.0008,
754
+ "reward": 4.1133527755737305,
755
+ "reward_std": 3.2583820819854736,
756
+ "rewards/reward_correctness": 0.625,
757
+ "rewards/reward_em_chunk": 0.625,
758
+ "rewards/reward_format": 0.25,
759
+ "rewards/reward_search_diversity": 0.36335283517837524,
760
+ "rewards/reward_search_strategy": 0.125,
761
+ "step": 47
762
+ },
763
+ {
764
+ "completion_length": 252.125,
765
+ "epoch": 0.16783216783216784,
766
+ "grad_norm": 0.7444542050361633,
767
+ "kl": 0.021463895216584206,
768
+ "learning_rate": 2.4000000000000003e-06,
769
+ "loss": 0.0009,
770
+ "reward": 1.631263017654419,
771
+ "reward_std": 2.5925517082214355,
772
+ "rewards/reward_correctness": 0.25,
773
+ "rewards/reward_em_chunk": 0.375,
774
+ "rewards/reward_format": 0.0,
775
+ "rewards/reward_search_diversity": 0.23126289248466492,
776
+ "rewards/reward_search_strategy": 0.02500000037252903,
777
+ "step": 48
778
+ },
779
+ {
780
+ "completion_length": 117.625,
781
+ "epoch": 0.17132867132867133,
782
+ "grad_norm": 1.888673186302185,
783
+ "kl": 0.03609447553753853,
784
+ "learning_rate": 2.4500000000000003e-06,
785
+ "loss": 0.0014,
786
+ "reward": 1.9036250114440918,
787
+ "reward_std": 2.2273151874542236,
788
+ "rewards/reward_correctness": 0.25,
789
+ "rewards/reward_em_chunk": 0.625,
790
+ "rewards/reward_format": 0.0,
791
+ "rewards/reward_search_diversity": 0.20362500846385956,
792
+ "rewards/reward_search_strategy": 0.07500000298023224,
793
+ "step": 49
794
+ },
795
+ {
796
+ "completion_length": 302.75,
797
+ "epoch": 0.17482517482517482,
798
+ "grad_norm": 1.2723031044006348,
799
+ "kl": 0.2012804001569748,
800
+ "learning_rate": 2.5e-06,
801
+ "loss": 0.0081,
802
+ "reward": 0.15956448018550873,
803
+ "reward_std": 0.4513165056705475,
804
+ "rewards/reward_correctness": 0.0,
805
+ "rewards/reward_em_chunk": 0.125,
806
+ "rewards/reward_format": 0.0,
807
+ "rewards/reward_search_diversity": 0.03456447646021843,
808
+ "rewards/reward_search_strategy": 0.0,
809
+ "step": 50
810
+ },
811
+ {
812
+ "completion_length": 222.0,
813
+ "epoch": 0.17832167832167833,
814
+ "grad_norm": 0.8149501085281372,
815
+ "kl": 0.04784020781517029,
816
+ "learning_rate": 2.55e-06,
817
+ "loss": 0.0019,
818
+ "reward": 0.49046826362609863,
819
+ "reward_std": 0.9328532814979553,
820
+ "rewards/reward_correctness": 0.0,
821
+ "rewards/reward_em_chunk": 0.0,
822
+ "rewards/reward_format": 0.125,
823
+ "rewards/reward_search_diversity": 0.1654682457447052,
824
+ "rewards/reward_search_strategy": 0.07500000298023224,
825
+ "step": 51
826
+ },
827
+ {
828
+ "completion_length": 329.75,
829
+ "epoch": 0.18181818181818182,
830
+ "grad_norm": 1.0090314149856567,
831
+ "kl": 0.03431350365281105,
832
+ "learning_rate": 2.6e-06,
833
+ "loss": 0.0014,
834
+ "reward": 1.8717395067214966,
835
+ "reward_std": 2.0185225009918213,
836
+ "rewards/reward_correctness": 0.125,
837
+ "rewards/reward_em_chunk": 0.375,
838
+ "rewards/reward_format": 0.25,
839
+ "rewards/reward_search_diversity": 0.246739462018013,
840
+ "rewards/reward_search_strategy": 0.25,
841
+ "step": 52
842
+ },
843
+ {
844
+ "completion_length": 292.5,
845
+ "epoch": 0.1853146853146853,
846
+ "grad_norm": 0.9738456606864929,
847
+ "kl": 0.03869509696960449,
848
+ "learning_rate": 2.6500000000000005e-06,
849
+ "loss": 0.0015,
850
+ "reward": 3.411203384399414,
851
+ "reward_std": 2.776095390319824,
852
+ "rewards/reward_correctness": 0.625,
853
+ "rewards/reward_em_chunk": 0.625,
854
+ "rewards/reward_format": 0.0,
855
+ "rewards/reward_search_diversity": 0.28620344400405884,
856
+ "rewards/reward_search_strategy": 0.0,
857
+ "step": 53
858
+ },
859
+ {
860
+ "completion_length": 262.25,
861
+ "epoch": 0.1888111888111888,
862
+ "grad_norm": 1.0264172554016113,
863
+ "kl": 0.04221673682332039,
864
+ "learning_rate": 2.7000000000000004e-06,
865
+ "loss": 0.0017,
866
+ "reward": 3.2230210304260254,
867
+ "reward_std": 3.179140329360962,
868
+ "rewards/reward_correctness": 0.5,
869
+ "rewards/reward_em_chunk": 0.125,
870
+ "rewards/reward_format": 0.25,
871
+ "rewards/reward_search_diversity": 0.2730211913585663,
872
+ "rewards/reward_search_strategy": 0.32500001788139343,
873
+ "step": 54
874
+ },
875
+ {
876
+ "completion_length": 278.0,
877
+ "epoch": 0.19230769230769232,
878
+ "grad_norm": 1.219490885734558,
879
+ "kl": 0.07308313995599747,
880
+ "learning_rate": 2.7500000000000004e-06,
881
+ "loss": 0.0029,
882
+ "reward": 2.9714736938476562,
883
+ "reward_std": 3.078878164291382,
884
+ "rewards/reward_correctness": 0.25,
885
+ "rewards/reward_em_chunk": 0.625,
886
+ "rewards/reward_format": 0.375,
887
+ "rewards/reward_search_diversity": 0.32147371768951416,
888
+ "rewards/reward_search_strategy": 0.2750000059604645,
889
+ "step": 55
890
+ },
891
+ {
892
+ "completion_length": 198.125,
893
+ "epoch": 0.1958041958041958,
894
+ "grad_norm": 2.261676788330078,
895
+ "kl": 0.10734312981367111,
896
+ "learning_rate": 2.8000000000000003e-06,
897
+ "loss": 0.0043,
898
+ "reward": 1.751394271850586,
899
+ "reward_std": 2.916086196899414,
900
+ "rewards/reward_correctness": 0.125,
901
+ "rewards/reward_em_chunk": 0.5,
902
+ "rewards/reward_format": 0.125,
903
+ "rewards/reward_search_diversity": 0.35139432549476624,
904
+ "rewards/reward_search_strategy": 0.15000000596046448,
905
+ "step": 56
906
+ },
907
+ {
908
+ "completion_length": 368.25,
909
+ "epoch": 0.1993006993006993,
910
+ "grad_norm": 1.0139119625091553,
911
+ "kl": 0.07945723086595535,
912
+ "learning_rate": 2.85e-06,
913
+ "loss": 0.0032,
914
+ "reward": 2.6666977405548096,
915
+ "reward_std": 3.0744428634643555,
916
+ "rewards/reward_correctness": 0.375,
917
+ "rewards/reward_em_chunk": 0.625,
918
+ "rewards/reward_format": 0.125,
919
+ "rewards/reward_search_diversity": 0.1416977047920227,
920
+ "rewards/reward_search_strategy": 0.15000000596046448,
921
+ "step": 57
922
+ },
923
+ {
924
+ "completion_length": 445.875,
925
+ "epoch": 0.20279720279720279,
926
+ "grad_norm": 1.2591164112091064,
927
+ "kl": 0.0817643404006958,
928
+ "learning_rate": 2.9e-06,
929
+ "loss": 0.0033,
930
+ "reward": 3.105250358581543,
931
+ "reward_std": 2.503899574279785,
932
+ "rewards/reward_correctness": 0.375,
933
+ "rewards/reward_em_chunk": 0.75,
934
+ "rewards/reward_format": 0.125,
935
+ "rewards/reward_search_diversity": 0.4302505850791931,
936
+ "rewards/reward_search_strategy": 0.17499999701976776,
937
+ "step": 58
938
+ },
939
+ {
940
+ "completion_length": 465.875,
941
+ "epoch": 0.2062937062937063,
942
+ "grad_norm": 0.6122844219207764,
943
+ "kl": 0.0703798234462738,
944
+ "learning_rate": 2.95e-06,
945
+ "loss": 0.0028,
946
+ "reward": 1.6243177652359009,
947
+ "reward_std": 1.8378466367721558,
948
+ "rewards/reward_correctness": 0.25,
949
+ "rewards/reward_em_chunk": 0.125,
950
+ "rewards/reward_format": 0.0,
951
+ "rewards/reward_search_diversity": 0.37431782484054565,
952
+ "rewards/reward_search_strategy": 0.125,
953
+ "step": 59
954
+ },
955
+ {
956
+ "completion_length": 256.375,
957
+ "epoch": 0.2097902097902098,
958
+ "grad_norm": 0.9197457432746887,
959
+ "kl": 0.08273329585790634,
960
+ "learning_rate": 3e-06,
961
+ "loss": 0.0033,
962
+ "reward": 2.420247793197632,
963
+ "reward_std": 2.3122122287750244,
964
+ "rewards/reward_correctness": 0.375,
965
+ "rewards/reward_em_chunk": 0.0,
966
+ "rewards/reward_format": 0.125,
967
+ "rewards/reward_search_diversity": 0.4202479422092438,
968
+ "rewards/reward_search_strategy": 0.25,
969
+ "step": 60
970
+ },
971
+ {
972
+ "completion_length": 517.125,
973
+ "epoch": 0.21328671328671328,
974
+ "grad_norm": 0.8799907565116882,
975
+ "kl": 0.20334148406982422,
976
+ "learning_rate": 3.05e-06,
977
+ "loss": 0.0081,
978
+ "reward": 1.377384066581726,
979
+ "reward_std": 1.68935227394104,
980
+ "rewards/reward_correctness": 0.125,
981
+ "rewards/reward_em_chunk": 0.25,
982
+ "rewards/reward_format": 0.125,
983
+ "rewards/reward_search_diversity": 0.3023841083049774,
984
+ "rewards/reward_search_strategy": 0.07500000298023224,
985
+ "step": 61
986
+ },
987
+ {
988
+ "completion_length": 502.5,
989
+ "epoch": 0.21678321678321677,
990
+ "grad_norm": 0.7109338641166687,
991
+ "kl": 0.03114498406648636,
992
+ "learning_rate": 3.1000000000000004e-06,
993
+ "loss": 0.0012,
994
+ "reward": 5.466271877288818,
995
+ "reward_std": 2.7285211086273193,
996
+ "rewards/reward_correctness": 0.75,
997
+ "rewards/reward_em_chunk": 0.625,
998
+ "rewards/reward_format": 0.375,
999
+ "rewards/reward_search_diversity": 0.6912716627120972,
1000
+ "rewards/reward_search_strategy": 0.4000000059604645,
1001
+ "step": 62
1002
+ },
1003
+ {
1004
+ "completion_length": 503.25,
1005
+ "epoch": 0.2202797202797203,
1006
+ "grad_norm": 0.9971331357955933,
1007
+ "kl": 0.20209850370883942,
1008
+ "learning_rate": 3.1500000000000003e-06,
1009
+ "loss": 0.0081,
1010
+ "reward": 1.2392462491989136,
1011
+ "reward_std": 1.4006211757659912,
1012
+ "rewards/reward_correctness": 0.125,
1013
+ "rewards/reward_em_chunk": 0.375,
1014
+ "rewards/reward_format": 0.0,
1015
+ "rewards/reward_search_diversity": 0.189246267080307,
1016
+ "rewards/reward_search_strategy": 0.17500001192092896,
1017
+ "step": 63
1018
+ },
1019
+ {
1020
+ "completion_length": 288.5,
1021
+ "epoch": 0.22377622377622378,
1022
+ "grad_norm": 0.8857221603393555,
1023
+ "kl": 0.10349184274673462,
1024
+ "learning_rate": 3.2000000000000003e-06,
1025
+ "loss": 0.0041,
1026
+ "reward": 1.3573650121688843,
1027
+ "reward_std": 1.9148555994033813,
1028
+ "rewards/reward_correctness": 0.125,
1029
+ "rewards/reward_em_chunk": 0.375,
1030
+ "rewards/reward_format": 0.0,
1031
+ "rewards/reward_search_diversity": 0.40736502408981323,
1032
+ "rewards/reward_search_strategy": 0.07500000298023224,
1033
+ "step": 64
1034
+ },
1035
+ {
1036
+ "completion_length": 445.875,
1037
+ "epoch": 0.22727272727272727,
1038
+ "grad_norm": 2.050611734390259,
1039
+ "kl": 0.9011820554733276,
1040
+ "learning_rate": 3.2500000000000002e-06,
1041
+ "loss": 0.036,
1042
+ "reward": 2.7885334491729736,
1043
+ "reward_std": 2.6393096446990967,
1044
+ "rewards/reward_correctness": 0.375,
1045
+ "rewards/reward_em_chunk": 0.375,
1046
+ "rewards/reward_format": 0.125,
1047
+ "rewards/reward_search_diversity": 0.46353352069854736,
1048
+ "rewards/reward_search_strategy": 0.20000000298023224,
1049
+ "step": 65
1050
+ },
1051
+ {
1052
+ "completion_length": 321.75,
1053
+ "epoch": 0.23076923076923078,
1054
+ "grad_norm": 0.8712911605834961,
1055
+ "kl": 0.11524824798107147,
1056
+ "learning_rate": 3.3000000000000006e-06,
1057
+ "loss": 0.0046,
1058
+ "reward": 2.963777542114258,
1059
+ "reward_std": 2.7310569286346436,
1060
+ "rewards/reward_correctness": 0.5,
1061
+ "rewards/reward_em_chunk": 0.375,
1062
+ "rewards/reward_format": 0.125,
1063
+ "rewards/reward_search_diversity": 0.21377724409103394,
1064
+ "rewards/reward_search_strategy": 0.125,
1065
+ "step": 66
1066
+ },
1067
+ {
1068
+ "completion_length": 579.5,
1069
+ "epoch": 0.23426573426573427,
1070
+ "grad_norm": 0.6312026977539062,
1071
+ "kl": 0.08477935940027237,
1072
+ "learning_rate": 3.3500000000000005e-06,
1073
+ "loss": 0.0034,
1074
+ "reward": 4.128048896789551,
1075
+ "reward_std": 2.959887742996216,
1076
+ "rewards/reward_correctness": 0.625,
1077
+ "rewards/reward_em_chunk": 0.875,
1078
+ "rewards/reward_format": 0.125,
1079
+ "rewards/reward_search_diversity": 0.30304890871047974,
1080
+ "rewards/reward_search_strategy": 0.20000000298023224,
1081
+ "step": 67
1082
+ },
1083
+ {
1084
+ "completion_length": 256.625,
1085
+ "epoch": 0.23776223776223776,
1086
+ "grad_norm": 0.835229218006134,
1087
+ "kl": 0.1031595766544342,
1088
+ "learning_rate": 3.4000000000000005e-06,
1089
+ "loss": 0.0041,
1090
+ "reward": 5.231247425079346,
1091
+ "reward_std": 2.7173686027526855,
1092
+ "rewards/reward_correctness": 0.75,
1093
+ "rewards/reward_em_chunk": 1.0,
1094
+ "rewards/reward_format": 0.25,
1095
+ "rewards/reward_search_diversity": 0.48124733567237854,
1096
+ "rewards/reward_search_strategy": 0.25,
1097
+ "step": 68
1098
+ },
1099
+ {
1100
+ "completion_length": 458.125,
1101
+ "epoch": 0.24125874125874125,
1102
+ "grad_norm": 1.0669630765914917,
1103
+ "kl": 0.050319548696279526,
1104
+ "learning_rate": 3.45e-06,
1105
+ "loss": 0.002,
1106
+ "reward": 2.627213716506958,
1107
+ "reward_std": 2.752366781234741,
1108
+ "rewards/reward_correctness": 0.25,
1109
+ "rewards/reward_em_chunk": 0.875,
1110
+ "rewards/reward_format": 0.125,
1111
+ "rewards/reward_search_diversity": 0.1022137925028801,
1112
+ "rewards/reward_search_strategy": 0.4000000059604645,
1113
+ "step": 69
1114
+ },
1115
+ {
1116
+ "completion_length": 758.125,
1117
+ "epoch": 0.24475524475524477,
1118
+ "grad_norm": 0.4896698594093323,
1119
+ "kl": 0.03787853941321373,
1120
+ "learning_rate": 3.5e-06,
1121
+ "loss": 0.0015,
1122
+ "reward": 3.715177059173584,
1123
+ "reward_std": 2.108518362045288,
1124
+ "rewards/reward_correctness": 0.25,
1125
+ "rewards/reward_em_chunk": 0.875,
1126
+ "rewards/reward_format": 0.5,
1127
+ "rewards/reward_search_diversity": 0.44017714262008667,
1128
+ "rewards/reward_search_strategy": 0.3999999761581421,
1129
+ "step": 70
1130
+ },
1131
+ {
1132
+ "completion_length": 359.625,
1133
+ "epoch": 0.24825174825174826,
1134
+ "grad_norm": 1.1720679998397827,
1135
+ "kl": 0.09393578767776489,
1136
+ "learning_rate": 3.5500000000000003e-06,
1137
+ "loss": 0.0038,
1138
+ "reward": 5.1651530265808105,
1139
+ "reward_std": 2.7064919471740723,
1140
+ "rewards/reward_correctness": 0.625,
1141
+ "rewards/reward_em_chunk": 1.0,
1142
+ "rewards/reward_format": 0.375,
1143
+ "rewards/reward_search_diversity": 0.39015328884124756,
1144
+ "rewards/reward_search_strategy": 0.5249999761581421,
1145
+ "step": 71
1146
+ },
1147
+ {
1148
+ "completion_length": 603.75,
1149
+ "epoch": 0.2517482517482518,
1150
+ "grad_norm": 0.92381352186203,
1151
+ "kl": 0.03434322774410248,
1152
+ "learning_rate": 3.6000000000000003e-06,
1153
+ "loss": 0.0014,
1154
+ "reward": 1.6090435981750488,
1155
+ "reward_std": 1.3871439695358276,
1156
+ "rewards/reward_correctness": 0.125,
1157
+ "rewards/reward_em_chunk": 0.125,
1158
+ "rewards/reward_format": 0.125,
1159
+ "rewards/reward_search_diversity": 0.5090435743331909,
1160
+ "rewards/reward_search_strategy": 0.22500000894069672,
1161
+ "step": 72
1162
+ },
1163
+ {
1164
+ "completion_length": 324.125,
1165
+ "epoch": 0.25524475524475526,
1166
+ "grad_norm": 0.8183465003967285,
1167
+ "kl": 0.09460737556219101,
1168
+ "learning_rate": 3.65e-06,
1169
+ "loss": 0.0038,
1170
+ "reward": 1.5781946182250977,
1171
+ "reward_std": 2.772611618041992,
1172
+ "rewards/reward_correctness": 0.125,
1173
+ "rewards/reward_em_chunk": 0.5,
1174
+ "rewards/reward_format": 0.125,
1175
+ "rewards/reward_search_diversity": 0.25319457054138184,
1176
+ "rewards/reward_search_strategy": 0.07500000298023224,
1177
+ "step": 73
1178
+ },
1179
+ {
1180
+ "completion_length": 479.5,
1181
+ "epoch": 0.25874125874125875,
1182
+ "grad_norm": 0.8604242205619812,
1183
+ "kl": 0.053619399666786194,
1184
+ "learning_rate": 3.7e-06,
1185
+ "loss": 0.0021,
1186
+ "reward": 4.117947578430176,
1187
+ "reward_std": 2.7907135486602783,
1188
+ "rewards/reward_correctness": 0.75,
1189
+ "rewards/reward_em_chunk": 0.0,
1190
+ "rewards/reward_format": 0.25,
1191
+ "rewards/reward_search_diversity": 0.41794782876968384,
1192
+ "rewards/reward_search_strategy": 0.20000000298023224,
1193
+ "step": 74
1194
+ },
1195
+ {
1196
+ "completion_length": 450.25,
1197
+ "epoch": 0.26223776223776224,
1198
+ "grad_norm": 2.1643834114074707,
1199
+ "kl": 0.19324736297130585,
1200
+ "learning_rate": 3.7500000000000005e-06,
1201
+ "loss": 0.0077,
1202
+ "reward": 4.815071105957031,
1203
+ "reward_std": 3.0326616764068604,
1204
+ "rewards/reward_correctness": 0.5,
1205
+ "rewards/reward_em_chunk": 0.75,
1206
+ "rewards/reward_format": 0.625,
1207
+ "rewards/reward_search_diversity": 0.39007121324539185,
1208
+ "rewards/reward_search_strategy": 0.42500001192092896,
1209
+ "step": 75
1210
+ },
1211
+ {
1212
+ "completion_length": 412.25,
1213
+ "epoch": 0.26573426573426573,
1214
+ "grad_norm": 0.8062530159950256,
1215
+ "kl": 0.0793648362159729,
1216
+ "learning_rate": 3.8000000000000005e-06,
1217
+ "loss": 0.0032,
1218
+ "reward": 3.5049312114715576,
1219
+ "reward_std": 2.922109603881836,
1220
+ "rewards/reward_correctness": 0.5,
1221
+ "rewards/reward_em_chunk": 0.25,
1222
+ "rewards/reward_format": 0.25,
1223
+ "rewards/reward_search_diversity": 0.5549312829971313,
1224
+ "rewards/reward_search_strategy": 0.20000000298023224,
1225
+ "step": 76
1226
+ },
1227
+ {
1228
+ "completion_length": 369.75,
1229
+ "epoch": 0.2692307692307692,
1230
+ "grad_norm": 1.467880368232727,
1231
+ "kl": 0.0835878923535347,
1232
+ "learning_rate": 3.85e-06,
1233
+ "loss": 0.0033,
1234
+ "reward": 2.802757978439331,
1235
+ "reward_std": 2.5307087898254395,
1236
+ "rewards/reward_correctness": 0.375,
1237
+ "rewards/reward_em_chunk": 0.0,
1238
+ "rewards/reward_format": 0.375,
1239
+ "rewards/reward_search_diversity": 0.3277580440044403,
1240
+ "rewards/reward_search_strategy": 0.22500000894069672,
1241
+ "step": 77
1242
+ },
1243
+ {
1244
+ "completion_length": 382.375,
1245
+ "epoch": 0.2727272727272727,
1246
+ "grad_norm": 4.771082401275635,
1247
+ "kl": 0.9713490605354309,
1248
+ "learning_rate": 3.900000000000001e-06,
1249
+ "loss": 0.0389,
1250
+ "reward": 2.052755117416382,
1251
+ "reward_std": 3.0059754848480225,
1252
+ "rewards/reward_correctness": 0.25,
1253
+ "rewards/reward_em_chunk": 0.125,
1254
+ "rewards/reward_format": 0.125,
1255
+ "rewards/reward_search_diversity": 0.3777550160884857,
1256
+ "rewards/reward_search_strategy": 0.30000001192092896,
1257
+ "step": 78
1258
+ },
1259
+ {
1260
+ "completion_length": 546.125,
1261
+ "epoch": 0.2762237762237762,
1262
+ "grad_norm": 0.48559486865997314,
1263
+ "kl": 0.037933606654405594,
1264
+ "learning_rate": 3.95e-06,
1265
+ "loss": 0.0015,
1266
+ "reward": 4.67194938659668,
1267
+ "reward_std": 1.9323244094848633,
1268
+ "rewards/reward_correctness": 0.375,
1269
+ "rewards/reward_em_chunk": 1.0,
1270
+ "rewards/reward_format": 0.625,
1271
+ "rewards/reward_search_diversity": 0.5219494700431824,
1272
+ "rewards/reward_search_strategy": 0.3999999761581421,
1273
+ "step": 79
1274
+ },
1275
+ {
1276
+ "completion_length": 677.25,
1277
+ "epoch": 0.27972027972027974,
1278
+ "grad_norm": 0.42382290959358215,
1279
+ "kl": 0.0389033704996109,
1280
+ "learning_rate": 4.000000000000001e-06,
1281
+ "loss": 0.0016,
1282
+ "reward": 1.6928536891937256,
1283
+ "reward_std": 2.6118526458740234,
1284
+ "rewards/reward_correctness": 0.125,
1285
+ "rewards/reward_em_chunk": 0.125,
1286
+ "rewards/reward_format": 0.25,
1287
+ "rewards/reward_search_diversity": 0.367853581905365,
1288
+ "rewards/reward_search_strategy": 0.20000000298023224,
1289
+ "step": 80
1290
+ },
1291
+ {
1292
+ "completion_length": 472.125,
1293
+ "epoch": 0.28321678321678323,
1294
+ "grad_norm": 0.8816371560096741,
1295
+ "kl": 0.07524556666612625,
1296
+ "learning_rate": 4.05e-06,
1297
+ "loss": 0.003,
1298
+ "reward": 3.7551965713500977,
1299
+ "reward_std": 2.652488946914673,
1300
+ "rewards/reward_correctness": 0.375,
1301
+ "rewards/reward_em_chunk": 0.875,
1302
+ "rewards/reward_format": 0.375,
1303
+ "rewards/reward_search_diversity": 0.4801965653896332,
1304
+ "rewards/reward_search_strategy": 0.15000000596046448,
1305
+ "step": 81
1306
+ },
1307
+ {
1308
+ "completion_length": 1057.125,
1309
+ "epoch": 0.2867132867132867,
1310
+ "grad_norm": 0.5135111808776855,
1311
+ "kl": 0.03152136504650116,
1312
+ "learning_rate": 4.1e-06,
1313
+ "loss": 0.0013,
1314
+ "reward": 3.2323527336120605,
1315
+ "reward_std": 1.7208728790283203,
1316
+ "rewards/reward_correctness": 0.125,
1317
+ "rewards/reward_em_chunk": 0.625,
1318
+ "rewards/reward_format": 0.5,
1319
+ "rewards/reward_search_diversity": 0.682352602481842,
1320
+ "rewards/reward_search_strategy": 0.42500001192092896,
1321
+ "step": 82
1322
+ },
1323
+ {
1324
+ "completion_length": 485.375,
1325
+ "epoch": 0.2902097902097902,
1326
+ "grad_norm": 0.9151804447174072,
1327
+ "kl": 0.059312522411346436,
1328
+ "learning_rate": 4.15e-06,
1329
+ "loss": 0.0024,
1330
+ "reward": 1.5200467109680176,
1331
+ "reward_std": 1.384164810180664,
1332
+ "rewards/reward_correctness": 0.0,
1333
+ "rewards/reward_em_chunk": 0.75,
1334
+ "rewards/reward_format": 0.125,
1335
+ "rewards/reward_search_diversity": 0.4450467824935913,
1336
+ "rewards/reward_search_strategy": 0.07500000298023224,
1337
+ "step": 83
1338
+ },
1339
+ {
1340
+ "completion_length": 703.25,
1341
+ "epoch": 0.2937062937062937,
1342
+ "grad_norm": 0.708080530166626,
1343
+ "kl": 0.02395041473209858,
1344
+ "learning_rate": 4.2000000000000004e-06,
1345
+ "loss": 0.001,
1346
+ "reward": 4.584571838378906,
1347
+ "reward_std": 2.8503193855285645,
1348
+ "rewards/reward_correctness": 0.5,
1349
+ "rewards/reward_em_chunk": 0.75,
1350
+ "rewards/reward_format": 0.5,
1351
+ "rewards/reward_search_diversity": 0.4345718026161194,
1352
+ "rewards/reward_search_strategy": 0.4000000059604645,
1353
+ "step": 84
1354
+ },
1355
+ {
1356
+ "completion_length": 507.75,
1357
+ "epoch": 0.2972027972027972,
1358
+ "grad_norm": 0.9842731356620789,
1359
+ "kl": 0.045889340341091156,
1360
+ "learning_rate": 4.25e-06,
1361
+ "loss": 0.0018,
1362
+ "reward": 6.216353893280029,
1363
+ "reward_std": 3.617387056350708,
1364
+ "rewards/reward_correctness": 0.75,
1365
+ "rewards/reward_em_chunk": 0.75,
1366
+ "rewards/reward_format": 0.625,
1367
+ "rewards/reward_search_diversity": 0.4663536846637726,
1368
+ "rewards/reward_search_strategy": 0.75,
1369
+ "step": 85
1370
+ },
1371
+ {
1372
+ "completion_length": 362.75,
1373
+ "epoch": 0.3006993006993007,
1374
+ "grad_norm": 5.553736686706543,
1375
+ "kl": 0.31082066893577576,
1376
+ "learning_rate": 4.3e-06,
1377
+ "loss": 0.0124,
1378
+ "reward": 2.6352591514587402,
1379
+ "reward_std": 3.6418111324310303,
1380
+ "rewards/reward_correctness": 0.25,
1381
+ "rewards/reward_em_chunk": 0.375,
1382
+ "rewards/reward_format": 0.375,
1383
+ "rewards/reward_search_diversity": 0.18525923788547516,
1384
+ "rewards/reward_search_strategy": 0.32499998807907104,
1385
+ "step": 86
1386
+ },
1387
+ {
1388
+ "completion_length": 760.625,
1389
+ "epoch": 0.3041958041958042,
1390
+ "grad_norm": 0.40838149189949036,
1391
+ "kl": 0.03904329240322113,
1392
+ "learning_rate": 4.350000000000001e-06,
1393
+ "loss": 0.0016,
1394
+ "reward": 2.3138082027435303,
1395
+ "reward_std": 2.5393922328948975,
1396
+ "rewards/reward_correctness": 0.125,
1397
+ "rewards/reward_em_chunk": 0.25,
1398
+ "rewards/reward_format": 0.375,
1399
+ "rewards/reward_search_diversity": 0.43880823254585266,
1400
+ "rewards/reward_search_strategy": 0.375,
1401
+ "step": 87
1402
+ },
1403
+ {
1404
+ "completion_length": 233.875,
1405
+ "epoch": 0.3076923076923077,
1406
+ "grad_norm": 1.6991461515426636,
1407
+ "kl": 0.11344132572412491,
1408
+ "learning_rate": 4.4e-06,
1409
+ "loss": 0.0045,
1410
+ "reward": 5.137988090515137,
1411
+ "reward_std": 3.6587538719177246,
1412
+ "rewards/reward_correctness": 0.625,
1413
+ "rewards/reward_em_chunk": 0.875,
1414
+ "rewards/reward_format": 0.5,
1415
+ "rewards/reward_search_diversity": 0.28798776865005493,
1416
+ "rewards/reward_search_strategy": 0.4750000238418579,
1417
+ "step": 88
1418
+ },
1419
+ {
1420
+ "completion_length": 634.0,
1421
+ "epoch": 0.3111888111888112,
1422
+ "grad_norm": 1.008798599243164,
1423
+ "kl": 0.13237585127353668,
1424
+ "learning_rate": 4.450000000000001e-06,
1425
+ "loss": 0.0053,
1426
+ "reward": 2.58494234085083,
1427
+ "reward_std": 3.3475492000579834,
1428
+ "rewards/reward_correctness": 0.25,
1429
+ "rewards/reward_em_chunk": 0.375,
1430
+ "rewards/reward_format": 0.25,
1431
+ "rewards/reward_search_diversity": 0.30994224548339844,
1432
+ "rewards/reward_search_strategy": 0.3999999761581421,
1433
+ "step": 89
1434
+ },
1435
+ {
1436
+ "completion_length": 673.875,
1437
+ "epoch": 0.3146853146853147,
1438
+ "grad_norm": 0.38143813610076904,
1439
+ "kl": 0.04431832954287529,
1440
+ "learning_rate": 4.5e-06,
1441
+ "loss": 0.0018,
1442
+ "reward": 3.379831552505493,
1443
+ "reward_std": 2.6894783973693848,
1444
+ "rewards/reward_correctness": 0.25,
1445
+ "rewards/reward_em_chunk": 1.0,
1446
+ "rewards/reward_format": 0.25,
1447
+ "rewards/reward_search_diversity": 0.5048315525054932,
1448
+ "rewards/reward_search_strategy": 0.375,
1449
+ "step": 90
1450
+ },
1451
+ {
1452
+ "completion_length": 335.5,
1453
+ "epoch": 0.3181818181818182,
1454
+ "grad_norm": 1.326707124710083,
1455
+ "kl": 0.1567000150680542,
1456
+ "learning_rate": 4.5500000000000005e-06,
1457
+ "loss": 0.0063,
1458
+ "reward": 1.540712594985962,
1459
+ "reward_std": 1.9064555168151855,
1460
+ "rewards/reward_correctness": 0.0,
1461
+ "rewards/reward_em_chunk": 0.25,
1462
+ "rewards/reward_format": 0.375,
1463
+ "rewards/reward_search_diversity": 0.24071267247200012,
1464
+ "rewards/reward_search_strategy": 0.30000001192092896,
1465
+ "step": 91
1466
+ },
1467
+ {
1468
+ "completion_length": 479.25,
1469
+ "epoch": 0.32167832167832167,
1470
+ "grad_norm": 0.8233426213264465,
1471
+ "kl": 0.046305958181619644,
1472
+ "learning_rate": 4.600000000000001e-06,
1473
+ "loss": 0.0019,
1474
+ "reward": 4.979320526123047,
1475
+ "reward_std": 2.5221211910247803,
1476
+ "rewards/reward_correctness": 0.5,
1477
+ "rewards/reward_em_chunk": 1.0,
1478
+ "rewards/reward_format": 0.5,
1479
+ "rewards/reward_search_diversity": 0.6293203234672546,
1480
+ "rewards/reward_search_strategy": 0.3500000238418579,
1481
+ "step": 92
1482
+ },
1483
+ {
1484
+ "completion_length": 529.625,
1485
+ "epoch": 0.32517482517482516,
1486
+ "grad_norm": 0.8791444301605225,
1487
+ "kl": 0.049900904297828674,
1488
+ "learning_rate": 4.65e-06,
1489
+ "loss": 0.002,
1490
+ "reward": 4.73832893371582,
1491
+ "reward_std": 2.957406520843506,
1492
+ "rewards/reward_correctness": 0.375,
1493
+ "rewards/reward_em_chunk": 0.875,
1494
+ "rewards/reward_format": 0.625,
1495
+ "rewards/reward_search_diversity": 0.5633291006088257,
1496
+ "rewards/reward_search_strategy": 0.550000011920929,
1497
+ "step": 93
1498
+ },
1499
+ {
1500
+ "completion_length": 566.25,
1501
+ "epoch": 0.32867132867132864,
1502
+ "grad_norm": 0.93157559633255,
1503
+ "kl": 0.10382921993732452,
1504
+ "learning_rate": 4.7e-06,
1505
+ "loss": 0.0042,
1506
+ "reward": 3.921233654022217,
1507
+ "reward_std": 3.259979486465454,
1508
+ "rewards/reward_correctness": 0.25,
1509
+ "rewards/reward_em_chunk": 0.75,
1510
+ "rewards/reward_format": 0.625,
1511
+ "rewards/reward_search_diversity": 0.39623361825942993,
1512
+ "rewards/reward_search_strategy": 0.5249999761581421,
1513
+ "step": 94
1514
+ },
1515
+ {
1516
+ "completion_length": 405.0,
1517
+ "epoch": 0.3321678321678322,
1518
+ "grad_norm": 0.6553046703338623,
1519
+ "kl": 0.05014060437679291,
1520
+ "learning_rate": 4.75e-06,
1521
+ "loss": 0.002,
1522
+ "reward": 4.048189163208008,
1523
+ "reward_std": 3.046299934387207,
1524
+ "rewards/reward_correctness": 0.375,
1525
+ "rewards/reward_em_chunk": 0.375,
1526
+ "rewards/reward_format": 0.625,
1527
+ "rewards/reward_search_diversity": 0.3731893002986908,
1528
+ "rewards/reward_search_strategy": 0.550000011920929,
1529
+ "step": 95
1530
+ },
1531
+ {
1532
+ "completion_length": 559.0,
1533
+ "epoch": 0.3356643356643357,
1534
+ "grad_norm": 0.9019679427146912,
1535
+ "kl": 0.1154535710811615,
1536
+ "learning_rate": 4.800000000000001e-06,
1537
+ "loss": 0.0046,
1538
+ "reward": 3.3237497806549072,
1539
+ "reward_std": 2.755406379699707,
1540
+ "rewards/reward_correctness": 0.375,
1541
+ "rewards/reward_em_chunk": 0.5,
1542
+ "rewards/reward_format": 0.375,
1543
+ "rewards/reward_search_diversity": 0.19874979555606842,
1544
+ "rewards/reward_search_strategy": 0.375,
1545
+ "step": 96
1546
+ },
1547
+ {
1548
+ "completion_length": 513.125,
1549
+ "epoch": 0.33916083916083917,
1550
+ "grad_norm": 1.1792876720428467,
1551
+ "kl": 0.20403671264648438,
1552
+ "learning_rate": 4.85e-06,
1553
+ "loss": 0.0082,
1554
+ "reward": 4.584352970123291,
1555
+ "reward_std": 3.532867908477783,
1556
+ "rewards/reward_correctness": 0.5,
1557
+ "rewards/reward_em_chunk": 0.625,
1558
+ "rewards/reward_format": 0.5,
1559
+ "rewards/reward_search_diversity": 0.4093528091907501,
1560
+ "rewards/reward_search_strategy": 0.550000011920929,
1561
+ "step": 97
1562
+ },
1563
+ {
1564
+ "completion_length": 390.75,
1565
+ "epoch": 0.34265734265734266,
1566
+ "grad_norm": 24.102558135986328,
1567
+ "kl": 1.4576557874679565,
1568
+ "learning_rate": 4.9000000000000005e-06,
1569
+ "loss": 0.0583,
1570
+ "reward": 3.2650551795959473,
1571
+ "reward_std": 1.5778415203094482,
1572
+ "rewards/reward_correctness": 0.125,
1573
+ "rewards/reward_em_chunk": 0.875,
1574
+ "rewards/reward_format": 0.5,
1575
+ "rewards/reward_search_diversity": 0.4150553047657013,
1576
+ "rewards/reward_search_strategy": 0.4749999940395355,
1577
+ "step": 98
1578
+ },
1579
+ {
1580
+ "completion_length": 992.0,
1581
+ "epoch": 0.34615384615384615,
1582
+ "grad_norm": 1.07889723777771,
1583
+ "kl": 0.15134873986244202,
1584
+ "learning_rate": 4.95e-06,
1585
+ "loss": 0.0061,
1586
+ "reward": 3.4669156074523926,
1587
+ "reward_std": 3.278291940689087,
1588
+ "rewards/reward_correctness": 0.375,
1589
+ "rewards/reward_em_chunk": 0.25,
1590
+ "rewards/reward_format": 0.5,
1591
+ "rewards/reward_search_diversity": 0.31691551208496094,
1592
+ "rewards/reward_search_strategy": 0.4000000059604645,
1593
+ "step": 99
1594
+ },
1595
+ {
1596
+ "completion_length": 839.625,
1597
+ "epoch": 0.34965034965034963,
1598
+ "grad_norm": 0.5948315262794495,
1599
+ "kl": 0.03611273318529129,
1600
+ "learning_rate": 5e-06,
1601
+ "loss": 0.0014,
1602
+ "reward": 2.273786783218384,
1603
+ "reward_std": 1.3839948177337646,
1604
+ "rewards/reward_correctness": 0.0,
1605
+ "rewards/reward_em_chunk": 0.0,
1606
+ "rewards/reward_format": 0.625,
1607
+ "rewards/reward_search_diversity": 0.5487868189811707,
1608
+ "rewards/reward_search_strategy": 0.4750000238418579,
1609
+ "step": 100
1610
+ },
1611
+ {
1612
+ "completion_length": 658.5,
1613
+ "epoch": 0.3531468531468531,
1614
+ "grad_norm": 0.6043696999549866,
1615
+ "kl": 0.07113679498434067,
1616
+ "learning_rate": 4.999984769144476e-06,
1617
+ "loss": 0.0028,
1618
+ "reward": 4.308359622955322,
1619
+ "reward_std": 2.9922401905059814,
1620
+ "rewards/reward_correctness": 0.375,
1621
+ "rewards/reward_em_chunk": 0.75,
1622
+ "rewards/reward_format": 0.5,
1623
+ "rewards/reward_search_diversity": 0.5333598256111145,
1624
+ "rewards/reward_search_strategy": 0.5250000357627869,
1625
+ "step": 101
1626
+ },
1627
+ {
1628
+ "completion_length": 658.375,
1629
+ "epoch": 0.35664335664335667,
1630
+ "grad_norm": 0.6331404447555542,
1631
+ "kl": 0.06461314111948013,
1632
+ "learning_rate": 4.999939076763487e-06,
1633
+ "loss": 0.0026,
1634
+ "reward": 4.334439277648926,
1635
+ "reward_std": 3.60390567779541,
1636
+ "rewards/reward_correctness": 0.375,
1637
+ "rewards/reward_em_chunk": 0.875,
1638
+ "rewards/reward_format": 0.5,
1639
+ "rewards/reward_search_diversity": 0.3594394326210022,
1640
+ "rewards/reward_search_strategy": 0.6000000238418579,
1641
+ "step": 102
1642
+ },
1643
+ {
1644
+ "completion_length": 549.875,
1645
+ "epoch": 0.36013986013986016,
1646
+ "grad_norm": 0.9000433087348938,
1647
+ "kl": 0.18242445588111877,
1648
+ "learning_rate": 4.999862923413781e-06,
1649
+ "loss": 0.0073,
1650
+ "reward": 3.720637559890747,
1651
+ "reward_std": 3.3442742824554443,
1652
+ "rewards/reward_correctness": 0.375,
1653
+ "rewards/reward_em_chunk": 0.625,
1654
+ "rewards/reward_format": 0.375,
1655
+ "rewards/reward_search_diversity": 0.3706376552581787,
1656
+ "rewards/reward_search_strategy": 0.4750000238418579,
1657
+ "step": 103
1658
+ },
1659
+ {
1660
+ "completion_length": 560.875,
1661
+ "epoch": 0.36363636363636365,
1662
+ "grad_norm": 0.9529889822006226,
1663
+ "kl": 0.13583947718143463,
1664
+ "learning_rate": 4.999756310023261e-06,
1665
+ "loss": 0.0054,
1666
+ "reward": 5.090951442718506,
1667
+ "reward_std": 3.163343906402588,
1668
+ "rewards/reward_correctness": 0.625,
1669
+ "rewards/reward_em_chunk": 1.0,
1670
+ "rewards/reward_format": 0.375,
1671
+ "rewards/reward_search_diversity": 0.41595128178596497,
1672
+ "rewards/reward_search_strategy": 0.42500001192092896,
1673
+ "step": 104
1674
+ },
1675
+ {
1676
+ "completion_length": 784.5,
1677
+ "epoch": 0.36713286713286714,
1678
+ "grad_norm": 0.5621578693389893,
1679
+ "kl": 0.06874603033065796,
1680
+ "learning_rate": 4.9996192378909785e-06,
1681
+ "loss": 0.0027,
1682
+ "reward": 1.6759297847747803,
1683
+ "reward_std": 1.3889375925064087,
1684
+ "rewards/reward_correctness": 0.125,
1685
+ "rewards/reward_em_chunk": 0.25,
1686
+ "rewards/reward_format": 0.125,
1687
+ "rewards/reward_search_diversity": 0.4009298086166382,
1688
+ "rewards/reward_search_strategy": 0.2750000059604645,
1689
+ "step": 105
1690
+ },
1691
+ {
1692
+ "completion_length": 811.875,
1693
+ "epoch": 0.3706293706293706,
1694
+ "grad_norm": 0.3865280747413635,
1695
+ "kl": 0.03063635341823101,
1696
+ "learning_rate": 4.999451708687114e-06,
1697
+ "loss": 0.0012,
1698
+ "reward": 1.8364933729171753,
1699
+ "reward_std": 1.0776033401489258,
1700
+ "rewards/reward_correctness": 0.0,
1701
+ "rewards/reward_em_chunk": 0.25,
1702
+ "rewards/reward_format": 0.375,
1703
+ "rewards/reward_search_diversity": 0.186493381857872,
1704
+ "rewards/reward_search_strategy": 0.6499999761581421,
1705
+ "step": 106
1706
+ },
1707
+ {
1708
+ "completion_length": 767.0,
1709
+ "epoch": 0.3741258741258741,
1710
+ "grad_norm": 1.0235356092453003,
1711
+ "kl": 0.05863216146826744,
1712
+ "learning_rate": 4.9992537244529585e-06,
1713
+ "loss": 0.0023,
1714
+ "reward": 3.36350154876709,
1715
+ "reward_std": 2.900977611541748,
1716
+ "rewards/reward_correctness": 0.25,
1717
+ "rewards/reward_em_chunk": 0.0,
1718
+ "rewards/reward_format": 0.625,
1719
+ "rewards/reward_search_diversity": 0.43850138783454895,
1720
+ "rewards/reward_search_strategy": 0.6749999523162842,
1721
+ "step": 107
1722
+ },
1723
+ {
1724
+ "completion_length": 471.125,
1725
+ "epoch": 0.3776223776223776,
1726
+ "grad_norm": 1.1427947282791138,
1727
+ "kl": 0.05708540976047516,
1728
+ "learning_rate": 4.999025287600886e-06,
1729
+ "loss": 0.0023,
1730
+ "reward": 3.4347455501556396,
1731
+ "reward_std": 3.3557960987091064,
1732
+ "rewards/reward_correctness": 0.375,
1733
+ "rewards/reward_em_chunk": 0.0,
1734
+ "rewards/reward_format": 0.625,
1735
+ "rewards/reward_search_diversity": 0.28474536538124084,
1736
+ "rewards/reward_search_strategy": 0.4000000059604645,
1737
+ "step": 108
1738
+ },
1739
+ {
1740
+ "completion_length": 680.5,
1741
+ "epoch": 0.3811188811188811,
1742
+ "grad_norm": 0.5091893076896667,
1743
+ "kl": 0.06495320051908493,
1744
+ "learning_rate": 4.998766400914329e-06,
1745
+ "loss": 0.0026,
1746
+ "reward": 5.424283981323242,
1747
+ "reward_std": 3.0205914974212646,
1748
+ "rewards/reward_correctness": 0.75,
1749
+ "rewards/reward_em_chunk": 0.125,
1750
+ "rewards/reward_format": 0.625,
1751
+ "rewards/reward_search_diversity": 0.2242841124534607,
1752
+ "rewards/reward_search_strategy": 0.824999988079071,
1753
+ "step": 109
1754
+ },
1755
+ {
1756
+ "completion_length": 546.875,
1757
+ "epoch": 0.38461538461538464,
1758
+ "grad_norm": 0.7380320429801941,
1759
+ "kl": 0.080781489610672,
1760
+ "learning_rate": 4.99847706754774e-06,
1761
+ "loss": 0.0032,
1762
+ "reward": 3.1829848289489746,
1763
+ "reward_std": 1.9441657066345215,
1764
+ "rewards/reward_correctness": 0.25,
1765
+ "rewards/reward_em_chunk": 0.75,
1766
+ "rewards/reward_format": 0.375,
1767
+ "rewards/reward_search_diversity": 0.45798495411872864,
1768
+ "rewards/reward_search_strategy": 0.22500000894069672,
1769
+ "step": 110
1770
+ },
1771
+ {
1772
+ "completion_length": 696.125,
1773
+ "epoch": 0.3881118881118881,
1774
+ "grad_norm": 0.7519396543502808,
1775
+ "kl": 0.0903296023607254,
1776
+ "learning_rate": 4.998157291026553e-06,
1777
+ "loss": 0.0036,
1778
+ "reward": 3.140177011489868,
1779
+ "reward_std": 2.6969096660614014,
1780
+ "rewards/reward_correctness": 0.125,
1781
+ "rewards/reward_em_chunk": 0.875,
1782
+ "rewards/reward_format": 0.5,
1783
+ "rewards/reward_search_diversity": 0.4151769280433655,
1784
+ "rewards/reward_search_strategy": 0.3500000238418579,
1785
+ "step": 111
1786
+ },
1787
+ {
1788
+ "completion_length": 530.5,
1789
+ "epoch": 0.3916083916083916,
1790
+ "grad_norm": 1.3212255239486694,
1791
+ "kl": 0.17164835333824158,
1792
+ "learning_rate": 4.997807075247147e-06,
1793
+ "loss": 0.0069,
1794
+ "reward": 2.3374075889587402,
1795
+ "reward_std": 1.7672338485717773,
1796
+ "rewards/reward_correctness": 0.125,
1797
+ "rewards/reward_em_chunk": 0.375,
1798
+ "rewards/reward_format": 0.375,
1799
+ "rewards/reward_search_diversity": 0.41240769624710083,
1800
+ "rewards/reward_search_strategy": 0.30000001192092896,
1801
+ "step": 112
1802
+ },
1803
+ {
1804
+ "completion_length": 703.375,
1805
+ "epoch": 0.3951048951048951,
1806
+ "grad_norm": 0.48862800002098083,
1807
+ "kl": 0.04361271113157272,
1808
+ "learning_rate": 4.997426424476787e-06,
1809
+ "loss": 0.0017,
1810
+ "reward": 4.811786651611328,
1811
+ "reward_std": 3.4794275760650635,
1812
+ "rewards/reward_correctness": 0.375,
1813
+ "rewards/reward_em_chunk": 0.625,
1814
+ "rewards/reward_format": 0.75,
1815
+ "rewards/reward_search_diversity": 0.48678621649742126,
1816
+ "rewards/reward_search_strategy": 0.699999988079071,
1817
+ "step": 113
1818
+ },
1819
+ {
1820
+ "completion_length": 666.375,
1821
+ "epoch": 0.3986013986013986,
1822
+ "grad_norm": 0.7718109488487244,
1823
+ "kl": 0.040162038058042526,
1824
+ "learning_rate": 4.9970153433535855e-06,
1825
+ "loss": 0.0016,
1826
+ "reward": 3.659369468688965,
1827
+ "reward_std": 2.0675926208496094,
1828
+ "rewards/reward_correctness": 0.125,
1829
+ "rewards/reward_em_chunk": 0.375,
1830
+ "rewards/reward_format": 0.875,
1831
+ "rewards/reward_search_diversity": 0.4593694806098938,
1832
+ "rewards/reward_search_strategy": 0.5750000476837158,
1833
+ "step": 114
1834
+ },
1835
+ {
1836
+ "completion_length": 640.625,
1837
+ "epoch": 0.4020979020979021,
1838
+ "grad_norm": 0.5138198137283325,
1839
+ "kl": 0.05123981833457947,
1840
+ "learning_rate": 4.9965738368864345e-06,
1841
+ "loss": 0.002,
1842
+ "reward": 2.629551410675049,
1843
+ "reward_std": 1.7166107892990112,
1844
+ "rewards/reward_correctness": 0.0,
1845
+ "rewards/reward_em_chunk": 0.375,
1846
+ "rewards/reward_format": 0.625,
1847
+ "rewards/reward_search_diversity": 0.5045512914657593,
1848
+ "rewards/reward_search_strategy": 0.5,
1849
+ "step": 115
1850
+ },
1851
+ {
1852
+ "completion_length": 586.75,
1853
+ "epoch": 0.40559440559440557,
1854
+ "grad_norm": 1.4575413465499878,
1855
+ "kl": 0.08412657678127289,
1856
+ "learning_rate": 4.996101910454953e-06,
1857
+ "loss": 0.0034,
1858
+ "reward": 4.0647077560424805,
1859
+ "reward_std": 1.9030133485794067,
1860
+ "rewards/reward_correctness": 0.25,
1861
+ "rewards/reward_em_chunk": 1.0,
1862
+ "rewards/reward_format": 0.625,
1863
+ "rewards/reward_search_diversity": 0.4147075116634369,
1864
+ "rewards/reward_search_strategy": 0.40000003576278687,
1865
+ "step": 116
1866
+ },
1867
+ {
1868
+ "completion_length": 514.625,
1869
+ "epoch": 0.4090909090909091,
1870
+ "grad_norm": 1.051775574684143,
1871
+ "kl": 0.09374314546585083,
1872
+ "learning_rate": 4.995599569809414e-06,
1873
+ "loss": 0.0037,
1874
+ "reward": 2.5817337036132812,
1875
+ "reward_std": 2.1470091342926025,
1876
+ "rewards/reward_correctness": 0.25,
1877
+ "rewards/reward_em_chunk": 0.5,
1878
+ "rewards/reward_format": 0.25,
1879
+ "rewards/reward_search_diversity": 0.30673372745513916,
1880
+ "rewards/reward_search_strategy": 0.2750000059604645,
1881
+ "step": 117
1882
+ },
1883
+ {
1884
+ "completion_length": 814.375,
1885
+ "epoch": 0.4125874125874126,
1886
+ "grad_norm": 0.4415126144886017,
1887
+ "kl": 0.07567695528268814,
1888
+ "learning_rate": 4.9950668210706795e-06,
1889
+ "loss": 0.003,
1890
+ "reward": 2.189971685409546,
1891
+ "reward_std": 1.4690890312194824,
1892
+ "rewards/reward_correctness": 0.0,
1893
+ "rewards/reward_em_chunk": 0.75,
1894
+ "rewards/reward_format": 0.25,
1895
+ "rewards/reward_search_diversity": 0.5649716854095459,
1896
+ "rewards/reward_search_strategy": 0.375,
1897
+ "step": 118
1898
+ },
1899
+ {
1900
+ "completion_length": 550.375,
1901
+ "epoch": 0.4160839160839161,
1902
+ "grad_norm": 0.50792396068573,
1903
+ "kl": 0.05492626503109932,
1904
+ "learning_rate": 4.994503670730126e-06,
1905
+ "loss": 0.0022,
1906
+ "reward": 4.787566661834717,
1907
+ "reward_std": 2.5005829334259033,
1908
+ "rewards/reward_correctness": 0.25,
1909
+ "rewards/reward_em_chunk": 1.0,
1910
+ "rewards/reward_format": 0.75,
1911
+ "rewards/reward_search_diversity": 0.6875668168067932,
1912
+ "rewards/reward_search_strategy": 0.6000000238418579,
1913
+ "step": 119
1914
+ },
1915
+ {
1916
+ "completion_length": 609.0,
1917
+ "epoch": 0.4195804195804196,
1918
+ "grad_norm": 0.6223260760307312,
1919
+ "kl": 0.047494076192379,
1920
+ "learning_rate": 4.993910125649561e-06,
1921
+ "loss": 0.0019,
1922
+ "reward": 4.249635696411133,
1923
+ "reward_std": 2.9354586601257324,
1924
+ "rewards/reward_correctness": 0.375,
1925
+ "rewards/reward_em_chunk": 1.0,
1926
+ "rewards/reward_format": 0.5,
1927
+ "rewards/reward_search_diversity": 0.3746356964111328,
1928
+ "rewards/reward_search_strategy": 0.3750000298023224,
1929
+ "step": 120
1930
+ },
1931
+ {
1932
+ "completion_length": 560.875,
1933
+ "epoch": 0.4230769230769231,
1934
+ "grad_norm": 0.9563676118850708,
1935
+ "kl": 0.09799660742282867,
1936
+ "learning_rate": 4.993286193061145e-06,
1937
+ "loss": 0.0039,
1938
+ "reward": 2.565558910369873,
1939
+ "reward_std": 2.178126811981201,
1940
+ "rewards/reward_correctness": 0.125,
1941
+ "rewards/reward_em_chunk": 0.375,
1942
+ "rewards/reward_format": 0.5,
1943
+ "rewards/reward_search_diversity": 0.3405587375164032,
1944
+ "rewards/reward_search_strategy": 0.3500000238418579,
1945
+ "step": 121
1946
+ },
1947
+ {
1948
+ "completion_length": 387.625,
1949
+ "epoch": 0.42657342657342656,
1950
+ "grad_norm": 0.7505446076393127,
1951
+ "kl": 0.14984500408172607,
1952
+ "learning_rate": 4.992631880567301e-06,
1953
+ "loss": 0.006,
1954
+ "reward": 1.1751203536987305,
1955
+ "reward_std": 1.6967118978500366,
1956
+ "rewards/reward_correctness": 0.125,
1957
+ "rewards/reward_em_chunk": 0.0,
1958
+ "rewards/reward_format": 0.125,
1959
+ "rewards/reward_search_diversity": 0.20012035965919495,
1960
+ "rewards/reward_search_strategy": 0.22500000894069672,
1961
+ "step": 122
1962
+ },
1963
+ {
1964
+ "completion_length": 411.875,
1965
+ "epoch": 0.43006993006993005,
1966
+ "grad_norm": 1.1681523323059082,
1967
+ "kl": 0.0963008776307106,
1968
+ "learning_rate": 4.991947196140619e-06,
1969
+ "loss": 0.0039,
1970
+ "reward": 3.0484721660614014,
1971
+ "reward_std": 3.416553497314453,
1972
+ "rewards/reward_correctness": 0.375,
1973
+ "rewards/reward_em_chunk": 0.0,
1974
+ "rewards/reward_format": 0.375,
1975
+ "rewards/reward_search_diversity": 0.3984720706939697,
1976
+ "rewards/reward_search_strategy": 0.4000000059604645,
1977
+ "step": 123
1978
+ },
1979
+ {
1980
+ "completion_length": 423.75,
1981
+ "epoch": 0.43356643356643354,
1982
+ "grad_norm": 0.9286041259765625,
1983
+ "kl": 0.07872038334608078,
1984
+ "learning_rate": 4.9912321481237616e-06,
1985
+ "loss": 0.0031,
1986
+ "reward": 3.2697560787200928,
1987
+ "reward_std": 3.4370007514953613,
1988
+ "rewards/reward_correctness": 0.25,
1989
+ "rewards/reward_em_chunk": 0.375,
1990
+ "rewards/reward_format": 0.5,
1991
+ "rewards/reward_search_diversity": 0.3947560787200928,
1992
+ "rewards/reward_search_strategy": 0.5,
1993
+ "step": 124
1994
+ },
1995
+ {
1996
+ "completion_length": 463.625,
1997
+ "epoch": 0.4370629370629371,
1998
+ "grad_norm": 1.0566741228103638,
1999
+ "kl": 0.0985063686966896,
2000
+ "learning_rate": 4.990486745229364e-06,
2001
+ "loss": 0.0039,
2002
+ "reward": 1.5522143840789795,
2003
+ "reward_std": 1.579607605934143,
2004
+ "rewards/reward_correctness": 0.0,
2005
+ "rewards/reward_em_chunk": 0.5,
2006
+ "rewards/reward_format": 0.25,
2007
+ "rewards/reward_search_diversity": 0.37721437215805054,
2008
+ "rewards/reward_search_strategy": 0.17500001192092896,
2009
+ "step": 125
2010
+ },
2011
+ {
2012
+ "completion_length": 685.625,
2013
+ "epoch": 0.4405594405594406,
2014
+ "grad_norm": 0.6656001806259155,
2015
+ "kl": 0.06633864343166351,
2016
+ "learning_rate": 4.989710996539926e-06,
2017
+ "loss": 0.0027,
2018
+ "reward": 2.43574857711792,
2019
+ "reward_std": 2.3410024642944336,
2020
+ "rewards/reward_correctness": 0.125,
2021
+ "rewards/reward_em_chunk": 0.0,
2022
+ "rewards/reward_format": 0.5,
2023
+ "rewards/reward_search_diversity": 0.585748553276062,
2024
+ "rewards/reward_search_strategy": 0.3500000238418579,
2025
+ "step": 126
2026
+ },
2027
+ {
2028
+ "completion_length": 637.375,
2029
+ "epoch": 0.44405594405594406,
2030
+ "grad_norm": 0.7161982655525208,
2031
+ "kl": 0.07665619254112244,
2032
+ "learning_rate": 4.9889049115077e-06,
2033
+ "loss": 0.0031,
2034
+ "reward": 3.5046868324279785,
2035
+ "reward_std": 2.549543619155884,
2036
+ "rewards/reward_correctness": 0.125,
2037
+ "rewards/reward_em_chunk": 0.375,
2038
+ "rewards/reward_format": 0.75,
2039
+ "rewards/reward_search_diversity": 0.5796867609024048,
2040
+ "rewards/reward_search_strategy": 0.550000011920929,
2041
+ "step": 127
2042
+ },
2043
+ {
2044
+ "completion_length": 644.375,
2045
+ "epoch": 0.44755244755244755,
2046
+ "grad_norm": 0.5414532423019409,
2047
+ "kl": 0.06415767967700958,
2048
+ "learning_rate": 4.988068499954578e-06,
2049
+ "loss": 0.0026,
2050
+ "reward": 5.926258563995361,
2051
+ "reward_std": 2.7303335666656494,
2052
+ "rewards/reward_correctness": 0.625,
2053
+ "rewards/reward_em_chunk": 0.625,
2054
+ "rewards/reward_format": 0.75,
2055
+ "rewards/reward_search_diversity": 0.6762584447860718,
2056
+ "rewards/reward_search_strategy": 0.625,
2057
+ "step": 128
2058
+ },
2059
+ {
2060
+ "completion_length": 397.25,
2061
+ "epoch": 0.45104895104895104,
2062
+ "grad_norm": 0.8846190571784973,
2063
+ "kl": 0.14254269003868103,
2064
+ "learning_rate": 4.987201772071971e-06,
2065
+ "loss": 0.0057,
2066
+ "reward": 2.7677345275878906,
2067
+ "reward_std": 2.424544095993042,
2068
+ "rewards/reward_correctness": 0.125,
2069
+ "rewards/reward_em_chunk": 0.0,
2070
+ "rewards/reward_format": 0.625,
2071
+ "rewards/reward_search_diversity": 0.5427343845367432,
2072
+ "rewards/reward_search_strategy": 0.4750000238418579,
2073
+ "step": 129
2074
+ },
2075
+ {
2076
+ "completion_length": 463.875,
2077
+ "epoch": 0.45454545454545453,
2078
+ "grad_norm": 0.6526610851287842,
2079
+ "kl": 0.12603093683719635,
2080
+ "learning_rate": 4.986304738420684e-06,
2081
+ "loss": 0.005,
2082
+ "reward": 5.665769577026367,
2083
+ "reward_std": 2.0002214908599854,
2084
+ "rewards/reward_correctness": 0.625,
2085
+ "rewards/reward_em_chunk": 1.0,
2086
+ "rewards/reward_format": 0.75,
2087
+ "rewards/reward_search_diversity": 0.1657698005437851,
2088
+ "rewards/reward_search_strategy": 0.5,
2089
+ "step": 130
2090
+ },
2091
+ {
2092
+ "completion_length": 425.125,
2093
+ "epoch": 0.458041958041958,
2094
+ "grad_norm": 1.6641560792922974,
2095
+ "kl": 0.2266431599855423,
2096
+ "learning_rate": 4.985377409930789e-06,
2097
+ "loss": 0.0091,
2098
+ "reward": 4.595471382141113,
2099
+ "reward_std": 3.3347935676574707,
2100
+ "rewards/reward_correctness": 0.375,
2101
+ "rewards/reward_em_chunk": 0.875,
2102
+ "rewards/reward_format": 0.625,
2103
+ "rewards/reward_search_diversity": 0.42047110199928284,
2104
+ "rewards/reward_search_strategy": 0.550000011920929,
2105
+ "step": 131
2106
+ },
2107
+ {
2108
+ "completion_length": 708.75,
2109
+ "epoch": 0.46153846153846156,
2110
+ "grad_norm": 0.49309638142585754,
2111
+ "kl": 0.07724378257989883,
2112
+ "learning_rate": 4.984419797901491e-06,
2113
+ "loss": 0.0031,
2114
+ "reward": 2.9709227085113525,
2115
+ "reward_std": 0.63145512342453,
2116
+ "rewards/reward_correctness": 0.0,
2117
+ "rewards/reward_em_chunk": 0.25,
2118
+ "rewards/reward_format": 0.875,
2119
+ "rewards/reward_search_diversity": 0.4459228515625,
2120
+ "rewards/reward_search_strategy": 0.5249999761581421,
2121
+ "step": 132
2122
+ },
2123
+ {
2124
+ "completion_length": 570.75,
2125
+ "epoch": 0.46503496503496505,
2126
+ "grad_norm": 0.8325252532958984,
2127
+ "kl": 0.15752217173576355,
2128
+ "learning_rate": 4.983431914000991e-06,
2129
+ "loss": 0.0063,
2130
+ "reward": 2.9882287979125977,
2131
+ "reward_std": 2.527655601501465,
2132
+ "rewards/reward_correctness": 0.125,
2133
+ "rewards/reward_em_chunk": 0.25,
2134
+ "rewards/reward_format": 0.625,
2135
+ "rewards/reward_search_diversity": 0.463228702545166,
2136
+ "rewards/reward_search_strategy": 0.5250000357627869,
2137
+ "step": 133
2138
+ },
2139
+ {
2140
+ "completion_length": 669.625,
2141
+ "epoch": 0.46853146853146854,
2142
+ "grad_norm": 1.057653784751892,
2143
+ "kl": 0.10220281034708023,
2144
+ "learning_rate": 4.9824137702663424e-06,
2145
+ "loss": 0.0041,
2146
+ "reward": 2.843283176422119,
2147
+ "reward_std": 2.226605176925659,
2148
+ "rewards/reward_correctness": 0.125,
2149
+ "rewards/reward_em_chunk": 0.0,
2150
+ "rewards/reward_format": 0.75,
2151
+ "rewards/reward_search_diversity": 0.3932831287384033,
2152
+ "rewards/reward_search_strategy": 0.45000001788139343,
2153
+ "step": 134
2154
+ },
2155
+ {
2156
+ "completion_length": 387.25,
2157
+ "epoch": 0.47202797202797203,
2158
+ "grad_norm": 0.7793525457382202,
2159
+ "kl": 0.09381990879774094,
2160
+ "learning_rate": 4.981365379103306e-06,
2161
+ "loss": 0.0038,
2162
+ "reward": 3.3774726390838623,
2163
+ "reward_std": 2.2550406455993652,
2164
+ "rewards/reward_correctness": 0.125,
2165
+ "rewards/reward_em_chunk": 0.75,
2166
+ "rewards/reward_format": 0.625,
2167
+ "rewards/reward_search_diversity": 0.37747257947921753,
2168
+ "rewards/reward_search_strategy": 0.5,
2169
+ "step": 135
2170
+ },
2171
+ {
2172
+ "completion_length": 454.625,
2173
+ "epoch": 0.4755244755244755,
2174
+ "grad_norm": 0.6707426309585571,
2175
+ "kl": 0.09792742133140564,
2176
+ "learning_rate": 4.980286753286196e-06,
2177
+ "loss": 0.0039,
2178
+ "reward": 5.85577392578125,
2179
+ "reward_std": 2.534198522567749,
2180
+ "rewards/reward_correctness": 0.625,
2181
+ "rewards/reward_em_chunk": 0.875,
2182
+ "rewards/reward_format": 0.625,
2183
+ "rewards/reward_search_diversity": 0.5807737112045288,
2184
+ "rewards/reward_search_strategy": 0.6499999761581421,
2185
+ "step": 136
2186
+ },
2187
+ {
2188
+ "completion_length": 513.0,
2189
+ "epoch": 0.479020979020979,
2190
+ "grad_norm": 0.91905677318573,
2191
+ "kl": 0.12576593458652496,
2192
+ "learning_rate": 4.979177905957726e-06,
2193
+ "loss": 0.005,
2194
+ "reward": 2.693246603012085,
2195
+ "reward_std": 1.9298425912857056,
2196
+ "rewards/reward_correctness": 0.125,
2197
+ "rewards/reward_em_chunk": 0.75,
2198
+ "rewards/reward_format": 0.375,
2199
+ "rewards/reward_search_diversity": 0.44324639439582825,
2200
+ "rewards/reward_search_strategy": 0.25,
2201
+ "step": 137
2202
+ },
2203
+ {
2204
+ "completion_length": 535.0,
2205
+ "epoch": 0.4825174825174825,
2206
+ "grad_norm": 0.6421681642532349,
2207
+ "kl": 0.16189059615135193,
2208
+ "learning_rate": 4.978038850628855e-06,
2209
+ "loss": 0.0065,
2210
+ "reward": 2.3643674850463867,
2211
+ "reward_std": 2.4537479877471924,
2212
+ "rewards/reward_correctness": 0.125,
2213
+ "rewards/reward_em_chunk": 0.0,
2214
+ "rewards/reward_format": 0.375,
2215
+ "rewards/reward_search_diversity": 0.614367663860321,
2216
+ "rewards/reward_search_strategy": 0.5,
2217
+ "step": 138
2218
+ },
2219
+ {
2220
+ "completion_length": 388.625,
2221
+ "epoch": 0.486013986013986,
2222
+ "grad_norm": 1.6358879804611206,
2223
+ "kl": 0.31070151925086975,
2224
+ "learning_rate": 4.9768696011786095e-06,
2225
+ "loss": 0.0124,
2226
+ "reward": 7.369345664978027,
2227
+ "reward_std": 2.027414560317993,
2228
+ "rewards/reward_correctness": 0.875,
2229
+ "rewards/reward_em_chunk": 0.875,
2230
+ "rewards/reward_format": 1.0,
2231
+ "rewards/reward_search_diversity": 0.11934606730937958,
2232
+ "rewards/reward_search_strategy": 0.875,
2233
+ "step": 139
2234
+ },
2235
+ {
2236
+ "completion_length": 430.375,
2237
+ "epoch": 0.48951048951048953,
2238
+ "grad_norm": 1.3875221014022827,
2239
+ "kl": 0.1299194097518921,
2240
+ "learning_rate": 4.975670171853926e-06,
2241
+ "loss": 0.0052,
2242
+ "reward": 4.600214958190918,
2243
+ "reward_std": 3.4139461517333984,
2244
+ "rewards/reward_correctness": 0.5,
2245
+ "rewards/reward_em_chunk": 0.0,
2246
+ "rewards/reward_format": 0.75,
2247
+ "rewards/reward_search_diversity": 0.4752153754234314,
2248
+ "rewards/reward_search_strategy": 0.625,
2249
+ "step": 140
2250
+ },
2251
+ {
2252
+ "completion_length": 619.375,
2253
+ "epoch": 0.493006993006993,
2254
+ "grad_norm": 1.2012630701065063,
2255
+ "kl": 0.07434721291065216,
2256
+ "learning_rate": 4.974440577269473e-06,
2257
+ "loss": 0.003,
2258
+ "reward": 3.8403759002685547,
2259
+ "reward_std": 2.251944065093994,
2260
+ "rewards/reward_correctness": 0.125,
2261
+ "rewards/reward_em_chunk": 0.625,
2262
+ "rewards/reward_format": 0.875,
2263
+ "rewards/reward_search_diversity": 0.34037598967552185,
2264
+ "rewards/reward_search_strategy": 0.625,
2265
+ "step": 141
2266
+ },
2267
+ {
2268
+ "completion_length": 662.0,
2269
+ "epoch": 0.4965034965034965,
2270
+ "grad_norm": 0.4479227066040039,
2271
+ "kl": 0.08045605570077896,
2272
+ "learning_rate": 4.973180832407471e-06,
2273
+ "loss": 0.0032,
2274
+ "reward": 4.356062889099121,
2275
+ "reward_std": 1.873792052268982,
2276
+ "rewards/reward_correctness": 0.125,
2277
+ "rewards/reward_em_chunk": 0.75,
2278
+ "rewards/reward_format": 1.0,
2279
+ "rewards/reward_search_diversity": 0.6060628294944763,
2280
+ "rewards/reward_search_strategy": 0.5,
2281
+ "step": 142
2282
+ },
2283
+ {
2284
+ "completion_length": 408.0,
2285
+ "epoch": 0.5,
2286
+ "grad_norm": 0.774638831615448,
2287
+ "kl": 0.16293062269687653,
2288
+ "learning_rate": 4.971890952617515e-06,
2289
+ "loss": 0.0065,
2290
+ "reward": 3.544522762298584,
2291
+ "reward_std": 3.194159507751465,
2292
+ "rewards/reward_correctness": 0.375,
2293
+ "rewards/reward_em_chunk": 0.625,
2294
+ "rewards/reward_format": 0.375,
2295
+ "rewards/reward_search_diversity": 0.31952300667762756,
2296
+ "rewards/reward_search_strategy": 0.3500000238418579,
2297
+ "step": 143
2298
+ },
2299
+ {
2300
+ "completion_length": 466.75,
2301
+ "epoch": 0.5034965034965035,
2302
+ "grad_norm": 0.8625693917274475,
2303
+ "kl": 0.10907953977584839,
2304
+ "learning_rate": 4.970570953616383e-06,
2305
+ "loss": 0.0044,
2306
+ "reward": 3.3587875366210938,
2307
+ "reward_std": 2.7467174530029297,
2308
+ "rewards/reward_correctness": 0.25,
2309
+ "rewards/reward_em_chunk": 0.875,
2310
+ "rewards/reward_format": 0.375,
2311
+ "rewards/reward_search_diversity": 0.3837875723838806,
2312
+ "rewards/reward_search_strategy": 0.3500000238418579,
2313
+ "step": 144
2314
+ },
2315
+ {
2316
+ "completion_length": 856.125,
2317
+ "epoch": 0.506993006993007,
2318
+ "grad_norm": 0.37043091654777527,
2319
+ "kl": 0.05690326541662216,
2320
+ "learning_rate": 4.9692208514878445e-06,
2321
+ "loss": 0.0023,
2322
+ "reward": 5.424896240234375,
2323
+ "reward_std": 2.465031862258911,
2324
+ "rewards/reward_correctness": 0.375,
2325
+ "rewards/reward_em_chunk": 0.875,
2326
+ "rewards/reward_format": 0.875,
2327
+ "rewards/reward_search_diversity": 0.49989593029022217,
2328
+ "rewards/reward_search_strategy": 0.7999999523162842,
2329
+ "step": 145
2330
+ },
2331
+ {
2332
+ "completion_length": 557.25,
2333
+ "epoch": 0.5104895104895105,
2334
+ "grad_norm": 0.8445433378219604,
2335
+ "kl": 0.06749890744686127,
2336
+ "learning_rate": 4.96784066268247e-06,
2337
+ "loss": 0.0027,
2338
+ "reward": 2.7921762466430664,
2339
+ "reward_std": 1.2953386306762695,
2340
+ "rewards/reward_correctness": 0.0,
2341
+ "rewards/reward_em_chunk": 0.125,
2342
+ "rewards/reward_format": 0.75,
2343
+ "rewards/reward_search_diversity": 0.5421763062477112,
2344
+ "rewards/reward_search_strategy": 0.625,
2345
+ "step": 146
2346
+ },
2347
+ {
2348
+ "completion_length": 447.5,
2349
+ "epoch": 0.513986013986014,
2350
+ "grad_norm": 0.9278783798217773,
2351
+ "kl": 0.10697238147258759,
2352
+ "learning_rate": 4.966430404017424e-06,
2353
+ "loss": 0.0043,
2354
+ "reward": 3.9682509899139404,
2355
+ "reward_std": 3.156663417816162,
2356
+ "rewards/reward_correctness": 0.25,
2357
+ "rewards/reward_em_chunk": 0.875,
2358
+ "rewards/reward_format": 0.625,
2359
+ "rewards/reward_search_diversity": 0.41825127601623535,
2360
+ "rewards/reward_search_strategy": 0.42500001192092896,
2361
+ "step": 147
2362
+ },
2363
+ {
2364
+ "completion_length": 379.625,
2365
+ "epoch": 0.5174825174825175,
2366
+ "grad_norm": 1.5938533544540405,
2367
+ "kl": 0.11513354629278183,
2368
+ "learning_rate": 4.964990092676263e-06,
2369
+ "loss": 0.0046,
2370
+ "reward": 3.4113523960113525,
2371
+ "reward_std": 2.4409544467926025,
2372
+ "rewards/reward_correctness": 0.125,
2373
+ "rewards/reward_em_chunk": 0.875,
2374
+ "rewards/reward_format": 0.625,
2375
+ "rewards/reward_search_diversity": 0.2863525450229645,
2376
+ "rewards/reward_search_strategy": 0.5,
2377
+ "step": 148
2378
+ },
2379
+ {
2380
+ "completion_length": 411.875,
2381
+ "epoch": 0.5209790209790209,
2382
+ "grad_norm": 1.070616364479065,
2383
+ "kl": 0.2734951078891754,
2384
+ "learning_rate": 4.963519746208726e-06,
2385
+ "loss": 0.0109,
2386
+ "reward": 2.4380977153778076,
2387
+ "reward_std": 2.1429409980773926,
2388
+ "rewards/reward_correctness": 0.25,
2389
+ "rewards/reward_em_chunk": 0.625,
2390
+ "rewards/reward_format": 0.125,
2391
+ "rewards/reward_search_diversity": 0.363097608089447,
2392
+ "rewards/reward_search_strategy": 0.20000000298023224,
2393
+ "step": 149
2394
+ },
2395
+ {
2396
+ "completion_length": 355.75,
2397
+ "epoch": 0.5244755244755245,
2398
+ "grad_norm": 0.9825189113616943,
2399
+ "kl": 0.14074762165546417,
2400
+ "learning_rate": 4.962019382530521e-06,
2401
+ "loss": 0.0056,
2402
+ "reward": 6.416107177734375,
2403
+ "reward_std": 3.2488479614257812,
2404
+ "rewards/reward_correctness": 0.625,
2405
+ "rewards/reward_em_chunk": 1.0,
2406
+ "rewards/reward_format": 0.75,
2407
+ "rewards/reward_search_diversity": 0.6411075592041016,
2408
+ "rewards/reward_search_strategy": 0.7749999761581421,
2409
+ "step": 150
2410
+ }
2411
+ ],
2412
+ "logging_steps": 1,
2413
+ "max_steps": 1000,
2414
+ "num_input_tokens_seen": 0,
2415
+ "num_train_epochs": 4,
2416
+ "save_steps": 50,
2417
+ "stateful_callbacks": {
2418
+ "TrainerControl": {
2419
+ "args": {
2420
+ "should_epoch_stop": false,
2421
+ "should_evaluate": false,
2422
+ "should_log": false,
2423
+ "should_save": true,
2424
+ "should_training_stop": false
2425
+ },
2426
+ "attributes": {}
2427
+ }
2428
+ },
2429
+ "total_flos": 0.0,
2430
+ "train_batch_size": 8,
2431
+ "trial_name": null,
2432
+ "trial_params": null
2433
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5bc2ce9fdda7e038f3836e0b24edb51569455f9c88149bdac5d77d744168c8
3
+ size 6072
checkpoint-50/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/llama-3.2-3b-instruct-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 0.15.1
checkpoint-50/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "down_proj",
28
+ "gate_proj",
29
+ "o_proj",
30
+ "q_proj",
31
+ "k_proj",
32
+ "up_proj",
33
+ "v_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
checkpoint-50/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58ab977408816837a2c5ce794015458e5ef4c65efa7abaa0208b9e6e614eff9
3
+ size 778096664
checkpoint-50/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0a464066dafd530eb2aa984b161f47fa71bd271c9e359a198c829eb4ce14ef
3
+ size 395570868
checkpoint-50/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd3c8de6dfbe260ca7c74471738eab4bfed2b9dfafe57117ebc3407f516ad59e
3
+ size 14244
checkpoint-50/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b11cb3de8de7058f230fc2b6aa30f5bd7853edd07d1a171d6770dc706874789d
3
+ size 1064
checkpoint-50/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-50/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-50/tokenizer_config.json ADDED
@@ -0,0 +1,2067 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "added_tokens_decoder": {
4
+ "128000": {
5
+ "content": "<|begin_of_text|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "128001": {
13
+ "content": "<|end_of_text|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "128002": {
21
+ "content": "<|reserved_special_token_0|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "128003": {
29
+ "content": "<|reserved_special_token_1|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "128004": {
37
+ "content": "<|finetune_right_pad_id|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "128005": {
45
+ "content": "<|reserved_special_token_2|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "128006": {
53
+ "content": "<|start_header_id|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "128007": {
61
+ "content": "<|end_header_id|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "128008": {
69
+ "content": "<|eom_id|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "128009": {
77
+ "content": "<|eot_id|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "128010": {
85
+ "content": "<|python_tag|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128011": {
93
+ "content": "<|reserved_special_token_3|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "128012": {
101
+ "content": "<|reserved_special_token_4|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "128013": {
109
+ "content": "<|reserved_special_token_5|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "128014": {
117
+ "content": "<|reserved_special_token_6|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "128015": {
125
+ "content": "<|reserved_special_token_7|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "128016": {
133
+ "content": "<|reserved_special_token_8|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "128017": {
141
+ "content": "<|reserved_special_token_9|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "128018": {
149
+ "content": "<|reserved_special_token_10|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "128019": {
157
+ "content": "<|reserved_special_token_11|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "128020": {
165
+ "content": "<|reserved_special_token_12|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "128021": {
173
+ "content": "<|reserved_special_token_13|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "128022": {
181
+ "content": "<|reserved_special_token_14|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "128023": {
189
+ "content": "<|reserved_special_token_15|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "128024": {
197
+ "content": "<|reserved_special_token_16|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "128025": {
205
+ "content": "<|reserved_special_token_17|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "128026": {
213
+ "content": "<|reserved_special_token_18|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "128027": {
221
+ "content": "<|reserved_special_token_19|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "128028": {
229
+ "content": "<|reserved_special_token_20|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "128029": {
237
+ "content": "<|reserved_special_token_21|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "128030": {
245
+ "content": "<|reserved_special_token_22|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "128031": {
253
+ "content": "<|reserved_special_token_23|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "128032": {
261
+ "content": "<|reserved_special_token_24|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "128033": {
269
+ "content": "<|reserved_special_token_25|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "128034": {
277
+ "content": "<|reserved_special_token_26|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "128035": {
285
+ "content": "<|reserved_special_token_27|>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "128036": {
293
+ "content": "<|reserved_special_token_28|>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "128037": {
301
+ "content": "<|reserved_special_token_29|>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "128038": {
309
+ "content": "<|reserved_special_token_30|>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "128039": {
317
+ "content": "<|reserved_special_token_31|>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "128040": {
325
+ "content": "<|reserved_special_token_32|>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "128041": {
333
+ "content": "<|reserved_special_token_33|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "128042": {
341
+ "content": "<|reserved_special_token_34|>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "128043": {
349
+ "content": "<|reserved_special_token_35|>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "128044": {
357
+ "content": "<|reserved_special_token_36|>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "128045": {
365
+ "content": "<|reserved_special_token_37|>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "128046": {
373
+ "content": "<|reserved_special_token_38|>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "128047": {
381
+ "content": "<|reserved_special_token_39|>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "128048": {
389
+ "content": "<|reserved_special_token_40|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "128049": {
397
+ "content": "<|reserved_special_token_41|>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "128050": {
405
+ "content": "<|reserved_special_token_42|>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "128051": {
413
+ "content": "<|reserved_special_token_43|>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "128052": {
421
+ "content": "<|reserved_special_token_44|>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "128053": {
429
+ "content": "<|reserved_special_token_45|>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "128054": {
437
+ "content": "<|reserved_special_token_46|>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "128055": {
445
+ "content": "<|reserved_special_token_47|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "128056": {
453
+ "content": "<|reserved_special_token_48|>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "128057": {
461
+ "content": "<|reserved_special_token_49|>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "128058": {
469
+ "content": "<|reserved_special_token_50|>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "128059": {
477
+ "content": "<|reserved_special_token_51|>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "128060": {
485
+ "content": "<|reserved_special_token_52|>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "128061": {
493
+ "content": "<|reserved_special_token_53|>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "128062": {
501
+ "content": "<|reserved_special_token_54|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "128063": {
509
+ "content": "<|reserved_special_token_55|>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "128064": {
517
+ "content": "<|reserved_special_token_56|>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "128065": {
525
+ "content": "<|reserved_special_token_57|>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "128066": {
533
+ "content": "<|reserved_special_token_58|>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "128067": {
541
+ "content": "<|reserved_special_token_59|>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "128068": {
549
+ "content": "<|reserved_special_token_60|>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "128069": {
557
+ "content": "<|reserved_special_token_61|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "128070": {
565
+ "content": "<|reserved_special_token_62|>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "128071": {
573
+ "content": "<|reserved_special_token_63|>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "128072": {
581
+ "content": "<|reserved_special_token_64|>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "128073": {
589
+ "content": "<|reserved_special_token_65|>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "128074": {
597
+ "content": "<|reserved_special_token_66|>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "128075": {
605
+ "content": "<|reserved_special_token_67|>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "128076": {
613
+ "content": "<|reserved_special_token_68|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "128077": {
621
+ "content": "<|reserved_special_token_69|>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "128078": {
629
+ "content": "<|reserved_special_token_70|>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "128079": {
637
+ "content": "<|reserved_special_token_71|>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "128080": {
645
+ "content": "<|reserved_special_token_72|>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "128081": {
653
+ "content": "<|reserved_special_token_73|>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "128082": {
661
+ "content": "<|reserved_special_token_74|>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "128083": {
669
+ "content": "<|reserved_special_token_75|>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "128084": {
677
+ "content": "<|reserved_special_token_76|>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "128085": {
685
+ "content": "<|reserved_special_token_77|>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "128086": {
693
+ "content": "<|reserved_special_token_78|>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "128087": {
701
+ "content": "<|reserved_special_token_79|>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "128088": {
709
+ "content": "<|reserved_special_token_80|>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "128089": {
717
+ "content": "<|reserved_special_token_81|>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "128090": {
725
+ "content": "<|reserved_special_token_82|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "128091": {
733
+ "content": "<|reserved_special_token_83|>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "128092": {
741
+ "content": "<|reserved_special_token_84|>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "128093": {
749
+ "content": "<|reserved_special_token_85|>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "128094": {
757
+ "content": "<|reserved_special_token_86|>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "128095": {
765
+ "content": "<|reserved_special_token_87|>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "128096": {
773
+ "content": "<|reserved_special_token_88|>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "128097": {
781
+ "content": "<|reserved_special_token_89|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "128098": {
789
+ "content": "<|reserved_special_token_90|>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "128099": {
797
+ "content": "<|reserved_special_token_91|>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "128100": {
805
+ "content": "<|reserved_special_token_92|>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "128101": {
813
+ "content": "<|reserved_special_token_93|>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "128102": {
821
+ "content": "<|reserved_special_token_94|>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "128103": {
829
+ "content": "<|reserved_special_token_95|>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "128104": {
837
+ "content": "<|reserved_special_token_96|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": true
843
+ },
844
+ "128105": {
845
+ "content": "<|reserved_special_token_97|>",
846
+ "lstrip": false,
847
+ "normalized": false,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": true
851
+ },
852
+ "128106": {
853
+ "content": "<|reserved_special_token_98|>",
854
+ "lstrip": false,
855
+ "normalized": false,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": true
859
+ },
860
+ "128107": {
861
+ "content": "<|reserved_special_token_99|>",
862
+ "lstrip": false,
863
+ "normalized": false,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": true
867
+ },
868
+ "128108": {
869
+ "content": "<|reserved_special_token_100|>",
870
+ "lstrip": false,
871
+ "normalized": false,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": true
875
+ },
876
+ "128109": {
877
+ "content": "<|reserved_special_token_101|>",
878
+ "lstrip": false,
879
+ "normalized": false,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": true
883
+ },
884
+ "128110": {
885
+ "content": "<|reserved_special_token_102|>",
886
+ "lstrip": false,
887
+ "normalized": false,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": true
891
+ },
892
+ "128111": {
893
+ "content": "<|reserved_special_token_103|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": true
899
+ },
900
+ "128112": {
901
+ "content": "<|reserved_special_token_104|>",
902
+ "lstrip": false,
903
+ "normalized": false,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": true
907
+ },
908
+ "128113": {
909
+ "content": "<|reserved_special_token_105|>",
910
+ "lstrip": false,
911
+ "normalized": false,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": true
915
+ },
916
+ "128114": {
917
+ "content": "<|reserved_special_token_106|>",
918
+ "lstrip": false,
919
+ "normalized": false,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": true
923
+ },
924
+ "128115": {
925
+ "content": "<|reserved_special_token_107|>",
926
+ "lstrip": false,
927
+ "normalized": false,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": true
931
+ },
932
+ "128116": {
933
+ "content": "<|reserved_special_token_108|>",
934
+ "lstrip": false,
935
+ "normalized": false,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": true
939
+ },
940
+ "128117": {
941
+ "content": "<|reserved_special_token_109|>",
942
+ "lstrip": false,
943
+ "normalized": false,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": true
947
+ },
948
+ "128118": {
949
+ "content": "<|reserved_special_token_110|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": true
955
+ },
956
+ "128119": {
957
+ "content": "<|reserved_special_token_111|>",
958
+ "lstrip": false,
959
+ "normalized": false,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": true
963
+ },
964
+ "128120": {
965
+ "content": "<|reserved_special_token_112|>",
966
+ "lstrip": false,
967
+ "normalized": false,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": true
971
+ },
972
+ "128121": {
973
+ "content": "<|reserved_special_token_113|>",
974
+ "lstrip": false,
975
+ "normalized": false,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": true
979
+ },
980
+ "128122": {
981
+ "content": "<|reserved_special_token_114|>",
982
+ "lstrip": false,
983
+ "normalized": false,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": true
987
+ },
988
+ "128123": {
989
+ "content": "<|reserved_special_token_115|>",
990
+ "lstrip": false,
991
+ "normalized": false,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": true
995
+ },
996
+ "128124": {
997
+ "content": "<|reserved_special_token_116|>",
998
+ "lstrip": false,
999
+ "normalized": false,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": true
1003
+ },
1004
+ "128125": {
1005
+ "content": "<|reserved_special_token_117|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": true
1011
+ },
1012
+ "128126": {
1013
+ "content": "<|reserved_special_token_118|>",
1014
+ "lstrip": false,
1015
+ "normalized": false,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": true
1019
+ },
1020
+ "128127": {
1021
+ "content": "<|reserved_special_token_119|>",
1022
+ "lstrip": false,
1023
+ "normalized": false,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": true
1027
+ },
1028
+ "128128": {
1029
+ "content": "<|reserved_special_token_120|>",
1030
+ "lstrip": false,
1031
+ "normalized": false,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": true
1035
+ },
1036
+ "128129": {
1037
+ "content": "<|reserved_special_token_121|>",
1038
+ "lstrip": false,
1039
+ "normalized": false,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": true
1043
+ },
1044
+ "128130": {
1045
+ "content": "<|reserved_special_token_122|>",
1046
+ "lstrip": false,
1047
+ "normalized": false,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": true
1051
+ },
1052
+ "128131": {
1053
+ "content": "<|reserved_special_token_123|>",
1054
+ "lstrip": false,
1055
+ "normalized": false,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": true
1059
+ },
1060
+ "128132": {
1061
+ "content": "<|reserved_special_token_124|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": true
1067
+ },
1068
+ "128133": {
1069
+ "content": "<|reserved_special_token_125|>",
1070
+ "lstrip": false,
1071
+ "normalized": false,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": true
1075
+ },
1076
+ "128134": {
1077
+ "content": "<|reserved_special_token_126|>",
1078
+ "lstrip": false,
1079
+ "normalized": false,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": true
1083
+ },
1084
+ "128135": {
1085
+ "content": "<|reserved_special_token_127|>",
1086
+ "lstrip": false,
1087
+ "normalized": false,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": true
1091
+ },
1092
+ "128136": {
1093
+ "content": "<|reserved_special_token_128|>",
1094
+ "lstrip": false,
1095
+ "normalized": false,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": true
1099
+ },
1100
+ "128137": {
1101
+ "content": "<|reserved_special_token_129|>",
1102
+ "lstrip": false,
1103
+ "normalized": false,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": true
1107
+ },
1108
+ "128138": {
1109
+ "content": "<|reserved_special_token_130|>",
1110
+ "lstrip": false,
1111
+ "normalized": false,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": true
1115
+ },
1116
+ "128139": {
1117
+ "content": "<|reserved_special_token_131|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": true
1123
+ },
1124
+ "128140": {
1125
+ "content": "<|reserved_special_token_132|>",
1126
+ "lstrip": false,
1127
+ "normalized": false,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": true
1131
+ },
1132
+ "128141": {
1133
+ "content": "<|reserved_special_token_133|>",
1134
+ "lstrip": false,
1135
+ "normalized": false,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": true
1139
+ },
1140
+ "128142": {
1141
+ "content": "<|reserved_special_token_134|>",
1142
+ "lstrip": false,
1143
+ "normalized": false,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": true
1147
+ },
1148
+ "128143": {
1149
+ "content": "<|reserved_special_token_135|>",
1150
+ "lstrip": false,
1151
+ "normalized": false,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": true
1155
+ },
1156
+ "128144": {
1157
+ "content": "<|reserved_special_token_136|>",
1158
+ "lstrip": false,
1159
+ "normalized": false,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": true
1163
+ },
1164
+ "128145": {
1165
+ "content": "<|reserved_special_token_137|>",
1166
+ "lstrip": false,
1167
+ "normalized": false,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": true
1171
+ },
1172
+ "128146": {
1173
+ "content": "<|reserved_special_token_138|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": true
1179
+ },
1180
+ "128147": {
1181
+ "content": "<|reserved_special_token_139|>",
1182
+ "lstrip": false,
1183
+ "normalized": false,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": true
1187
+ },
1188
+ "128148": {
1189
+ "content": "<|reserved_special_token_140|>",
1190
+ "lstrip": false,
1191
+ "normalized": false,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": true
1195
+ },
1196
+ "128149": {
1197
+ "content": "<|reserved_special_token_141|>",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "128150": {
1205
+ "content": "<|reserved_special_token_142|>",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ },
1212
+ "128151": {
1213
+ "content": "<|reserved_special_token_143|>",
1214
+ "lstrip": false,
1215
+ "normalized": false,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": true
1219
+ },
1220
+ "128152": {
1221
+ "content": "<|reserved_special_token_144|>",
1222
+ "lstrip": false,
1223
+ "normalized": false,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": true
1227
+ },
1228
+ "128153": {
1229
+ "content": "<|reserved_special_token_145|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": true
1235
+ },
1236
+ "128154": {
1237
+ "content": "<|reserved_special_token_146|>",
1238
+ "lstrip": false,
1239
+ "normalized": false,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": true
1243
+ },
1244
+ "128155": {
1245
+ "content": "<|reserved_special_token_147|>",
1246
+ "lstrip": false,
1247
+ "normalized": false,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": true
1251
+ },
1252
+ "128156": {
1253
+ "content": "<|reserved_special_token_148|>",
1254
+ "lstrip": false,
1255
+ "normalized": false,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": true
1259
+ },
1260
+ "128157": {
1261
+ "content": "<|reserved_special_token_149|>",
1262
+ "lstrip": false,
1263
+ "normalized": false,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": true
1267
+ },
1268
+ "128158": {
1269
+ "content": "<|reserved_special_token_150|>",
1270
+ "lstrip": false,
1271
+ "normalized": false,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": true
1275
+ },
1276
+ "128159": {
1277
+ "content": "<|reserved_special_token_151|>",
1278
+ "lstrip": false,
1279
+ "normalized": false,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": true
1283
+ },
1284
+ "128160": {
1285
+ "content": "<|reserved_special_token_152|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": true
1291
+ },
1292
+ "128161": {
1293
+ "content": "<|reserved_special_token_153|>",
1294
+ "lstrip": false,
1295
+ "normalized": false,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": true
1299
+ },
1300
+ "128162": {
1301
+ "content": "<|reserved_special_token_154|>",
1302
+ "lstrip": false,
1303
+ "normalized": false,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": true
1307
+ },
1308
+ "128163": {
1309
+ "content": "<|reserved_special_token_155|>",
1310
+ "lstrip": false,
1311
+ "normalized": false,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": true
1315
+ },
1316
+ "128164": {
1317
+ "content": "<|reserved_special_token_156|>",
1318
+ "lstrip": false,
1319
+ "normalized": false,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": true
1323
+ },
1324
+ "128165": {
1325
+ "content": "<|reserved_special_token_157|>",
1326
+ "lstrip": false,
1327
+ "normalized": false,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": true
1331
+ },
1332
+ "128166": {
1333
+ "content": "<|reserved_special_token_158|>",
1334
+ "lstrip": false,
1335
+ "normalized": false,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": true
1339
+ },
1340
+ "128167": {
1341
+ "content": "<|reserved_special_token_159|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": true
1347
+ },
1348
+ "128168": {
1349
+ "content": "<|reserved_special_token_160|>",
1350
+ "lstrip": false,
1351
+ "normalized": false,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": true
1355
+ },
1356
+ "128169": {
1357
+ "content": "<|reserved_special_token_161|>",
1358
+ "lstrip": false,
1359
+ "normalized": false,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": true
1363
+ },
1364
+ "128170": {
1365
+ "content": "<|reserved_special_token_162|>",
1366
+ "lstrip": false,
1367
+ "normalized": false,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": true
1371
+ },
1372
+ "128171": {
1373
+ "content": "<|reserved_special_token_163|>",
1374
+ "lstrip": false,
1375
+ "normalized": false,
1376
+ "rstrip": false,
1377
+ "single_word": false,
1378
+ "special": true
1379
+ },
1380
+ "128172": {
1381
+ "content": "<|reserved_special_token_164|>",
1382
+ "lstrip": false,
1383
+ "normalized": false,
1384
+ "rstrip": false,
1385
+ "single_word": false,
1386
+ "special": true
1387
+ },
1388
+ "128173": {
1389
+ "content": "<|reserved_special_token_165|>",
1390
+ "lstrip": false,
1391
+ "normalized": false,
1392
+ "rstrip": false,
1393
+ "single_word": false,
1394
+ "special": true
1395
+ },
1396
+ "128174": {
1397
+ "content": "<|reserved_special_token_166|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false,
1402
+ "special": true
1403
+ },
1404
+ "128175": {
1405
+ "content": "<|reserved_special_token_167|>",
1406
+ "lstrip": false,
1407
+ "normalized": false,
1408
+ "rstrip": false,
1409
+ "single_word": false,
1410
+ "special": true
1411
+ },
1412
+ "128176": {
1413
+ "content": "<|reserved_special_token_168|>",
1414
+ "lstrip": false,
1415
+ "normalized": false,
1416
+ "rstrip": false,
1417
+ "single_word": false,
1418
+ "special": true
1419
+ },
1420
+ "128177": {
1421
+ "content": "<|reserved_special_token_169|>",
1422
+ "lstrip": false,
1423
+ "normalized": false,
1424
+ "rstrip": false,
1425
+ "single_word": false,
1426
+ "special": true
1427
+ },
1428
+ "128178": {
1429
+ "content": "<|reserved_special_token_170|>",
1430
+ "lstrip": false,
1431
+ "normalized": false,
1432
+ "rstrip": false,
1433
+ "single_word": false,
1434
+ "special": true
1435
+ },
1436
+ "128179": {
1437
+ "content": "<|reserved_special_token_171|>",
1438
+ "lstrip": false,
1439
+ "normalized": false,
1440
+ "rstrip": false,
1441
+ "single_word": false,
1442
+ "special": true
1443
+ },
1444
+ "128180": {
1445
+ "content": "<|reserved_special_token_172|>",
1446
+ "lstrip": false,
1447
+ "normalized": false,
1448
+ "rstrip": false,
1449
+ "single_word": false,
1450
+ "special": true
1451
+ },
1452
+ "128181": {
1453
+ "content": "<|reserved_special_token_173|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false,
1458
+ "special": true
1459
+ },
1460
+ "128182": {
1461
+ "content": "<|reserved_special_token_174|>",
1462
+ "lstrip": false,
1463
+ "normalized": false,
1464
+ "rstrip": false,
1465
+ "single_word": false,
1466
+ "special": true
1467
+ },
1468
+ "128183": {
1469
+ "content": "<|reserved_special_token_175|>",
1470
+ "lstrip": false,
1471
+ "normalized": false,
1472
+ "rstrip": false,
1473
+ "single_word": false,
1474
+ "special": true
1475
+ },
1476
+ "128184": {
1477
+ "content": "<|reserved_special_token_176|>",
1478
+ "lstrip": false,
1479
+ "normalized": false,
1480
+ "rstrip": false,
1481
+ "single_word": false,
1482
+ "special": true
1483
+ },
1484
+ "128185": {
1485
+ "content": "<|reserved_special_token_177|>",
1486
+ "lstrip": false,
1487
+ "normalized": false,
1488
+ "rstrip": false,
1489
+ "single_word": false,
1490
+ "special": true
1491
+ },
1492
+ "128186": {
1493
+ "content": "<|reserved_special_token_178|>",
1494
+ "lstrip": false,
1495
+ "normalized": false,
1496
+ "rstrip": false,
1497
+ "single_word": false,
1498
+ "special": true
1499
+ },
1500
+ "128187": {
1501
+ "content": "<|reserved_special_token_179|>",
1502
+ "lstrip": false,
1503
+ "normalized": false,
1504
+ "rstrip": false,
1505
+ "single_word": false,
1506
+ "special": true
1507
+ },
1508
+ "128188": {
1509
+ "content": "<|reserved_special_token_180|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false,
1514
+ "special": true
1515
+ },
1516
+ "128189": {
1517
+ "content": "<|reserved_special_token_181|>",
1518
+ "lstrip": false,
1519
+ "normalized": false,
1520
+ "rstrip": false,
1521
+ "single_word": false,
1522
+ "special": true
1523
+ },
1524
+ "128190": {
1525
+ "content": "<|reserved_special_token_182|>",
1526
+ "lstrip": false,
1527
+ "normalized": false,
1528
+ "rstrip": false,
1529
+ "single_word": false,
1530
+ "special": true
1531
+ },
1532
+ "128191": {
1533
+ "content": "<|reserved_special_token_183|>",
1534
+ "lstrip": false,
1535
+ "normalized": false,
1536
+ "rstrip": false,
1537
+ "single_word": false,
1538
+ "special": true
1539
+ },
1540
+ "128192": {
1541
+ "content": "<|reserved_special_token_184|>",
1542
+ "lstrip": false,
1543
+ "normalized": false,
1544
+ "rstrip": false,
1545
+ "single_word": false,
1546
+ "special": true
1547
+ },
1548
+ "128193": {
1549
+ "content": "<|reserved_special_token_185|>",
1550
+ "lstrip": false,
1551
+ "normalized": false,
1552
+ "rstrip": false,
1553
+ "single_word": false,
1554
+ "special": true
1555
+ },
1556
+ "128194": {
1557
+ "content": "<|reserved_special_token_186|>",
1558
+ "lstrip": false,
1559
+ "normalized": false,
1560
+ "rstrip": false,
1561
+ "single_word": false,
1562
+ "special": true
1563
+ },
1564
+ "128195": {
1565
+ "content": "<|reserved_special_token_187|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false,
1570
+ "special": true
1571
+ },
1572
+ "128196": {
1573
+ "content": "<|reserved_special_token_188|>",
1574
+ "lstrip": false,
1575
+ "normalized": false,
1576
+ "rstrip": false,
1577
+ "single_word": false,
1578
+ "special": true
1579
+ },
1580
+ "128197": {
1581
+ "content": "<|reserved_special_token_189|>",
1582
+ "lstrip": false,
1583
+ "normalized": false,
1584
+ "rstrip": false,
1585
+ "single_word": false,
1586
+ "special": true
1587
+ },
1588
+ "128198": {
1589
+ "content": "<|reserved_special_token_190|>",
1590
+ "lstrip": false,
1591
+ "normalized": false,
1592
+ "rstrip": false,
1593
+ "single_word": false,
1594
+ "special": true
1595
+ },
1596
+ "128199": {
1597
+ "content": "<|reserved_special_token_191|>",
1598
+ "lstrip": false,
1599
+ "normalized": false,
1600
+ "rstrip": false,
1601
+ "single_word": false,
1602
+ "special": true
1603
+ },
1604
+ "128200": {
1605
+ "content": "<|reserved_special_token_192|>",
1606
+ "lstrip": false,
1607
+ "normalized": false,
1608
+ "rstrip": false,
1609
+ "single_word": false,
1610
+ "special": true
1611
+ },
1612
+ "128201": {
1613
+ "content": "<|reserved_special_token_193|>",
1614
+ "lstrip": false,
1615
+ "normalized": false,
1616
+ "rstrip": false,
1617
+ "single_word": false,
1618
+ "special": true
1619
+ },
1620
+ "128202": {
1621
+ "content": "<|reserved_special_token_194|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false,
1626
+ "special": true
1627
+ },
1628
+ "128203": {
1629
+ "content": "<|reserved_special_token_195|>",
1630
+ "lstrip": false,
1631
+ "normalized": false,
1632
+ "rstrip": false,
1633
+ "single_word": false,
1634
+ "special": true
1635
+ },
1636
+ "128204": {
1637
+ "content": "<|reserved_special_token_196|>",
1638
+ "lstrip": false,
1639
+ "normalized": false,
1640
+ "rstrip": false,
1641
+ "single_word": false,
1642
+ "special": true
1643
+ },
1644
+ "128205": {
1645
+ "content": "<|reserved_special_token_197|>",
1646
+ "lstrip": false,
1647
+ "normalized": false,
1648
+ "rstrip": false,
1649
+ "single_word": false,
1650
+ "special": true
1651
+ },
1652
+ "128206": {
1653
+ "content": "<|reserved_special_token_198|>",
1654
+ "lstrip": false,
1655
+ "normalized": false,
1656
+ "rstrip": false,
1657
+ "single_word": false,
1658
+ "special": true
1659
+ },
1660
+ "128207": {
1661
+ "content": "<|reserved_special_token_199|>",
1662
+ "lstrip": false,
1663
+ "normalized": false,
1664
+ "rstrip": false,
1665
+ "single_word": false,
1666
+ "special": true
1667
+ },
1668
+ "128208": {
1669
+ "content": "<|reserved_special_token_200|>",
1670
+ "lstrip": false,
1671
+ "normalized": false,
1672
+ "rstrip": false,
1673
+ "single_word": false,
1674
+ "special": true
1675
+ },
1676
+ "128209": {
1677
+ "content": "<|reserved_special_token_201|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false,
1682
+ "special": true
1683
+ },
1684
+ "128210": {
1685
+ "content": "<|reserved_special_token_202|>",
1686
+ "lstrip": false,
1687
+ "normalized": false,
1688
+ "rstrip": false,
1689
+ "single_word": false,
1690
+ "special": true
1691
+ },
1692
+ "128211": {
1693
+ "content": "<|reserved_special_token_203|>",
1694
+ "lstrip": false,
1695
+ "normalized": false,
1696
+ "rstrip": false,
1697
+ "single_word": false,
1698
+ "special": true
1699
+ },
1700
+ "128212": {
1701
+ "content": "<|reserved_special_token_204|>",
1702
+ "lstrip": false,
1703
+ "normalized": false,
1704
+ "rstrip": false,
1705
+ "single_word": false,
1706
+ "special": true
1707
+ },
1708
+ "128213": {
1709
+ "content": "<|reserved_special_token_205|>",
1710
+ "lstrip": false,
1711
+ "normalized": false,
1712
+ "rstrip": false,
1713
+ "single_word": false,
1714
+ "special": true
1715
+ },
1716
+ "128214": {
1717
+ "content": "<|reserved_special_token_206|>",
1718
+ "lstrip": false,
1719
+ "normalized": false,
1720
+ "rstrip": false,
1721
+ "single_word": false,
1722
+ "special": true
1723
+ },
1724
+ "128215": {
1725
+ "content": "<|reserved_special_token_207|>",
1726
+ "lstrip": false,
1727
+ "normalized": false,
1728
+ "rstrip": false,
1729
+ "single_word": false,
1730
+ "special": true
1731
+ },
1732
+ "128216": {
1733
+ "content": "<|reserved_special_token_208|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false,
1738
+ "special": true
1739
+ },
1740
+ "128217": {
1741
+ "content": "<|reserved_special_token_209|>",
1742
+ "lstrip": false,
1743
+ "normalized": false,
1744
+ "rstrip": false,
1745
+ "single_word": false,
1746
+ "special": true
1747
+ },
1748
+ "128218": {
1749
+ "content": "<|reserved_special_token_210|>",
1750
+ "lstrip": false,
1751
+ "normalized": false,
1752
+ "rstrip": false,
1753
+ "single_word": false,
1754
+ "special": true
1755
+ },
1756
+ "128219": {
1757
+ "content": "<|reserved_special_token_211|>",
1758
+ "lstrip": false,
1759
+ "normalized": false,
1760
+ "rstrip": false,
1761
+ "single_word": false,
1762
+ "special": true
1763
+ },
1764
+ "128220": {
1765
+ "content": "<|reserved_special_token_212|>",
1766
+ "lstrip": false,
1767
+ "normalized": false,
1768
+ "rstrip": false,
1769
+ "single_word": false,
1770
+ "special": true
1771
+ },
1772
+ "128221": {
1773
+ "content": "<|reserved_special_token_213|>",
1774
+ "lstrip": false,
1775
+ "normalized": false,
1776
+ "rstrip": false,
1777
+ "single_word": false,
1778
+ "special": true
1779
+ },
1780
+ "128222": {
1781
+ "content": "<|reserved_special_token_214|>",
1782
+ "lstrip": false,
1783
+ "normalized": false,
1784
+ "rstrip": false,
1785
+ "single_word": false,
1786
+ "special": true
1787
+ },
1788
+ "128223": {
1789
+ "content": "<|reserved_special_token_215|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false,
1794
+ "special": true
1795
+ },
1796
+ "128224": {
1797
+ "content": "<|reserved_special_token_216|>",
1798
+ "lstrip": false,
1799
+ "normalized": false,
1800
+ "rstrip": false,
1801
+ "single_word": false,
1802
+ "special": true
1803
+ },
1804
+ "128225": {
1805
+ "content": "<|reserved_special_token_217|>",
1806
+ "lstrip": false,
1807
+ "normalized": false,
1808
+ "rstrip": false,
1809
+ "single_word": false,
1810
+ "special": true
1811
+ },
1812
+ "128226": {
1813
+ "content": "<|reserved_special_token_218|>",
1814
+ "lstrip": false,
1815
+ "normalized": false,
1816
+ "rstrip": false,
1817
+ "single_word": false,
1818
+ "special": true
1819
+ },
1820
+ "128227": {
1821
+ "content": "<|reserved_special_token_219|>",
1822
+ "lstrip": false,
1823
+ "normalized": false,
1824
+ "rstrip": false,
1825
+ "single_word": false,
1826
+ "special": true
1827
+ },
1828
+ "128228": {
1829
+ "content": "<|reserved_special_token_220|>",
1830
+ "lstrip": false,
1831
+ "normalized": false,
1832
+ "rstrip": false,
1833
+ "single_word": false,
1834
+ "special": true
1835
+ },
1836
+ "128229": {
1837
+ "content": "<|reserved_special_token_221|>",
1838
+ "lstrip": false,
1839
+ "normalized": false,
1840
+ "rstrip": false,
1841
+ "single_word": false,
1842
+ "special": true
1843
+ },
1844
+ "128230": {
1845
+ "content": "<|reserved_special_token_222|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false,
1850
+ "special": true
1851
+ },
1852
+ "128231": {
1853
+ "content": "<|reserved_special_token_223|>",
1854
+ "lstrip": false,
1855
+ "normalized": false,
1856
+ "rstrip": false,
1857
+ "single_word": false,
1858
+ "special": true
1859
+ },
1860
+ "128232": {
1861
+ "content": "<|reserved_special_token_224|>",
1862
+ "lstrip": false,
1863
+ "normalized": false,
1864
+ "rstrip": false,
1865
+ "single_word": false,
1866
+ "special": true
1867
+ },
1868
+ "128233": {
1869
+ "content": "<|reserved_special_token_225|>",
1870
+ "lstrip": false,
1871
+ "normalized": false,
1872
+ "rstrip": false,
1873
+ "single_word": false,
1874
+ "special": true
1875
+ },
1876
+ "128234": {
1877
+ "content": "<|reserved_special_token_226|>",
1878
+ "lstrip": false,
1879
+ "normalized": false,
1880
+ "rstrip": false,
1881
+ "single_word": false,
1882
+ "special": true
1883
+ },
1884
+ "128235": {
1885
+ "content": "<|reserved_special_token_227|>",
1886
+ "lstrip": false,
1887
+ "normalized": false,
1888
+ "rstrip": false,
1889
+ "single_word": false,
1890
+ "special": true
1891
+ },
1892
+ "128236": {
1893
+ "content": "<|reserved_special_token_228|>",
1894
+ "lstrip": false,
1895
+ "normalized": false,
1896
+ "rstrip": false,
1897
+ "single_word": false,
1898
+ "special": true
1899
+ },
1900
+ "128237": {
1901
+ "content": "<|reserved_special_token_229|>",
1902
+ "lstrip": false,
1903
+ "normalized": false,
1904
+ "rstrip": false,
1905
+ "single_word": false,
1906
+ "special": true
1907
+ },
1908
+ "128238": {
1909
+ "content": "<|reserved_special_token_230|>",
1910
+ "lstrip": false,
1911
+ "normalized": false,
1912
+ "rstrip": false,
1913
+ "single_word": false,
1914
+ "special": true
1915
+ },
1916
+ "128239": {
1917
+ "content": "<|reserved_special_token_231|>",
1918
+ "lstrip": false,
1919
+ "normalized": false,
1920
+ "rstrip": false,
1921
+ "single_word": false,
1922
+ "special": true
1923
+ },
1924
+ "128240": {
1925
+ "content": "<|reserved_special_token_232|>",
1926
+ "lstrip": false,
1927
+ "normalized": false,
1928
+ "rstrip": false,
1929
+ "single_word": false,
1930
+ "special": true
1931
+ },
1932
+ "128241": {
1933
+ "content": "<|reserved_special_token_233|>",
1934
+ "lstrip": false,
1935
+ "normalized": false,
1936
+ "rstrip": false,
1937
+ "single_word": false,
1938
+ "special": true
1939
+ },
1940
+ "128242": {
1941
+ "content": "<|reserved_special_token_234|>",
1942
+ "lstrip": false,
1943
+ "normalized": false,
1944
+ "rstrip": false,
1945
+ "single_word": false,
1946
+ "special": true
1947
+ },
1948
+ "128243": {
1949
+ "content": "<|reserved_special_token_235|>",
1950
+ "lstrip": false,
1951
+ "normalized": false,
1952
+ "rstrip": false,
1953
+ "single_word": false,
1954
+ "special": true
1955
+ },
1956
+ "128244": {
1957
+ "content": "<|reserved_special_token_236|>",
1958
+ "lstrip": false,
1959
+ "normalized": false,
1960
+ "rstrip": false,
1961
+ "single_word": false,
1962
+ "special": true
1963
+ },
1964
+ "128245": {
1965
+ "content": "<|reserved_special_token_237|>",
1966
+ "lstrip": false,
1967
+ "normalized": false,
1968
+ "rstrip": false,
1969
+ "single_word": false,
1970
+ "special": true
1971
+ },
1972
+ "128246": {
1973
+ "content": "<|reserved_special_token_238|>",
1974
+ "lstrip": false,
1975
+ "normalized": false,
1976
+ "rstrip": false,
1977
+ "single_word": false,
1978
+ "special": true
1979
+ },
1980
+ "128247": {
1981
+ "content": "<|reserved_special_token_239|>",
1982
+ "lstrip": false,
1983
+ "normalized": false,
1984
+ "rstrip": false,
1985
+ "single_word": false,
1986
+ "special": true
1987
+ },
1988
+ "128248": {
1989
+ "content": "<|reserved_special_token_240|>",
1990
+ "lstrip": false,
1991
+ "normalized": false,
1992
+ "rstrip": false,
1993
+ "single_word": false,
1994
+ "special": true
1995
+ },
1996
+ "128249": {
1997
+ "content": "<|reserved_special_token_241|>",
1998
+ "lstrip": false,
1999
+ "normalized": false,
2000
+ "rstrip": false,
2001
+ "single_word": false,
2002
+ "special": true
2003
+ },
2004
+ "128250": {
2005
+ "content": "<|reserved_special_token_242|>",
2006
+ "lstrip": false,
2007
+ "normalized": false,
2008
+ "rstrip": false,
2009
+ "single_word": false,
2010
+ "special": true
2011
+ },
2012
+ "128251": {
2013
+ "content": "<|reserved_special_token_243|>",
2014
+ "lstrip": false,
2015
+ "normalized": false,
2016
+ "rstrip": false,
2017
+ "single_word": false,
2018
+ "special": true
2019
+ },
2020
+ "128252": {
2021
+ "content": "<|reserved_special_token_244|>",
2022
+ "lstrip": false,
2023
+ "normalized": false,
2024
+ "rstrip": false,
2025
+ "single_word": false,
2026
+ "special": true
2027
+ },
2028
+ "128253": {
2029
+ "content": "<|reserved_special_token_245|>",
2030
+ "lstrip": false,
2031
+ "normalized": false,
2032
+ "rstrip": false,
2033
+ "single_word": false,
2034
+ "special": true
2035
+ },
2036
+ "128254": {
2037
+ "content": "<|reserved_special_token_246|>",
2038
+ "lstrip": false,
2039
+ "normalized": false,
2040
+ "rstrip": false,
2041
+ "single_word": false,
2042
+ "special": true
2043
+ },
2044
+ "128255": {
2045
+ "content": "<|reserved_special_token_247|>",
2046
+ "lstrip": false,
2047
+ "normalized": false,
2048
+ "rstrip": false,
2049
+ "single_word": false,
2050
+ "special": true
2051
+ }
2052
+ },
2053
+ "bos_token": "<|begin_of_text|>",
2054
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2055
+ "clean_up_tokenization_spaces": true,
2056
+ "eos_token": "<|eot_id|>",
2057
+ "extra_special_tokens": {},
2058
+ "model_input_names": [
2059
+ "input_ids",
2060
+ "attention_mask"
2061
+ ],
2062
+ "model_max_length": 131072,
2063
+ "pad_token": "<|finetune_right_pad_id|>",
2064
+ "padding_side": "right",
2065
+ "tokenizer_class": "PreTrainedTokenizer",
2066
+ "unk_token": null
2067
+ }
checkpoint-50/trainer_state.json ADDED
@@ -0,0 +1,833 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.17482517482517482,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
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": 145.875,
13
+ "epoch": 0.0034965034965034965,
14
+ "grad_norm": 8.602514266967773,
15
+ "kl": 0.0,
16
+ "learning_rate": 5.0000000000000004e-08,
17
+ "loss": 0.0,
18
+ "reward": 0.7051772475242615,
19
+ "reward_std": 0.8263505697250366,
20
+ "rewards/reward_correctness": 0.0,
21
+ "rewards/reward_em_chunk": 0.375,
22
+ "rewards/reward_format": 0.0,
23
+ "rewards/reward_search_diversity": 0.3301772475242615,
24
+ "rewards/reward_search_strategy": 0.0,
25
+ "step": 1
26
+ },
27
+ {
28
+ "completion_length": 88.125,
29
+ "epoch": 0.006993006993006993,
30
+ "grad_norm": 1.4985997676849365,
31
+ "kl": 0.0,
32
+ "learning_rate": 1.0000000000000001e-07,
33
+ "loss": -0.0,
34
+ "reward": 1.8388628959655762,
35
+ "reward_std": 2.5329272747039795,
36
+ "rewards/reward_correctness": 0.25,
37
+ "rewards/reward_em_chunk": 0.5,
38
+ "rewards/reward_format": 0.0,
39
+ "rewards/reward_search_diversity": 0.2388630509376526,
40
+ "rewards/reward_search_strategy": 0.10000000149011612,
41
+ "step": 2
42
+ },
43
+ {
44
+ "completion_length": 296.5,
45
+ "epoch": 0.01048951048951049,
46
+ "grad_norm": 0.7674520611763,
47
+ "kl": 0.0006381775019690394,
48
+ "learning_rate": 1.5000000000000002e-07,
49
+ "loss": 0.0,
50
+ "reward": 1.654070258140564,
51
+ "reward_std": 2.827007532119751,
52
+ "rewards/reward_correctness": 0.125,
53
+ "rewards/reward_em_chunk": 0.5,
54
+ "rewards/reward_format": 0.125,
55
+ "rewards/reward_search_diversity": 0.17907029390335083,
56
+ "rewards/reward_search_strategy": 0.22499999403953552,
57
+ "step": 3
58
+ },
59
+ {
60
+ "completion_length": 290.125,
61
+ "epoch": 0.013986013986013986,
62
+ "grad_norm": 1.0457236766815186,
63
+ "kl": 0.0007995082996785641,
64
+ "learning_rate": 2.0000000000000002e-07,
65
+ "loss": 0.0,
66
+ "reward": 3.421433448791504,
67
+ "reward_std": 2.9866631031036377,
68
+ "rewards/reward_correctness": 0.5,
69
+ "rewards/reward_em_chunk": 0.0,
70
+ "rewards/reward_format": 0.375,
71
+ "rewards/reward_search_diversity": 0.396433562040329,
72
+ "rewards/reward_search_strategy": 0.2750000059604645,
73
+ "step": 4
74
+ },
75
+ {
76
+ "completion_length": 259.125,
77
+ "epoch": 0.017482517482517484,
78
+ "grad_norm": 1.3121755123138428,
79
+ "kl": 0.000728036102373153,
80
+ "learning_rate": 2.5000000000000004e-07,
81
+ "loss": 0.0,
82
+ "reward": 0.9268761873245239,
83
+ "reward_std": 0.7560767531394958,
84
+ "rewards/reward_correctness": 0.0,
85
+ "rewards/reward_em_chunk": 0.625,
86
+ "rewards/reward_format": 0.0,
87
+ "rewards/reward_search_diversity": 0.2268761545419693,
88
+ "rewards/reward_search_strategy": 0.07500000298023224,
89
+ "step": 5
90
+ },
91
+ {
92
+ "completion_length": 383.5,
93
+ "epoch": 0.02097902097902098,
94
+ "grad_norm": 0.9658453464508057,
95
+ "kl": 0.0007470359560102224,
96
+ "learning_rate": 3.0000000000000004e-07,
97
+ "loss": 0.0,
98
+ "reward": 1.4594597816467285,
99
+ "reward_std": 2.2520837783813477,
100
+ "rewards/reward_correctness": 0.25,
101
+ "rewards/reward_em_chunk": 0.125,
102
+ "rewards/reward_format": 0.0,
103
+ "rewards/reward_search_diversity": 0.25945988297462463,
104
+ "rewards/reward_search_strategy": 0.07500000298023224,
105
+ "step": 6
106
+ },
107
+ {
108
+ "completion_length": 144.375,
109
+ "epoch": 0.024475524475524476,
110
+ "grad_norm": 1.1642646789550781,
111
+ "kl": 0.0009361266857013106,
112
+ "learning_rate": 3.5000000000000004e-07,
113
+ "loss": 0.0,
114
+ "reward": 1.378964900970459,
115
+ "reward_std": 2.0963218212127686,
116
+ "rewards/reward_correctness": 0.25,
117
+ "rewards/reward_em_chunk": 0.0,
118
+ "rewards/reward_format": 0.0,
119
+ "rewards/reward_search_diversity": 0.30396491289138794,
120
+ "rewards/reward_search_strategy": 0.07500000298023224,
121
+ "step": 7
122
+ },
123
+ {
124
+ "completion_length": 314.375,
125
+ "epoch": 0.027972027972027972,
126
+ "grad_norm": 5.21930456161499,
127
+ "kl": 0.0008346753311343491,
128
+ "learning_rate": 4.0000000000000003e-07,
129
+ "loss": 0.0,
130
+ "reward": 1.181166410446167,
131
+ "reward_std": 1.6016024351119995,
132
+ "rewards/reward_correctness": 0.125,
133
+ "rewards/reward_em_chunk": 0.0,
134
+ "rewards/reward_format": 0.125,
135
+ "rewards/reward_search_diversity": 0.3561664819717407,
136
+ "rewards/reward_search_strategy": 0.07500000298023224,
137
+ "step": 8
138
+ },
139
+ {
140
+ "completion_length": 98.375,
141
+ "epoch": 0.03146853146853147,
142
+ "grad_norm": 1.6168773174285889,
143
+ "kl": 0.0009058149298653007,
144
+ "learning_rate": 4.5000000000000003e-07,
145
+ "loss": 0.0,
146
+ "reward": 1.141206979751587,
147
+ "reward_std": 2.1089890003204346,
148
+ "rewards/reward_correctness": 0.125,
149
+ "rewards/reward_em_chunk": 0.375,
150
+ "rewards/reward_format": 0.0,
151
+ "rewards/reward_search_diversity": 0.16620691120624542,
152
+ "rewards/reward_search_strategy": 0.10000000149011612,
153
+ "step": 9
154
+ },
155
+ {
156
+ "completion_length": 269.625,
157
+ "epoch": 0.03496503496503497,
158
+ "grad_norm": 1.310072660446167,
159
+ "kl": 0.000750248203985393,
160
+ "learning_rate": 5.000000000000001e-07,
161
+ "loss": 0.0,
162
+ "reward": 1.901651382446289,
163
+ "reward_std": 3.08128023147583,
164
+ "rewards/reward_correctness": 0.25,
165
+ "rewards/reward_em_chunk": 0.25,
166
+ "rewards/reward_format": 0.125,
167
+ "rewards/reward_search_diversity": 0.27665144205093384,
168
+ "rewards/reward_search_strategy": 0.125,
169
+ "step": 10
170
+ },
171
+ {
172
+ "completion_length": 311.125,
173
+ "epoch": 0.038461538461538464,
174
+ "grad_norm": 1.1051065921783447,
175
+ "kl": 0.000834438658785075,
176
+ "learning_rate": 5.5e-07,
177
+ "loss": 0.0,
178
+ "reward": 2.1270594596862793,
179
+ "reward_std": 2.309929132461548,
180
+ "rewards/reward_correctness": 0.25,
181
+ "rewards/reward_em_chunk": 0.625,
182
+ "rewards/reward_format": 0.0,
183
+ "rewards/reward_search_diversity": 0.377059668302536,
184
+ "rewards/reward_search_strategy": 0.125,
185
+ "step": 11
186
+ },
187
+ {
188
+ "completion_length": 182.375,
189
+ "epoch": 0.04195804195804196,
190
+ "grad_norm": 1.3039528131484985,
191
+ "kl": 0.0007587745785713196,
192
+ "learning_rate": 6.000000000000001e-07,
193
+ "loss": 0.0,
194
+ "reward": 0.24762853980064392,
195
+ "reward_std": 0.28513866662979126,
196
+ "rewards/reward_correctness": 0.0,
197
+ "rewards/reward_em_chunk": 0.0,
198
+ "rewards/reward_format": 0.0,
199
+ "rewards/reward_search_diversity": 0.17262855172157288,
200
+ "rewards/reward_search_strategy": 0.07500000298023224,
201
+ "step": 12
202
+ },
203
+ {
204
+ "completion_length": 198.5,
205
+ "epoch": 0.045454545454545456,
206
+ "grad_norm": 1.176461935043335,
207
+ "kl": 0.0008510244661010802,
208
+ "learning_rate": 6.5e-07,
209
+ "loss": 0.0,
210
+ "reward": 2.0060770511627197,
211
+ "reward_std": 2.2957346439361572,
212
+ "rewards/reward_correctness": 0.25,
213
+ "rewards/reward_em_chunk": 0.625,
214
+ "rewards/reward_format": 0.0,
215
+ "rewards/reward_search_diversity": 0.3060770034790039,
216
+ "rewards/reward_search_strategy": 0.07500000298023224,
217
+ "step": 13
218
+ },
219
+ {
220
+ "completion_length": 158.25,
221
+ "epoch": 0.04895104895104895,
222
+ "grad_norm": 1.1484898328781128,
223
+ "kl": 0.0009028888889588416,
224
+ "learning_rate": 7.000000000000001e-07,
225
+ "loss": 0.0,
226
+ "reward": 0.2598831355571747,
227
+ "reward_std": 0.4156216084957123,
228
+ "rewards/reward_correctness": 0.0,
229
+ "rewards/reward_em_chunk": 0.125,
230
+ "rewards/reward_format": 0.0,
231
+ "rewards/reward_search_diversity": 0.1348831057548523,
232
+ "rewards/reward_search_strategy": 0.0,
233
+ "step": 14
234
+ },
235
+ {
236
+ "completion_length": 321.125,
237
+ "epoch": 0.05244755244755245,
238
+ "grad_norm": 1.08210027217865,
239
+ "kl": 0.0007499511120840907,
240
+ "learning_rate": 7.5e-07,
241
+ "loss": 0.0,
242
+ "reward": 2.711674213409424,
243
+ "reward_std": 3.2537524700164795,
244
+ "rewards/reward_correctness": 0.375,
245
+ "rewards/reward_em_chunk": 0.375,
246
+ "rewards/reward_format": 0.125,
247
+ "rewards/reward_search_diversity": 0.3866744041442871,
248
+ "rewards/reward_search_strategy": 0.20000000298023224,
249
+ "step": 15
250
+ },
251
+ {
252
+ "completion_length": 176.0,
253
+ "epoch": 0.055944055944055944,
254
+ "grad_norm": 1.007460117340088,
255
+ "kl": 0.0008281145128421485,
256
+ "learning_rate": 8.000000000000001e-07,
257
+ "loss": 0.0,
258
+ "reward": 1.6642776727676392,
259
+ "reward_std": 3.1836605072021484,
260
+ "rewards/reward_correctness": 0.25,
261
+ "rewards/reward_em_chunk": 0.125,
262
+ "rewards/reward_format": 0.125,
263
+ "rewards/reward_search_diversity": 0.1892777681350708,
264
+ "rewards/reward_search_strategy": 0.10000000149011612,
265
+ "step": 16
266
+ },
267
+ {
268
+ "completion_length": 299.0,
269
+ "epoch": 0.05944055944055944,
270
+ "grad_norm": 0.9308914542198181,
271
+ "kl": 0.0006533896084874868,
272
+ "learning_rate": 8.500000000000001e-07,
273
+ "loss": 0.0,
274
+ "reward": 2.9600870609283447,
275
+ "reward_std": 3.002318859100342,
276
+ "rewards/reward_correctness": 0.375,
277
+ "rewards/reward_em_chunk": 0.75,
278
+ "rewards/reward_format": 0.125,
279
+ "rewards/reward_search_diversity": 0.38508710265159607,
280
+ "rewards/reward_search_strategy": 0.07500000298023224,
281
+ "step": 17
282
+ },
283
+ {
284
+ "completion_length": 170.125,
285
+ "epoch": 0.06293706293706294,
286
+ "grad_norm": 1.6546720266342163,
287
+ "kl": 0.0009436010150238872,
288
+ "learning_rate": 9.000000000000001e-07,
289
+ "loss": 0.0,
290
+ "reward": 1.807711124420166,
291
+ "reward_std": 2.873779773712158,
292
+ "rewards/reward_correctness": 0.25,
293
+ "rewards/reward_em_chunk": 0.0,
294
+ "rewards/reward_format": 0.125,
295
+ "rewards/reward_search_diversity": 0.33271118998527527,
296
+ "rewards/reward_search_strategy": 0.22499999403953552,
297
+ "step": 18
298
+ },
299
+ {
300
+ "completion_length": 377.125,
301
+ "epoch": 0.06643356643356643,
302
+ "grad_norm": 0.7977221608161926,
303
+ "kl": 0.0008231342071667314,
304
+ "learning_rate": 9.500000000000001e-07,
305
+ "loss": 0.0,
306
+ "reward": 0.7038719058036804,
307
+ "reward_std": 1.2563936710357666,
308
+ "rewards/reward_correctness": 0.0,
309
+ "rewards/reward_em_chunk": 0.125,
310
+ "rewards/reward_format": 0.125,
311
+ "rewards/reward_search_diversity": 0.22887186706066132,
312
+ "rewards/reward_search_strategy": 0.10000000149011612,
313
+ "step": 19
314
+ },
315
+ {
316
+ "completion_length": 161.625,
317
+ "epoch": 0.06993006993006994,
318
+ "grad_norm": 1.5974496603012085,
319
+ "kl": 0.000790413178037852,
320
+ "learning_rate": 1.0000000000000002e-06,
321
+ "loss": 0.0,
322
+ "reward": 2.404862880706787,
323
+ "reward_std": 2.712550163269043,
324
+ "rewards/reward_correctness": 0.375,
325
+ "rewards/reward_em_chunk": 0.625,
326
+ "rewards/reward_format": 0.0,
327
+ "rewards/reward_search_diversity": 0.179862841963768,
328
+ "rewards/reward_search_strategy": 0.10000000149011612,
329
+ "step": 20
330
+ },
331
+ {
332
+ "completion_length": 298.875,
333
+ "epoch": 0.07342657342657342,
334
+ "grad_norm": 0.8817616105079651,
335
+ "kl": 0.0007674504304304719,
336
+ "learning_rate": 1.0500000000000001e-06,
337
+ "loss": 0.0,
338
+ "reward": 2.6999998092651367,
339
+ "reward_std": 3.122270345687866,
340
+ "rewards/reward_correctness": 0.375,
341
+ "rewards/reward_em_chunk": 0.125,
342
+ "rewards/reward_format": 0.375,
343
+ "rewards/reward_search_diversity": 0.05000000074505806,
344
+ "rewards/reward_search_strategy": 0.2750000059604645,
345
+ "step": 21
346
+ },
347
+ {
348
+ "completion_length": 150.125,
349
+ "epoch": 0.07692307692307693,
350
+ "grad_norm": 1.345902919769287,
351
+ "kl": 0.0010101046646013856,
352
+ "learning_rate": 1.1e-06,
353
+ "loss": 0.0,
354
+ "reward": 1.2625212669372559,
355
+ "reward_std": 1.9802589416503906,
356
+ "rewards/reward_correctness": 0.25,
357
+ "rewards/reward_em_chunk": 0.125,
358
+ "rewards/reward_format": 0.0,
359
+ "rewards/reward_search_diversity": 0.13752126693725586,
360
+ "rewards/reward_search_strategy": 0.0,
361
+ "step": 22
362
+ },
363
+ {
364
+ "completion_length": 156.625,
365
+ "epoch": 0.08041958041958042,
366
+ "grad_norm": 3.1841650009155273,
367
+ "kl": 0.0009282200480811298,
368
+ "learning_rate": 1.1500000000000002e-06,
369
+ "loss": 0.0,
370
+ "reward": 2.532832145690918,
371
+ "reward_std": 3.623222827911377,
372
+ "rewards/reward_correctness": 0.375,
373
+ "rewards/reward_em_chunk": 0.375,
374
+ "rewards/reward_format": 0.125,
375
+ "rewards/reward_search_diversity": 0.18283231556415558,
376
+ "rewards/reward_search_strategy": 0.22500000894069672,
377
+ "step": 23
378
+ },
379
+ {
380
+ "completion_length": 230.625,
381
+ "epoch": 0.08391608391608392,
382
+ "grad_norm": 0.560590922832489,
383
+ "kl": 0.0008200581069104373,
384
+ "learning_rate": 1.2000000000000002e-06,
385
+ "loss": 0.0,
386
+ "reward": 0.7196725606918335,
387
+ "reward_std": 1.5131947994232178,
388
+ "rewards/reward_correctness": 0.125,
389
+ "rewards/reward_em_chunk": 0.0,
390
+ "rewards/reward_format": 0.0,
391
+ "rewards/reward_search_diversity": 0.1946725845336914,
392
+ "rewards/reward_search_strategy": 0.02500000037252903,
393
+ "step": 24
394
+ },
395
+ {
396
+ "completion_length": 232.5,
397
+ "epoch": 0.08741258741258741,
398
+ "grad_norm": 5.627699375152588,
399
+ "kl": 0.0007359281880781054,
400
+ "learning_rate": 1.25e-06,
401
+ "loss": 0.0,
402
+ "reward": 2.3161444664001465,
403
+ "reward_std": 2.266465425491333,
404
+ "rewards/reward_correctness": 0.5,
405
+ "rewards/reward_em_chunk": 0.0,
406
+ "rewards/reward_format": 0.0,
407
+ "rewards/reward_search_diversity": 0.31614452600479126,
408
+ "rewards/reward_search_strategy": 0.0,
409
+ "step": 25
410
+ },
411
+ {
412
+ "completion_length": 256.625,
413
+ "epoch": 0.09090909090909091,
414
+ "grad_norm": 1.243622064590454,
415
+ "kl": 0.0009776452789083123,
416
+ "learning_rate": 1.3e-06,
417
+ "loss": 0.0,
418
+ "reward": 1.8542793989181519,
419
+ "reward_std": 2.3880927562713623,
420
+ "rewards/reward_correctness": 0.25,
421
+ "rewards/reward_em_chunk": 0.625,
422
+ "rewards/reward_format": 0.0,
423
+ "rewards/reward_search_diversity": 0.22927939891815186,
424
+ "rewards/reward_search_strategy": 0.0,
425
+ "step": 26
426
+ },
427
+ {
428
+ "completion_length": 221.625,
429
+ "epoch": 0.0944055944055944,
430
+ "grad_norm": 2.455430030822754,
431
+ "kl": 0.0014260835014283657,
432
+ "learning_rate": 1.3500000000000002e-06,
433
+ "loss": 0.0001,
434
+ "reward": 1.0012282133102417,
435
+ "reward_std": 1.7000349760055542,
436
+ "rewards/reward_correctness": 0.125,
437
+ "rewards/reward_em_chunk": 0.0,
438
+ "rewards/reward_format": 0.125,
439
+ "rewards/reward_search_diversity": 0.15122826397418976,
440
+ "rewards/reward_search_strategy": 0.10000000149011612,
441
+ "step": 27
442
+ },
443
+ {
444
+ "completion_length": 185.75,
445
+ "epoch": 0.0979020979020979,
446
+ "grad_norm": 1.199497938156128,
447
+ "kl": 0.0007826727814972401,
448
+ "learning_rate": 1.4000000000000001e-06,
449
+ "loss": 0.0,
450
+ "reward": 2.173332691192627,
451
+ "reward_std": 2.801347255706787,
452
+ "rewards/reward_correctness": 0.375,
453
+ "rewards/reward_em_chunk": 0.0,
454
+ "rewards/reward_format": 0.125,
455
+ "rewards/reward_search_diversity": 0.32333269715309143,
456
+ "rewards/reward_search_strategy": 0.10000000149011612,
457
+ "step": 28
458
+ },
459
+ {
460
+ "completion_length": 243.125,
461
+ "epoch": 0.10139860139860139,
462
+ "grad_norm": 0.8430306315422058,
463
+ "kl": 0.0008962135761976242,
464
+ "learning_rate": 1.45e-06,
465
+ "loss": 0.0,
466
+ "reward": 1.0625323057174683,
467
+ "reward_std": 1.898645043373108,
468
+ "rewards/reward_correctness": 0.125,
469
+ "rewards/reward_em_chunk": 0.375,
470
+ "rewards/reward_format": 0.0,
471
+ "rewards/reward_search_diversity": 0.18753226101398468,
472
+ "rewards/reward_search_strategy": 0.0,
473
+ "step": 29
474
+ },
475
+ {
476
+ "completion_length": 334.875,
477
+ "epoch": 0.1048951048951049,
478
+ "grad_norm": 0.8412113785743713,
479
+ "kl": 0.001170428702607751,
480
+ "learning_rate": 1.5e-06,
481
+ "loss": 0.0,
482
+ "reward": 1.303612232208252,
483
+ "reward_std": 2.1826775074005127,
484
+ "rewards/reward_correctness": 0.25,
485
+ "rewards/reward_em_chunk": 0.0,
486
+ "rewards/reward_format": 0.0,
487
+ "rewards/reward_search_diversity": 0.27861225605010986,
488
+ "rewards/reward_search_strategy": 0.02500000037252903,
489
+ "step": 30
490
+ },
491
+ {
492
+ "completion_length": 165.75,
493
+ "epoch": 0.10839160839160839,
494
+ "grad_norm": 1.9105679988861084,
495
+ "kl": 0.0031302073039114475,
496
+ "learning_rate": 1.5500000000000002e-06,
497
+ "loss": 0.0001,
498
+ "reward": 1.0198408365249634,
499
+ "reward_std": 2.1316380500793457,
500
+ "rewards/reward_correctness": 0.125,
501
+ "rewards/reward_em_chunk": 0.25,
502
+ "rewards/reward_format": 0.0,
503
+ "rewards/reward_search_diversity": 0.16984085738658905,
504
+ "rewards/reward_search_strategy": 0.10000000149011612,
505
+ "step": 31
506
+ },
507
+ {
508
+ "completion_length": 174.625,
509
+ "epoch": 0.11188811188811189,
510
+ "grad_norm": 2.309382915496826,
511
+ "kl": 0.0032356895972043276,
512
+ "learning_rate": 1.6000000000000001e-06,
513
+ "loss": 0.0001,
514
+ "reward": 0.9216341376304626,
515
+ "reward_std": 1.8671420812606812,
516
+ "rewards/reward_correctness": 0.125,
517
+ "rewards/reward_em_chunk": 0.25,
518
+ "rewards/reward_format": 0.0,
519
+ "rewards/reward_search_diversity": 0.14663413166999817,
520
+ "rewards/reward_search_strategy": 0.02500000037252903,
521
+ "step": 32
522
+ },
523
+ {
524
+ "completion_length": 85.75,
525
+ "epoch": 0.11538461538461539,
526
+ "grad_norm": 1.4122040271759033,
527
+ "kl": 0.0017049856251105666,
528
+ "learning_rate": 1.6500000000000003e-06,
529
+ "loss": 0.0001,
530
+ "reward": 1.524999976158142,
531
+ "reward_std": 2.2926902770996094,
532
+ "rewards/reward_correctness": 0.25,
533
+ "rewards/reward_em_chunk": 0.125,
534
+ "rewards/reward_format": 0.125,
535
+ "rewards/reward_search_diversity": 0.10000000149011612,
536
+ "rewards/reward_search_strategy": 0.05000000074505806,
537
+ "step": 33
538
+ },
539
+ {
540
+ "completion_length": 173.5,
541
+ "epoch": 0.11888111888111888,
542
+ "grad_norm": 0.9712541699409485,
543
+ "kl": 0.0014842856908217072,
544
+ "learning_rate": 1.7000000000000002e-06,
545
+ "loss": 0.0001,
546
+ "reward": 3.4844837188720703,
547
+ "reward_std": 3.1145381927490234,
548
+ "rewards/reward_correctness": 0.5,
549
+ "rewards/reward_em_chunk": 0.75,
550
+ "rewards/reward_format": 0.125,
551
+ "rewards/reward_search_diversity": 0.3094840347766876,
552
+ "rewards/reward_search_strategy": 0.17499999701976776,
553
+ "step": 34
554
+ },
555
+ {
556
+ "completion_length": 268.25,
557
+ "epoch": 0.12237762237762238,
558
+ "grad_norm": 1.1684075593948364,
559
+ "kl": 0.0012478481512516737,
560
+ "learning_rate": 1.75e-06,
561
+ "loss": 0.0,
562
+ "reward": 2.8716678619384766,
563
+ "reward_std": 2.387646198272705,
564
+ "rewards/reward_correctness": 0.5,
565
+ "rewards/reward_em_chunk": 0.375,
566
+ "rewards/reward_format": 0.0,
567
+ "rewards/reward_search_diversity": 0.3716679811477661,
568
+ "rewards/reward_search_strategy": 0.125,
569
+ "step": 35
570
+ },
571
+ {
572
+ "completion_length": 235.125,
573
+ "epoch": 0.1258741258741259,
574
+ "grad_norm": 1.2749513387680054,
575
+ "kl": 0.004472827073186636,
576
+ "learning_rate": 1.8000000000000001e-06,
577
+ "loss": 0.0002,
578
+ "reward": 1.8775699138641357,
579
+ "reward_std": 2.413510322570801,
580
+ "rewards/reward_correctness": 0.375,
581
+ "rewards/reward_em_chunk": 0.0,
582
+ "rewards/reward_format": 0.0,
583
+ "rewards/reward_search_diversity": 0.30256983637809753,
584
+ "rewards/reward_search_strategy": 0.07500000298023224,
585
+ "step": 36
586
+ },
587
+ {
588
+ "completion_length": 175.5,
589
+ "epoch": 0.12937062937062938,
590
+ "grad_norm": 0.8929537534713745,
591
+ "kl": 0.0037049425300210714,
592
+ "learning_rate": 1.85e-06,
593
+ "loss": 0.0001,
594
+ "reward": 0.6821428537368774,
595
+ "reward_std": 1.4377206563949585,
596
+ "rewards/reward_correctness": 0.125,
597
+ "rewards/reward_em_chunk": 0.0,
598
+ "rewards/reward_format": 0.0,
599
+ "rewards/reward_search_diversity": 0.18214285373687744,
600
+ "rewards/reward_search_strategy": 0.0,
601
+ "step": 37
602
+ },
603
+ {
604
+ "completion_length": 290.125,
605
+ "epoch": 0.13286713286713286,
606
+ "grad_norm": 2.52665114402771,
607
+ "kl": 0.005157872103154659,
608
+ "learning_rate": 1.9000000000000002e-06,
609
+ "loss": 0.0002,
610
+ "reward": 2.574741840362549,
611
+ "reward_std": 2.5146002769470215,
612
+ "rewards/reward_correctness": 0.375,
613
+ "rewards/reward_em_chunk": 0.75,
614
+ "rewards/reward_format": 0.0,
615
+ "rewards/reward_search_diversity": 0.14974190294742584,
616
+ "rewards/reward_search_strategy": 0.17500001192092896,
617
+ "step": 38
618
+ },
619
+ {
620
+ "completion_length": 344.125,
621
+ "epoch": 0.13636363636363635,
622
+ "grad_norm": 0.8259175419807434,
623
+ "kl": 0.002582128159701824,
624
+ "learning_rate": 1.9500000000000004e-06,
625
+ "loss": 0.0001,
626
+ "reward": 2.376612901687622,
627
+ "reward_std": 2.9910624027252197,
628
+ "rewards/reward_correctness": 0.375,
629
+ "rewards/reward_em_chunk": 0.125,
630
+ "rewards/reward_format": 0.125,
631
+ "rewards/reward_search_diversity": 0.4266127943992615,
632
+ "rewards/reward_search_strategy": 0.07500000298023224,
633
+ "step": 39
634
+ },
635
+ {
636
+ "completion_length": 243.125,
637
+ "epoch": 0.13986013986013987,
638
+ "grad_norm": 1.0021271705627441,
639
+ "kl": 0.004831339232623577,
640
+ "learning_rate": 2.0000000000000003e-06,
641
+ "loss": 0.0002,
642
+ "reward": 2.04349946975708,
643
+ "reward_std": 2.3903656005859375,
644
+ "rewards/reward_correctness": 0.25,
645
+ "rewards/reward_em_chunk": 0.625,
646
+ "rewards/reward_format": 0.0,
647
+ "rewards/reward_search_diversity": 0.34349945187568665,
648
+ "rewards/reward_search_strategy": 0.07500000298023224,
649
+ "step": 40
650
+ },
651
+ {
652
+ "completion_length": 207.375,
653
+ "epoch": 0.14335664335664336,
654
+ "grad_norm": 1.2446260452270508,
655
+ "kl": 0.005710378754884005,
656
+ "learning_rate": 2.05e-06,
657
+ "loss": 0.0002,
658
+ "reward": 2.8324475288391113,
659
+ "reward_std": 3.167931079864502,
660
+ "rewards/reward_correctness": 0.375,
661
+ "rewards/reward_em_chunk": 0.625,
662
+ "rewards/reward_format": 0.125,
663
+ "rewards/reward_search_diversity": 0.25744765996932983,
664
+ "rewards/reward_search_strategy": 0.20000000298023224,
665
+ "step": 41
666
+ },
667
+ {
668
+ "completion_length": 441.125,
669
+ "epoch": 0.14685314685314685,
670
+ "grad_norm": 0.8263920545578003,
671
+ "kl": 0.0030913222581148148,
672
+ "learning_rate": 2.1000000000000002e-06,
673
+ "loss": 0.0001,
674
+ "reward": 2.5794529914855957,
675
+ "reward_std": 2.6344144344329834,
676
+ "rewards/reward_correctness": 0.375,
677
+ "rewards/reward_em_chunk": 0.125,
678
+ "rewards/reward_format": 0.25,
679
+ "rewards/reward_search_diversity": 0.30445292592048645,
680
+ "rewards/reward_search_strategy": 0.15000000596046448,
681
+ "step": 42
682
+ },
683
+ {
684
+ "completion_length": 226.375,
685
+ "epoch": 0.15034965034965034,
686
+ "grad_norm": 1.141964316368103,
687
+ "kl": 0.008909309282898903,
688
+ "learning_rate": 2.15e-06,
689
+ "loss": 0.0004,
690
+ "reward": 1.8603672981262207,
691
+ "reward_std": 2.203197479248047,
692
+ "rewards/reward_correctness": 0.25,
693
+ "rewards/reward_em_chunk": 0.625,
694
+ "rewards/reward_format": 0.0,
695
+ "rewards/reward_search_diversity": 0.21036729216575623,
696
+ "rewards/reward_search_strategy": 0.02500000037252903,
697
+ "step": 43
698
+ },
699
+ {
700
+ "completion_length": 397.75,
701
+ "epoch": 0.15384615384615385,
702
+ "grad_norm": 0.9564006328582764,
703
+ "kl": 0.01092858798801899,
704
+ "learning_rate": 2.2e-06,
705
+ "loss": 0.0004,
706
+ "reward": 2.557056188583374,
707
+ "reward_std": 2.429002046585083,
708
+ "rewards/reward_correctness": 0.375,
709
+ "rewards/reward_em_chunk": 0.75,
710
+ "rewards/reward_format": 0.0,
711
+ "rewards/reward_search_diversity": 0.28205621242523193,
712
+ "rewards/reward_search_strategy": 0.02500000037252903,
713
+ "step": 44
714
+ },
715
+ {
716
+ "completion_length": 307.25,
717
+ "epoch": 0.15734265734265734,
718
+ "grad_norm": 1.0510841608047485,
719
+ "kl": 0.007918575778603554,
720
+ "learning_rate": 2.25e-06,
721
+ "loss": 0.0003,
722
+ "reward": 1.2331278324127197,
723
+ "reward_std": 1.7548075914382935,
724
+ "rewards/reward_correctness": 0.25,
725
+ "rewards/reward_em_chunk": 0.0,
726
+ "rewards/reward_format": 0.0,
727
+ "rewards/reward_search_diversity": 0.15812794864177704,
728
+ "rewards/reward_search_strategy": 0.07500000298023224,
729
+ "step": 45
730
+ },
731
+ {
732
+ "completion_length": 277.0,
733
+ "epoch": 0.16083916083916083,
734
+ "grad_norm": 0.9169591665267944,
735
+ "kl": 0.015062836930155754,
736
+ "learning_rate": 2.3000000000000004e-06,
737
+ "loss": 0.0006,
738
+ "reward": 1.2089338302612305,
739
+ "reward_std": 2.5115318298339844,
740
+ "rewards/reward_correctness": 0.125,
741
+ "rewards/reward_em_chunk": 0.125,
742
+ "rewards/reward_format": 0.125,
743
+ "rewards/reward_search_diversity": 0.1339338719844818,
744
+ "rewards/reward_search_strategy": 0.20000000298023224,
745
+ "step": 46
746
+ },
747
+ {
748
+ "completion_length": 206.25,
749
+ "epoch": 0.16433566433566432,
750
+ "grad_norm": 1.3427180051803589,
751
+ "kl": 0.019624339416623116,
752
+ "learning_rate": 2.35e-06,
753
+ "loss": 0.0008,
754
+ "reward": 4.1133527755737305,
755
+ "reward_std": 3.2583820819854736,
756
+ "rewards/reward_correctness": 0.625,
757
+ "rewards/reward_em_chunk": 0.625,
758
+ "rewards/reward_format": 0.25,
759
+ "rewards/reward_search_diversity": 0.36335283517837524,
760
+ "rewards/reward_search_strategy": 0.125,
761
+ "step": 47
762
+ },
763
+ {
764
+ "completion_length": 252.125,
765
+ "epoch": 0.16783216783216784,
766
+ "grad_norm": 0.7444542050361633,
767
+ "kl": 0.021463895216584206,
768
+ "learning_rate": 2.4000000000000003e-06,
769
+ "loss": 0.0009,
770
+ "reward": 1.631263017654419,
771
+ "reward_std": 2.5925517082214355,
772
+ "rewards/reward_correctness": 0.25,
773
+ "rewards/reward_em_chunk": 0.375,
774
+ "rewards/reward_format": 0.0,
775
+ "rewards/reward_search_diversity": 0.23126289248466492,
776
+ "rewards/reward_search_strategy": 0.02500000037252903,
777
+ "step": 48
778
+ },
779
+ {
780
+ "completion_length": 117.625,
781
+ "epoch": 0.17132867132867133,
782
+ "grad_norm": 1.888673186302185,
783
+ "kl": 0.03609447553753853,
784
+ "learning_rate": 2.4500000000000003e-06,
785
+ "loss": 0.0014,
786
+ "reward": 1.9036250114440918,
787
+ "reward_std": 2.2273151874542236,
788
+ "rewards/reward_correctness": 0.25,
789
+ "rewards/reward_em_chunk": 0.625,
790
+ "rewards/reward_format": 0.0,
791
+ "rewards/reward_search_diversity": 0.20362500846385956,
792
+ "rewards/reward_search_strategy": 0.07500000298023224,
793
+ "step": 49
794
+ },
795
+ {
796
+ "completion_length": 302.75,
797
+ "epoch": 0.17482517482517482,
798
+ "grad_norm": 1.2723031044006348,
799
+ "kl": 0.2012804001569748,
800
+ "learning_rate": 2.5e-06,
801
+ "loss": 0.0081,
802
+ "reward": 0.15956448018550873,
803
+ "reward_std": 0.4513165056705475,
804
+ "rewards/reward_correctness": 0.0,
805
+ "rewards/reward_em_chunk": 0.125,
806
+ "rewards/reward_format": 0.0,
807
+ "rewards/reward_search_diversity": 0.03456447646021843,
808
+ "rewards/reward_search_strategy": 0.0,
809
+ "step": 50
810
+ }
811
+ ],
812
+ "logging_steps": 1,
813
+ "max_steps": 1000,
814
+ "num_input_tokens_seen": 0,
815
+ "num_train_epochs": 4,
816
+ "save_steps": 50,
817
+ "stateful_callbacks": {
818
+ "TrainerControl": {
819
+ "args": {
820
+ "should_epoch_stop": false,
821
+ "should_evaluate": false,
822
+ "should_log": false,
823
+ "should_save": true,
824
+ "should_training_stop": false
825
+ },
826
+ "attributes": {}
827
+ }
828
+ },
829
+ "total_flos": 0.0,
830
+ "train_batch_size": 8,
831
+ "trial_name": null,
832
+ "trial_params": null
833
+ }
checkpoint-50/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5bc2ce9fdda7e038f3836e0b24edb51569455f9c88149bdac5d77d744168c8
3
+ size 6072
logs/app.log CHANGED
The diff for this file is too large to render. See raw diff
 
runs/Apr09_02-14-09_879c0348b78a/events.out.tfevents.1744164850.879c0348b78a.920.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df4898335734ffb11e6c591bdf3488363331846e56b769755a8266782fc12d18
3
- size 25757
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642ef5f8d982585fcf6c223d2f9337e4b7d48a9e0297fa5021b7f32bb266f227
3
+ size 130001