igidn commited on
Commit
570820a
·
verified ·
1 Parent(s): 485c677

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,209 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: HuggingFaceTB/SmolLM3-3B-Base
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:HuggingFaceTB/SmolLM3-3B-Base
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ ---
12
+
13
+ # Model Card for Model ID
14
+
15
+ <!-- Provide a quick summary of what the model is/does. -->
16
+
17
+
18
+
19
+ ## Model Details
20
+
21
+ ### Model Description
22
+
23
+ <!-- Provide a longer summary of what this model is. -->
24
+
25
+
26
+
27
+ - **Developed by:** [More Information Needed]
28
+ - **Funded by [optional]:** [More Information Needed]
29
+ - **Shared by [optional]:** [More Information Needed]
30
+ - **Model type:** [More Information Needed]
31
+ - **Language(s) (NLP):** [More Information Needed]
32
+ - **License:** [More Information Needed]
33
+ - **Finetuned from model [optional]:** [More Information Needed]
34
+
35
+ ### Model Sources [optional]
36
+
37
+ <!-- Provide the basic links for the model. -->
38
+
39
+ - **Repository:** [More Information Needed]
40
+ - **Paper [optional]:** [More Information Needed]
41
+ - **Demo [optional]:** [More Information Needed]
42
+
43
+ ## Uses
44
+
45
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
46
+
47
+ ### Direct Use
48
+
49
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
50
+
51
+ [More Information Needed]
52
+
53
+ ### Downstream Use [optional]
54
+
55
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
56
+
57
+ [More Information Needed]
58
+
59
+ ### Out-of-Scope Use
60
+
61
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
62
+
63
+ [More Information Needed]
64
+
65
+ ## Bias, Risks, and Limitations
66
+
67
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
68
+
69
+ [More Information Needed]
70
+
71
+ ### Recommendations
72
+
73
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
74
+
75
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
76
+
77
+ ## How to Get Started with the Model
78
+
79
+ Use the code below to get started with the model.
80
+
81
+ [More Information Needed]
82
+
83
+ ## Training Details
84
+
85
+ ### Training Data
86
+
87
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
88
+
89
+ [More Information Needed]
90
+
91
+ ### Training Procedure
92
+
93
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
94
+
95
+ #### Preprocessing [optional]
96
+
97
+ [More Information Needed]
98
+
99
+
100
+ #### Training Hyperparameters
101
+
102
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
103
+
104
+ #### Speeds, Sizes, Times [optional]
105
+
106
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
107
+
108
+ [More Information Needed]
109
+
110
+ ## Evaluation
111
+
112
+ <!-- This section describes the evaluation protocols and provides the results. -->
113
+
114
+ ### Testing Data, Factors & Metrics
115
+
116
+ #### Testing Data
117
+
118
+ <!-- This should link to a Dataset Card if possible. -->
119
+
120
+ [More Information Needed]
121
+
122
+ #### Factors
123
+
124
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
125
+
126
+ [More Information Needed]
127
+
128
+ #### Metrics
129
+
130
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
131
+
132
+ [More Information Needed]
133
+
134
+ ### Results
135
+
136
+ [More Information Needed]
137
+
138
+ #### Summary
139
+
140
+
141
+
142
+ ## Model Examination [optional]
143
+
144
+ <!-- Relevant interpretability work for the model goes here -->
145
+
146
+ [More Information Needed]
147
+
148
+ ## Environmental Impact
149
+
150
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
151
+
152
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
153
+
154
+ - **Hardware Type:** [More Information Needed]
155
+ - **Hours used:** [More Information Needed]
156
+ - **Cloud Provider:** [More Information Needed]
157
+ - **Compute Region:** [More Information Needed]
158
+ - **Carbon Emitted:** [More Information Needed]
159
+
160
+ ## Technical Specifications [optional]
161
+
162
+ ### Model Architecture and Objective
163
+
164
+ [More Information Needed]
165
+
166
+ ### Compute Infrastructure
167
+
168
+ [More Information Needed]
169
+
170
+ #### Hardware
171
+
172
+ [More Information Needed]
173
+
174
+ #### Software
175
+
176
+ [More Information Needed]
177
+
178
+ ## Citation [optional]
179
+
180
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
181
+
182
+ **BibTeX:**
183
+
184
+ [More Information Needed]
185
+
186
+ **APA:**
187
+
188
+ [More Information Needed]
189
+
190
+ ## Glossary [optional]
191
+
192
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
193
+
194
+ [More Information Needed]
195
+
196
+ ## More Information [optional]
197
+
198
+ [More Information Needed]
199
+
200
+ ## Model Card Authors [optional]
201
+
202
+ [More Information Needed]
203
+
204
+ ## Model Card Contact
205
+
206
+ [More Information Needed]
207
+ ### Framework versions
208
+
209
+ - PEFT 0.18.0
adapter_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "HuggingFaceTB/SmolLM3-3B-Base",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.05,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "peft_version": "0.18.0",
27
+ "qalora_group_size": 16,
28
+ "r": 32,
29
+ "rank_pattern": {},
30
+ "revision": null,
31
+ "target_modules": [
32
+ "o_proj",
33
+ "down_proj",
34
+ "q_proj",
35
+ "k_proj",
36
+ "up_proj",
37
+ "lm_head",
38
+ "embed_tokens",
39
+ "v_proj",
40
+ "gate_proj"
41
+ ],
42
+ "target_parameters": null,
43
+ "task_type": "CAUSAL_LM",
44
+ "trainable_token_indices": null,
45
+ "use_dora": false,
46
+ "use_qalora": false,
47
+ "use_rslora": false
48
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a55a0ef7d67e5d57a65a21831be57082163ccc89a82875cb51079d426694b46
3
+ size 2376601904
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% if messages[0]['role'] == 'system' %}{{'<|im_start|>system
2
+ ' + messages[0]['content'] + '<|im_end|>
3
+ '}}{% set loop_messages = messages[1:] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{{'<|im_start|>' + message['role'] + '
4
+ ' + message['content'] + '<|im_end|>
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
+ '}}{% endif %}
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34a1c90c97decd1e8cf570c96e77d4f78abb0607cee4e99ef2f76431d64124c
3
+ size 550676891
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c3de83b35aa25f8cdcdf6638ffe08c56d2f27c34e13b615f6d3fbf8b4016f63
3
+ size 14917
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36f07f016c77f55081c74409d4ee1e633bf3d543b38c3d8954158b459a32861
3
+ size 14917
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a982952463c6e8ff476e504caa041a544e4eb2f8b059e560b0c21332149f503
3
+ size 1383
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7305b1871e0192b26813bbd26be70f7d883dd11a1ef6ca421631aa11f1cfa245
3
+ size 1465
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "eos_token": {
19
+ "content": "<|end_of_text|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "pad_token": "<|end_of_text|>"
26
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab4da6b2aa68247e9c0fa9b97fc7fcc796505038d01f7e144522a65ce0dbd2e5
3
+ size 17208861
tokenizer_config.json ADDED
@@ -0,0 +1,2068 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<think>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "</think>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|im_start|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|im_end|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<tool_response>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<tool_call>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</tool_call>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|im_start|>",
2054
+ "<|im_end|>"
2055
+ ],
2056
+ "bos_token": null,
2057
+ "clean_up_tokenization_spaces": true,
2058
+ "eos_token": "<|end_of_text|>",
2059
+ "extra_special_tokens": {},
2060
+ "fast": false,
2061
+ "model_input_names": [
2062
+ "input_ids",
2063
+ "attention_mask"
2064
+ ],
2065
+ "model_max_length": 131072,
2066
+ "pad_token": "<|end_of_text|>",
2067
+ "tokenizer_class": "PreTrainedTokenizerFast"
2068
+ }
trainer_state.json ADDED
@@ -0,0 +1,1224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1198,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 2.376227322220802,
14
+ "epoch": 0.01670843776106934,
15
+ "grad_norm": 23.182296752929688,
16
+ "learning_rate": 1.5e-06,
17
+ "loss": 2.4729,
18
+ "mean_token_accuracy": 0.5330174341797829,
19
+ "num_tokens": 23968.0,
20
+ "step": 10
21
+ },
22
+ {
23
+ "entropy": 2.4090343087911608,
24
+ "epoch": 0.03341687552213868,
25
+ "grad_norm": 16.90180778503418,
26
+ "learning_rate": 4e-06,
27
+ "loss": 2.2456,
28
+ "mean_token_accuracy": 0.546089893579483,
29
+ "num_tokens": 50061.0,
30
+ "step": 20
31
+ },
32
+ {
33
+ "entropy": 2.3292118519544602,
34
+ "epoch": 0.05012531328320802,
35
+ "grad_norm": 7.097179889678955,
36
+ "learning_rate": 6.5000000000000004e-06,
37
+ "loss": 2.0194,
38
+ "mean_token_accuracy": 0.5704705387353897,
39
+ "num_tokens": 77221.0,
40
+ "step": 30
41
+ },
42
+ {
43
+ "entropy": 2.38493994474411,
44
+ "epoch": 0.06683375104427736,
45
+ "grad_norm": 3.9334213733673096,
46
+ "learning_rate": 9e-06,
47
+ "loss": 2.091,
48
+ "mean_token_accuracy": 0.5746636532247067,
49
+ "num_tokens": 102592.0,
50
+ "step": 40
51
+ },
52
+ {
53
+ "entropy": 2.4236884146928785,
54
+ "epoch": 0.0835421888053467,
55
+ "grad_norm": 2.742833375930786,
56
+ "learning_rate": 1.1500000000000002e-05,
57
+ "loss": 1.9327,
58
+ "mean_token_accuracy": 0.5654355354607106,
59
+ "num_tokens": 130876.0,
60
+ "step": 50
61
+ },
62
+ {
63
+ "entropy": 2.4756928414106367,
64
+ "epoch": 0.10025062656641603,
65
+ "grad_norm": 4.295400142669678,
66
+ "learning_rate": 1.4e-05,
67
+ "loss": 2.0381,
68
+ "mean_token_accuracy": 0.5688402287662029,
69
+ "num_tokens": 155526.0,
70
+ "step": 60
71
+ },
72
+ {
73
+ "entropy": 2.422525143623352,
74
+ "epoch": 0.11695906432748537,
75
+ "grad_norm": 37.36378479003906,
76
+ "learning_rate": 1.65e-05,
77
+ "loss": 1.9249,
78
+ "mean_token_accuracy": 0.5765560433268547,
79
+ "num_tokens": 181754.0,
80
+ "step": 70
81
+ },
82
+ {
83
+ "entropy": 2.3750332206487657,
84
+ "epoch": 0.1336675020885547,
85
+ "grad_norm": 53.244632720947266,
86
+ "learning_rate": 1.9e-05,
87
+ "loss": 1.7852,
88
+ "mean_token_accuracy": 0.5806652165949344,
89
+ "num_tokens": 208156.0,
90
+ "step": 80
91
+ },
92
+ {
93
+ "entropy": 2.1606528967618943,
94
+ "epoch": 0.15037593984962405,
95
+ "grad_norm": 1.9780453443527222,
96
+ "learning_rate": 2.15e-05,
97
+ "loss": 1.74,
98
+ "mean_token_accuracy": 0.595666554570198,
99
+ "num_tokens": 236321.0,
100
+ "step": 90
101
+ },
102
+ {
103
+ "entropy": 2.1004574805498124,
104
+ "epoch": 0.1670843776106934,
105
+ "grad_norm": 2.5225274562835693,
106
+ "learning_rate": 2.4e-05,
107
+ "loss": 1.7544,
108
+ "mean_token_accuracy": 0.5997186966240406,
109
+ "num_tokens": 263316.0,
110
+ "step": 100
111
+ },
112
+ {
113
+ "entropy": 2.0930860340595245,
114
+ "epoch": 0.18379281537176273,
115
+ "grad_norm": 2.0412206649780273,
116
+ "learning_rate": 2.65e-05,
117
+ "loss": 1.6994,
118
+ "mean_token_accuracy": 0.6029496222734452,
119
+ "num_tokens": 289555.0,
120
+ "step": 110
121
+ },
122
+ {
123
+ "entropy": 2.0005944788455965,
124
+ "epoch": 0.20050125313283207,
125
+ "grad_norm": 5.798661231994629,
126
+ "learning_rate": 2.9e-05,
127
+ "loss": 1.5928,
128
+ "mean_token_accuracy": 0.6268587596714497,
129
+ "num_tokens": 322035.0,
130
+ "step": 120
131
+ },
132
+ {
133
+ "entropy": 2.1824300229549407,
134
+ "epoch": 0.2172096908939014,
135
+ "grad_norm": 2.135401964187622,
136
+ "learning_rate": 2.999770694261986e-05,
137
+ "loss": 1.7705,
138
+ "mean_token_accuracy": 0.5905720897018909,
139
+ "num_tokens": 343574.0,
140
+ "step": 130
141
+ },
142
+ {
143
+ "entropy": 2.317758610844612,
144
+ "epoch": 0.23391812865497075,
145
+ "grad_norm": 4.436051368713379,
146
+ "learning_rate": 2.9983696353001538e-05,
147
+ "loss": 1.8244,
148
+ "mean_token_accuracy": 0.578718575835228,
149
+ "num_tokens": 367065.0,
150
+ "step": 140
151
+ },
152
+ {
153
+ "entropy": 2.0938976377248766,
154
+ "epoch": 0.2506265664160401,
155
+ "grad_norm": 1.6219489574432373,
156
+ "learning_rate": 2.995696097848732e-05,
157
+ "loss": 1.6849,
158
+ "mean_token_accuracy": 0.6061625145375729,
159
+ "num_tokens": 395337.0,
160
+ "step": 150
161
+ },
162
+ {
163
+ "entropy": 2.05442219376564,
164
+ "epoch": 0.2673350041771094,
165
+ "grad_norm": 1.6669152975082397,
166
+ "learning_rate": 2.9917523523881268e-05,
167
+ "loss": 1.7082,
168
+ "mean_token_accuracy": 0.6042715333402157,
169
+ "num_tokens": 420868.0,
170
+ "step": 160
171
+ },
172
+ {
173
+ "entropy": 2.032812547683716,
174
+ "epoch": 0.28404344193817876,
175
+ "grad_norm": 1.9019651412963867,
176
+ "learning_rate": 2.9865417481127877e-05,
177
+ "loss": 1.546,
178
+ "mean_token_accuracy": 0.6138139866292477,
179
+ "num_tokens": 451944.0,
180
+ "step": 170
181
+ },
182
+ {
183
+ "entropy": 2.0105547934770582,
184
+ "epoch": 0.3007518796992481,
185
+ "grad_norm": 1.7808424234390259,
186
+ "learning_rate": 2.9800687100869334e-05,
187
+ "loss": 1.5909,
188
+ "mean_token_accuracy": 0.6109806254506112,
189
+ "num_tokens": 482345.0,
190
+ "step": 180
191
+ },
192
+ {
193
+ "entropy": 2.0666785687208176,
194
+ "epoch": 0.31746031746031744,
195
+ "grad_norm": 1.7441576719284058,
196
+ "learning_rate": 2.972338735486598e-05,
197
+ "loss": 1.6263,
198
+ "mean_token_accuracy": 0.6088879898190498,
199
+ "num_tokens": 508164.0,
200
+ "step": 190
201
+ },
202
+ {
203
+ "entropy": 2.0136130273342134,
204
+ "epoch": 0.3341687552213868,
205
+ "grad_norm": 1.8193825483322144,
206
+ "learning_rate": 2.9633583889312e-05,
207
+ "loss": 1.6149,
208
+ "mean_token_accuracy": 0.619242499768734,
209
+ "num_tokens": 536345.0,
210
+ "step": 200
211
+ },
212
+ {
213
+ "entropy": 2.0101848542690277,
214
+ "epoch": 0.3508771929824561,
215
+ "grad_norm": 1.11763596534729,
216
+ "learning_rate": 2.9531352969085914e-05,
217
+ "loss": 1.5869,
218
+ "mean_token_accuracy": 0.6176401123404502,
219
+ "num_tokens": 563157.0,
220
+ "step": 210
221
+ },
222
+ {
223
+ "entropy": 1.9853627145290376,
224
+ "epoch": 0.36758563074352546,
225
+ "grad_norm": 2.025529384613037,
226
+ "learning_rate": 2.9416781412983223e-05,
227
+ "loss": 1.6008,
228
+ "mean_token_accuracy": 0.6206148102879524,
229
+ "num_tokens": 590929.0,
230
+ "step": 220
231
+ },
232
+ {
233
+ "entropy": 2.108823761343956,
234
+ "epoch": 0.3842940685045948,
235
+ "grad_norm": 1.4173170328140259,
236
+ "learning_rate": 2.9289966519986258e-05,
237
+ "loss": 1.6553,
238
+ "mean_token_accuracy": 0.598318774998188,
239
+ "num_tokens": 615814.0,
240
+ "step": 230
241
+ },
242
+ {
243
+ "entropy": 2.0000301033258436,
244
+ "epoch": 0.40100250626566414,
245
+ "grad_norm": 2.162895679473877,
246
+ "learning_rate": 2.9151015986633762e-05,
247
+ "loss": 1.6305,
248
+ "mean_token_accuracy": 0.6174192741513252,
249
+ "num_tokens": 643303.0,
250
+ "step": 240
251
+ },
252
+ {
253
+ "entropy": 2.0013814836740496,
254
+ "epoch": 0.4177109440267335,
255
+ "grad_norm": 3.5182316303253174,
256
+ "learning_rate": 2.90000478155605e-05,
257
+ "loss": 1.5884,
258
+ "mean_token_accuracy": 0.615642835944891,
259
+ "num_tokens": 670279.0,
260
+ "step": 250
261
+ },
262
+ {
263
+ "entropy": 2.061664643883705,
264
+ "epoch": 0.4344193817878028,
265
+ "grad_norm": 2.530327558517456,
266
+ "learning_rate": 2.883719021528444e-05,
267
+ "loss": 1.7341,
268
+ "mean_token_accuracy": 0.6077517293393612,
269
+ "num_tokens": 695006.0,
270
+ "step": 260
271
+ },
272
+ {
273
+ "entropy": 2.0266662567853926,
274
+ "epoch": 0.45112781954887216,
275
+ "grad_norm": 2.2248501777648926,
276
+ "learning_rate": 2.8662581491326686e-05,
277
+ "loss": 1.5991,
278
+ "mean_token_accuracy": 0.6176492936909199,
279
+ "num_tokens": 720926.0,
280
+ "step": 270
281
+ },
282
+ {
283
+ "entropy": 1.998877900838852,
284
+ "epoch": 0.4678362573099415,
285
+ "grad_norm": 1.6995679140090942,
286
+ "learning_rate": 2.847636992875661e-05,
287
+ "loss": 1.5343,
288
+ "mean_token_accuracy": 0.6100999519228936,
289
+ "num_tokens": 753552.0,
290
+ "step": 280
291
+ },
292
+ {
293
+ "entropy": 2.0063836723566055,
294
+ "epoch": 0.48454469507101083,
295
+ "grad_norm": 1.5225791931152344,
296
+ "learning_rate": 2.827871366626197e-05,
297
+ "loss": 1.6512,
298
+ "mean_token_accuracy": 0.6144520066678524,
299
+ "num_tokens": 776650.0,
300
+ "step": 290
301
+ },
302
+ {
303
+ "entropy": 1.9781533569097518,
304
+ "epoch": 0.5012531328320802,
305
+ "grad_norm": 1.590501070022583,
306
+ "learning_rate": 2.806978056185084e-05,
307
+ "loss": 1.6408,
308
+ "mean_token_accuracy": 0.6150619685649872,
309
+ "num_tokens": 801816.0,
310
+ "step": 300
311
+ },
312
+ {
313
+ "entropy": 1.9714119344949723,
314
+ "epoch": 0.5179615705931495,
315
+ "grad_norm": 2.535109519958496,
316
+ "learning_rate": 2.7849748050299578e-05,
317
+ "loss": 1.603,
318
+ "mean_token_accuracy": 0.6225824594497681,
319
+ "num_tokens": 826564.0,
320
+ "step": 310
321
+ },
322
+ {
323
+ "entropy": 1.94197179377079,
324
+ "epoch": 0.5346700083542189,
325
+ "grad_norm": 1.5610677003860474,
326
+ "learning_rate": 2.7618802992467718e-05,
327
+ "loss": 1.5703,
328
+ "mean_token_accuracy": 0.6192868888378144,
329
+ "num_tokens": 855007.0,
330
+ "step": 320
331
+ },
332
+ {
333
+ "entropy": 1.9983945518732071,
334
+ "epoch": 0.5513784461152882,
335
+ "grad_norm": 1.7279447317123413,
336
+ "learning_rate": 2.7377141516607896e-05,
337
+ "loss": 1.5837,
338
+ "mean_token_accuracy": 0.6141151934862137,
339
+ "num_tokens": 881616.0,
340
+ "step": 330
341
+ },
342
+ {
343
+ "entropy": 1.8347389072179794,
344
+ "epoch": 0.5680868838763575,
345
+ "grad_norm": 1.3221409320831299,
346
+ "learning_rate": 2.712496885180547e-05,
347
+ "loss": 1.4675,
348
+ "mean_token_accuracy": 0.6429531842470169,
349
+ "num_tokens": 913148.0,
350
+ "step": 340
351
+ },
352
+ {
353
+ "entropy": 1.8934204697608947,
354
+ "epoch": 0.5847953216374269,
355
+ "grad_norm": 1.4465378522872925,
356
+ "learning_rate": 2.686249915368938e-05,
357
+ "loss": 1.4669,
358
+ "mean_token_accuracy": 0.6286376528441906,
359
+ "num_tokens": 944937.0,
360
+ "step": 350
361
+ },
362
+ {
363
+ "entropy": 1.9060048371553422,
364
+ "epoch": 0.6015037593984962,
365
+ "grad_norm": 1.6246923208236694,
366
+ "learning_rate": 2.658995532256217e-05,
367
+ "loss": 1.5736,
368
+ "mean_token_accuracy": 0.622390191257,
369
+ "num_tokens": 974558.0,
370
+ "step": 360
371
+ },
372
+ {
373
+ "entropy": 2.025865262746811,
374
+ "epoch": 0.6182121971595655,
375
+ "grad_norm": 1.2998696565628052,
376
+ "learning_rate": 2.6307568814103658e-05,
377
+ "loss": 1.6277,
378
+ "mean_token_accuracy": 0.6089055955410003,
379
+ "num_tokens": 1001232.0,
380
+ "step": 370
381
+ },
382
+ {
383
+ "entropy": 1.9043485343456268,
384
+ "epoch": 0.6349206349206349,
385
+ "grad_norm": 1.7911604642868042,
386
+ "learning_rate": 2.6015579442809094e-05,
387
+ "loss": 1.5542,
388
+ "mean_token_accuracy": 0.6255838416516781,
389
+ "num_tokens": 1029679.0,
390
+ "step": 380
391
+ },
392
+ {
393
+ "entropy": 2.0594927102327345,
394
+ "epoch": 0.6516290726817042,
395
+ "grad_norm": 1.6075160503387451,
396
+ "learning_rate": 2.5714235178328554e-05,
397
+ "loss": 1.664,
398
+ "mean_token_accuracy": 0.608974926173687,
399
+ "num_tokens": 1053040.0,
400
+ "step": 390
401
+ },
402
+ {
403
+ "entropy": 2.034518975019455,
404
+ "epoch": 0.6683375104427736,
405
+ "grad_norm": 3.4272360801696777,
406
+ "learning_rate": 2.540379193488072e-05,
407
+ "loss": 1.7209,
408
+ "mean_token_accuracy": 0.6031469151377677,
409
+ "num_tokens": 1075141.0,
410
+ "step": 400
411
+ },
412
+ {
413
+ "entropy": 2.0515862941741942,
414
+ "epoch": 0.6850459482038429,
415
+ "grad_norm": 1.2661142349243164,
416
+ "learning_rate": 2.5084513353919753e-05,
417
+ "loss": 1.6599,
418
+ "mean_token_accuracy": 0.6064547099173069,
419
+ "num_tokens": 1097768.0,
420
+ "step": 410
421
+ },
422
+ {
423
+ "entropy": 1.9067467480897904,
424
+ "epoch": 0.7017543859649122,
425
+ "grad_norm": 2.2614035606384277,
426
+ "learning_rate": 2.4756670580239894e-05,
427
+ "loss": 1.5424,
428
+ "mean_token_accuracy": 0.6350538037717343,
429
+ "num_tokens": 1125706.0,
430
+ "step": 420
431
+ },
432
+ {
433
+ "entropy": 2.103572541475296,
434
+ "epoch": 0.7184628237259816,
435
+ "grad_norm": 2.4501664638519287,
436
+ "learning_rate": 2.4420542031707905e-05,
437
+ "loss": 1.703,
438
+ "mean_token_accuracy": 0.6036252595484257,
439
+ "num_tokens": 1147357.0,
440
+ "step": 430
441
+ },
442
+ {
443
+ "entropy": 2.072985142469406,
444
+ "epoch": 0.7351712614870509,
445
+ "grad_norm": 1.8719037771224976,
446
+ "learning_rate": 2.4076413162818904e-05,
447
+ "loss": 1.6609,
448
+ "mean_token_accuracy": 0.606941219419241,
449
+ "num_tokens": 1170179.0,
450
+ "step": 440
451
+ },
452
+ {
453
+ "entropy": 2.022436353564262,
454
+ "epoch": 0.7518796992481203,
455
+ "grad_norm": 2.076544761657715,
456
+ "learning_rate": 2.3724576222276405e-05,
457
+ "loss": 1.7007,
458
+ "mean_token_accuracy": 0.6098736897110939,
459
+ "num_tokens": 1196284.0,
460
+ "step": 450
461
+ },
462
+ {
463
+ "entropy": 2.1311296701431273,
464
+ "epoch": 0.7685881370091896,
465
+ "grad_norm": 2.9471235275268555,
466
+ "learning_rate": 2.3365330004802443e-05,
467
+ "loss": 1.7893,
468
+ "mean_token_accuracy": 0.5961334474384785,
469
+ "num_tokens": 1217358.0,
470
+ "step": 460
471
+ },
472
+ {
473
+ "entropy": 1.9371352732181548,
474
+ "epoch": 0.7852965747702589,
475
+ "grad_norm": 1.4203218221664429,
476
+ "learning_rate": 2.2998979597388526e-05,
477
+ "loss": 1.608,
478
+ "mean_token_accuracy": 0.6184874981641769,
479
+ "num_tokens": 1243374.0,
480
+ "step": 470
481
+ },
482
+ {
483
+ "entropy": 2.0747445046901705,
484
+ "epoch": 0.8020050125313283,
485
+ "grad_norm": 2.2124152183532715,
486
+ "learning_rate": 2.262583612020294e-05,
487
+ "loss": 1.6711,
488
+ "mean_token_accuracy": 0.6062519766390324,
489
+ "num_tokens": 1267314.0,
490
+ "step": 480
491
+ },
492
+ {
493
+ "entropy": 1.7878674179315568,
494
+ "epoch": 0.8187134502923976,
495
+ "grad_norm": 1.3049612045288086,
496
+ "learning_rate": 2.224621646237442e-05,
497
+ "loss": 1.4722,
498
+ "mean_token_accuracy": 0.6389728732407093,
499
+ "num_tokens": 1296917.0,
500
+ "step": 490
501
+ },
502
+ {
503
+ "entropy": 1.925000047683716,
504
+ "epoch": 0.835421888053467,
505
+ "grad_norm": 1.4271504878997803,
506
+ "learning_rate": 2.1860443012876574e-05,
507
+ "loss": 1.6114,
508
+ "mean_token_accuracy": 0.616053618490696,
509
+ "num_tokens": 1322826.0,
510
+ "step": 500
511
+ },
512
+ {
513
+ "entropy": 2.0017556965351107,
514
+ "epoch": 0.8521303258145363,
515
+ "grad_norm": 1.6036300659179688,
516
+ "learning_rate": 2.146884338674161e-05,
517
+ "loss": 1.5247,
518
+ "mean_token_accuracy": 0.6218138873577118,
519
+ "num_tokens": 1349542.0,
520
+ "step": 510
521
+ },
522
+ {
523
+ "entropy": 1.995826429128647,
524
+ "epoch": 0.8688387635756056,
525
+ "grad_norm": 1.979646921157837,
526
+ "learning_rate": 2.1071750146835906e-05,
527
+ "loss": 1.5882,
528
+ "mean_token_accuracy": 0.6175018042325974,
529
+ "num_tokens": 1375550.0,
530
+ "step": 520
531
+ },
532
+ {
533
+ "entropy": 1.918816116452217,
534
+ "epoch": 0.885547201336675,
535
+ "grad_norm": 1.531023383140564,
536
+ "learning_rate": 2.06695005214336e-05,
537
+ "loss": 1.5158,
538
+ "mean_token_accuracy": 0.6258822798728942,
539
+ "num_tokens": 1401535.0,
540
+ "step": 530
541
+ },
542
+ {
543
+ "entropy": 1.918640747666359,
544
+ "epoch": 0.9022556390977443,
545
+ "grad_norm": 1.6574758291244507,
546
+ "learning_rate": 2.026243611782818e-05,
547
+ "loss": 1.4805,
548
+ "mean_token_accuracy": 0.6370069451630116,
549
+ "num_tokens": 1430094.0,
550
+ "step": 540
551
+ },
552
+ {
553
+ "entropy": 2.0166410475969316,
554
+ "epoch": 0.9189640768588136,
555
+ "grad_norm": 2.085106372833252,
556
+ "learning_rate": 1.9850902632225228e-05,
557
+ "loss": 1.6067,
558
+ "mean_token_accuracy": 0.613443473726511,
559
+ "num_tokens": 1453767.0,
560
+ "step": 550
561
+ },
562
+ {
563
+ "entropy": 1.9751090347766875,
564
+ "epoch": 0.935672514619883,
565
+ "grad_norm": 1.5619549751281738,
566
+ "learning_rate": 1.9435249556162633e-05,
567
+ "loss": 1.5186,
568
+ "mean_token_accuracy": 0.6245452538132668,
569
+ "num_tokens": 1479122.0,
570
+ "step": 560
571
+ },
572
+ {
573
+ "entropy": 2.0289832055568695,
574
+ "epoch": 0.9523809523809523,
575
+ "grad_norm": 1.9765042066574097,
576
+ "learning_rate": 1.9015829879707705e-05,
577
+ "loss": 1.635,
578
+ "mean_token_accuracy": 0.6078214071691036,
579
+ "num_tokens": 1502393.0,
580
+ "step": 570
581
+ },
582
+ {
583
+ "entropy": 2.0707653611898422,
584
+ "epoch": 0.9690893901420217,
585
+ "grad_norm": 2.33292293548584,
586
+ "learning_rate": 1.8592999791683163e-05,
587
+ "loss": 1.7044,
588
+ "mean_token_accuracy": 0.5983508452773094,
589
+ "num_tokens": 1528688.0,
590
+ "step": 580
591
+ },
592
+ {
593
+ "entropy": 1.830039870738983,
594
+ "epoch": 0.985797827903091,
595
+ "grad_norm": 1.7089521884918213,
596
+ "learning_rate": 1.8167118377176626e-05,
597
+ "loss": 1.4488,
598
+ "mean_token_accuracy": 0.6382713422179223,
599
+ "num_tokens": 1559267.0,
600
+ "step": 590
601
+ },
602
+ {
603
+ "entropy": 2.093587511464169,
604
+ "epoch": 1.001670843776107,
605
+ "grad_norm": 1.8502051830291748,
606
+ "learning_rate": 1.7738547312590426e-05,
607
+ "loss": 1.6569,
608
+ "mean_token_accuracy": 0.6035293050502476,
609
+ "num_tokens": 1579777.0,
610
+ "step": 600
611
+ },
612
+ {
613
+ "entropy": 1.986822435259819,
614
+ "epoch": 1.0183792815371762,
615
+ "grad_norm": 1.8095533847808838,
616
+ "learning_rate": 1.7307650558490842e-05,
617
+ "loss": 1.5196,
618
+ "mean_token_accuracy": 0.624878978729248,
619
+ "num_tokens": 1603371.0,
620
+ "step": 610
621
+ },
622
+ {
623
+ "entropy": 1.8720842987298965,
624
+ "epoch": 1.0350877192982457,
625
+ "grad_norm": 1.418859601020813,
626
+ "learning_rate": 1.687479405051745e-05,
627
+ "loss": 1.4617,
628
+ "mean_token_accuracy": 0.6376385740935803,
629
+ "num_tokens": 1629671.0,
630
+ "step": 620
631
+ },
632
+ {
633
+ "entropy": 1.9420676857233048,
634
+ "epoch": 1.0517961570593148,
635
+ "grad_norm": 1.9264510869979858,
636
+ "learning_rate": 1.6440345388615225e-05,
637
+ "loss": 1.5184,
638
+ "mean_token_accuracy": 0.6275502189993858,
639
+ "num_tokens": 1654665.0,
640
+ "step": 630
641
+ },
642
+ {
643
+ "entropy": 1.877267986536026,
644
+ "epoch": 1.0685045948203844,
645
+ "grad_norm": 1.5752804279327393,
646
+ "learning_rate": 1.6004673524853184e-05,
647
+ "loss": 1.4846,
648
+ "mean_token_accuracy": 0.6406380534172058,
649
+ "num_tokens": 1681208.0,
650
+ "step": 640
651
+ },
652
+ {
653
+ "entropy": 1.7192733228206634,
654
+ "epoch": 1.0852130325814535,
655
+ "grad_norm": 1.8777337074279785,
656
+ "learning_rate": 1.5568148450094788e-05,
657
+ "loss": 1.3596,
658
+ "mean_token_accuracy": 0.6518337815999985,
659
+ "num_tokens": 1711943.0,
660
+ "step": 650
661
+ },
662
+ {
663
+ "entropy": 1.8170194894075393,
664
+ "epoch": 1.101921470342523,
665
+ "grad_norm": 1.324455738067627,
666
+ "learning_rate": 1.5131140879786162e-05,
667
+ "loss": 1.3627,
668
+ "mean_token_accuracy": 0.6482401996850967,
669
+ "num_tokens": 1744406.0,
670
+ "step": 660
671
+ },
672
+ {
673
+ "entropy": 1.9752755105495452,
674
+ "epoch": 1.1186299081035922,
675
+ "grad_norm": 1.697969913482666,
676
+ "learning_rate": 1.4694021939128925e-05,
677
+ "loss": 1.6435,
678
+ "mean_token_accuracy": 0.6173132970929146,
679
+ "num_tokens": 1763684.0,
680
+ "step": 670
681
+ },
682
+ {
683
+ "entropy": 1.810714191198349,
684
+ "epoch": 1.1353383458646618,
685
+ "grad_norm": 1.6863676309585571,
686
+ "learning_rate": 1.4257162847905073e-05,
687
+ "loss": 1.4572,
688
+ "mean_token_accuracy": 0.6450446091592312,
689
+ "num_tokens": 1790387.0,
690
+ "step": 680
691
+ },
692
+ {
693
+ "entropy": 1.7295511305332183,
694
+ "epoch": 1.1520467836257309,
695
+ "grad_norm": 1.8147404193878174,
696
+ "learning_rate": 1.3820934605221554e-05,
697
+ "loss": 1.4375,
698
+ "mean_token_accuracy": 0.656483718752861,
699
+ "num_tokens": 1818936.0,
700
+ "step": 690
701
+ },
702
+ {
703
+ "entropy": 1.876406043767929,
704
+ "epoch": 1.1687552213868004,
705
+ "grad_norm": 1.4509400129318237,
706
+ "learning_rate": 1.3385707674442212e-05,
707
+ "loss": 1.5038,
708
+ "mean_token_accuracy": 0.6330045036971569,
709
+ "num_tokens": 1844285.0,
710
+ "step": 700
711
+ },
712
+ {
713
+ "entropy": 1.7754180505871773,
714
+ "epoch": 1.1854636591478696,
715
+ "grad_norm": 1.8553998470306396,
716
+ "learning_rate": 1.295185166857471e-05,
717
+ "loss": 1.3342,
718
+ "mean_token_accuracy": 0.6631456315517426,
719
+ "num_tokens": 1872386.0,
720
+ "step": 710
721
+ },
722
+ {
723
+ "entropy": 1.8854310810565948,
724
+ "epoch": 1.2021720969089391,
725
+ "grad_norm": 1.9020118713378906,
726
+ "learning_rate": 1.2519735036379654e-05,
727
+ "loss": 1.5075,
728
+ "mean_token_accuracy": 0.6296862445771694,
729
+ "num_tokens": 1898136.0,
730
+ "step": 720
731
+ },
732
+ {
733
+ "entropy": 1.8075116664171218,
734
+ "epoch": 1.2188805346700082,
735
+ "grad_norm": 1.4228155612945557,
736
+ "learning_rate": 1.2089724749468383e-05,
737
+ "loss": 1.475,
738
+ "mean_token_accuracy": 0.63388437256217,
739
+ "num_tokens": 1926755.0,
740
+ "step": 730
741
+ },
742
+ {
743
+ "entropy": 1.9176389634609223,
744
+ "epoch": 1.2355889724310778,
745
+ "grad_norm": 1.4030358791351318,
746
+ "learning_rate": 1.1662185990655285e-05,
747
+ "loss": 1.4261,
748
+ "mean_token_accuracy": 0.6366409629583358,
749
+ "num_tokens": 1954094.0,
750
+ "step": 740
751
+ },
752
+ {
753
+ "entropy": 1.9318130016326904,
754
+ "epoch": 1.252297410192147,
755
+ "grad_norm": 2.5528788566589355,
756
+ "learning_rate": 1.1237481843829162e-05,
757
+ "loss": 1.637,
758
+ "mean_token_accuracy": 0.6269572585821152,
759
+ "num_tokens": 1977028.0,
760
+ "step": 750
761
+ },
762
+ {
763
+ "entropy": 1.8894671678543091,
764
+ "epoch": 1.2690058479532165,
765
+ "grad_norm": 1.5508147478103638,
766
+ "learning_rate": 1.0815972985607149e-05,
767
+ "loss": 1.5153,
768
+ "mean_token_accuracy": 0.6365115389227867,
769
+ "num_tokens": 2000096.0,
770
+ "step": 760
771
+ },
772
+ {
773
+ "entropy": 1.9068289607763291,
774
+ "epoch": 1.2857142857142856,
775
+ "grad_norm": 1.2476104497909546,
776
+ "learning_rate": 1.0398017379032955e-05,
777
+ "loss": 1.5797,
778
+ "mean_token_accuracy": 0.6310160294175148,
779
+ "num_tokens": 2024669.0,
780
+ "step": 770
781
+ },
782
+ {
783
+ "entropy": 1.7813611298799514,
784
+ "epoch": 1.3024227234753551,
785
+ "grad_norm": 2.0824921131134033,
786
+ "learning_rate": 9.983969969579616e-06,
787
+ "loss": 1.4656,
788
+ "mean_token_accuracy": 0.6474256098270417,
789
+ "num_tokens": 2051877.0,
790
+ "step": 780
791
+ },
792
+ {
793
+ "entropy": 1.8404263019561768,
794
+ "epoch": 1.3191311612364243,
795
+ "grad_norm": 1.2777612209320068,
796
+ "learning_rate": 9.574182383714839e-06,
797
+ "loss": 1.4355,
798
+ "mean_token_accuracy": 0.6538358055055141,
799
+ "num_tokens": 2079905.0,
800
+ "step": 790
801
+ },
802
+ {
803
+ "entropy": 1.8420085251331328,
804
+ "epoch": 1.3358395989974938,
805
+ "grad_norm": 1.2849156856536865,
806
+ "learning_rate": 9.169002630285063e-06,
807
+ "loss": 1.4413,
808
+ "mean_token_accuracy": 0.6362872712314129,
809
+ "num_tokens": 2109705.0,
810
+ "step": 800
811
+ },
812
+ {
813
+ "entropy": 1.9093056112527846,
814
+ "epoch": 1.352548036758563,
815
+ "grad_norm": 1.3787521123886108,
816
+ "learning_rate": 8.768774804971705e-06,
817
+ "loss": 1.4332,
818
+ "mean_token_accuracy": 0.646092452853918,
819
+ "num_tokens": 2136002.0,
820
+ "step": 810
821
+ },
822
+ {
823
+ "entropy": 1.8188541814684869,
824
+ "epoch": 1.3692564745196325,
825
+ "grad_norm": 1.9946447610855103,
826
+ "learning_rate": 8.37383879807061e-06,
827
+ "loss": 1.4213,
828
+ "mean_token_accuracy": 0.6514127373695373,
829
+ "num_tokens": 2162939.0,
830
+ "step": 820
831
+ },
832
+ {
833
+ "entropy": 1.767152488231659,
834
+ "epoch": 1.3859649122807016,
835
+ "grad_norm": 2.6128296852111816,
836
+ "learning_rate": 7.98453000584296e-06,
837
+ "loss": 1.4077,
838
+ "mean_token_accuracy": 0.6433039925992489,
839
+ "num_tokens": 2192868.0,
840
+ "step": 830
841
+ },
842
+ {
843
+ "entropy": 1.8834378957748412,
844
+ "epoch": 1.4026733500417712,
845
+ "grad_norm": 2.5565028190612793,
846
+ "learning_rate": 7.601179045682659e-06,
847
+ "loss": 1.4508,
848
+ "mean_token_accuracy": 0.6357239708304405,
849
+ "num_tokens": 2220574.0,
850
+ "step": 840
851
+ },
852
+ {
853
+ "entropy": 1.8659739628434182,
854
+ "epoch": 1.4193817878028403,
855
+ "grad_norm": 1.6156526803970337,
856
+ "learning_rate": 7.2241114753421245e-06,
857
+ "loss": 1.4151,
858
+ "mean_token_accuracy": 0.6440570905804635,
859
+ "num_tokens": 2247980.0,
860
+ "step": 850
861
+ },
862
+ {
863
+ "entropy": 2.0131053000688555,
864
+ "epoch": 1.4360902255639099,
865
+ "grad_norm": 1.5411407947540283,
866
+ "learning_rate": 6.853647516454978e-06,
867
+ "loss": 1.7022,
868
+ "mean_token_accuracy": 0.6108858585357666,
869
+ "num_tokens": 2271288.0,
870
+ "step": 860
871
+ },
872
+ {
873
+ "entropy": 1.9804413557052611,
874
+ "epoch": 1.452798663324979,
875
+ "grad_norm": 1.2808128595352173,
876
+ "learning_rate": 6.490101782590357e-06,
877
+ "loss": 1.502,
878
+ "mean_token_accuracy": 0.6262324623763561,
879
+ "num_tokens": 2297295.0,
880
+ "step": 870
881
+ },
882
+ {
883
+ "entropy": 1.7805092990398408,
884
+ "epoch": 1.4695071010860485,
885
+ "grad_norm": 1.404811978340149,
886
+ "learning_rate": 6.133783012069853e-06,
887
+ "loss": 1.3104,
888
+ "mean_token_accuracy": 0.6503325693309308,
889
+ "num_tokens": 2325314.0,
890
+ "step": 880
891
+ },
892
+ {
893
+ "entropy": 1.8354784041643142,
894
+ "epoch": 1.4862155388471177,
895
+ "grad_norm": 1.467010736465454,
896
+ "learning_rate": 5.784993805773946e-06,
897
+ "loss": 1.4201,
898
+ "mean_token_accuracy": 0.6422530055046082,
899
+ "num_tokens": 2353565.0,
900
+ "step": 890
901
+ },
902
+ {
903
+ "entropy": 1.9021347552537917,
904
+ "epoch": 1.5029239766081872,
905
+ "grad_norm": 1.5276216268539429,
906
+ "learning_rate": 5.44403037016061e-06,
907
+ "loss": 1.5201,
908
+ "mean_token_accuracy": 0.6460477262735367,
909
+ "num_tokens": 2375717.0,
910
+ "step": 900
911
+ },
912
+ {
913
+ "entropy": 1.8378847867250443,
914
+ "epoch": 1.5196324143692563,
915
+ "grad_norm": 1.413011908531189,
916
+ "learning_rate": 5.11118226571434e-06,
917
+ "loss": 1.4236,
918
+ "mean_token_accuracy": 0.6440291911363601,
919
+ "num_tokens": 2404483.0,
920
+ "step": 910
921
+ },
922
+ {
923
+ "entropy": 1.8757817566394805,
924
+ "epoch": 1.536340852130326,
925
+ "grad_norm": 1.5251425504684448,
926
+ "learning_rate": 4.786732161039234e-06,
927
+ "loss": 1.5295,
928
+ "mean_token_accuracy": 0.6261114202439785,
929
+ "num_tokens": 2431919.0,
930
+ "step": 920
931
+ },
932
+ {
933
+ "entropy": 1.8587533831596375,
934
+ "epoch": 1.553049289891395,
935
+ "grad_norm": 1.647172451019287,
936
+ "learning_rate": 4.470955592804871e-06,
937
+ "loss": 1.3916,
938
+ "mean_token_accuracy": 0.6414183430373669,
939
+ "num_tokens": 2461737.0,
940
+ "step": 930
941
+ },
942
+ {
943
+ "entropy": 1.8832595944404602,
944
+ "epoch": 1.5697577276524646,
945
+ "grad_norm": 2.1904146671295166,
946
+ "learning_rate": 4.164120731749072e-06,
947
+ "loss": 1.5253,
948
+ "mean_token_accuracy": 0.63388307467103,
949
+ "num_tokens": 2484053.0,
950
+ "step": 940
951
+ },
952
+ {
953
+ "entropy": 1.9385288596153258,
954
+ "epoch": 1.5864661654135337,
955
+ "grad_norm": 1.4704978466033936,
956
+ "learning_rate": 3.866488154935951e-06,
957
+ "loss": 1.544,
958
+ "mean_token_accuracy": 0.6218141697347164,
959
+ "num_tokens": 2509336.0,
960
+ "step": 950
961
+ },
962
+ {
963
+ "entropy": 1.92947296500206,
964
+ "epoch": 1.6031746031746033,
965
+ "grad_norm": 2.599453926086426,
966
+ "learning_rate": 3.5783106244629837e-06,
967
+ "loss": 1.4998,
968
+ "mean_token_accuracy": 0.6333407089114189,
969
+ "num_tokens": 2534725.0,
970
+ "step": 960
971
+ },
972
+ {
973
+ "entropy": 1.7914826542139053,
974
+ "epoch": 1.6198830409356724,
975
+ "grad_norm": 1.3860251903533936,
976
+ "learning_rate": 3.299832872804765e-06,
977
+ "loss": 1.4052,
978
+ "mean_token_accuracy": 0.6594420954585075,
979
+ "num_tokens": 2561604.0,
980
+ "step": 970
981
+ },
982
+ {
983
+ "entropy": 1.9076363742351532,
984
+ "epoch": 1.636591478696742,
985
+ "grad_norm": 1.7287890911102295,
986
+ "learning_rate": 3.0312913949759196e-06,
987
+ "loss": 1.4772,
988
+ "mean_token_accuracy": 0.6380034938454628,
989
+ "num_tokens": 2586962.0,
990
+ "step": 980
991
+ },
992
+ {
993
+ "entropy": 1.897977489233017,
994
+ "epoch": 1.653299916457811,
995
+ "grad_norm": 1.6165651082992554,
996
+ "learning_rate": 2.77291424768959e-06,
997
+ "loss": 1.4259,
998
+ "mean_token_accuracy": 0.6349127419292927,
999
+ "num_tokens": 2614128.0,
1000
+ "step": 990
1001
+ },
1002
+ {
1003
+ "entropy": 1.9598186224699021,
1004
+ "epoch": 1.6700083542188806,
1005
+ "grad_norm": 2.7245564460754395,
1006
+ "learning_rate": 2.5249208556820908e-06,
1007
+ "loss": 1.5447,
1008
+ "mean_token_accuracy": 0.6180414237082005,
1009
+ "num_tokens": 2638378.0,
1010
+ "step": 1000
1011
+ },
1012
+ {
1013
+ "entropy": 1.8438974112272262,
1014
+ "epoch": 1.6867167919799497,
1015
+ "grad_norm": 1.519782543182373,
1016
+ "learning_rate": 2.287521825368189e-06,
1017
+ "loss": 1.4452,
1018
+ "mean_token_accuracy": 0.6378182969987393,
1019
+ "num_tokens": 2667006.0,
1020
+ "step": 1010
1021
+ },
1022
+ {
1023
+ "entropy": 1.8624888569116593,
1024
+ "epoch": 1.7034252297410193,
1025
+ "grad_norm": 1.3807040452957153,
1026
+ "learning_rate": 2.060918765985288e-06,
1027
+ "loss": 1.4039,
1028
+ "mean_token_accuracy": 0.6466488510370254,
1029
+ "num_tokens": 2694457.0,
1030
+ "step": 1020
1031
+ },
1032
+ {
1033
+ "entropy": 1.752406159043312,
1034
+ "epoch": 1.7201336675020884,
1035
+ "grad_norm": 1.9477757215499878,
1036
+ "learning_rate": 1.8453041183783953e-06,
1037
+ "loss": 1.3724,
1038
+ "mean_token_accuracy": 0.6649182379245758,
1039
+ "num_tokens": 2721514.0,
1040
+ "step": 1030
1041
+ },
1042
+ {
1043
+ "entropy": 1.867113146185875,
1044
+ "epoch": 1.736842105263158,
1045
+ "grad_norm": 1.5146008729934692,
1046
+ "learning_rate": 1.6408609915712397e-06,
1047
+ "loss": 1.4912,
1048
+ "mean_token_accuracy": 0.6285726055502892,
1049
+ "num_tokens": 2749941.0,
1050
+ "step": 1040
1051
+ },
1052
+ {
1053
+ "entropy": 1.881867691874504,
1054
+ "epoch": 1.753550543024227,
1055
+ "grad_norm": 1.1970162391662598,
1056
+ "learning_rate": 1.447763007262431e-06,
1057
+ "loss": 1.4274,
1058
+ "mean_token_accuracy": 0.6479133352637291,
1059
+ "num_tokens": 2774956.0,
1060
+ "step": 1050
1061
+ },
1062
+ {
1063
+ "entropy": 1.8124820232391357,
1064
+ "epoch": 1.7702589807852966,
1065
+ "grad_norm": 1.135063886642456,
1066
+ "learning_rate": 1.2661741523785637e-06,
1067
+ "loss": 1.3427,
1068
+ "mean_token_accuracy": 0.6474431194365025,
1069
+ "num_tokens": 2805317.0,
1070
+ "step": 1060
1071
+ },
1072
+ {
1073
+ "entropy": 1.9482445955276488,
1074
+ "epoch": 1.7869674185463658,
1075
+ "grad_norm": 1.608454942703247,
1076
+ "learning_rate": 1.0962486398096755e-06,
1077
+ "loss": 1.5699,
1078
+ "mean_token_accuracy": 0.6215325608849526,
1079
+ "num_tokens": 2832036.0,
1080
+ "step": 1070
1081
+ },
1082
+ {
1083
+ "entropy": 1.945644235610962,
1084
+ "epoch": 1.8036758563074353,
1085
+ "grad_norm": 2.766500949859619,
1086
+ "learning_rate": 9.381307774451348e-07,
1087
+ "loss": 1.5286,
1088
+ "mean_token_accuracy": 0.6369006544351578,
1089
+ "num_tokens": 2855743.0,
1090
+ "step": 1080
1091
+ },
1092
+ {
1093
+ "entropy": 1.8863470137119294,
1094
+ "epoch": 1.8203842940685044,
1095
+ "grad_norm": 1.3567376136779785,
1096
+ "learning_rate": 7.919548456213516e-07,
1097
+ "loss": 1.5037,
1098
+ "mean_token_accuracy": 0.6256943866610527,
1099
+ "num_tokens": 2881629.0,
1100
+ "step": 1090
1101
+ },
1102
+ {
1103
+ "entropy": 1.7123635321855546,
1104
+ "epoch": 1.837092731829574,
1105
+ "grad_norm": 1.452407956123352,
1106
+ "learning_rate": 6.578449830852279e-07,
1107
+ "loss": 1.4047,
1108
+ "mean_token_accuracy": 0.65928635597229,
1109
+ "num_tokens": 2908678.0,
1110
+ "step": 1100
1111
+ },
1112
+ {
1113
+ "entropy": 1.8440750926733016,
1114
+ "epoch": 1.8538011695906431,
1115
+ "grad_norm": 1.331641435623169,
1116
+ "learning_rate": 5.359150815703629e-07,
1117
+ "loss": 1.4408,
1118
+ "mean_token_accuracy": 0.6417556688189506,
1119
+ "num_tokens": 2937408.0,
1120
+ "step": 1110
1121
+ },
1122
+ {
1123
+ "entropy": 1.919699600338936,
1124
+ "epoch": 1.8705096073517127,
1125
+ "grad_norm": 1.5076831579208374,
1126
+ "learning_rate": 4.2626868907536034e-07,
1127
+ "loss": 1.4585,
1128
+ "mean_token_accuracy": 0.6399278536438942,
1129
+ "num_tokens": 2962447.0,
1130
+ "step": 1120
1131
+ },
1132
+ {
1133
+ "entropy": 1.8350076168775558,
1134
+ "epoch": 1.8872180451127818,
1135
+ "grad_norm": 1.707216739654541,
1136
+ "learning_rate": 3.289989219265466e-07,
1137
+ "loss": 1.4885,
1138
+ "mean_token_accuracy": 0.6428370043635369,
1139
+ "num_tokens": 2987461.0,
1140
+ "step": 1130
1141
+ },
1142
+ {
1143
+ "entropy": 1.8436865717172624,
1144
+ "epoch": 1.9039264828738514,
1145
+ "grad_norm": 2.3200364112854004,
1146
+ "learning_rate": 2.441883856996513e-07,
1147
+ "loss": 1.5211,
1148
+ "mean_token_accuracy": 0.640003713965416,
1149
+ "num_tokens": 3011483.0,
1150
+ "step": 1140
1151
+ },
1152
+ {
1153
+ "entropy": 1.8367240995168685,
1154
+ "epoch": 1.9206349206349205,
1155
+ "grad_norm": 1.7375178337097168,
1156
+ "learning_rate": 1.719091050676902e-07,
1157
+ "loss": 1.4348,
1158
+ "mean_token_accuracy": 0.644163503497839,
1159
+ "num_tokens": 3038564.0,
1160
+ "step": 1150
1161
+ },
1162
+ {
1163
+ "entropy": 1.9745660215616225,
1164
+ "epoch": 1.93734335839599,
1165
+ "grad_norm": 1.5831917524337769,
1166
+ "learning_rate": 1.1222246263458469e-07,
1167
+ "loss": 1.6556,
1168
+ "mean_token_accuracy": 0.6158465214073658,
1169
+ "num_tokens": 3059313.0,
1170
+ "step": 1160
1171
+ },
1172
+ {
1173
+ "entropy": 1.8914725601673126,
1174
+ "epoch": 1.9540517961570592,
1175
+ "grad_norm": 1.6992645263671875,
1176
+ "learning_rate": 6.517914680646386e-08,
1177
+ "loss": 1.39,
1178
+ "mean_token_accuracy": 0.6418868929147721,
1179
+ "num_tokens": 3084800.0,
1180
+ "step": 1170
1181
+ },
1182
+ {
1183
+ "entropy": 1.8038861930370331,
1184
+ "epoch": 1.9707602339181287,
1185
+ "grad_norm": 1.4963058233261108,
1186
+ "learning_rate": 3.081910874495497e-08,
1187
+ "loss": 1.3698,
1188
+ "mean_token_accuracy": 0.6503725171089172,
1189
+ "num_tokens": 3113883.0,
1190
+ "step": 1180
1191
+ },
1192
+ {
1193
+ "entropy": 1.8201948583126069,
1194
+ "epoch": 1.9874686716791978,
1195
+ "grad_norm": 2.040982723236084,
1196
+ "learning_rate": 9.171528438959852e-09,
1197
+ "loss": 1.4156,
1198
+ "mean_token_accuracy": 0.6591305956244469,
1199
+ "num_tokens": 3138912.0,
1200
+ "step": 1190
1201
+ }
1202
+ ],
1203
+ "logging_steps": 10,
1204
+ "max_steps": 1198,
1205
+ "num_input_tokens_seen": 0,
1206
+ "num_train_epochs": 2,
1207
+ "save_steps": 500,
1208
+ "stateful_callbacks": {
1209
+ "TrainerControl": {
1210
+ "args": {
1211
+ "should_epoch_stop": false,
1212
+ "should_evaluate": false,
1213
+ "should_log": false,
1214
+ "should_save": true,
1215
+ "should_training_stop": true
1216
+ },
1217
+ "attributes": {}
1218
+ }
1219
+ },
1220
+ "total_flos": 1.4514045996918374e+17,
1221
+ "train_batch_size": 4,
1222
+ "trial_name": null,
1223
+ "trial_params": null
1224
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f550b84b2a5ce96c524e9755c1ad56be730f5a1e569546f129fde224923c78d5
3
+ size 6289