bharathkumarK commited on
Commit
8c01688
·
verified ·
1 Parent(s): 6121f92

Add iter3-2epoch adapter

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. iter3-2epoch/README.md +62 -0
  3. iter3-2epoch/adapter_config.json +42 -0
  4. iter3-2epoch/adapter_model.safetensors +3 -0
  5. iter3-2epoch/chat_template.jinja +5 -0
  6. iter3-2epoch/checkpoint-6000/README.md +209 -0
  7. iter3-2epoch/checkpoint-6000/adapter_config.json +42 -0
  8. iter3-2epoch/checkpoint-6000/adapter_model.safetensors +3 -0
  9. iter3-2epoch/checkpoint-6000/chat_template.jinja +5 -0
  10. iter3-2epoch/checkpoint-6000/rng_state_0.pth +3 -0
  11. iter3-2epoch/checkpoint-6000/rng_state_1.pth +3 -0
  12. iter3-2epoch/checkpoint-6000/rng_state_2.pth +3 -0
  13. iter3-2epoch/checkpoint-6000/rng_state_3.pth +3 -0
  14. iter3-2epoch/checkpoint-6000/rng_state_4.pth +3 -0
  15. iter3-2epoch/checkpoint-6000/rng_state_5.pth +3 -0
  16. iter3-2epoch/checkpoint-6000/rng_state_6.pth +3 -0
  17. iter3-2epoch/checkpoint-6000/rng_state_7.pth +3 -0
  18. iter3-2epoch/checkpoint-6000/special_tokens_map.json +17 -0
  19. iter3-2epoch/checkpoint-6000/tokenizer.json +3 -0
  20. iter3-2epoch/checkpoint-6000/tokenizer_config.json +2063 -0
  21. iter3-2epoch/checkpoint-6000/trainer_state.json +1310 -0
  22. iter3-2epoch/checkpoint-7000/README.md +209 -0
  23. iter3-2epoch/checkpoint-7000/adapter_config.json +42 -0
  24. iter3-2epoch/checkpoint-7000/adapter_model.safetensors +3 -0
  25. iter3-2epoch/checkpoint-7000/chat_template.jinja +5 -0
  26. iter3-2epoch/checkpoint-7000/rng_state_0.pth +3 -0
  27. iter3-2epoch/checkpoint-7000/rng_state_1.pth +3 -0
  28. iter3-2epoch/checkpoint-7000/rng_state_2.pth +3 -0
  29. iter3-2epoch/checkpoint-7000/rng_state_3.pth +3 -0
  30. iter3-2epoch/checkpoint-7000/rng_state_4.pth +3 -0
  31. iter3-2epoch/checkpoint-7000/rng_state_5.pth +3 -0
  32. iter3-2epoch/checkpoint-7000/rng_state_6.pth +3 -0
  33. iter3-2epoch/checkpoint-7000/rng_state_7.pth +3 -0
  34. iter3-2epoch/checkpoint-7000/special_tokens_map.json +17 -0
  35. iter3-2epoch/checkpoint-7000/tokenizer.json +3 -0
  36. iter3-2epoch/checkpoint-7000/tokenizer_config.json +2063 -0
  37. iter3-2epoch/checkpoint-7000/trainer_state.json +1521 -0
  38. iter3-2epoch/checkpoint-7658/README.md +209 -0
  39. iter3-2epoch/checkpoint-7658/adapter_config.json +42 -0
  40. iter3-2epoch/checkpoint-7658/adapter_model.safetensors +3 -0
  41. iter3-2epoch/checkpoint-7658/chat_template.jinja +5 -0
  42. iter3-2epoch/checkpoint-7658/rng_state_0.pth +3 -0
  43. iter3-2epoch/checkpoint-7658/rng_state_1.pth +3 -0
  44. iter3-2epoch/checkpoint-7658/rng_state_2.pth +3 -0
  45. iter3-2epoch/checkpoint-7658/rng_state_3.pth +3 -0
  46. iter3-2epoch/checkpoint-7658/rng_state_4.pth +3 -0
  47. iter3-2epoch/checkpoint-7658/rng_state_5.pth +3 -0
  48. iter3-2epoch/checkpoint-7658/rng_state_6.pth +3 -0
  49. iter3-2epoch/checkpoint-7658/rng_state_7.pth +3 -0
  50. iter3-2epoch/checkpoint-7658/special_tokens_map.json +17 -0
.gitattributes CHANGED
@@ -40,3 +40,7 @@ iter2-3epoch/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  iter2-3epoch/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  iter2-3epoch/checkpoint-4596/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  iter2-3epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
40
  iter2-3epoch/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  iter2-3epoch/checkpoint-4596/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
  iter2-3epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ iter3-2epoch/checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
44
+ iter3-2epoch/checkpoint-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
45
+ iter3-2epoch/checkpoint-7658/tokenizer.json filter=lfs diff=lfs merge=lfs -text
46
+ iter3-2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
iter3-2epoch/README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ model_name: iter3_2epoch_r256_aggressive
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
7
+ - lora
8
+ - sft
9
+ - transformers
10
+ - trl
11
+ licence: license
12
+ pipeline_tag: text-generation
13
+ ---
14
+
15
+ # Model Card for iter3_2epoch_r256_aggressive
16
+
17
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
18
+ It has been trained using [TRL](https://github.com/huggingface/trl).
19
+
20
+ ## Quick start
21
+
22
+ ```python
23
+ from transformers import pipeline
24
+
25
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
26
+ generator = pipeline("text-generation", model="None", device="cuda")
27
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
28
+ print(output["generated_text"])
29
+ ```
30
+
31
+ ## Training procedure
32
+
33
+
34
+
35
+
36
+ This model was trained with SFT.
37
+
38
+ ### Framework versions
39
+
40
+ - PEFT 0.17.1
41
+ - TRL: 0.24.0
42
+ - Transformers: 4.57.1
43
+ - Pytorch: 2.5.1+cu124
44
+ - Datasets: 4.3.0
45
+ - Tokenizers: 0.22.1
46
+
47
+ ## Citations
48
+
49
+
50
+
51
+ Cite TRL as:
52
+
53
+ ```bibtex
54
+ @misc{vonwerra2022trl,
55
+ title = {{TRL: Transformer Reinforcement Learning}},
56
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
57
+ year = 2020,
58
+ journal = {GitHub repository},
59
+ publisher = {GitHub},
60
+ howpublished = {\url{https://github.com/huggingface/trl}}
61
+ }
62
+ ```
iter3-2epoch/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 256,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "down_proj",
29
+ "v_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
iter3-2epoch/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3d64c6b16fa8a9f121abe5b3d76dfbb7f0bdce0ed47f514bceabd19bbf33cc
3
+ size 2684416208
iter3-2epoch/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
iter3-2epoch/checkpoint-6000/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
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 0.17.1
iter3-2epoch/checkpoint-6000/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 256,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "down_proj",
29
+ "v_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
iter3-2epoch/checkpoint-6000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9115debfa57164f0bafea747b7b4e511d02115140a53519b7dc6f9ea09730bbd
3
+ size 2684416208
iter3-2epoch/checkpoint-6000/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
iter3-2epoch/checkpoint-6000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ca1743ca269063c84209059566cdbcb948d23923fb3a64cf79a0f02ae7a507
3
+ size 15984
iter3-2epoch/checkpoint-6000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc34529e04009a4dc517bfb2a73fbffdf8b472f98caadd5516fb13f1346a1e1
3
+ size 15984
iter3-2epoch/checkpoint-6000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472bd8e2758282ed79b4f570c1e412480cb51d0079fb7a201daabec0b9388a5e
3
+ size 15984
iter3-2epoch/checkpoint-6000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a5b267819d021ce3d21a67a712581d83ec2cd308c2542d43eefd61e3a506c53
3
+ size 15984
iter3-2epoch/checkpoint-6000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74580bbb7ca310e1a9888dda0b2ca4b05dc2febcf6059b99ad06732b9ad68e82
3
+ size 15984
iter3-2epoch/checkpoint-6000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aefcf5f7b093d632c81f7c50999af29afdf2c3ed8ef686fd12cbef7db93e1ede
3
+ size 15984
iter3-2epoch/checkpoint-6000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f892e60346bbf4cdf544c806440df7c451833dd7019042367f9e015757899f5f
3
+ size 15984
iter3-2epoch/checkpoint-6000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8232814e2c2217da5227e3ea6028b2420b04509805c8099967ca8c150ff71a4a
3
+ size 15984
iter3-2epoch/checkpoint-6000/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
iter3-2epoch/checkpoint-6000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
iter3-2epoch/checkpoint-6000/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
iter3-2epoch/checkpoint-6000/trainer_state.json ADDED
@@ -0,0 +1,1310 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 6000,
3
+ "best_metric": 0.06929752975702286,
4
+ "best_model_checkpoint": "runs/iter3_2epoch_r256_aggressive/checkpoint-6000",
5
+ "epoch": 1.5671183673469389,
6
+ "eval_steps": 1000,
7
+ "global_step": 6000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 0.9600491151213646,
14
+ "epoch": 0.00026122448979591835,
15
+ "grad_norm": 4.874749183654785,
16
+ "learning_rate": 0.0,
17
+ "loss": 1.5426,
18
+ "mean_token_accuracy": 0.5253331288695335,
19
+ "num_tokens": 92658.0,
20
+ "step": 1
21
+ },
22
+ {
23
+ "entropy": 1.0668207285355549,
24
+ "epoch": 0.013061224489795919,
25
+ "grad_norm": 0.3741045296192169,
26
+ "learning_rate": 3.181818181818182e-05,
27
+ "loss": 0.8201,
28
+ "mean_token_accuracy": 0.713900758295643,
29
+ "num_tokens": 4695822.0,
30
+ "step": 50
31
+ },
32
+ {
33
+ "entropy": 0.7840494087338448,
34
+ "epoch": 0.026122448979591838,
35
+ "grad_norm": 1.6816201210021973,
36
+ "learning_rate": 6.428571428571429e-05,
37
+ "loss": 0.5652,
38
+ "mean_token_accuracy": 0.8121247433125973,
39
+ "num_tokens": 9384030.0,
40
+ "step": 100
41
+ },
42
+ {
43
+ "entropy": 0.6429135516285897,
44
+ "epoch": 0.03918367346938775,
45
+ "grad_norm": 1.8123995065689087,
46
+ "learning_rate": 9.675324675324677e-05,
47
+ "loss": 0.4768,
48
+ "mean_token_accuracy": 0.8343716338276863,
49
+ "num_tokens": 14068659.0,
50
+ "step": 150
51
+ },
52
+ {
53
+ "entropy": 0.6180185662209987,
54
+ "epoch": 0.052244897959183675,
55
+ "grad_norm": 0.228230819106102,
56
+ "learning_rate": 9.99911270857259e-05,
57
+ "loss": 0.4195,
58
+ "mean_token_accuracy": 0.8369381006062031,
59
+ "num_tokens": 18749150.0,
60
+ "step": 200
61
+ },
62
+ {
63
+ "entropy": 0.6392524507641792,
64
+ "epoch": 0.0653061224489796,
65
+ "grad_norm": 0.3391082286834717,
66
+ "learning_rate": 9.99604593263008e-05,
67
+ "loss": 0.3747,
68
+ "mean_token_accuracy": 0.8521625240147114,
69
+ "num_tokens": 23444738.0,
70
+ "step": 250
71
+ },
72
+ {
73
+ "entropy": 0.6395396235585212,
74
+ "epoch": 0.0783673469387755,
75
+ "grad_norm": 0.35865047574043274,
76
+ "learning_rate": 9.990790061392936e-05,
77
+ "loss": 0.4622,
78
+ "mean_token_accuracy": 0.817176415771246,
79
+ "num_tokens": 28146459.0,
80
+ "step": 300
81
+ },
82
+ {
83
+ "entropy": 0.6052160003781318,
84
+ "epoch": 0.09142857142857143,
85
+ "grad_norm": 0.461127907037735,
86
+ "learning_rate": 9.983347397802953e-05,
87
+ "loss": 0.3964,
88
+ "mean_token_accuracy": 0.865231085717678,
89
+ "num_tokens": 32829584.0,
90
+ "step": 350
91
+ },
92
+ {
93
+ "entropy": 0.6162980204820633,
94
+ "epoch": 0.10448979591836735,
95
+ "grad_norm": 0.6675931811332703,
96
+ "learning_rate": 9.973721202979037e-05,
97
+ "loss": 0.4523,
98
+ "mean_token_accuracy": 0.8371678332984448,
99
+ "num_tokens": 37519736.0,
100
+ "step": 400
101
+ },
102
+ {
103
+ "entropy": 0.6373377884924412,
104
+ "epoch": 0.11755102040816326,
105
+ "grad_norm": 0.7843639254570007,
106
+ "learning_rate": 9.961915694788294e-05,
107
+ "loss": 0.4246,
108
+ "mean_token_accuracy": 0.8822347274422646,
109
+ "num_tokens": 42214834.0,
110
+ "step": 450
111
+ },
112
+ {
113
+ "entropy": 0.6182832332700491,
114
+ "epoch": 0.1306122448979592,
115
+ "grad_norm": 0.12627503275871277,
116
+ "learning_rate": 9.9479360459979e-05,
117
+ "loss": 0.3963,
118
+ "mean_token_accuracy": 0.8835959336161614,
119
+ "num_tokens": 46896384.0,
120
+ "step": 500
121
+ },
122
+ {
123
+ "entropy": 0.604607280343771,
124
+ "epoch": 0.1436734693877551,
125
+ "grad_norm": 0.33763670921325684,
126
+ "learning_rate": 9.931788382008588e-05,
127
+ "loss": 0.3126,
128
+ "mean_token_accuracy": 0.8891353133320808,
129
+ "num_tokens": 51611949.0,
130
+ "step": 550
131
+ },
132
+ {
133
+ "entropy": 0.6003445901721716,
134
+ "epoch": 0.156734693877551,
135
+ "grad_norm": 0.4399724304676056,
136
+ "learning_rate": 9.913479778170688e-05,
137
+ "loss": 0.2951,
138
+ "mean_token_accuracy": 0.89730602607131,
139
+ "num_tokens": 56295022.0,
140
+ "step": 600
141
+ },
142
+ {
143
+ "entropy": 0.6263976456224918,
144
+ "epoch": 0.16979591836734695,
145
+ "grad_norm": 0.24783462285995483,
146
+ "learning_rate": 9.893018256683967e-05,
147
+ "loss": 0.345,
148
+ "mean_token_accuracy": 0.8859454789757728,
149
+ "num_tokens": 60989496.0,
150
+ "step": 650
151
+ },
152
+ {
153
+ "entropy": 0.6047938592731953,
154
+ "epoch": 0.18285714285714286,
155
+ "grad_norm": 0.6106021404266357,
156
+ "learning_rate": 9.870412783082573e-05,
157
+ "loss": 0.4187,
158
+ "mean_token_accuracy": 0.8859497668594122,
159
+ "num_tokens": 65706938.0,
160
+ "step": 700
161
+ },
162
+ {
163
+ "entropy": 0.6086559303104877,
164
+ "epoch": 0.19591836734693877,
165
+ "grad_norm": 0.6276345252990723,
166
+ "learning_rate": 9.845673262306643e-05,
167
+ "loss": 0.2703,
168
+ "mean_token_accuracy": 0.9083889089524746,
169
+ "num_tokens": 70440218.0,
170
+ "step": 750
171
+ },
172
+ {
173
+ "entropy": 0.5998903425782919,
174
+ "epoch": 0.2089795918367347,
175
+ "grad_norm": 0.46106088161468506,
176
+ "learning_rate": 9.818810534362306e-05,
177
+ "loss": 0.3502,
178
+ "mean_token_accuracy": 0.8987785133719445,
179
+ "num_tokens": 75125260.0,
180
+ "step": 800
181
+ },
182
+ {
183
+ "entropy": 0.5996488413214683,
184
+ "epoch": 0.2220408163265306,
185
+ "grad_norm": 0.2753312289714813,
186
+ "learning_rate": 9.789836369571958e-05,
187
+ "loss": 0.3382,
188
+ "mean_token_accuracy": 0.9013783724606037,
189
+ "num_tokens": 79822058.0,
190
+ "step": 850
191
+ },
192
+ {
193
+ "entropy": 0.6070075839012862,
194
+ "epoch": 0.23510204081632652,
195
+ "grad_norm": 0.44265103340148926,
196
+ "learning_rate": 9.758763463416922e-05,
197
+ "loss": 0.3303,
198
+ "mean_token_accuracy": 0.9064150702953339,
199
+ "num_tokens": 84511616.0,
200
+ "step": 900
201
+ },
202
+ {
203
+ "entropy": 0.6011689330637455,
204
+ "epoch": 0.24816326530612245,
205
+ "grad_norm": 0.2258819341659546,
206
+ "learning_rate": 9.725605430974712e-05,
207
+ "loss": 0.281,
208
+ "mean_token_accuracy": 0.9128213880956173,
209
+ "num_tokens": 89218784.0,
210
+ "step": 950
211
+ },
212
+ {
213
+ "entropy": 0.610101203173399,
214
+ "epoch": 0.2612244897959184,
215
+ "grad_norm": 0.5324413180351257,
216
+ "learning_rate": 9.690376800953389e-05,
217
+ "loss": 0.2765,
218
+ "mean_token_accuracy": 0.9096981877088547,
219
+ "num_tokens": 93934733.0,
220
+ "step": 1000
221
+ },
222
+ {
223
+ "epoch": 0.2612244897959184,
224
+ "eval_entropy": 0.6072796992301941,
225
+ "eval_loss": 0.22717319428920746,
226
+ "eval_mean_token_accuracy": 0.9097091863632202,
227
+ "eval_num_tokens": 93934733.0,
228
+ "eval_runtime": 105.7447,
229
+ "eval_samples_per_second": 189.135,
230
+ "eval_steps_per_second": 5.91,
231
+ "step": 1000
232
+ },
233
+ {
234
+ "entropy": 0.6069025094807148,
235
+ "epoch": 0.2742857142857143,
236
+ "grad_norm": 0.32851845026016235,
237
+ "learning_rate": 9.65309300932557e-05,
238
+ "loss": 0.3301,
239
+ "mean_token_accuracy": 0.9123546965420246,
240
+ "num_tokens": 98646726.0,
241
+ "step": 1050
242
+ },
243
+ {
244
+ "entropy": 0.5923496520519257,
245
+ "epoch": 0.2873469387755102,
246
+ "grad_norm": 0.22054198384284973,
247
+ "learning_rate": 9.61377039256492e-05,
248
+ "loss": 0.2866,
249
+ "mean_token_accuracy": 0.9174483200907707,
250
+ "num_tokens": 103376112.0,
251
+ "step": 1100
252
+ },
253
+ {
254
+ "entropy": 0.5921645154803992,
255
+ "epoch": 0.3004081632653061,
256
+ "grad_norm": 0.8782572150230408,
257
+ "learning_rate": 9.572426180488079e-05,
258
+ "loss": 0.312,
259
+ "mean_token_accuracy": 0.9164931161701679,
260
+ "num_tokens": 108072462.0,
261
+ "step": 1150
262
+ },
263
+ {
264
+ "entropy": 0.6070084515213966,
265
+ "epoch": 0.313469387755102,
266
+ "grad_norm": 0.4552319049835205,
267
+ "learning_rate": 9.529078488705135e-05,
268
+ "loss": 0.3169,
269
+ "mean_token_accuracy": 0.9169696615636349,
270
+ "num_tokens": 112781107.0,
271
+ "step": 1200
272
+ },
273
+ {
274
+ "entropy": 0.5912807537615299,
275
+ "epoch": 0.32653061224489793,
276
+ "grad_norm": 0.3097328841686249,
277
+ "learning_rate": 9.483746310682004e-05,
278
+ "loss": 0.2641,
279
+ "mean_token_accuracy": 0.9121362474560738,
280
+ "num_tokens": 117459347.0,
281
+ "step": 1250
282
+ },
283
+ {
284
+ "entropy": 0.5872646420449018,
285
+ "epoch": 0.3395918367346939,
286
+ "grad_norm": 0.7857140898704529,
287
+ "learning_rate": 9.43644950941813e-05,
288
+ "loss": 0.3741,
289
+ "mean_token_accuracy": 0.9139573207497597,
290
+ "num_tokens": 122161796.0,
291
+ "step": 1300
292
+ },
293
+ {
294
+ "entropy": 0.5643932522833347,
295
+ "epoch": 0.3526530612244898,
296
+ "grad_norm": 0.4844133257865906,
297
+ "learning_rate": 9.387208808743222e-05,
298
+ "loss": 0.2447,
299
+ "mean_token_accuracy": 0.9241362990438938,
300
+ "num_tokens": 126862525.0,
301
+ "step": 1350
302
+ },
303
+ {
304
+ "entropy": 0.5853312531858683,
305
+ "epoch": 0.3657142857142857,
306
+ "grad_norm": 0.7309156656265259,
307
+ "learning_rate": 9.336045784236764e-05,
308
+ "loss": 0.2758,
309
+ "mean_token_accuracy": 0.9223621267080307,
310
+ "num_tokens": 131562166.0,
311
+ "step": 1400
312
+ },
313
+ {
314
+ "entropy": 0.5751851069927215,
315
+ "epoch": 0.3787755102040816,
316
+ "grad_norm": 0.6382029056549072,
317
+ "learning_rate": 9.28298285377436e-05,
318
+ "loss": 0.3572,
319
+ "mean_token_accuracy": 0.9173358491063118,
320
+ "num_tokens": 136280998.0,
321
+ "step": 1450
322
+ },
323
+ {
324
+ "entropy": 0.5755070626735688,
325
+ "epoch": 0.39183673469387753,
326
+ "grad_norm": 0.4856666326522827,
327
+ "learning_rate": 9.228043267704974e-05,
328
+ "loss": 0.2431,
329
+ "mean_token_accuracy": 0.9318676285445691,
330
+ "num_tokens": 140963483.0,
331
+ "step": 1500
332
+ },
333
+ {
334
+ "entropy": 0.5901833316683769,
335
+ "epoch": 0.4048979591836735,
336
+ "grad_norm": 0.23288387060165405,
337
+ "learning_rate": 9.171251098663445e-05,
338
+ "loss": 0.3199,
339
+ "mean_token_accuracy": 0.9218292973935605,
340
+ "num_tokens": 145663835.0,
341
+ "step": 1550
342
+ },
343
+ {
344
+ "entropy": 0.6068822190165519,
345
+ "epoch": 0.4179591836734694,
346
+ "grad_norm": 0.7570965886116028,
347
+ "learning_rate": 9.112631231022669e-05,
348
+ "loss": 0.2503,
349
+ "mean_token_accuracy": 0.9219834499061108,
350
+ "num_tokens": 150388643.0,
351
+ "step": 1600
352
+ },
353
+ {
354
+ "entropy": 0.6086373251676559,
355
+ "epoch": 0.4310204081632653,
356
+ "grad_norm": 0.40420103073120117,
357
+ "learning_rate": 9.052209349990144e-05,
358
+ "loss": 0.2979,
359
+ "mean_token_accuracy": 0.9300994580984115,
360
+ "num_tokens": 155072117.0,
361
+ "step": 1650
362
+ },
363
+ {
364
+ "entropy": 0.5892787943035365,
365
+ "epoch": 0.4440816326530612,
366
+ "grad_norm": 0.28975844383239746,
367
+ "learning_rate": 8.990011930353579e-05,
368
+ "loss": 0.2509,
369
+ "mean_token_accuracy": 0.9298394879698754,
370
+ "num_tokens": 159761671.0,
371
+ "step": 1700
372
+ },
373
+ {
374
+ "entropy": 0.5920831595361232,
375
+ "epoch": 0.45714285714285713,
376
+ "grad_norm": 0.3639383018016815,
377
+ "learning_rate": 8.926066224880565e-05,
378
+ "loss": 0.2603,
379
+ "mean_token_accuracy": 0.9342290599644184,
380
+ "num_tokens": 164475669.0,
381
+ "step": 1750
382
+ },
383
+ {
384
+ "entropy": 0.5960557947307825,
385
+ "epoch": 0.47020408163265304,
386
+ "grad_norm": 0.7768979668617249,
387
+ "learning_rate": 8.86040025237734e-05,
388
+ "loss": 0.3215,
389
+ "mean_token_accuracy": 0.9318660141527653,
390
+ "num_tokens": 169186115.0,
391
+ "step": 1800
392
+ },
393
+ {
394
+ "entropy": 0.596306427642703,
395
+ "epoch": 0.483265306122449,
396
+ "grad_norm": 0.2945772409439087,
397
+ "learning_rate": 8.793042785411927e-05,
398
+ "loss": 0.2908,
399
+ "mean_token_accuracy": 0.9278665748238564,
400
+ "num_tokens": 173898142.0,
401
+ "step": 1850
402
+ },
403
+ {
404
+ "entropy": 0.5824826972186565,
405
+ "epoch": 0.4963265306122449,
406
+ "grad_norm": 0.629438042640686,
407
+ "learning_rate": 8.724023337706972e-05,
408
+ "loss": 0.2442,
409
+ "mean_token_accuracy": 0.9366743673384189,
410
+ "num_tokens": 178579887.0,
411
+ "step": 1900
412
+ },
413
+ {
414
+ "entropy": 0.6178072960674763,
415
+ "epoch": 0.5093877551020408,
416
+ "grad_norm": 0.2474866807460785,
417
+ "learning_rate": 8.653372151207855e-05,
418
+ "loss": 0.2979,
419
+ "mean_token_accuracy": 0.9314125381410122,
420
+ "num_tokens": 183276089.0,
421
+ "step": 1950
422
+ },
423
+ {
424
+ "entropy": 0.6088858918845653,
425
+ "epoch": 0.5224489795918368,
426
+ "grad_norm": 0.4756447970867157,
427
+ "learning_rate": 8.58112018283171e-05,
428
+ "loss": 0.3085,
429
+ "mean_token_accuracy": 0.933091163188219,
430
+ "num_tokens": 187979857.0,
431
+ "step": 2000
432
+ },
433
+ {
434
+ "epoch": 0.5224489795918368,
435
+ "eval_entropy": 0.5824218388557434,
436
+ "eval_loss": 0.1687791496515274,
437
+ "eval_mean_token_accuracy": 0.9382246346473694,
438
+ "eval_num_tokens": 187979857.0,
439
+ "eval_runtime": 105.81,
440
+ "eval_samples_per_second": 189.018,
441
+ "eval_steps_per_second": 5.907,
442
+ "step": 2000
443
+ },
444
+ {
445
+ "entropy": 0.6008229818940163,
446
+ "epoch": 0.5355102040816326,
447
+ "grad_norm": 0.968726634979248,
448
+ "learning_rate": 8.507299090903164e-05,
449
+ "loss": 0.217,
450
+ "mean_token_accuracy": 0.9400185799598694,
451
+ "num_tokens": 192675403.0,
452
+ "step": 2050
453
+ },
454
+ {
455
+ "entropy": 0.5939074163138867,
456
+ "epoch": 0.5485714285714286,
457
+ "grad_norm": 0.33287671208381653,
458
+ "learning_rate": 8.43194122128276e-05,
459
+ "loss": 0.2473,
460
+ "mean_token_accuracy": 0.9392171530425548,
461
+ "num_tokens": 197339702.0,
462
+ "step": 2100
463
+ },
464
+ {
465
+ "entropy": 0.5947689298540354,
466
+ "epoch": 0.5616326530612245,
467
+ "grad_norm": 0.5438774228096008,
468
+ "learning_rate": 8.355079593194101e-05,
469
+ "loss": 0.2401,
470
+ "mean_token_accuracy": 0.9419188013672829,
471
+ "num_tokens": 202042351.0,
472
+ "step": 2150
473
+ },
474
+ {
475
+ "entropy": 0.6115065851807594,
476
+ "epoch": 0.5746938775510204,
477
+ "grad_norm": 0.3915332555770874,
478
+ "learning_rate": 8.276747884755978e-05,
479
+ "loss": 0.2958,
480
+ "mean_token_accuracy": 0.9387796081602573,
481
+ "num_tokens": 206746259.0,
482
+ "step": 2200
483
+ },
484
+ {
485
+ "entropy": 0.5970733669400216,
486
+ "epoch": 0.5877551020408164,
487
+ "grad_norm": 0.7760431170463562,
488
+ "learning_rate": 8.196980418225764e-05,
489
+ "loss": 0.2355,
490
+ "mean_token_accuracy": 0.94012371301651,
491
+ "num_tokens": 211462162.0,
492
+ "step": 2250
493
+ },
494
+ {
495
+ "entropy": 0.5940753533691168,
496
+ "epoch": 0.6008163265306122,
497
+ "grad_norm": 0.2869822382926941,
498
+ "learning_rate": 8.115812144960594e-05,
499
+ "loss": 0.2469,
500
+ "mean_token_accuracy": 0.9416494782269001,
501
+ "num_tokens": 216190557.0,
502
+ "step": 2300
503
+ },
504
+ {
505
+ "entropy": 0.60329102024436,
506
+ "epoch": 0.6138775510204082,
507
+ "grad_norm": 0.6603459715843201,
508
+ "learning_rate": 8.033278630102877e-05,
509
+ "loss": 0.2189,
510
+ "mean_token_accuracy": 0.9444279509782791,
511
+ "num_tokens": 220880056.0,
512
+ "step": 2350
513
+ },
514
+ {
515
+ "entropy": 0.6052355971932412,
516
+ "epoch": 0.626938775510204,
517
+ "grad_norm": 0.3574765622615814,
518
+ "learning_rate": 7.949416036996879e-05,
519
+ "loss": 0.2728,
520
+ "mean_token_accuracy": 0.9418448767066002,
521
+ "num_tokens": 225589999.0,
522
+ "step": 2400
523
+ },
524
+ {
525
+ "entropy": 0.5736296055465937,
526
+ "epoch": 0.64,
527
+ "grad_norm": 0.31953155994415283,
528
+ "learning_rate": 7.864261111343187e-05,
529
+ "loss": 0.2291,
530
+ "mean_token_accuracy": 0.9489433655142784,
531
+ "num_tokens": 230305382.0,
532
+ "step": 2450
533
+ },
534
+ {
535
+ "entropy": 0.602155731767416,
536
+ "epoch": 0.6530612244897959,
537
+ "grad_norm": 0.6838288903236389,
538
+ "learning_rate": 7.777851165098012e-05,
539
+ "loss": 0.1958,
540
+ "mean_token_accuracy": 0.946748715788126,
541
+ "num_tokens": 235011703.0,
542
+ "step": 2500
543
+ },
544
+ {
545
+ "entropy": 0.5958992087841034,
546
+ "epoch": 0.6661224489795918,
547
+ "grad_norm": 0.22716443240642548,
548
+ "learning_rate": 7.690224060124371e-05,
549
+ "loss": 0.2536,
550
+ "mean_token_accuracy": 0.9489493478089571,
551
+ "num_tokens": 239706919.0,
552
+ "step": 2550
553
+ },
554
+ {
555
+ "entropy": 0.6019650375843049,
556
+ "epoch": 0.6791836734693878,
557
+ "grad_norm": 0.3493569493293762,
558
+ "learning_rate": 7.601418191602328e-05,
559
+ "loss": 0.2586,
560
+ "mean_token_accuracy": 0.9482229042053223,
561
+ "num_tokens": 244418186.0,
562
+ "step": 2600
563
+ },
564
+ {
565
+ "entropy": 0.586955601349473,
566
+ "epoch": 0.6922448979591836,
567
+ "grad_norm": 0.25364527106285095,
568
+ "learning_rate": 7.511472471205541e-05,
569
+ "loss": 0.2511,
570
+ "mean_token_accuracy": 0.9499958890676499,
571
+ "num_tokens": 249105699.0,
572
+ "step": 2650
573
+ },
574
+ {
575
+ "entropy": 0.57311468757689,
576
+ "epoch": 0.7053061224489796,
577
+ "grad_norm": 0.854145884513855,
578
+ "learning_rate": 7.42042631005151e-05,
579
+ "loss": 0.2548,
580
+ "mean_token_accuracy": 0.948536623865366,
581
+ "num_tokens": 253800051.0,
582
+ "step": 2700
583
+ },
584
+ {
585
+ "entropy": 0.5846149046719075,
586
+ "epoch": 0.7183673469387755,
587
+ "grad_norm": 0.7333242297172546,
588
+ "learning_rate": 7.328319601432987e-05,
589
+ "loss": 0.2424,
590
+ "mean_token_accuracy": 0.951610994040966,
591
+ "num_tokens": 258490956.0,
592
+ "step": 2750
593
+ },
594
+ {
595
+ "entropy": 0.5881183807551861,
596
+ "epoch": 0.7314285714285714,
597
+ "grad_norm": 0.34874463081359863,
598
+ "learning_rate": 7.2351927033381e-05,
599
+ "loss": 0.3103,
600
+ "mean_token_accuracy": 0.9474381080269814,
601
+ "num_tokens": 263183558.0,
602
+ "step": 2800
603
+ },
604
+ {
605
+ "entropy": 0.6000971308350563,
606
+ "epoch": 0.7444897959183674,
607
+ "grad_norm": 0.40719911456108093,
608
+ "learning_rate": 7.141086420766875e-05,
609
+ "loss": 0.2412,
610
+ "mean_token_accuracy": 0.9557790002226829,
611
+ "num_tokens": 267896256.0,
612
+ "step": 2850
613
+ },
614
+ {
615
+ "entropy": 0.6206524230539798,
616
+ "epoch": 0.7575510204081632,
617
+ "grad_norm": 0.3394398093223572,
618
+ "learning_rate": 7.046041987851896e-05,
619
+ "loss": 0.2431,
620
+ "mean_token_accuracy": 0.9514926019310951,
621
+ "num_tokens": 272576019.0,
622
+ "step": 2900
623
+ },
624
+ {
625
+ "entropy": 0.5987586285173893,
626
+ "epoch": 0.7706122448979592,
627
+ "grad_norm": 0.435951828956604,
628
+ "learning_rate": 6.950101049790922e-05,
629
+ "loss": 0.2353,
630
+ "mean_token_accuracy": 0.9547148038446903,
631
+ "num_tokens": 277288513.0,
632
+ "step": 2950
633
+ },
634
+ {
635
+ "entropy": 0.5921910824626684,
636
+ "epoch": 0.7836734693877551,
637
+ "grad_norm": 0.39050304889678955,
638
+ "learning_rate": 6.853305644599397e-05,
639
+ "loss": 0.2647,
640
+ "mean_token_accuracy": 0.9546147619187831,
641
+ "num_tokens": 281988009.0,
642
+ "step": 3000
643
+ },
644
+ {
645
+ "epoch": 0.7836734693877551,
646
+ "eval_entropy": 0.5917929359436035,
647
+ "eval_loss": 0.13952013850212097,
648
+ "eval_mean_token_accuracy": 0.9494351725578308,
649
+ "eval_num_tokens": 281988009.0,
650
+ "eval_runtime": 105.8253,
651
+ "eval_samples_per_second": 188.991,
652
+ "eval_steps_per_second": 5.906,
653
+ "step": 3000
654
+ },
655
+ {
656
+ "entropy": 0.5995206294953823,
657
+ "epoch": 0.796734693877551,
658
+ "grad_norm": 0.5683656334877014,
659
+ "learning_rate": 6.755698184690837e-05,
660
+ "loss": 0.2358,
661
+ "mean_token_accuracy": 0.954430370926857,
662
+ "num_tokens": 286687009.0,
663
+ "step": 3050
664
+ },
665
+ {
666
+ "entropy": 0.6226249255239964,
667
+ "epoch": 0.809795918367347,
668
+ "grad_norm": 0.17246268689632416,
669
+ "learning_rate": 6.657321438293174e-05,
670
+ "loss": 0.2491,
671
+ "mean_token_accuracy": 0.9509413394331933,
672
+ "num_tokens": 291376119.0,
673
+ "step": 3100
674
+ },
675
+ {
676
+ "entropy": 0.5907960905134678,
677
+ "epoch": 0.8228571428571428,
678
+ "grad_norm": 0.14905746281147003,
679
+ "learning_rate": 6.558218510709192e-05,
680
+ "loss": 0.1754,
681
+ "mean_token_accuracy": 0.9620982597768307,
682
+ "num_tokens": 296068600.0,
683
+ "step": 3150
684
+ },
685
+ {
686
+ "entropy": 0.6032850205898285,
687
+ "epoch": 0.8359183673469388,
688
+ "grad_norm": 0.7370997071266174,
689
+ "learning_rate": 6.458432825429263e-05,
690
+ "loss": 0.2096,
691
+ "mean_token_accuracy": 0.9580010569095612,
692
+ "num_tokens": 300766641.0,
693
+ "step": 3200
694
+ },
695
+ {
696
+ "entropy": 0.6270367397367954,
697
+ "epoch": 0.8489795918367347,
698
+ "grad_norm": 0.25541967153549194,
699
+ "learning_rate": 6.358008105104673e-05,
700
+ "loss": 0.2168,
701
+ "mean_token_accuracy": 0.9566573745012283,
702
+ "num_tokens": 305487589.0,
703
+ "step": 3250
704
+ },
705
+ {
706
+ "entropy": 0.5874304908514023,
707
+ "epoch": 0.8620408163265306,
708
+ "grad_norm": 0.6642680764198303,
709
+ "learning_rate": 6.256988352389859e-05,
710
+ "loss": 0.2361,
711
+ "mean_token_accuracy": 0.9588885164260864,
712
+ "num_tokens": 310194698.0,
713
+ "step": 3300
714
+ },
715
+ {
716
+ "entropy": 0.6110400749742985,
717
+ "epoch": 0.8751020408163265,
718
+ "grad_norm": 0.26045140624046326,
719
+ "learning_rate": 6.155417830661963e-05,
720
+ "loss": 0.1988,
721
+ "mean_token_accuracy": 0.9600324124097824,
722
+ "num_tokens": 314871495.0,
723
+ "step": 3350
724
+ },
725
+ {
726
+ "entropy": 0.5896776075661182,
727
+ "epoch": 0.8881632653061224,
728
+ "grad_norm": 0.6913824677467346,
729
+ "learning_rate": 6.0533410446261415e-05,
730
+ "loss": 0.2404,
731
+ "mean_token_accuracy": 0.9585775223374366,
732
+ "num_tokens": 319562203.0,
733
+ "step": 3400
734
+ },
735
+ {
736
+ "entropy": 0.6021107806265354,
737
+ "epoch": 0.9012244897959184,
738
+ "grad_norm": 1.0586336851119995,
739
+ "learning_rate": 5.950802720815143e-05,
740
+ "loss": 0.242,
741
+ "mean_token_accuracy": 0.9604564820230007,
742
+ "num_tokens": 324272631.0,
743
+ "step": 3450
744
+ },
745
+ {
746
+ "entropy": 0.6005905717611313,
747
+ "epoch": 0.9142857142857143,
748
+ "grad_norm": 0.33950117230415344,
749
+ "learning_rate": 5.8478477879916714e-05,
750
+ "loss": 0.2179,
751
+ "mean_token_accuracy": 0.9604296152293682,
752
+ "num_tokens": 328972230.0,
753
+ "step": 3500
754
+ },
755
+ {
756
+ "entropy": 0.6018191055953502,
757
+ "epoch": 0.9273469387755102,
758
+ "grad_norm": 0.34331461787223816,
759
+ "learning_rate": 5.744521357462156e-05,
760
+ "loss": 0.2278,
761
+ "mean_token_accuracy": 0.9604898960888386,
762
+ "num_tokens": 333680964.0,
763
+ "step": 3550
764
+ },
765
+ {
766
+ "entropy": 0.6024402364343405,
767
+ "epoch": 0.9404081632653061,
768
+ "grad_norm": 0.14388936758041382,
769
+ "learning_rate": 5.64086870331053e-05,
770
+ "loss": 0.227,
771
+ "mean_token_accuracy": 0.963430253714323,
772
+ "num_tokens": 338368553.0,
773
+ "step": 3600
774
+ },
775
+ {
776
+ "entropy": 0.5977859281003475,
777
+ "epoch": 0.953469387755102,
778
+ "grad_norm": 0.7793987989425659,
779
+ "learning_rate": 5.5369352425606816e-05,
780
+ "loss": 0.1802,
781
+ "mean_token_accuracy": 0.9638005784153938,
782
+ "num_tokens": 343050682.0,
783
+ "step": 3650
784
+ },
785
+ {
786
+ "entropy": 0.5996729772537946,
787
+ "epoch": 0.966530612244898,
788
+ "grad_norm": 1.3826709985733032,
789
+ "learning_rate": 5.4327665152762876e-05,
790
+ "loss": 0.2326,
791
+ "mean_token_accuracy": 0.9609452857077122,
792
+ "num_tokens": 347754882.0,
793
+ "step": 3700
794
+ },
795
+ {
796
+ "entropy": 0.5990429550409317,
797
+ "epoch": 0.9795918367346939,
798
+ "grad_norm": 0.921048641204834,
799
+ "learning_rate": 5.3284081646067105e-05,
800
+ "loss": 0.2117,
801
+ "mean_token_accuracy": 0.9624172969162464,
802
+ "num_tokens": 352466908.0,
803
+ "step": 3750
804
+ },
805
+ {
806
+ "entropy": 0.5920401379466057,
807
+ "epoch": 0.9926530612244898,
808
+ "grad_norm": 0.9255926012992859,
809
+ "learning_rate": 5.223905916787757e-05,
810
+ "loss": 0.2149,
811
+ "mean_token_accuracy": 0.9625219763815402,
812
+ "num_tokens": 357183033.0,
813
+ "step": 3800
814
+ },
815
+ {
816
+ "entropy": 0.5910900549124215,
817
+ "epoch": 1.0054857142857143,
818
+ "grad_norm": 0.31576788425445557,
819
+ "learning_rate": 5.119305561106008e-05,
820
+ "loss": 0.1889,
821
+ "mean_token_accuracy": 0.9667121869613803,
822
+ "num_tokens": 361822524.0,
823
+ "step": 3850
824
+ },
825
+ {
826
+ "entropy": 0.5463350272923708,
827
+ "epoch": 1.0185469387755102,
828
+ "grad_norm": 0.15527017414569855,
829
+ "learning_rate": 5.0146529298355305e-05,
830
+ "loss": 0.1567,
831
+ "mean_token_accuracy": 0.9730980744957924,
832
+ "num_tokens": 366524404.0,
833
+ "step": 3900
834
+ },
835
+ {
836
+ "entropy": 0.5311270990222693,
837
+ "epoch": 1.031608163265306,
838
+ "grad_norm": 0.7653639316558838,
839
+ "learning_rate": 4.909993878155755e-05,
840
+ "loss": 0.1941,
841
+ "mean_token_accuracy": 0.9723508515954018,
842
+ "num_tokens": 371187218.0,
843
+ "step": 3950
844
+ },
845
+ {
846
+ "entropy": 0.5343203826993704,
847
+ "epoch": 1.044669387755102,
848
+ "grad_norm": 0.3685067594051361,
849
+ "learning_rate": 4.805374264059317e-05,
850
+ "loss": 0.1643,
851
+ "mean_token_accuracy": 0.9716256402432919,
852
+ "num_tokens": 375891451.0,
853
+ "step": 4000
854
+ },
855
+ {
856
+ "epoch": 1.044669387755102,
857
+ "eval_entropy": 0.5199984492301941,
858
+ "eval_loss": 0.10260085761547089,
859
+ "eval_mean_token_accuracy": 0.9630540296554565,
860
+ "eval_num_tokens": 375891451.0,
861
+ "eval_runtime": 105.9615,
862
+ "eval_samples_per_second": 188.748,
863
+ "eval_steps_per_second": 5.898,
864
+ "step": 4000
865
+ },
866
+ {
867
+ "entropy": 0.5307158456742763,
868
+ "epoch": 1.057730612244898,
869
+ "grad_norm": 0.7387518882751465,
870
+ "learning_rate": 4.700839928258657e-05,
871
+ "loss": 0.1336,
872
+ "mean_token_accuracy": 0.9701156315207481,
873
+ "num_tokens": 380573790.0,
874
+ "step": 4050
875
+ },
876
+ {
877
+ "entropy": 0.5245926366001368,
878
+ "epoch": 1.0707918367346938,
879
+ "grad_norm": 0.5187281370162964,
880
+ "learning_rate": 4.596436674100202e-05,
881
+ "loss": 0.1243,
882
+ "mean_token_accuracy": 0.9722427415847779,
883
+ "num_tokens": 385276643.0,
884
+ "step": 4100
885
+ },
886
+ {
887
+ "entropy": 0.525925776809454,
888
+ "epoch": 1.0838530612244899,
889
+ "grad_norm": 0.11235808581113815,
890
+ "learning_rate": 4.492210247494922e-05,
891
+ "loss": 0.1594,
892
+ "mean_token_accuracy": 0.974123645722866,
893
+ "num_tokens": 390015359.0,
894
+ "step": 4150
895
+ },
896
+ {
897
+ "entropy": 0.5073333897441625,
898
+ "epoch": 1.0969142857142857,
899
+ "grad_norm": 0.3686864376068115,
900
+ "learning_rate": 4.3882063168740405e-05,
901
+ "loss": 0.1789,
902
+ "mean_token_accuracy": 0.9707419118285179,
903
+ "num_tokens": 394707917.0,
904
+ "step": 4200
905
+ },
906
+ {
907
+ "entropy": 0.5056077273190022,
908
+ "epoch": 1.1099755102040816,
909
+ "grad_norm": 0.7848389744758606,
910
+ "learning_rate": 4.284470453178698e-05,
911
+ "loss": 0.166,
912
+ "mean_token_accuracy": 0.9751219192147255,
913
+ "num_tokens": 399431065.0,
914
+ "step": 4250
915
+ },
916
+ {
917
+ "entropy": 0.5062515323609114,
918
+ "epoch": 1.1230367346938777,
919
+ "grad_norm": 0.2769508361816406,
920
+ "learning_rate": 4.181048109892344e-05,
921
+ "loss": 0.1537,
922
+ "mean_token_accuracy": 0.9724229994416237,
923
+ "num_tokens": 404132094.0,
924
+ "step": 4300
925
+ },
926
+ {
927
+ "entropy": 0.5368214490264654,
928
+ "epoch": 1.1360979591836735,
929
+ "grad_norm": 1.615638256072998,
930
+ "learning_rate": 4.077984603124577e-05,
931
+ "loss": 0.2671,
932
+ "mean_token_accuracy": 0.9685475620627403,
933
+ "num_tokens": 408819783.0,
934
+ "step": 4350
935
+ },
936
+ {
937
+ "entropy": 0.5090609015524388,
938
+ "epoch": 1.1491591836734694,
939
+ "grad_norm": 0.13154712319374084,
940
+ "learning_rate": 3.975325091755189e-05,
941
+ "loss": 0.2047,
942
+ "mean_token_accuracy": 0.9727970556914807,
943
+ "num_tokens": 413512051.0,
944
+ "step": 4400
945
+ },
946
+ {
947
+ "entropy": 0.5156180077046156,
948
+ "epoch": 1.1622204081632652,
949
+ "grad_norm": 0.33791911602020264,
950
+ "learning_rate": 3.873114557647105e-05,
951
+ "loss": 0.2171,
952
+ "mean_token_accuracy": 0.9713401012122631,
953
+ "num_tokens": 418236972.0,
954
+ "step": 4450
955
+ },
956
+ {
957
+ "entropy": 0.5125152183324099,
958
+ "epoch": 1.1752816326530613,
959
+ "grad_norm": 0.5354299545288086,
960
+ "learning_rate": 3.771397785936868e-05,
961
+ "loss": 0.1564,
962
+ "mean_token_accuracy": 0.9742588277161122,
963
+ "num_tokens": 422939153.0,
964
+ "step": 4500
965
+ },
966
+ {
967
+ "entropy": 0.5200927007943392,
968
+ "epoch": 1.1883428571428571,
969
+ "grad_norm": 0.7117024064064026,
970
+ "learning_rate": 3.67021934541134e-05,
971
+ "loss": 0.1567,
972
+ "mean_token_accuracy": 0.9759668205678463,
973
+ "num_tokens": 427638623.0,
974
+ "step": 4550
975
+ },
976
+ {
977
+ "entropy": 0.5100678735226393,
978
+ "epoch": 1.201404081632653,
979
+ "grad_norm": 0.7776734828948975,
980
+ "learning_rate": 3.5696235689792e-05,
981
+ "loss": 0.1744,
982
+ "mean_token_accuracy": 0.9728824967145919,
983
+ "num_tokens": 432324424.0,
984
+ "step": 4600
985
+ },
986
+ {
987
+ "entropy": 0.5009938656538725,
988
+ "epoch": 1.214465306122449,
989
+ "grad_norm": 0.45003074407577515,
990
+ "learning_rate": 3.469654534245781e-05,
991
+ "loss": 0.1523,
992
+ "mean_token_accuracy": 0.975490598231554,
993
+ "num_tokens": 437053744.0,
994
+ "step": 4650
995
+ },
996
+ {
997
+ "entropy": 0.5198498579859734,
998
+ "epoch": 1.227526530612245,
999
+ "grad_norm": 0.7395092248916626,
1000
+ "learning_rate": 3.370356044199785e-05,
1001
+ "loss": 0.1622,
1002
+ "mean_token_accuracy": 0.9760421338677406,
1003
+ "num_tokens": 441776589.0,
1004
+ "step": 4700
1005
+ },
1006
+ {
1007
+ "entropy": 0.5041036491096019,
1008
+ "epoch": 1.2405877551020408,
1009
+ "grad_norm": 0.6011821031570435,
1010
+ "learning_rate": 3.271771608020324e-05,
1011
+ "loss": 0.1282,
1012
+ "mean_token_accuracy": 0.9775787754356862,
1013
+ "num_tokens": 446474446.0,
1014
+ "step": 4750
1015
+ },
1016
+ {
1017
+ "entropy": 0.5190455333888531,
1018
+ "epoch": 1.2536489795918366,
1019
+ "grad_norm": 0.24861446022987366,
1020
+ "learning_rate": 3.173944422012688e-05,
1021
+ "loss": 0.1396,
1022
+ "mean_token_accuracy": 0.9773434112966061,
1023
+ "num_tokens": 451196726.0,
1024
+ "step": 4800
1025
+ },
1026
+ {
1027
+ "entropy": 0.5022503357380629,
1028
+ "epoch": 1.2667102040816327,
1029
+ "grad_norm": 0.24570924043655396,
1030
+ "learning_rate": 3.076917350681222e-05,
1031
+ "loss": 0.1592,
1032
+ "mean_token_accuracy": 0.9746822196245194,
1033
+ "num_tokens": 455888329.0,
1034
+ "step": 4850
1035
+ },
1036
+ {
1037
+ "entropy": 0.5063729017972947,
1038
+ "epoch": 1.2797714285714286,
1039
+ "grad_norm": 0.843909502029419,
1040
+ "learning_rate": 2.9807329079475686e-05,
1041
+ "loss": 0.1479,
1042
+ "mean_token_accuracy": 0.9775361755490303,
1043
+ "num_tokens": 460588507.0,
1044
+ "step": 4900
1045
+ },
1046
+ {
1047
+ "entropy": 0.5099849846214056,
1048
+ "epoch": 1.2928326530612244,
1049
+ "grad_norm": 0.5658782124519348,
1050
+ "learning_rate": 2.8854332385225336e-05,
1051
+ "loss": 0.1365,
1052
+ "mean_token_accuracy": 0.9764770893752575,
1053
+ "num_tokens": 465292875.0,
1054
+ "step": 4950
1055
+ },
1056
+ {
1057
+ "entropy": 0.5075208330154419,
1058
+ "epoch": 1.3058938775510205,
1059
+ "grad_norm": 0.5681100487709045,
1060
+ "learning_rate": 2.791060099439724e-05,
1061
+ "loss": 0.1547,
1062
+ "mean_token_accuracy": 0.9766012115776539,
1063
+ "num_tokens": 470018553.0,
1064
+ "step": 5000
1065
+ },
1066
+ {
1067
+ "epoch": 1.3058938775510205,
1068
+ "eval_entropy": 0.5093407655239105,
1069
+ "eval_loss": 0.07968976348638535,
1070
+ "eval_mean_token_accuracy": 0.9728172892570496,
1071
+ "eval_num_tokens": 470018553.0,
1072
+ "eval_runtime": 105.9871,
1073
+ "eval_samples_per_second": 188.702,
1074
+ "eval_steps_per_second": 5.897,
1075
+ "step": 5000
1076
+ },
1077
+ {
1078
+ "entropy": 0.5292845606803894,
1079
+ "epoch": 1.3189551020408163,
1080
+ "grad_norm": 0.3377012014389038,
1081
+ "learning_rate": 2.6976548417590607e-05,
1082
+ "loss": 0.1478,
1083
+ "mean_token_accuracy": 0.9774796655774116,
1084
+ "num_tokens": 474695442.0,
1085
+ "step": 5050
1086
+ },
1087
+ {
1088
+ "entropy": 0.5115040161460638,
1089
+ "epoch": 1.3320163265306122,
1090
+ "grad_norm": 0.31330540776252747,
1091
+ "learning_rate": 2.6052583924481532e-05,
1092
+ "loss": 0.1651,
1093
+ "mean_token_accuracy": 0.9753667731583119,
1094
+ "num_tokens": 479387979.0,
1095
+ "step": 5100
1096
+ },
1097
+ {
1098
+ "entropy": 0.518300534710288,
1099
+ "epoch": 1.3450775510204083,
1100
+ "grad_norm": 0.579721987247467,
1101
+ "learning_rate": 2.5139112364495286e-05,
1102
+ "loss": 0.2114,
1103
+ "mean_token_accuracy": 0.975457195341587,
1104
+ "num_tokens": 484096122.0,
1105
+ "step": 5150
1106
+ },
1107
+ {
1108
+ "entropy": 0.5092091238498688,
1109
+ "epoch": 1.3581387755102041,
1110
+ "grad_norm": 0.04276373237371445,
1111
+ "learning_rate": 2.4236533989415084e-05,
1112
+ "loss": 0.1473,
1113
+ "mean_token_accuracy": 0.978675073236227,
1114
+ "num_tokens": 488804070.0,
1115
+ "step": 5200
1116
+ },
1117
+ {
1118
+ "entropy": 0.5108030308783055,
1119
+ "epoch": 1.3712,
1120
+ "grad_norm": 0.34016624093055725,
1121
+ "learning_rate": 2.334524427800569e-05,
1122
+ "loss": 0.1871,
1123
+ "mean_token_accuracy": 0.9755242675542831,
1124
+ "num_tokens": 493512802.0,
1125
+ "step": 5250
1126
+ },
1127
+ {
1128
+ "entropy": 0.5037990070134402,
1129
+ "epoch": 1.384261224489796,
1130
+ "grad_norm": 0.058522939682006836,
1131
+ "learning_rate": 2.2465633762728094e-05,
1132
+ "loss": 0.1241,
1133
+ "mean_token_accuracy": 0.9779052963852882,
1134
+ "num_tokens": 498224036.0,
1135
+ "step": 5300
1136
+ },
1137
+ {
1138
+ "entropy": 0.5202232024073601,
1139
+ "epoch": 1.397322448979592,
1140
+ "grad_norm": 0.7593867182731628,
1141
+ "learning_rate": 2.1598087858621707e-05,
1142
+ "loss": 0.1528,
1143
+ "mean_token_accuracy": 0.9765554815530777,
1144
+ "num_tokens": 502927469.0,
1145
+ "step": 5350
1146
+ },
1147
+ {
1148
+ "entropy": 0.5276015343517065,
1149
+ "epoch": 1.4103836734693878,
1150
+ "grad_norm": 0.8394476175308228,
1151
+ "learning_rate": 2.074298669442881e-05,
1152
+ "loss": 0.1965,
1153
+ "mean_token_accuracy": 0.9732386584579945,
1154
+ "num_tokens": 507642470.0,
1155
+ "step": 5400
1156
+ },
1157
+ {
1158
+ "entropy": 0.5179370325058699,
1159
+ "epoch": 1.4234448979591836,
1160
+ "grad_norm": 0.280915766954422,
1161
+ "learning_rate": 1.9900704946035115e-05,
1162
+ "loss": 0.1817,
1163
+ "mean_token_accuracy": 0.9782391162216664,
1164
+ "num_tokens": 512330334.0,
1165
+ "step": 5450
1166
+ },
1167
+ {
1168
+ "entropy": 0.5077722806483507,
1169
+ "epoch": 1.4365061224489795,
1170
+ "grad_norm": 0.37315860390663147,
1171
+ "learning_rate": 1.9071611672299756e-05,
1172
+ "loss": 0.1516,
1173
+ "mean_token_accuracy": 0.9786237494647503,
1174
+ "num_tokens": 517049296.0,
1175
+ "step": 5500
1176
+ },
1177
+ {
1178
+ "entropy": 0.521270957365632,
1179
+ "epoch": 1.4495673469387755,
1180
+ "grad_norm": 0.8134558200836182,
1181
+ "learning_rate": 1.825607015334644e-05,
1182
+ "loss": 0.1509,
1183
+ "mean_token_accuracy": 0.9779170905053616,
1184
+ "num_tokens": 521739525.0,
1185
+ "step": 5550
1186
+ },
1187
+ {
1188
+ "entropy": 0.5181563084572554,
1189
+ "epoch": 1.4626285714285714,
1190
+ "grad_norm": 0.17686356604099274,
1191
+ "learning_rate": 1.7454437731386558e-05,
1192
+ "loss": 0.2467,
1193
+ "mean_token_accuracy": 0.9748677863925695,
1194
+ "num_tokens": 526451360.0,
1195
+ "step": 5600
1196
+ },
1197
+ {
1198
+ "entropy": 0.5103141793608665,
1199
+ "epoch": 1.4756897959183672,
1200
+ "grad_norm": 0.45316168665885925,
1201
+ "learning_rate": 1.6667065654144103e-05,
1202
+ "loss": 0.1965,
1203
+ "mean_token_accuracy": 0.9771437807381154,
1204
+ "num_tokens": 531176496.0,
1205
+ "step": 5650
1206
+ },
1207
+ {
1208
+ "entropy": 0.5023327280580997,
1209
+ "epoch": 1.4887510204081633,
1210
+ "grad_norm": 0.20157447457313538,
1211
+ "learning_rate": 1.5894298920951106e-05,
1212
+ "loss": 0.1909,
1213
+ "mean_token_accuracy": 0.9771021957695484,
1214
+ "num_tokens": 535864937.0,
1215
+ "step": 5700
1216
+ },
1217
+ {
1218
+ "entropy": 0.5016037753224373,
1219
+ "epoch": 1.5018122448979592,
1220
+ "grad_norm": 0.33676010370254517,
1221
+ "learning_rate": 1.5136476131580701e-05,
1222
+ "loss": 0.1675,
1223
+ "mean_token_accuracy": 0.9775694438815117,
1224
+ "num_tokens": 540571806.0,
1225
+ "step": 5750
1226
+ },
1227
+ {
1228
+ "entropy": 0.5027693736553193,
1229
+ "epoch": 1.514873469387755,
1230
+ "grad_norm": 0.5053212642669678,
1231
+ "learning_rate": 1.439392933788447e-05,
1232
+ "loss": 0.1807,
1233
+ "mean_token_accuracy": 0.9797284063696862,
1234
+ "num_tokens": 545276790.0,
1235
+ "step": 5800
1236
+ },
1237
+ {
1238
+ "entropy": 0.5009680130332709,
1239
+ "epoch": 1.527934693877551,
1240
+ "grad_norm": 0.09157374501228333,
1241
+ "learning_rate": 1.3666983898298657e-05,
1242
+ "loss": 0.2042,
1243
+ "mean_token_accuracy": 0.977972183674574,
1244
+ "num_tokens": 549964631.0,
1245
+ "step": 5850
1246
+ },
1247
+ {
1248
+ "entropy": 0.5023607714474201,
1249
+ "epoch": 1.540995918367347,
1250
+ "grad_norm": 0.23668606579303741,
1251
+ "learning_rate": 1.2955958335283353e-05,
1252
+ "loss": 0.2045,
1253
+ "mean_token_accuracy": 0.9760315857827664,
1254
+ "num_tokens": 554656554.0,
1255
+ "step": 5900
1256
+ },
1257
+ {
1258
+ "entropy": 0.505893104672432,
1259
+ "epoch": 1.5540571428571428,
1260
+ "grad_norm": 0.2585294246673584,
1261
+ "learning_rate": 1.2261164195756963e-05,
1262
+ "loss": 0.1519,
1263
+ "mean_token_accuracy": 0.9788727892935276,
1264
+ "num_tokens": 559319350.0,
1265
+ "step": 5950
1266
+ },
1267
+ {
1268
+ "entropy": 0.5045397817343473,
1269
+ "epoch": 1.5671183673469389,
1270
+ "grad_norm": 0.41178709268569946,
1271
+ "learning_rate": 1.1582905914586961e-05,
1272
+ "loss": 0.1618,
1273
+ "mean_token_accuracy": 0.9804812078177929,
1274
+ "num_tokens": 564036376.0,
1275
+ "step": 6000
1276
+ },
1277
+ {
1278
+ "epoch": 1.5671183673469389,
1279
+ "eval_entropy": 0.5037064853668213,
1280
+ "eval_loss": 0.06929752975702286,
1281
+ "eval_mean_token_accuracy": 0.9767320104598999,
1282
+ "eval_num_tokens": 564036376.0,
1283
+ "eval_runtime": 105.8974,
1284
+ "eval_samples_per_second": 188.862,
1285
+ "eval_steps_per_second": 5.902,
1286
+ "step": 6000
1287
+ }
1288
+ ],
1289
+ "logging_steps": 50,
1290
+ "max_steps": 7658,
1291
+ "num_input_tokens_seen": 0,
1292
+ "num_train_epochs": 2,
1293
+ "save_steps": 1000,
1294
+ "stateful_callbacks": {
1295
+ "TrainerControl": {
1296
+ "args": {
1297
+ "should_epoch_stop": false,
1298
+ "should_evaluate": false,
1299
+ "should_log": false,
1300
+ "should_save": true,
1301
+ "should_training_stop": false
1302
+ },
1303
+ "attributes": {}
1304
+ }
1305
+ },
1306
+ "total_flos": 3.804321079366989e+19,
1307
+ "train_batch_size": 4,
1308
+ "trial_name": null,
1309
+ "trial_params": null
1310
+ }
iter3-2epoch/checkpoint-7000/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
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 0.17.1
iter3-2epoch/checkpoint-7000/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 256,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "down_proj",
29
+ "v_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
iter3-2epoch/checkpoint-7000/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb57e869f0ca80a8142e59b0e58c11229e595da93813781301ab88e8a6719d6
3
+ size 2684416208
iter3-2epoch/checkpoint-7000/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
iter3-2epoch/checkpoint-7000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e1ed41268491ca1b0c6dc62af9c90ca54fb01b973f87e41afafcc401297d722
3
+ size 15984
iter3-2epoch/checkpoint-7000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c088d7b28bc5220f2bdca11bf71a763cf8ed796663e1a0e34c4b6ed69a83a211
3
+ size 15984
iter3-2epoch/checkpoint-7000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8129201c83f264b26cea1611c96a067d378853f04dfe8ad680aa041ad048b972
3
+ size 15984
iter3-2epoch/checkpoint-7000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15c1bd007e12ea1d150333b6625da7ba72a3db9b336aa11de89000a85c3e2cb3
3
+ size 15984
iter3-2epoch/checkpoint-7000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c2915d649bfbf8a285d9c1cafdda6b1a8d985ac702122448c9771d2d94d820
3
+ size 15984
iter3-2epoch/checkpoint-7000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f031a903afa0996fdc7b2bd70273aa3efa7e822b4a1f1758aaa40a060108582
3
+ size 15984
iter3-2epoch/checkpoint-7000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0bcb9a105aa55eade084075dc11ac9083f835537465b7848fb229dd07c4849
3
+ size 15984
iter3-2epoch/checkpoint-7000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f4dad821afc7e54acb1f2b2c6bf409817ad5a8a0b4c2b962ad5029ad6c8078a
3
+ size 15984
iter3-2epoch/checkpoint-7000/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
iter3-2epoch/checkpoint-7000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
iter3-2epoch/checkpoint-7000/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
iter3-2epoch/checkpoint-7000/trainer_state.json ADDED
@@ -0,0 +1,1521 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7000,
3
+ "best_metric": 0.06544612348079681,
4
+ "best_model_checkpoint": "runs/iter3_2epoch_r256_aggressive/checkpoint-7000",
5
+ "epoch": 1.8283428571428573,
6
+ "eval_steps": 1000,
7
+ "global_step": 7000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 0.9600491151213646,
14
+ "epoch": 0.00026122448979591835,
15
+ "grad_norm": 4.874749183654785,
16
+ "learning_rate": 0.0,
17
+ "loss": 1.5426,
18
+ "mean_token_accuracy": 0.5253331288695335,
19
+ "num_tokens": 92658.0,
20
+ "step": 1
21
+ },
22
+ {
23
+ "entropy": 1.0668207285355549,
24
+ "epoch": 0.013061224489795919,
25
+ "grad_norm": 0.3741045296192169,
26
+ "learning_rate": 3.181818181818182e-05,
27
+ "loss": 0.8201,
28
+ "mean_token_accuracy": 0.713900758295643,
29
+ "num_tokens": 4695822.0,
30
+ "step": 50
31
+ },
32
+ {
33
+ "entropy": 0.7840494087338448,
34
+ "epoch": 0.026122448979591838,
35
+ "grad_norm": 1.6816201210021973,
36
+ "learning_rate": 6.428571428571429e-05,
37
+ "loss": 0.5652,
38
+ "mean_token_accuracy": 0.8121247433125973,
39
+ "num_tokens": 9384030.0,
40
+ "step": 100
41
+ },
42
+ {
43
+ "entropy": 0.6429135516285897,
44
+ "epoch": 0.03918367346938775,
45
+ "grad_norm": 1.8123995065689087,
46
+ "learning_rate": 9.675324675324677e-05,
47
+ "loss": 0.4768,
48
+ "mean_token_accuracy": 0.8343716338276863,
49
+ "num_tokens": 14068659.0,
50
+ "step": 150
51
+ },
52
+ {
53
+ "entropy": 0.6180185662209987,
54
+ "epoch": 0.052244897959183675,
55
+ "grad_norm": 0.228230819106102,
56
+ "learning_rate": 9.99911270857259e-05,
57
+ "loss": 0.4195,
58
+ "mean_token_accuracy": 0.8369381006062031,
59
+ "num_tokens": 18749150.0,
60
+ "step": 200
61
+ },
62
+ {
63
+ "entropy": 0.6392524507641792,
64
+ "epoch": 0.0653061224489796,
65
+ "grad_norm": 0.3391082286834717,
66
+ "learning_rate": 9.99604593263008e-05,
67
+ "loss": 0.3747,
68
+ "mean_token_accuracy": 0.8521625240147114,
69
+ "num_tokens": 23444738.0,
70
+ "step": 250
71
+ },
72
+ {
73
+ "entropy": 0.6395396235585212,
74
+ "epoch": 0.0783673469387755,
75
+ "grad_norm": 0.35865047574043274,
76
+ "learning_rate": 9.990790061392936e-05,
77
+ "loss": 0.4622,
78
+ "mean_token_accuracy": 0.817176415771246,
79
+ "num_tokens": 28146459.0,
80
+ "step": 300
81
+ },
82
+ {
83
+ "entropy": 0.6052160003781318,
84
+ "epoch": 0.09142857142857143,
85
+ "grad_norm": 0.461127907037735,
86
+ "learning_rate": 9.983347397802953e-05,
87
+ "loss": 0.3964,
88
+ "mean_token_accuracy": 0.865231085717678,
89
+ "num_tokens": 32829584.0,
90
+ "step": 350
91
+ },
92
+ {
93
+ "entropy": 0.6162980204820633,
94
+ "epoch": 0.10448979591836735,
95
+ "grad_norm": 0.6675931811332703,
96
+ "learning_rate": 9.973721202979037e-05,
97
+ "loss": 0.4523,
98
+ "mean_token_accuracy": 0.8371678332984448,
99
+ "num_tokens": 37519736.0,
100
+ "step": 400
101
+ },
102
+ {
103
+ "entropy": 0.6373377884924412,
104
+ "epoch": 0.11755102040816326,
105
+ "grad_norm": 0.7843639254570007,
106
+ "learning_rate": 9.961915694788294e-05,
107
+ "loss": 0.4246,
108
+ "mean_token_accuracy": 0.8822347274422646,
109
+ "num_tokens": 42214834.0,
110
+ "step": 450
111
+ },
112
+ {
113
+ "entropy": 0.6182832332700491,
114
+ "epoch": 0.1306122448979592,
115
+ "grad_norm": 0.12627503275871277,
116
+ "learning_rate": 9.9479360459979e-05,
117
+ "loss": 0.3963,
118
+ "mean_token_accuracy": 0.8835959336161614,
119
+ "num_tokens": 46896384.0,
120
+ "step": 500
121
+ },
122
+ {
123
+ "entropy": 0.604607280343771,
124
+ "epoch": 0.1436734693877551,
125
+ "grad_norm": 0.33763670921325684,
126
+ "learning_rate": 9.931788382008588e-05,
127
+ "loss": 0.3126,
128
+ "mean_token_accuracy": 0.8891353133320808,
129
+ "num_tokens": 51611949.0,
130
+ "step": 550
131
+ },
132
+ {
133
+ "entropy": 0.6003445901721716,
134
+ "epoch": 0.156734693877551,
135
+ "grad_norm": 0.4399724304676056,
136
+ "learning_rate": 9.913479778170688e-05,
137
+ "loss": 0.2951,
138
+ "mean_token_accuracy": 0.89730602607131,
139
+ "num_tokens": 56295022.0,
140
+ "step": 600
141
+ },
142
+ {
143
+ "entropy": 0.6263976456224918,
144
+ "epoch": 0.16979591836734695,
145
+ "grad_norm": 0.24783462285995483,
146
+ "learning_rate": 9.893018256683967e-05,
147
+ "loss": 0.345,
148
+ "mean_token_accuracy": 0.8859454789757728,
149
+ "num_tokens": 60989496.0,
150
+ "step": 650
151
+ },
152
+ {
153
+ "entropy": 0.6047938592731953,
154
+ "epoch": 0.18285714285714286,
155
+ "grad_norm": 0.6106021404266357,
156
+ "learning_rate": 9.870412783082573e-05,
157
+ "loss": 0.4187,
158
+ "mean_token_accuracy": 0.8859497668594122,
159
+ "num_tokens": 65706938.0,
160
+ "step": 700
161
+ },
162
+ {
163
+ "entropy": 0.6086559303104877,
164
+ "epoch": 0.19591836734693877,
165
+ "grad_norm": 0.6276345252990723,
166
+ "learning_rate": 9.845673262306643e-05,
167
+ "loss": 0.2703,
168
+ "mean_token_accuracy": 0.9083889089524746,
169
+ "num_tokens": 70440218.0,
170
+ "step": 750
171
+ },
172
+ {
173
+ "entropy": 0.5998903425782919,
174
+ "epoch": 0.2089795918367347,
175
+ "grad_norm": 0.46106088161468506,
176
+ "learning_rate": 9.818810534362306e-05,
177
+ "loss": 0.3502,
178
+ "mean_token_accuracy": 0.8987785133719445,
179
+ "num_tokens": 75125260.0,
180
+ "step": 800
181
+ },
182
+ {
183
+ "entropy": 0.5996488413214683,
184
+ "epoch": 0.2220408163265306,
185
+ "grad_norm": 0.2753312289714813,
186
+ "learning_rate": 9.789836369571958e-05,
187
+ "loss": 0.3382,
188
+ "mean_token_accuracy": 0.9013783724606037,
189
+ "num_tokens": 79822058.0,
190
+ "step": 850
191
+ },
192
+ {
193
+ "entropy": 0.6070075839012862,
194
+ "epoch": 0.23510204081632652,
195
+ "grad_norm": 0.44265103340148926,
196
+ "learning_rate": 9.758763463416922e-05,
197
+ "loss": 0.3303,
198
+ "mean_token_accuracy": 0.9064150702953339,
199
+ "num_tokens": 84511616.0,
200
+ "step": 900
201
+ },
202
+ {
203
+ "entropy": 0.6011689330637455,
204
+ "epoch": 0.24816326530612245,
205
+ "grad_norm": 0.2258819341659546,
206
+ "learning_rate": 9.725605430974712e-05,
207
+ "loss": 0.281,
208
+ "mean_token_accuracy": 0.9128213880956173,
209
+ "num_tokens": 89218784.0,
210
+ "step": 950
211
+ },
212
+ {
213
+ "entropy": 0.610101203173399,
214
+ "epoch": 0.2612244897959184,
215
+ "grad_norm": 0.5324413180351257,
216
+ "learning_rate": 9.690376800953389e-05,
217
+ "loss": 0.2765,
218
+ "mean_token_accuracy": 0.9096981877088547,
219
+ "num_tokens": 93934733.0,
220
+ "step": 1000
221
+ },
222
+ {
223
+ "epoch": 0.2612244897959184,
224
+ "eval_entropy": 0.6072796992301941,
225
+ "eval_loss": 0.22717319428920746,
226
+ "eval_mean_token_accuracy": 0.9097091863632202,
227
+ "eval_num_tokens": 93934733.0,
228
+ "eval_runtime": 105.7447,
229
+ "eval_samples_per_second": 189.135,
230
+ "eval_steps_per_second": 5.91,
231
+ "step": 1000
232
+ },
233
+ {
234
+ "entropy": 0.6069025094807148,
235
+ "epoch": 0.2742857142857143,
236
+ "grad_norm": 0.32851845026016235,
237
+ "learning_rate": 9.65309300932557e-05,
238
+ "loss": 0.3301,
239
+ "mean_token_accuracy": 0.9123546965420246,
240
+ "num_tokens": 98646726.0,
241
+ "step": 1050
242
+ },
243
+ {
244
+ "entropy": 0.5923496520519257,
245
+ "epoch": 0.2873469387755102,
246
+ "grad_norm": 0.22054198384284973,
247
+ "learning_rate": 9.61377039256492e-05,
248
+ "loss": 0.2866,
249
+ "mean_token_accuracy": 0.9174483200907707,
250
+ "num_tokens": 103376112.0,
251
+ "step": 1100
252
+ },
253
+ {
254
+ "entropy": 0.5921645154803992,
255
+ "epoch": 0.3004081632653061,
256
+ "grad_norm": 0.8782572150230408,
257
+ "learning_rate": 9.572426180488079e-05,
258
+ "loss": 0.312,
259
+ "mean_token_accuracy": 0.9164931161701679,
260
+ "num_tokens": 108072462.0,
261
+ "step": 1150
262
+ },
263
+ {
264
+ "entropy": 0.6070084515213966,
265
+ "epoch": 0.313469387755102,
266
+ "grad_norm": 0.4552319049835205,
267
+ "learning_rate": 9.529078488705135e-05,
268
+ "loss": 0.3169,
269
+ "mean_token_accuracy": 0.9169696615636349,
270
+ "num_tokens": 112781107.0,
271
+ "step": 1200
272
+ },
273
+ {
274
+ "entropy": 0.5912807537615299,
275
+ "epoch": 0.32653061224489793,
276
+ "grad_norm": 0.3097328841686249,
277
+ "learning_rate": 9.483746310682004e-05,
278
+ "loss": 0.2641,
279
+ "mean_token_accuracy": 0.9121362474560738,
280
+ "num_tokens": 117459347.0,
281
+ "step": 1250
282
+ },
283
+ {
284
+ "entropy": 0.5872646420449018,
285
+ "epoch": 0.3395918367346939,
286
+ "grad_norm": 0.7857140898704529,
287
+ "learning_rate": 9.43644950941813e-05,
288
+ "loss": 0.3741,
289
+ "mean_token_accuracy": 0.9139573207497597,
290
+ "num_tokens": 122161796.0,
291
+ "step": 1300
292
+ },
293
+ {
294
+ "entropy": 0.5643932522833347,
295
+ "epoch": 0.3526530612244898,
296
+ "grad_norm": 0.4844133257865906,
297
+ "learning_rate": 9.387208808743222e-05,
298
+ "loss": 0.2447,
299
+ "mean_token_accuracy": 0.9241362990438938,
300
+ "num_tokens": 126862525.0,
301
+ "step": 1350
302
+ },
303
+ {
304
+ "entropy": 0.5853312531858683,
305
+ "epoch": 0.3657142857142857,
306
+ "grad_norm": 0.7309156656265259,
307
+ "learning_rate": 9.336045784236764e-05,
308
+ "loss": 0.2758,
309
+ "mean_token_accuracy": 0.9223621267080307,
310
+ "num_tokens": 131562166.0,
311
+ "step": 1400
312
+ },
313
+ {
314
+ "entropy": 0.5751851069927215,
315
+ "epoch": 0.3787755102040816,
316
+ "grad_norm": 0.6382029056549072,
317
+ "learning_rate": 9.28298285377436e-05,
318
+ "loss": 0.3572,
319
+ "mean_token_accuracy": 0.9173358491063118,
320
+ "num_tokens": 136280998.0,
321
+ "step": 1450
322
+ },
323
+ {
324
+ "entropy": 0.5755070626735688,
325
+ "epoch": 0.39183673469387753,
326
+ "grad_norm": 0.4856666326522827,
327
+ "learning_rate": 9.228043267704974e-05,
328
+ "loss": 0.2431,
329
+ "mean_token_accuracy": 0.9318676285445691,
330
+ "num_tokens": 140963483.0,
331
+ "step": 1500
332
+ },
333
+ {
334
+ "entropy": 0.5901833316683769,
335
+ "epoch": 0.4048979591836735,
336
+ "grad_norm": 0.23288387060165405,
337
+ "learning_rate": 9.171251098663445e-05,
338
+ "loss": 0.3199,
339
+ "mean_token_accuracy": 0.9218292973935605,
340
+ "num_tokens": 145663835.0,
341
+ "step": 1550
342
+ },
343
+ {
344
+ "entropy": 0.6068822190165519,
345
+ "epoch": 0.4179591836734694,
346
+ "grad_norm": 0.7570965886116028,
347
+ "learning_rate": 9.112631231022669e-05,
348
+ "loss": 0.2503,
349
+ "mean_token_accuracy": 0.9219834499061108,
350
+ "num_tokens": 150388643.0,
351
+ "step": 1600
352
+ },
353
+ {
354
+ "entropy": 0.6086373251676559,
355
+ "epoch": 0.4310204081632653,
356
+ "grad_norm": 0.40420103073120117,
357
+ "learning_rate": 9.052209349990144e-05,
358
+ "loss": 0.2979,
359
+ "mean_token_accuracy": 0.9300994580984115,
360
+ "num_tokens": 155072117.0,
361
+ "step": 1650
362
+ },
363
+ {
364
+ "entropy": 0.5892787943035365,
365
+ "epoch": 0.4440816326530612,
366
+ "grad_norm": 0.28975844383239746,
367
+ "learning_rate": 8.990011930353579e-05,
368
+ "loss": 0.2509,
369
+ "mean_token_accuracy": 0.9298394879698754,
370
+ "num_tokens": 159761671.0,
371
+ "step": 1700
372
+ },
373
+ {
374
+ "entropy": 0.5920831595361232,
375
+ "epoch": 0.45714285714285713,
376
+ "grad_norm": 0.3639383018016815,
377
+ "learning_rate": 8.926066224880565e-05,
378
+ "loss": 0.2603,
379
+ "mean_token_accuracy": 0.9342290599644184,
380
+ "num_tokens": 164475669.0,
381
+ "step": 1750
382
+ },
383
+ {
384
+ "entropy": 0.5960557947307825,
385
+ "epoch": 0.47020408163265304,
386
+ "grad_norm": 0.7768979668617249,
387
+ "learning_rate": 8.86040025237734e-05,
388
+ "loss": 0.3215,
389
+ "mean_token_accuracy": 0.9318660141527653,
390
+ "num_tokens": 169186115.0,
391
+ "step": 1800
392
+ },
393
+ {
394
+ "entropy": 0.596306427642703,
395
+ "epoch": 0.483265306122449,
396
+ "grad_norm": 0.2945772409439087,
397
+ "learning_rate": 8.793042785411927e-05,
398
+ "loss": 0.2908,
399
+ "mean_token_accuracy": 0.9278665748238564,
400
+ "num_tokens": 173898142.0,
401
+ "step": 1850
402
+ },
403
+ {
404
+ "entropy": 0.5824826972186565,
405
+ "epoch": 0.4963265306122449,
406
+ "grad_norm": 0.629438042640686,
407
+ "learning_rate": 8.724023337706972e-05,
408
+ "loss": 0.2442,
409
+ "mean_token_accuracy": 0.9366743673384189,
410
+ "num_tokens": 178579887.0,
411
+ "step": 1900
412
+ },
413
+ {
414
+ "entropy": 0.6178072960674763,
415
+ "epoch": 0.5093877551020408,
416
+ "grad_norm": 0.2474866807460785,
417
+ "learning_rate": 8.653372151207855e-05,
418
+ "loss": 0.2979,
419
+ "mean_token_accuracy": 0.9314125381410122,
420
+ "num_tokens": 183276089.0,
421
+ "step": 1950
422
+ },
423
+ {
424
+ "entropy": 0.6088858918845653,
425
+ "epoch": 0.5224489795918368,
426
+ "grad_norm": 0.4756447970867157,
427
+ "learning_rate": 8.58112018283171e-05,
428
+ "loss": 0.3085,
429
+ "mean_token_accuracy": 0.933091163188219,
430
+ "num_tokens": 187979857.0,
431
+ "step": 2000
432
+ },
433
+ {
434
+ "epoch": 0.5224489795918368,
435
+ "eval_entropy": 0.5824218388557434,
436
+ "eval_loss": 0.1687791496515274,
437
+ "eval_mean_token_accuracy": 0.9382246346473694,
438
+ "eval_num_tokens": 187979857.0,
439
+ "eval_runtime": 105.81,
440
+ "eval_samples_per_second": 189.018,
441
+ "eval_steps_per_second": 5.907,
442
+ "step": 2000
443
+ },
444
+ {
445
+ "entropy": 0.6008229818940163,
446
+ "epoch": 0.5355102040816326,
447
+ "grad_norm": 0.968726634979248,
448
+ "learning_rate": 8.507299090903164e-05,
449
+ "loss": 0.217,
450
+ "mean_token_accuracy": 0.9400185799598694,
451
+ "num_tokens": 192675403.0,
452
+ "step": 2050
453
+ },
454
+ {
455
+ "entropy": 0.5939074163138867,
456
+ "epoch": 0.5485714285714286,
457
+ "grad_norm": 0.33287671208381653,
458
+ "learning_rate": 8.43194122128276e-05,
459
+ "loss": 0.2473,
460
+ "mean_token_accuracy": 0.9392171530425548,
461
+ "num_tokens": 197339702.0,
462
+ "step": 2100
463
+ },
464
+ {
465
+ "entropy": 0.5947689298540354,
466
+ "epoch": 0.5616326530612245,
467
+ "grad_norm": 0.5438774228096008,
468
+ "learning_rate": 8.355079593194101e-05,
469
+ "loss": 0.2401,
470
+ "mean_token_accuracy": 0.9419188013672829,
471
+ "num_tokens": 202042351.0,
472
+ "step": 2150
473
+ },
474
+ {
475
+ "entropy": 0.6115065851807594,
476
+ "epoch": 0.5746938775510204,
477
+ "grad_norm": 0.3915332555770874,
478
+ "learning_rate": 8.276747884755978e-05,
479
+ "loss": 0.2958,
480
+ "mean_token_accuracy": 0.9387796081602573,
481
+ "num_tokens": 206746259.0,
482
+ "step": 2200
483
+ },
484
+ {
485
+ "entropy": 0.5970733669400216,
486
+ "epoch": 0.5877551020408164,
487
+ "grad_norm": 0.7760431170463562,
488
+ "learning_rate": 8.196980418225764e-05,
489
+ "loss": 0.2355,
490
+ "mean_token_accuracy": 0.94012371301651,
491
+ "num_tokens": 211462162.0,
492
+ "step": 2250
493
+ },
494
+ {
495
+ "entropy": 0.5940753533691168,
496
+ "epoch": 0.6008163265306122,
497
+ "grad_norm": 0.2869822382926941,
498
+ "learning_rate": 8.115812144960594e-05,
499
+ "loss": 0.2469,
500
+ "mean_token_accuracy": 0.9416494782269001,
501
+ "num_tokens": 216190557.0,
502
+ "step": 2300
503
+ },
504
+ {
505
+ "entropy": 0.60329102024436,
506
+ "epoch": 0.6138775510204082,
507
+ "grad_norm": 0.6603459715843201,
508
+ "learning_rate": 8.033278630102877e-05,
509
+ "loss": 0.2189,
510
+ "mean_token_accuracy": 0.9444279509782791,
511
+ "num_tokens": 220880056.0,
512
+ "step": 2350
513
+ },
514
+ {
515
+ "entropy": 0.6052355971932412,
516
+ "epoch": 0.626938775510204,
517
+ "grad_norm": 0.3574765622615814,
518
+ "learning_rate": 7.949416036996879e-05,
519
+ "loss": 0.2728,
520
+ "mean_token_accuracy": 0.9418448767066002,
521
+ "num_tokens": 225589999.0,
522
+ "step": 2400
523
+ },
524
+ {
525
+ "entropy": 0.5736296055465937,
526
+ "epoch": 0.64,
527
+ "grad_norm": 0.31953155994415283,
528
+ "learning_rate": 7.864261111343187e-05,
529
+ "loss": 0.2291,
530
+ "mean_token_accuracy": 0.9489433655142784,
531
+ "num_tokens": 230305382.0,
532
+ "step": 2450
533
+ },
534
+ {
535
+ "entropy": 0.602155731767416,
536
+ "epoch": 0.6530612244897959,
537
+ "grad_norm": 0.6838288903236389,
538
+ "learning_rate": 7.777851165098012e-05,
539
+ "loss": 0.1958,
540
+ "mean_token_accuracy": 0.946748715788126,
541
+ "num_tokens": 235011703.0,
542
+ "step": 2500
543
+ },
544
+ {
545
+ "entropy": 0.5958992087841034,
546
+ "epoch": 0.6661224489795918,
547
+ "grad_norm": 0.22716443240642548,
548
+ "learning_rate": 7.690224060124371e-05,
549
+ "loss": 0.2536,
550
+ "mean_token_accuracy": 0.9489493478089571,
551
+ "num_tokens": 239706919.0,
552
+ "step": 2550
553
+ },
554
+ {
555
+ "entropy": 0.6019650375843049,
556
+ "epoch": 0.6791836734693878,
557
+ "grad_norm": 0.3493569493293762,
558
+ "learning_rate": 7.601418191602328e-05,
559
+ "loss": 0.2586,
560
+ "mean_token_accuracy": 0.9482229042053223,
561
+ "num_tokens": 244418186.0,
562
+ "step": 2600
563
+ },
564
+ {
565
+ "entropy": 0.586955601349473,
566
+ "epoch": 0.6922448979591836,
567
+ "grad_norm": 0.25364527106285095,
568
+ "learning_rate": 7.511472471205541e-05,
569
+ "loss": 0.2511,
570
+ "mean_token_accuracy": 0.9499958890676499,
571
+ "num_tokens": 249105699.0,
572
+ "step": 2650
573
+ },
574
+ {
575
+ "entropy": 0.57311468757689,
576
+ "epoch": 0.7053061224489796,
577
+ "grad_norm": 0.854145884513855,
578
+ "learning_rate": 7.42042631005151e-05,
579
+ "loss": 0.2548,
580
+ "mean_token_accuracy": 0.948536623865366,
581
+ "num_tokens": 253800051.0,
582
+ "step": 2700
583
+ },
584
+ {
585
+ "entropy": 0.5846149046719075,
586
+ "epoch": 0.7183673469387755,
587
+ "grad_norm": 0.7333242297172546,
588
+ "learning_rate": 7.328319601432987e-05,
589
+ "loss": 0.2424,
590
+ "mean_token_accuracy": 0.951610994040966,
591
+ "num_tokens": 258490956.0,
592
+ "step": 2750
593
+ },
594
+ {
595
+ "entropy": 0.5881183807551861,
596
+ "epoch": 0.7314285714285714,
597
+ "grad_norm": 0.34874463081359863,
598
+ "learning_rate": 7.2351927033381e-05,
599
+ "loss": 0.3103,
600
+ "mean_token_accuracy": 0.9474381080269814,
601
+ "num_tokens": 263183558.0,
602
+ "step": 2800
603
+ },
604
+ {
605
+ "entropy": 0.6000971308350563,
606
+ "epoch": 0.7444897959183674,
607
+ "grad_norm": 0.40719911456108093,
608
+ "learning_rate": 7.141086420766875e-05,
609
+ "loss": 0.2412,
610
+ "mean_token_accuracy": 0.9557790002226829,
611
+ "num_tokens": 267896256.0,
612
+ "step": 2850
613
+ },
614
+ {
615
+ "entropy": 0.6206524230539798,
616
+ "epoch": 0.7575510204081632,
617
+ "grad_norm": 0.3394398093223572,
618
+ "learning_rate": 7.046041987851896e-05,
619
+ "loss": 0.2431,
620
+ "mean_token_accuracy": 0.9514926019310951,
621
+ "num_tokens": 272576019.0,
622
+ "step": 2900
623
+ },
624
+ {
625
+ "entropy": 0.5987586285173893,
626
+ "epoch": 0.7706122448979592,
627
+ "grad_norm": 0.435951828956604,
628
+ "learning_rate": 6.950101049790922e-05,
629
+ "loss": 0.2353,
630
+ "mean_token_accuracy": 0.9547148038446903,
631
+ "num_tokens": 277288513.0,
632
+ "step": 2950
633
+ },
634
+ {
635
+ "entropy": 0.5921910824626684,
636
+ "epoch": 0.7836734693877551,
637
+ "grad_norm": 0.39050304889678955,
638
+ "learning_rate": 6.853305644599397e-05,
639
+ "loss": 0.2647,
640
+ "mean_token_accuracy": 0.9546147619187831,
641
+ "num_tokens": 281988009.0,
642
+ "step": 3000
643
+ },
644
+ {
645
+ "epoch": 0.7836734693877551,
646
+ "eval_entropy": 0.5917929359436035,
647
+ "eval_loss": 0.13952013850212097,
648
+ "eval_mean_token_accuracy": 0.9494351725578308,
649
+ "eval_num_tokens": 281988009.0,
650
+ "eval_runtime": 105.8253,
651
+ "eval_samples_per_second": 188.991,
652
+ "eval_steps_per_second": 5.906,
653
+ "step": 3000
654
+ },
655
+ {
656
+ "entropy": 0.5995206294953823,
657
+ "epoch": 0.796734693877551,
658
+ "grad_norm": 0.5683656334877014,
659
+ "learning_rate": 6.755698184690837e-05,
660
+ "loss": 0.2358,
661
+ "mean_token_accuracy": 0.954430370926857,
662
+ "num_tokens": 286687009.0,
663
+ "step": 3050
664
+ },
665
+ {
666
+ "entropy": 0.6226249255239964,
667
+ "epoch": 0.809795918367347,
668
+ "grad_norm": 0.17246268689632416,
669
+ "learning_rate": 6.657321438293174e-05,
670
+ "loss": 0.2491,
671
+ "mean_token_accuracy": 0.9509413394331933,
672
+ "num_tokens": 291376119.0,
673
+ "step": 3100
674
+ },
675
+ {
676
+ "entropy": 0.5907960905134678,
677
+ "epoch": 0.8228571428571428,
678
+ "grad_norm": 0.14905746281147003,
679
+ "learning_rate": 6.558218510709192e-05,
680
+ "loss": 0.1754,
681
+ "mean_token_accuracy": 0.9620982597768307,
682
+ "num_tokens": 296068600.0,
683
+ "step": 3150
684
+ },
685
+ {
686
+ "entropy": 0.6032850205898285,
687
+ "epoch": 0.8359183673469388,
688
+ "grad_norm": 0.7370997071266174,
689
+ "learning_rate": 6.458432825429263e-05,
690
+ "loss": 0.2096,
691
+ "mean_token_accuracy": 0.9580010569095612,
692
+ "num_tokens": 300766641.0,
693
+ "step": 3200
694
+ },
695
+ {
696
+ "entropy": 0.6270367397367954,
697
+ "epoch": 0.8489795918367347,
698
+ "grad_norm": 0.25541967153549194,
699
+ "learning_rate": 6.358008105104673e-05,
700
+ "loss": 0.2168,
701
+ "mean_token_accuracy": 0.9566573745012283,
702
+ "num_tokens": 305487589.0,
703
+ "step": 3250
704
+ },
705
+ {
706
+ "entropy": 0.5874304908514023,
707
+ "epoch": 0.8620408163265306,
708
+ "grad_norm": 0.6642680764198303,
709
+ "learning_rate": 6.256988352389859e-05,
710
+ "loss": 0.2361,
711
+ "mean_token_accuracy": 0.9588885164260864,
712
+ "num_tokens": 310194698.0,
713
+ "step": 3300
714
+ },
715
+ {
716
+ "entropy": 0.6110400749742985,
717
+ "epoch": 0.8751020408163265,
718
+ "grad_norm": 0.26045140624046326,
719
+ "learning_rate": 6.155417830661963e-05,
720
+ "loss": 0.1988,
721
+ "mean_token_accuracy": 0.9600324124097824,
722
+ "num_tokens": 314871495.0,
723
+ "step": 3350
724
+ },
725
+ {
726
+ "entropy": 0.5896776075661182,
727
+ "epoch": 0.8881632653061224,
728
+ "grad_norm": 0.6913824677467346,
729
+ "learning_rate": 6.0533410446261415e-05,
730
+ "loss": 0.2404,
731
+ "mean_token_accuracy": 0.9585775223374366,
732
+ "num_tokens": 319562203.0,
733
+ "step": 3400
734
+ },
735
+ {
736
+ "entropy": 0.6021107806265354,
737
+ "epoch": 0.9012244897959184,
738
+ "grad_norm": 1.0586336851119995,
739
+ "learning_rate": 5.950802720815143e-05,
740
+ "loss": 0.242,
741
+ "mean_token_accuracy": 0.9604564820230007,
742
+ "num_tokens": 324272631.0,
743
+ "step": 3450
744
+ },
745
+ {
746
+ "entropy": 0.6005905717611313,
747
+ "epoch": 0.9142857142857143,
748
+ "grad_norm": 0.33950117230415344,
749
+ "learning_rate": 5.8478477879916714e-05,
750
+ "loss": 0.2179,
751
+ "mean_token_accuracy": 0.9604296152293682,
752
+ "num_tokens": 328972230.0,
753
+ "step": 3500
754
+ },
755
+ {
756
+ "entropy": 0.6018191055953502,
757
+ "epoch": 0.9273469387755102,
758
+ "grad_norm": 0.34331461787223816,
759
+ "learning_rate": 5.744521357462156e-05,
760
+ "loss": 0.2278,
761
+ "mean_token_accuracy": 0.9604898960888386,
762
+ "num_tokens": 333680964.0,
763
+ "step": 3550
764
+ },
765
+ {
766
+ "entropy": 0.6024402364343405,
767
+ "epoch": 0.9404081632653061,
768
+ "grad_norm": 0.14388936758041382,
769
+ "learning_rate": 5.64086870331053e-05,
770
+ "loss": 0.227,
771
+ "mean_token_accuracy": 0.963430253714323,
772
+ "num_tokens": 338368553.0,
773
+ "step": 3600
774
+ },
775
+ {
776
+ "entropy": 0.5977859281003475,
777
+ "epoch": 0.953469387755102,
778
+ "grad_norm": 0.7793987989425659,
779
+ "learning_rate": 5.5369352425606816e-05,
780
+ "loss": 0.1802,
781
+ "mean_token_accuracy": 0.9638005784153938,
782
+ "num_tokens": 343050682.0,
783
+ "step": 3650
784
+ },
785
+ {
786
+ "entropy": 0.5996729772537946,
787
+ "epoch": 0.966530612244898,
788
+ "grad_norm": 1.3826709985733032,
789
+ "learning_rate": 5.4327665152762876e-05,
790
+ "loss": 0.2326,
791
+ "mean_token_accuracy": 0.9609452857077122,
792
+ "num_tokens": 347754882.0,
793
+ "step": 3700
794
+ },
795
+ {
796
+ "entropy": 0.5990429550409317,
797
+ "epoch": 0.9795918367346939,
798
+ "grad_norm": 0.921048641204834,
799
+ "learning_rate": 5.3284081646067105e-05,
800
+ "loss": 0.2117,
801
+ "mean_token_accuracy": 0.9624172969162464,
802
+ "num_tokens": 352466908.0,
803
+ "step": 3750
804
+ },
805
+ {
806
+ "entropy": 0.5920401379466057,
807
+ "epoch": 0.9926530612244898,
808
+ "grad_norm": 0.9255926012992859,
809
+ "learning_rate": 5.223905916787757e-05,
810
+ "loss": 0.2149,
811
+ "mean_token_accuracy": 0.9625219763815402,
812
+ "num_tokens": 357183033.0,
813
+ "step": 3800
814
+ },
815
+ {
816
+ "entropy": 0.5910900549124215,
817
+ "epoch": 1.0054857142857143,
818
+ "grad_norm": 0.31576788425445557,
819
+ "learning_rate": 5.119305561106008e-05,
820
+ "loss": 0.1889,
821
+ "mean_token_accuracy": 0.9667121869613803,
822
+ "num_tokens": 361822524.0,
823
+ "step": 3850
824
+ },
825
+ {
826
+ "entropy": 0.5463350272923708,
827
+ "epoch": 1.0185469387755102,
828
+ "grad_norm": 0.15527017414569855,
829
+ "learning_rate": 5.0146529298355305e-05,
830
+ "loss": 0.1567,
831
+ "mean_token_accuracy": 0.9730980744957924,
832
+ "num_tokens": 366524404.0,
833
+ "step": 3900
834
+ },
835
+ {
836
+ "entropy": 0.5311270990222693,
837
+ "epoch": 1.031608163265306,
838
+ "grad_norm": 0.7653639316558838,
839
+ "learning_rate": 4.909993878155755e-05,
840
+ "loss": 0.1941,
841
+ "mean_token_accuracy": 0.9723508515954018,
842
+ "num_tokens": 371187218.0,
843
+ "step": 3950
844
+ },
845
+ {
846
+ "entropy": 0.5343203826993704,
847
+ "epoch": 1.044669387755102,
848
+ "grad_norm": 0.3685067594051361,
849
+ "learning_rate": 4.805374264059317e-05,
850
+ "loss": 0.1643,
851
+ "mean_token_accuracy": 0.9716256402432919,
852
+ "num_tokens": 375891451.0,
853
+ "step": 4000
854
+ },
855
+ {
856
+ "epoch": 1.044669387755102,
857
+ "eval_entropy": 0.5199984492301941,
858
+ "eval_loss": 0.10260085761547089,
859
+ "eval_mean_token_accuracy": 0.9630540296554565,
860
+ "eval_num_tokens": 375891451.0,
861
+ "eval_runtime": 105.9615,
862
+ "eval_samples_per_second": 188.748,
863
+ "eval_steps_per_second": 5.898,
864
+ "step": 4000
865
+ },
866
+ {
867
+ "entropy": 0.5307158456742763,
868
+ "epoch": 1.057730612244898,
869
+ "grad_norm": 0.7387518882751465,
870
+ "learning_rate": 4.700839928258657e-05,
871
+ "loss": 0.1336,
872
+ "mean_token_accuracy": 0.9701156315207481,
873
+ "num_tokens": 380573790.0,
874
+ "step": 4050
875
+ },
876
+ {
877
+ "entropy": 0.5245926366001368,
878
+ "epoch": 1.0707918367346938,
879
+ "grad_norm": 0.5187281370162964,
880
+ "learning_rate": 4.596436674100202e-05,
881
+ "loss": 0.1243,
882
+ "mean_token_accuracy": 0.9722427415847779,
883
+ "num_tokens": 385276643.0,
884
+ "step": 4100
885
+ },
886
+ {
887
+ "entropy": 0.525925776809454,
888
+ "epoch": 1.0838530612244899,
889
+ "grad_norm": 0.11235808581113815,
890
+ "learning_rate": 4.492210247494922e-05,
891
+ "loss": 0.1594,
892
+ "mean_token_accuracy": 0.974123645722866,
893
+ "num_tokens": 390015359.0,
894
+ "step": 4150
895
+ },
896
+ {
897
+ "entropy": 0.5073333897441625,
898
+ "epoch": 1.0969142857142857,
899
+ "grad_norm": 0.3686864376068115,
900
+ "learning_rate": 4.3882063168740405e-05,
901
+ "loss": 0.1789,
902
+ "mean_token_accuracy": 0.9707419118285179,
903
+ "num_tokens": 394707917.0,
904
+ "step": 4200
905
+ },
906
+ {
907
+ "entropy": 0.5056077273190022,
908
+ "epoch": 1.1099755102040816,
909
+ "grad_norm": 0.7848389744758606,
910
+ "learning_rate": 4.284470453178698e-05,
911
+ "loss": 0.166,
912
+ "mean_token_accuracy": 0.9751219192147255,
913
+ "num_tokens": 399431065.0,
914
+ "step": 4250
915
+ },
916
+ {
917
+ "entropy": 0.5062515323609114,
918
+ "epoch": 1.1230367346938777,
919
+ "grad_norm": 0.2769508361816406,
920
+ "learning_rate": 4.181048109892344e-05,
921
+ "loss": 0.1537,
922
+ "mean_token_accuracy": 0.9724229994416237,
923
+ "num_tokens": 404132094.0,
924
+ "step": 4300
925
+ },
926
+ {
927
+ "entropy": 0.5368214490264654,
928
+ "epoch": 1.1360979591836735,
929
+ "grad_norm": 1.615638256072998,
930
+ "learning_rate": 4.077984603124577e-05,
931
+ "loss": 0.2671,
932
+ "mean_token_accuracy": 0.9685475620627403,
933
+ "num_tokens": 408819783.0,
934
+ "step": 4350
935
+ },
936
+ {
937
+ "entropy": 0.5090609015524388,
938
+ "epoch": 1.1491591836734694,
939
+ "grad_norm": 0.13154712319374084,
940
+ "learning_rate": 3.975325091755189e-05,
941
+ "loss": 0.2047,
942
+ "mean_token_accuracy": 0.9727970556914807,
943
+ "num_tokens": 413512051.0,
944
+ "step": 4400
945
+ },
946
+ {
947
+ "entropy": 0.5156180077046156,
948
+ "epoch": 1.1622204081632652,
949
+ "grad_norm": 0.33791911602020264,
950
+ "learning_rate": 3.873114557647105e-05,
951
+ "loss": 0.2171,
952
+ "mean_token_accuracy": 0.9713401012122631,
953
+ "num_tokens": 418236972.0,
954
+ "step": 4450
955
+ },
956
+ {
957
+ "entropy": 0.5125152183324099,
958
+ "epoch": 1.1752816326530613,
959
+ "grad_norm": 0.5354299545288086,
960
+ "learning_rate": 3.771397785936868e-05,
961
+ "loss": 0.1564,
962
+ "mean_token_accuracy": 0.9742588277161122,
963
+ "num_tokens": 422939153.0,
964
+ "step": 4500
965
+ },
966
+ {
967
+ "entropy": 0.5200927007943392,
968
+ "epoch": 1.1883428571428571,
969
+ "grad_norm": 0.7117024064064026,
970
+ "learning_rate": 3.67021934541134e-05,
971
+ "loss": 0.1567,
972
+ "mean_token_accuracy": 0.9759668205678463,
973
+ "num_tokens": 427638623.0,
974
+ "step": 4550
975
+ },
976
+ {
977
+ "entropy": 0.5100678735226393,
978
+ "epoch": 1.201404081632653,
979
+ "grad_norm": 0.7776734828948975,
980
+ "learning_rate": 3.5696235689792e-05,
981
+ "loss": 0.1744,
982
+ "mean_token_accuracy": 0.9728824967145919,
983
+ "num_tokens": 432324424.0,
984
+ "step": 4600
985
+ },
986
+ {
987
+ "entropy": 0.5009938656538725,
988
+ "epoch": 1.214465306122449,
989
+ "grad_norm": 0.45003074407577515,
990
+ "learning_rate": 3.469654534245781e-05,
991
+ "loss": 0.1523,
992
+ "mean_token_accuracy": 0.975490598231554,
993
+ "num_tokens": 437053744.0,
994
+ "step": 4650
995
+ },
996
+ {
997
+ "entropy": 0.5198498579859734,
998
+ "epoch": 1.227526530612245,
999
+ "grad_norm": 0.7395092248916626,
1000
+ "learning_rate": 3.370356044199785e-05,
1001
+ "loss": 0.1622,
1002
+ "mean_token_accuracy": 0.9760421338677406,
1003
+ "num_tokens": 441776589.0,
1004
+ "step": 4700
1005
+ },
1006
+ {
1007
+ "entropy": 0.5041036491096019,
1008
+ "epoch": 1.2405877551020408,
1009
+ "grad_norm": 0.6011821031570435,
1010
+ "learning_rate": 3.271771608020324e-05,
1011
+ "loss": 0.1282,
1012
+ "mean_token_accuracy": 0.9775787754356862,
1013
+ "num_tokens": 446474446.0,
1014
+ "step": 4750
1015
+ },
1016
+ {
1017
+ "entropy": 0.5190455333888531,
1018
+ "epoch": 1.2536489795918366,
1019
+ "grad_norm": 0.24861446022987366,
1020
+ "learning_rate": 3.173944422012688e-05,
1021
+ "loss": 0.1396,
1022
+ "mean_token_accuracy": 0.9773434112966061,
1023
+ "num_tokens": 451196726.0,
1024
+ "step": 4800
1025
+ },
1026
+ {
1027
+ "entropy": 0.5022503357380629,
1028
+ "epoch": 1.2667102040816327,
1029
+ "grad_norm": 0.24570924043655396,
1030
+ "learning_rate": 3.076917350681222e-05,
1031
+ "loss": 0.1592,
1032
+ "mean_token_accuracy": 0.9746822196245194,
1033
+ "num_tokens": 455888329.0,
1034
+ "step": 4850
1035
+ },
1036
+ {
1037
+ "entropy": 0.5063729017972947,
1038
+ "epoch": 1.2797714285714286,
1039
+ "grad_norm": 0.843909502029419,
1040
+ "learning_rate": 2.9807329079475686e-05,
1041
+ "loss": 0.1479,
1042
+ "mean_token_accuracy": 0.9775361755490303,
1043
+ "num_tokens": 460588507.0,
1044
+ "step": 4900
1045
+ },
1046
+ {
1047
+ "entropy": 0.5099849846214056,
1048
+ "epoch": 1.2928326530612244,
1049
+ "grad_norm": 0.5658782124519348,
1050
+ "learning_rate": 2.8854332385225336e-05,
1051
+ "loss": 0.1365,
1052
+ "mean_token_accuracy": 0.9764770893752575,
1053
+ "num_tokens": 465292875.0,
1054
+ "step": 4950
1055
+ },
1056
+ {
1057
+ "entropy": 0.5075208330154419,
1058
+ "epoch": 1.3058938775510205,
1059
+ "grad_norm": 0.5681100487709045,
1060
+ "learning_rate": 2.791060099439724e-05,
1061
+ "loss": 0.1547,
1062
+ "mean_token_accuracy": 0.9766012115776539,
1063
+ "num_tokens": 470018553.0,
1064
+ "step": 5000
1065
+ },
1066
+ {
1067
+ "epoch": 1.3058938775510205,
1068
+ "eval_entropy": 0.5093407655239105,
1069
+ "eval_loss": 0.07968976348638535,
1070
+ "eval_mean_token_accuracy": 0.9728172892570496,
1071
+ "eval_num_tokens": 470018553.0,
1072
+ "eval_runtime": 105.9871,
1073
+ "eval_samples_per_second": 188.702,
1074
+ "eval_steps_per_second": 5.897,
1075
+ "step": 5000
1076
+ },
1077
+ {
1078
+ "entropy": 0.5292845606803894,
1079
+ "epoch": 1.3189551020408163,
1080
+ "grad_norm": 0.3377012014389038,
1081
+ "learning_rate": 2.6976548417590607e-05,
1082
+ "loss": 0.1478,
1083
+ "mean_token_accuracy": 0.9774796655774116,
1084
+ "num_tokens": 474695442.0,
1085
+ "step": 5050
1086
+ },
1087
+ {
1088
+ "entropy": 0.5115040161460638,
1089
+ "epoch": 1.3320163265306122,
1090
+ "grad_norm": 0.31330540776252747,
1091
+ "learning_rate": 2.6052583924481532e-05,
1092
+ "loss": 0.1651,
1093
+ "mean_token_accuracy": 0.9753667731583119,
1094
+ "num_tokens": 479387979.0,
1095
+ "step": 5100
1096
+ },
1097
+ {
1098
+ "entropy": 0.518300534710288,
1099
+ "epoch": 1.3450775510204083,
1100
+ "grad_norm": 0.579721987247467,
1101
+ "learning_rate": 2.5139112364495286e-05,
1102
+ "loss": 0.2114,
1103
+ "mean_token_accuracy": 0.975457195341587,
1104
+ "num_tokens": 484096122.0,
1105
+ "step": 5150
1106
+ },
1107
+ {
1108
+ "entropy": 0.5092091238498688,
1109
+ "epoch": 1.3581387755102041,
1110
+ "grad_norm": 0.04276373237371445,
1111
+ "learning_rate": 2.4236533989415084e-05,
1112
+ "loss": 0.1473,
1113
+ "mean_token_accuracy": 0.978675073236227,
1114
+ "num_tokens": 488804070.0,
1115
+ "step": 5200
1116
+ },
1117
+ {
1118
+ "entropy": 0.5108030308783055,
1119
+ "epoch": 1.3712,
1120
+ "grad_norm": 0.34016624093055725,
1121
+ "learning_rate": 2.334524427800569e-05,
1122
+ "loss": 0.1871,
1123
+ "mean_token_accuracy": 0.9755242675542831,
1124
+ "num_tokens": 493512802.0,
1125
+ "step": 5250
1126
+ },
1127
+ {
1128
+ "entropy": 0.5037990070134402,
1129
+ "epoch": 1.384261224489796,
1130
+ "grad_norm": 0.058522939682006836,
1131
+ "learning_rate": 2.2465633762728094e-05,
1132
+ "loss": 0.1241,
1133
+ "mean_token_accuracy": 0.9779052963852882,
1134
+ "num_tokens": 498224036.0,
1135
+ "step": 5300
1136
+ },
1137
+ {
1138
+ "entropy": 0.5202232024073601,
1139
+ "epoch": 1.397322448979592,
1140
+ "grad_norm": 0.7593867182731628,
1141
+ "learning_rate": 2.1598087858621707e-05,
1142
+ "loss": 0.1528,
1143
+ "mean_token_accuracy": 0.9765554815530777,
1144
+ "num_tokens": 502927469.0,
1145
+ "step": 5350
1146
+ },
1147
+ {
1148
+ "entropy": 0.5276015343517065,
1149
+ "epoch": 1.4103836734693878,
1150
+ "grad_norm": 0.8394476175308228,
1151
+ "learning_rate": 2.074298669442881e-05,
1152
+ "loss": 0.1965,
1153
+ "mean_token_accuracy": 0.9732386584579945,
1154
+ "num_tokens": 507642470.0,
1155
+ "step": 5400
1156
+ },
1157
+ {
1158
+ "entropy": 0.5179370325058699,
1159
+ "epoch": 1.4234448979591836,
1160
+ "grad_norm": 0.280915766954422,
1161
+ "learning_rate": 1.9900704946035115e-05,
1162
+ "loss": 0.1817,
1163
+ "mean_token_accuracy": 0.9782391162216664,
1164
+ "num_tokens": 512330334.0,
1165
+ "step": 5450
1166
+ },
1167
+ {
1168
+ "entropy": 0.5077722806483507,
1169
+ "epoch": 1.4365061224489795,
1170
+ "grad_norm": 0.37315860390663147,
1171
+ "learning_rate": 1.9071611672299756e-05,
1172
+ "loss": 0.1516,
1173
+ "mean_token_accuracy": 0.9786237494647503,
1174
+ "num_tokens": 517049296.0,
1175
+ "step": 5500
1176
+ },
1177
+ {
1178
+ "entropy": 0.521270957365632,
1179
+ "epoch": 1.4495673469387755,
1180
+ "grad_norm": 0.8134558200836182,
1181
+ "learning_rate": 1.825607015334644e-05,
1182
+ "loss": 0.1509,
1183
+ "mean_token_accuracy": 0.9779170905053616,
1184
+ "num_tokens": 521739525.0,
1185
+ "step": 5550
1186
+ },
1187
+ {
1188
+ "entropy": 0.5181563084572554,
1189
+ "epoch": 1.4626285714285714,
1190
+ "grad_norm": 0.17686356604099274,
1191
+ "learning_rate": 1.7454437731386558e-05,
1192
+ "loss": 0.2467,
1193
+ "mean_token_accuracy": 0.9748677863925695,
1194
+ "num_tokens": 526451360.0,
1195
+ "step": 5600
1196
+ },
1197
+ {
1198
+ "entropy": 0.5103141793608665,
1199
+ "epoch": 1.4756897959183672,
1200
+ "grad_norm": 0.45316168665885925,
1201
+ "learning_rate": 1.6667065654144103e-05,
1202
+ "loss": 0.1965,
1203
+ "mean_token_accuracy": 0.9771437807381154,
1204
+ "num_tokens": 531176496.0,
1205
+ "step": 5650
1206
+ },
1207
+ {
1208
+ "entropy": 0.5023327280580997,
1209
+ "epoch": 1.4887510204081633,
1210
+ "grad_norm": 0.20157447457313538,
1211
+ "learning_rate": 1.5894298920951106e-05,
1212
+ "loss": 0.1909,
1213
+ "mean_token_accuracy": 0.9771021957695484,
1214
+ "num_tokens": 535864937.0,
1215
+ "step": 5700
1216
+ },
1217
+ {
1218
+ "entropy": 0.5016037753224373,
1219
+ "epoch": 1.5018122448979592,
1220
+ "grad_norm": 0.33676010370254517,
1221
+ "learning_rate": 1.5136476131580701e-05,
1222
+ "loss": 0.1675,
1223
+ "mean_token_accuracy": 0.9775694438815117,
1224
+ "num_tokens": 540571806.0,
1225
+ "step": 5750
1226
+ },
1227
+ {
1228
+ "entropy": 0.5027693736553193,
1229
+ "epoch": 1.514873469387755,
1230
+ "grad_norm": 0.5053212642669678,
1231
+ "learning_rate": 1.439392933788447e-05,
1232
+ "loss": 0.1807,
1233
+ "mean_token_accuracy": 0.9797284063696862,
1234
+ "num_tokens": 545276790.0,
1235
+ "step": 5800
1236
+ },
1237
+ {
1238
+ "entropy": 0.5009680130332709,
1239
+ "epoch": 1.527934693877551,
1240
+ "grad_norm": 0.09157374501228333,
1241
+ "learning_rate": 1.3666983898298657e-05,
1242
+ "loss": 0.2042,
1243
+ "mean_token_accuracy": 0.977972183674574,
1244
+ "num_tokens": 549964631.0,
1245
+ "step": 5850
1246
+ },
1247
+ {
1248
+ "entropy": 0.5023607714474201,
1249
+ "epoch": 1.540995918367347,
1250
+ "grad_norm": 0.23668606579303741,
1251
+ "learning_rate": 1.2955958335283353e-05,
1252
+ "loss": 0.2045,
1253
+ "mean_token_accuracy": 0.9760315857827664,
1254
+ "num_tokens": 554656554.0,
1255
+ "step": 5900
1256
+ },
1257
+ {
1258
+ "entropy": 0.505893104672432,
1259
+ "epoch": 1.5540571428571428,
1260
+ "grad_norm": 0.2585294246673584,
1261
+ "learning_rate": 1.2261164195756963e-05,
1262
+ "loss": 0.1519,
1263
+ "mean_token_accuracy": 0.9788727892935276,
1264
+ "num_tokens": 559319350.0,
1265
+ "step": 5950
1266
+ },
1267
+ {
1268
+ "entropy": 0.5045397817343473,
1269
+ "epoch": 1.5671183673469389,
1270
+ "grad_norm": 0.41178709268569946,
1271
+ "learning_rate": 1.1582905914586961e-05,
1272
+ "loss": 0.1618,
1273
+ "mean_token_accuracy": 0.9804812078177929,
1274
+ "num_tokens": 564036376.0,
1275
+ "step": 6000
1276
+ },
1277
+ {
1278
+ "epoch": 1.5671183673469389,
1279
+ "eval_entropy": 0.5037064853668213,
1280
+ "eval_loss": 0.06929752975702286,
1281
+ "eval_mean_token_accuracy": 0.9767320104598999,
1282
+ "eval_num_tokens": 564036376.0,
1283
+ "eval_runtime": 105.8974,
1284
+ "eval_samples_per_second": 188.862,
1285
+ "eval_steps_per_second": 5.902,
1286
+ "step": 6000
1287
+ },
1288
+ {
1289
+ "entropy": 0.5062011086195707,
1290
+ "epoch": 1.5801795918367347,
1291
+ "grad_norm": 0.3163544237613678,
1292
+ "learning_rate": 1.0921480681197138e-05,
1293
+ "loss": 0.196,
1294
+ "mean_token_accuracy": 0.977958171069622,
1295
+ "num_tokens": 568741475.0,
1296
+ "step": 6050
1297
+ },
1298
+ {
1299
+ "entropy": 0.5093516020476818,
1300
+ "epoch": 1.5932408163265306,
1301
+ "grad_norm": 0.23253564536571503,
1302
+ "learning_rate": 1.0277178309349372e-05,
1303
+ "loss": 0.144,
1304
+ "mean_token_accuracy": 0.9814330741763115,
1305
+ "num_tokens": 573428108.0,
1306
+ "step": 6100
1307
+ },
1308
+ {
1309
+ "entropy": 0.4951523919403553,
1310
+ "epoch": 1.6063020408163267,
1311
+ "grad_norm": 0.20008987188339233,
1312
+ "learning_rate": 9.650281110157183e-06,
1313
+ "loss": 0.1458,
1314
+ "mean_token_accuracy": 0.9807541972398758,
1315
+ "num_tokens": 578119662.0,
1316
+ "step": 6150
1317
+ },
1318
+ {
1319
+ "entropy": 0.496527906358242,
1320
+ "epoch": 1.6193632653061223,
1321
+ "grad_norm": 0.06572028249502182,
1322
+ "learning_rate": 9.041063768386771e-06,
1323
+ "loss": 0.177,
1324
+ "mean_token_accuracy": 0.9791599862277508,
1325
+ "num_tokens": 582814156.0,
1326
+ "step": 6200
1327
+ },
1328
+ {
1329
+ "entropy": 0.4998855730891228,
1330
+ "epoch": 1.6324244897959184,
1331
+ "grad_norm": 0.24737411737442017,
1332
+ "learning_rate": 8.449793222099634e-06,
1333
+ "loss": 0.1664,
1334
+ "mean_token_accuracy": 0.9825490611791611,
1335
+ "num_tokens": 587512323.0,
1336
+ "step": 6250
1337
+ },
1338
+ {
1339
+ "entropy": 0.5006625095009803,
1340
+ "epoch": 1.6454857142857144,
1341
+ "grad_norm": 0.30100393295288086,
1342
+ "learning_rate": 7.876728545689404e-06,
1343
+ "loss": 0.1073,
1344
+ "mean_token_accuracy": 0.9835961519181728,
1345
+ "num_tokens": 592189679.0,
1346
+ "step": 6300
1347
+ },
1348
+ {
1349
+ "entropy": 0.5041866586357355,
1350
+ "epoch": 1.65854693877551,
1351
+ "grad_norm": 0.652031421661377,
1352
+ "learning_rate": 7.322120836364504e-06,
1353
+ "loss": 0.1481,
1354
+ "mean_token_accuracy": 0.9796404030919075,
1355
+ "num_tokens": 596862019.0,
1356
+ "step": 6350
1357
+ },
1358
+ {
1359
+ "entropy": 0.5018126259744168,
1360
+ "epoch": 1.6716081632653061,
1361
+ "grad_norm": 0.42654654383659363,
1362
+ "learning_rate": 6.786213104125871e-06,
1363
+ "loss": 0.21,
1364
+ "mean_token_accuracy": 0.9779394802451133,
1365
+ "num_tokens": 601559394.0,
1366
+ "step": 6400
1367
+ },
1368
+ {
1369
+ "entropy": 0.5038939069211483,
1370
+ "epoch": 1.684669387755102,
1371
+ "grad_norm": 0.3602626919746399,
1372
+ "learning_rate": 6.269240165288398e-06,
1373
+ "loss": 0.178,
1374
+ "mean_token_accuracy": 0.9800453174114228,
1375
+ "num_tokens": 606253088.0,
1376
+ "step": 6450
1377
+ },
1378
+ {
1379
+ "entropy": 0.5044894518703222,
1380
+ "epoch": 1.6977306122448979,
1381
+ "grad_norm": 0.19107358157634735,
1382
+ "learning_rate": 5.771428539592538e-06,
1383
+ "loss": 0.1492,
1384
+ "mean_token_accuracy": 0.9798909470438957,
1385
+ "num_tokens": 610960360.0,
1386
+ "step": 6500
1387
+ },
1388
+ {
1389
+ "entropy": 0.5037923785299063,
1390
+ "epoch": 1.710791836734694,
1391
+ "grad_norm": 0.6636244058609009,
1392
+ "learning_rate": 5.2929963509511075e-06,
1393
+ "loss": 0.1676,
1394
+ "mean_token_accuracy": 0.9801163612306119,
1395
+ "num_tokens": 615644077.0,
1396
+ "step": 6550
1397
+ },
1398
+ {
1399
+ "entropy": 0.500140390098095,
1400
+ "epoch": 1.7238530612244898,
1401
+ "grad_norm": 0.32785269618034363,
1402
+ "learning_rate": 4.834153231874894e-06,
1403
+ "loss": 0.1749,
1404
+ "mean_token_accuracy": 0.9784755201637745,
1405
+ "num_tokens": 620360649.0,
1406
+ "step": 6600
1407
+ },
1408
+ {
1409
+ "entropy": 0.5020641582459211,
1410
+ "epoch": 1.7369142857142856,
1411
+ "grad_norm": 0.27923622727394104,
1412
+ "learning_rate": 4.39510023161897e-06,
1413
+ "loss": 0.1411,
1414
+ "mean_token_accuracy": 0.9816332237422466,
1415
+ "num_tokens": 625054261.0,
1416
+ "step": 6650
1417
+ },
1418
+ {
1419
+ "entropy": 0.49861018612980845,
1420
+ "epoch": 1.7499755102040817,
1421
+ "grad_norm": 0.5397801995277405,
1422
+ "learning_rate": 3.976029728089753e-06,
1423
+ "loss": 0.1326,
1424
+ "mean_token_accuracy": 0.9789401049911975,
1425
+ "num_tokens": 629754085.0,
1426
+ "step": 6700
1427
+ },
1428
+ {
1429
+ "entropy": 0.4957483353465795,
1430
+ "epoch": 1.7630367346938776,
1431
+ "grad_norm": 0.2673582434654236,
1432
+ "learning_rate": 3.5771253435516795e-06,
1433
+ "loss": 0.2066,
1434
+ "mean_token_accuracy": 0.9784379804134369,
1435
+ "num_tokens": 634458263.0,
1436
+ "step": 6750
1437
+ },
1438
+ {
1439
+ "entropy": 0.4926348590105772,
1440
+ "epoch": 1.7760979591836734,
1441
+ "grad_norm": 0.1889200657606125,
1442
+ "learning_rate": 3.198561864170252e-06,
1443
+ "loss": 0.1691,
1444
+ "mean_token_accuracy": 0.9774698014557361,
1445
+ "num_tokens": 639182514.0,
1446
+ "step": 6800
1447
+ },
1448
+ {
1449
+ "entropy": 0.49748403906822203,
1450
+ "epoch": 1.7891591836734695,
1451
+ "grad_norm": 0.41563114523887634,
1452
+ "learning_rate": 2.8405051634267377e-06,
1453
+ "loss": 0.1588,
1454
+ "mean_token_accuracy": 0.979499961733818,
1455
+ "num_tokens": 643873946.0,
1456
+ "step": 6850
1457
+ },
1458
+ {
1459
+ "entropy": 0.4990497587621212,
1460
+ "epoch": 1.8022204081632653,
1461
+ "grad_norm": 0.35716620087623596,
1462
+ "learning_rate": 2.5031121294381397e-06,
1463
+ "loss": 0.1517,
1464
+ "mean_token_accuracy": 0.9818871699273586,
1465
+ "num_tokens": 648556679.0,
1466
+ "step": 6900
1467
+ },
1468
+ {
1469
+ "entropy": 0.5038248886913061,
1470
+ "epoch": 1.8152816326530612,
1471
+ "grad_norm": 0.32431280612945557,
1472
+ "learning_rate": 2.186530596214215e-06,
1473
+ "loss": 0.1527,
1474
+ "mean_token_accuracy": 0.9806360864639282,
1475
+ "num_tokens": 653240714.0,
1476
+ "step": 6950
1477
+ },
1478
+ {
1479
+ "entropy": 0.49982765793800354,
1480
+ "epoch": 1.8283428571428573,
1481
+ "grad_norm": 0.8585988283157349,
1482
+ "learning_rate": 1.8908992788816915e-06,
1483
+ "loss": 0.1196,
1484
+ "mean_token_accuracy": 0.9828112371265888,
1485
+ "num_tokens": 657923166.0,
1486
+ "step": 7000
1487
+ },
1488
+ {
1489
+ "epoch": 1.8283428571428573,
1490
+ "eval_entropy": 0.49939153037071227,
1491
+ "eval_loss": 0.06544612348079681,
1492
+ "eval_mean_token_accuracy": 0.9783449116706848,
1493
+ "eval_num_tokens": 657923166.0,
1494
+ "eval_runtime": 106.0946,
1495
+ "eval_samples_per_second": 188.511,
1496
+ "eval_steps_per_second": 5.891,
1497
+ "step": 7000
1498
+ }
1499
+ ],
1500
+ "logging_steps": 50,
1501
+ "max_steps": 7658,
1502
+ "num_input_tokens_seen": 0,
1503
+ "num_train_epochs": 2,
1504
+ "save_steps": 1000,
1505
+ "stateful_callbacks": {
1506
+ "TrainerControl": {
1507
+ "args": {
1508
+ "should_epoch_stop": false,
1509
+ "should_evaluate": false,
1510
+ "should_log": false,
1511
+ "should_save": true,
1512
+ "should_training_stop": false
1513
+ },
1514
+ "attributes": {}
1515
+ }
1516
+ },
1517
+ "total_flos": 4.4371247004360114e+19,
1518
+ "train_batch_size": 4,
1519
+ "trial_name": null,
1520
+ "trial_params": null
1521
+ }
iter3-2epoch/checkpoint-7658/README.md ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct
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 0.17.1
iter3-2epoch/checkpoint-7658/adapter_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "qalora_group_size": 16,
24
+ "r": 256,
25
+ "rank_pattern": {},
26
+ "revision": null,
27
+ "target_modules": [
28
+ "down_proj",
29
+ "v_proj",
30
+ "o_proj",
31
+ "up_proj",
32
+ "gate_proj",
33
+ "q_proj",
34
+ "k_proj"
35
+ ],
36
+ "target_parameters": null,
37
+ "task_type": "CAUSAL_LM",
38
+ "trainable_token_indices": null,
39
+ "use_dora": false,
40
+ "use_qalora": false,
41
+ "use_rslora": false
42
+ }
iter3-2epoch/checkpoint-7658/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a3d64c6b16fa8a9f121abe5b3d76dfbb7f0bdce0ed47f514bceabd19bbf33cc
3
+ size 2684416208
iter3-2epoch/checkpoint-7658/chat_template.jinja ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
2
+
3
+ '+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
4
+
5
+ ' }}{% endif %}
iter3-2epoch/checkpoint-7658/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b6c1347d8778c2c5c9e8d9348b88b10ae2d27b84f4c17eadcdefb1191feb093
3
+ size 15984
iter3-2epoch/checkpoint-7658/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ccf0220a6d3fe2f0b879ffb3e1eb59ca98d0658a33c5a051c3e4f0245139ce5
3
+ size 15984
iter3-2epoch/checkpoint-7658/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74b7463a7705ceffe806c5f01e06babfe3520e2e22a9c4263f3f727b4e37abd7
3
+ size 15984
iter3-2epoch/checkpoint-7658/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e484b100fe259668cb7e62e5fa69c0d78e3a917ec0b1480f132bdf7b9382cb27
3
+ size 15984
iter3-2epoch/checkpoint-7658/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e444c89db00f6c36920cd31d860953e46103ed5e4416c12092bb97708699591
3
+ size 15984
iter3-2epoch/checkpoint-7658/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3ae0161fe409bee9be73b072e9176198d2c417e0b6d74b4a5709f20d58bd0d
3
+ size 15984
iter3-2epoch/checkpoint-7658/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22579ea7258cfdf2e892611172143e4c8ba73a63eb75761cff9fb4ad87a448b9
3
+ size 15984
iter3-2epoch/checkpoint-7658/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4de3632cbccabcc21b2877ca71586ccef76e0c4c98fa67c5d9f7843a8bb464a
3
+ size 15984
iter3-2epoch/checkpoint-7658/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }