Hugging Face's logo

AdithyaSK
/
LLama3-Gaja-Hindi-8B-Instruct-alpha

PEFT
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
AdithyaSK commited on
Commit
ee4137a
•
1 Parent(s): 2da36e7

Upload folder using huggingface_hub

Browse files
Files changed (39) hide show
  1. README.md +143 -0
  2. adapter_config.json +34 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-256/README.md +202 -0
  5. checkpoint-256/adapter_config.json +34 -0
  6. checkpoint-256/adapter_model.safetensors +3 -0
  7. checkpoint-256/optimizer.pt +3 -0
  8. checkpoint-256/rng_state.pth +3 -0
  9. checkpoint-256/scheduler.pt +3 -0
  10. checkpoint-256/special_tokens_map.json +23 -0
  11. checkpoint-256/tokenizer.json +0 -0
  12. checkpoint-256/tokenizer_config.json +2063 -0
  13. checkpoint-256/trainer_state.json +1837 -0
  14. checkpoint-256/training_args.bin +3 -0
  15. checkpoint-512/README.md +202 -0
  16. checkpoint-512/adapter_config.json +34 -0
  17. checkpoint-512/adapter_model.safetensors +3 -0
  18. checkpoint-512/optimizer.pt +3 -0
  19. checkpoint-512/rng_state.pth +3 -0
  20. checkpoint-512/scheduler.pt +3 -0
  21. checkpoint-512/special_tokens_map.json +23 -0
  22. checkpoint-512/tokenizer.json +0 -0
  23. checkpoint-512/tokenizer_config.json +2063 -0
  24. checkpoint-512/trainer_state.json +3645 -0
  25. checkpoint-512/training_args.bin +3 -0
  26. config.json +43 -0
  27. merged/config.json +28 -0
  28. merged/generation_config.json +10 -0
  29. merged/pytorch_model-00001-of-00004.bin +3 -0
  30. merged/pytorch_model-00002-of-00004.bin +3 -0
  31. merged/pytorch_model-00003-of-00004.bin +3 -0
  32. merged/pytorch_model-00004-of-00004.bin +3 -0
  33. merged/pytorch_model.bin.index.json +298 -0
  34. merged/special_tokens_map.json +23 -0
  35. merged/tokenizer.json +0 -0
  36. merged/tokenizer_config.json +2063 -0
  37. special_tokens_map.json +23 -0
  38. tokenizer.json +0 -0
  39. tokenizer_config.json +2063 -0
README.md ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
7
+ model-index:
8
+ - name: llama3-gaja-v0.1
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.0`
19
+ ```yaml
20
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
21
+ model_type: LlamaForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+
24
+ load_in_8bit: true
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: CognitiveLab/Samvaad_Hindi_Hinglish_Llama3_Prompt_formate
30
+ type: completion
31
+ field: text
32
+ dataset_prepared_path:
33
+ val_set_size: 0.05
34
+ output_dir: ./llama3-gaja-v0.1
35
+
36
+ sequence_len: 8000
37
+ sample_packing: true
38
+ pad_to_sequence_len: true
39
+
40
+ adapter: lora
41
+ lora_model_dir:
42
+ lora_r: 64
43
+ lora_alpha: 32
44
+ lora_dropout: 0.05
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project: llama3-gaja-v0.1
49
+ wandb_entity:
50
+ wandb_watch:
51
+ wandb_name:
52
+ wandb_log_model:
53
+
54
+ gradient_accumulation_steps: 6
55
+ micro_batch_size: 4
56
+ num_epochs: 1
57
+ optimizer: adamw_bnb_8bit
58
+ lr_scheduler: cosine
59
+ learning_rate: 0.00002
60
+
61
+ train_on_inputs: false
62
+ group_by_length: false
63
+ bf16: auto
64
+ fp16:
65
+ tf32: false
66
+
67
+ gradient_checkpointing: true
68
+ early_stopping_patience:
69
+ resume_from_checkpoint:
70
+ local_rank:
71
+ logging_steps: 1
72
+ xformers_attention:
73
+ flash_attention: true
74
+ s2_attention:
75
+
76
+ warmup_steps: 10
77
+ evals_per_epoch: 4
78
+ eval_table_size:
79
+ eval_max_new_tokens: 128
80
+ saves_per_epoch: 2
81
+ debug:
82
+ deepspeed:
83
+ weight_decay: 0.0
84
+ fsdp:
85
+ fsdp_config:
86
+ special_tokens:
87
+ pad_token: <|end_of_text|>
88
+ ```
89
+
90
+ </details><br>
91
+
92
+ # llama3-gaja-v0.1
93
+
94
+ 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) on the None dataset.
95
+ It achieves the following results on the evaluation set:
96
+ - Loss: 1.0365
97
+
98
+ ## Model description
99
+
100
+ More information needed
101
+
102
+ ## Intended uses & limitations
103
+
104
+ More information needed
105
+
106
+ ## Training and evaluation data
107
+
108
+ More information needed
109
+
110
+ ## Training procedure
111
+
112
+ ### Training hyperparameters
113
+
114
+ The following hyperparameters were used during training:
115
+ - learning_rate: 2e-05
116
+ - train_batch_size: 4
117
+ - eval_batch_size: 4
118
+ - seed: 42
119
+ - gradient_accumulation_steps: 6
120
+ - total_train_batch_size: 24
121
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
122
+ - lr_scheduler_type: cosine
123
+ - lr_scheduler_warmup_steps: 10
124
+ - num_epochs: 1
125
+
126
+ ### Training results
127
+
128
+ | Training Loss | Epoch | Step | Validation Loss |
129
+ |:-------------:|:-----:|:----:|:---------------:|
130
+ | 1.8709 | 0.0 | 1 | 1.8383 |
131
+ | 1.1106 | 0.25 | 128 | 1.0989 |
132
+ | 1.0379 | 0.5 | 256 | 1.0510 |
133
+ | 1.0402 | 0.75 | 384 | 1.0386 |
134
+ | 1.0703 | 1.0 | 512 | 1.0365 |
135
+
136
+
137
+ ### Framework versions
138
+
139
+ - PEFT 0.10.0
140
+ - Transformers 4.40.0.dev0
141
+ - Pytorch 2.0.1+cu118
142
+ - Datasets 2.15.0
143
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "o_proj",
26
+ "down_proj",
27
+ "q_proj",
28
+ "k_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcad3e502c6e260c888598cb3c1edcd30fed0ed695cc84179e3597a8a8be6ac7
3
+ size 671250189
checkpoint-256/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
checkpoint-256/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "o_proj",
26
+ "down_proj",
27
+ "q_proj",
28
+ "k_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-256/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e304643bf83d7bb3058702522b8e79554452f840cb85af402287d2a7fbda33
3
+ size 671149168
checkpoint-256/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb49fb1f4f7436ac7b75e6bd2771127c5b7d398bb2e2148fde8285b5ea35889
3
+ size 336725215
checkpoint-256/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:737cc3a7d3773fcb7499bb266cb471221889e731ba3fb4a4722ddf5ed61487c3
3
+ size 14575
checkpoint-256/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59b2bf6bb82cde99535e5e0002060b2f3067b6032a7ddde0a70e3081e5024632
3
+ size 627
checkpoint-256/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-256/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-256/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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ 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|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-256/trainer_state.json ADDED
@@ -0,0 +1,1837 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4991875203119922,
5
+ "eval_steps": 128,
6
+ "global_step": 256,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.5149741172790527,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.8709,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 1.8383064270019531,
21
+ "eval_runtime": 707.8127,
22
+ "eval_samples_per_second": 7.169,
23
+ "eval_steps_per_second": 1.793,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0,
28
+ "grad_norm": 0.48140937089920044,
29
+ "learning_rate": 4.000000000000001e-06,
30
+ "loss": 1.7751,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 0.4886001944541931,
36
+ "learning_rate": 6e-06,
37
+ "loss": 1.795,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "grad_norm": 0.46349120140075684,
43
+ "learning_rate": 8.000000000000001e-06,
44
+ "loss": 1.7569,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "grad_norm": 0.5320057272911072,
50
+ "learning_rate": 1e-05,
51
+ "loss": 1.9278,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.01,
56
+ "grad_norm": 0.48083460330963135,
57
+ "learning_rate": 1.2e-05,
58
+ "loss": 1.778,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.01,
63
+ "grad_norm": 0.503804624080658,
64
+ "learning_rate": 1.4e-05,
65
+ "loss": 1.8358,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.02,
70
+ "grad_norm": 0.5177507400512695,
71
+ "learning_rate": 1.6000000000000003e-05,
72
+ "loss": 1.8655,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.02,
77
+ "grad_norm": 0.5006410479545593,
78
+ "learning_rate": 1.8e-05,
79
+ "loss": 1.8087,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "grad_norm": 0.500285804271698,
85
+ "learning_rate": 2e-05,
86
+ "loss": 1.8254,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "grad_norm": 0.4819566607475281,
92
+ "learning_rate": 1.9999804178263253e-05,
93
+ "loss": 1.7627,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.02,
98
+ "grad_norm": 0.4860954284667969,
99
+ "learning_rate": 1.999921672072223e-05,
100
+ "loss": 1.7034,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.03,
105
+ "grad_norm": 0.5111412405967712,
106
+ "learning_rate": 1.9998237650384324e-05,
107
+ "loss": 1.7203,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.03,
112
+ "grad_norm": 0.500988245010376,
113
+ "learning_rate": 1.9996867005594193e-05,
114
+ "loss": 1.6721,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.03,
119
+ "grad_norm": 0.4903103709220886,
120
+ "learning_rate": 1.999510484003224e-05,
121
+ "loss": 1.6167,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "grad_norm": 0.4756762683391571,
127
+ "learning_rate": 1.999295122271253e-05,
128
+ "loss": 1.57,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "grad_norm": 0.4689522385597229,
134
+ "learning_rate": 1.999040623798008e-05,
135
+ "loss": 1.5461,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.04,
140
+ "grad_norm": 0.5094612836837769,
141
+ "learning_rate": 1.9987469985507553e-05,
142
+ "loss": 1.5526,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.04,
147
+ "grad_norm": 0.49769631028175354,
148
+ "learning_rate": 1.9984142580291368e-05,
149
+ "loss": 1.5115,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.04,
154
+ "grad_norm": 0.46388670802116394,
155
+ "learning_rate": 1.9980424152647174e-05,
156
+ "loss": 1.467,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.04,
161
+ "grad_norm": 0.4357146918773651,
162
+ "learning_rate": 1.9976314848204762e-05,
163
+ "loss": 1.3887,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.04,
168
+ "grad_norm": 0.440377414226532,
169
+ "learning_rate": 1.997181482790236e-05,
170
+ "loss": 1.3845,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "grad_norm": 0.4116402566432953,
176
+ "learning_rate": 1.9966924267980326e-05,
177
+ "loss": 1.4091,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.05,
182
+ "grad_norm": 0.3181552588939667,
183
+ "learning_rate": 1.996164335997425e-05,
184
+ "loss": 1.3324,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.05,
189
+ "grad_norm": 0.2932267189025879,
190
+ "learning_rate": 1.995597231070744e-05,
191
+ "loss": 1.315,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.05,
196
+ "grad_norm": 0.328800231218338,
197
+ "learning_rate": 1.994991134228285e-05,
198
+ "loss": 1.3334,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.05,
203
+ "grad_norm": 0.32027724385261536,
204
+ "learning_rate": 1.9943460692074345e-05,
205
+ "loss": 1.3161,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.05,
210
+ "grad_norm": 0.3247709274291992,
211
+ "learning_rate": 1.993662061271743e-05,
212
+ "loss": 1.2601,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.06,
217
+ "grad_norm": 0.33424896001815796,
218
+ "learning_rate": 1.9929391372099352e-05,
219
+ "loss": 1.2807,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.06,
224
+ "grad_norm": 0.28847330808639526,
225
+ "learning_rate": 1.9921773253348604e-05,
226
+ "loss": 1.2427,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.06,
231
+ "grad_norm": 0.2601753771305084,
232
+ "learning_rate": 1.991376655482383e-05,
233
+ "loss": 1.2602,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.06,
238
+ "grad_norm": 0.25505828857421875,
239
+ "learning_rate": 1.9905371590102157e-05,
240
+ "loss": 1.2539,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.06,
245
+ "grad_norm": 0.25789541006088257,
246
+ "learning_rate": 1.989658868796689e-05,
247
+ "loss": 1.2796,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.07,
252
+ "grad_norm": 0.1963696926832199,
253
+ "learning_rate": 1.988741819239467e-05,
254
+ "loss": 1.2533,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.07,
259
+ "grad_norm": 0.1652669906616211,
260
+ "learning_rate": 1.9877860462541964e-05,
261
+ "loss": 1.27,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.07,
266
+ "grad_norm": 0.15272551774978638,
267
+ "learning_rate": 1.986791587273103e-05,
268
+ "loss": 1.2092,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.07,
273
+ "grad_norm": 0.14809414744377136,
274
+ "learning_rate": 1.985758481243523e-05,
275
+ "loss": 1.2028,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.07,
280
+ "grad_norm": 0.14091093838214874,
281
+ "learning_rate": 1.98468676862638e-05,
282
+ "loss": 1.1737,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.08,
287
+ "grad_norm": 0.13234961032867432,
288
+ "learning_rate": 1.9835764913945998e-05,
289
+ "loss": 1.2242,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.08,
294
+ "grad_norm": 0.12562313675880432,
295
+ "learning_rate": 1.982427693031465e-05,
296
+ "loss": 1.1846,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.08,
301
+ "grad_norm": 0.12460777163505554,
302
+ "learning_rate": 1.981240418528914e-05,
303
+ "loss": 1.1954,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.08,
308
+ "grad_norm": 0.1261477917432785,
309
+ "learning_rate": 1.9800147143857774e-05,
310
+ "loss": 1.1944,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.08,
315
+ "grad_norm": 0.12070100754499435,
316
+ "learning_rate": 1.9787506286059584e-05,
317
+ "loss": 1.1814,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.09,
322
+ "grad_norm": 0.1318473368883133,
323
+ "learning_rate": 1.9774482106965512e-05,
324
+ "loss": 1.2289,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.09,
329
+ "grad_norm": 0.11869361251592636,
330
+ "learning_rate": 1.9761075116659037e-05,
331
+ "loss": 1.1507,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.09,
336
+ "grad_norm": 0.11668427288532257,
337
+ "learning_rate": 1.974728584021618e-05,
338
+ "loss": 1.1693,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.09,
343
+ "grad_norm": 0.12271205335855484,
344
+ "learning_rate": 1.9733114817684957e-05,
345
+ "loss": 1.219,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.09,
350
+ "grad_norm": 0.12055838108062744,
351
+ "learning_rate": 1.9718562604064213e-05,
352
+ "loss": 1.2424,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.1,
357
+ "grad_norm": 0.1191168949007988,
358
+ "learning_rate": 1.97036297692819e-05,
359
+ "loss": 1.2206,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.1,
364
+ "grad_norm": 0.11361384391784668,
365
+ "learning_rate": 1.9688316898172744e-05,
366
+ "loss": 1.1927,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.1,
371
+ "grad_norm": 0.109556645154953,
372
+ "learning_rate": 1.967262459045535e-05,
373
+ "loss": 1.2013,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.1,
378
+ "grad_norm": 0.11278169602155685,
379
+ "learning_rate": 1.9656553460708707e-05,
380
+ "loss": 1.2379,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.1,
385
+ "grad_norm": 0.11011548340320587,
386
+ "learning_rate": 1.9640104138348124e-05,
387
+ "loss": 1.1808,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.11,
392
+ "grad_norm": 0.09818632155656815,
393
+ "learning_rate": 1.9623277267600574e-05,
394
+ "loss": 1.1731,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.11,
399
+ "grad_norm": 0.1045491099357605,
400
+ "learning_rate": 1.9606073507479466e-05,
401
+ "loss": 1.1729,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.11,
406
+ "grad_norm": 0.0985143780708313,
407
+ "learning_rate": 1.9588493531758843e-05,
408
+ "loss": 1.165,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.11,
413
+ "grad_norm": 0.09513280540704727,
414
+ "learning_rate": 1.9570538028946974e-05,
415
+ "loss": 1.1765,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.11,
420
+ "grad_norm": 0.09834066778421402,
421
+ "learning_rate": 1.9552207702259412e-05,
422
+ "loss": 1.1411,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.12,
427
+ "grad_norm": 0.09748240560293198,
428
+ "learning_rate": 1.9533503269591438e-05,
429
+ "loss": 1.1995,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.12,
434
+ "grad_norm": 0.09501401335000992,
435
+ "learning_rate": 1.9514425463489946e-05,
436
+ "loss": 1.1414,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.12,
441
+ "grad_norm": 0.09078366309404373,
442
+ "learning_rate": 1.9494975031124768e-05,
443
+ "loss": 1.1132,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.12,
448
+ "grad_norm": 0.09064218401908875,
449
+ "learning_rate": 1.947515273425939e-05,
450
+ "loss": 1.1498,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.12,
455
+ "grad_norm": 0.09029112011194229,
456
+ "learning_rate": 1.945495934922113e-05,
457
+ "loss": 1.158,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.12,
462
+ "grad_norm": 0.09335145354270935,
463
+ "learning_rate": 1.9434395666870735e-05,
464
+ "loss": 1.181,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.13,
469
+ "grad_norm": 0.08959628641605377,
470
+ "learning_rate": 1.9413462492571403e-05,
471
+ "loss": 1.1353,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.13,
476
+ "grad_norm": 0.09235028922557831,
477
+ "learning_rate": 1.9392160646157242e-05,
478
+ "loss": 1.1566,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.13,
483
+ "grad_norm": 0.08852320164442062,
484
+ "learning_rate": 1.937049096190117e-05,
485
+ "loss": 1.1015,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.13,
490
+ "grad_norm": 0.09060905128717422,
491
+ "learning_rate": 1.934845428848222e-05,
492
+ "loss": 1.1312,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.13,
497
+ "grad_norm": 0.09065355360507965,
498
+ "learning_rate": 1.9326051488952334e-05,
499
+ "loss": 1.1456,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.14,
504
+ "grad_norm": 0.09140690416097641,
505
+ "learning_rate": 1.9303283440702524e-05,
506
+ "loss": 1.1661,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.14,
511
+ "grad_norm": 0.08641023188829422,
512
+ "learning_rate": 1.9280151035428544e-05,
513
+ "loss": 1.1153,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.14,
518
+ "grad_norm": 0.08729224652051926,
519
+ "learning_rate": 1.9256655179095954e-05,
520
+ "loss": 1.1956,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.14,
525
+ "grad_norm": 0.08514908701181412,
526
+ "learning_rate": 1.9232796791904627e-05,
527
+ "loss": 1.0969,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.14,
532
+ "grad_norm": 0.08789129555225372,
533
+ "learning_rate": 1.9208576808252725e-05,
534
+ "loss": 1.1669,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.15,
539
+ "grad_norm": 0.0829731896519661,
540
+ "learning_rate": 1.918399617670011e-05,
541
+ "loss": 1.101,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.15,
546
+ "grad_norm": 0.08415351063013077,
547
+ "learning_rate": 1.9159055859931163e-05,
548
+ "loss": 1.122,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.15,
553
+ "grad_norm": 0.07933653146028519,
554
+ "learning_rate": 1.9133756834717118e-05,
555
+ "loss": 1.1175,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.15,
560
+ "grad_norm": 0.0849999189376831,
561
+ "learning_rate": 1.9108100091877787e-05,
562
+ "loss": 1.1577,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.15,
567
+ "grad_norm": 0.0835108831524849,
568
+ "learning_rate": 1.9082086636242757e-05,
569
+ "loss": 1.1253,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.16,
574
+ "grad_norm": 0.07834841310977936,
575
+ "learning_rate": 1.905571748661204e-05,
576
+ "loss": 1.0963,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.16,
581
+ "grad_norm": 0.07953493297100067,
582
+ "learning_rate": 1.902899367571617e-05,
583
+ "loss": 1.1102,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.16,
588
+ "grad_norm": 0.07989759743213654,
589
+ "learning_rate": 1.9001916250175764e-05,
590
+ "loss": 1.1576,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.16,
595
+ "grad_norm": 0.07849448174238205,
596
+ "learning_rate": 1.8974486270460518e-05,
597
+ "loss": 1.0963,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.16,
602
+ "grad_norm": 0.07805287837982178,
603
+ "learning_rate": 1.894670481084769e-05,
604
+ "loss": 1.1364,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.17,
609
+ "grad_norm": 0.07698098570108414,
610
+ "learning_rate": 1.8918572959380005e-05,
611
+ "loss": 1.1407,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.17,
616
+ "grad_norm": 0.0766262486577034,
617
+ "learning_rate": 1.8890091817823073e-05,
618
+ "loss": 1.1225,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.17,
623
+ "grad_norm": 0.0798678770661354,
624
+ "learning_rate": 1.8861262501622213e-05,
625
+ "loss": 1.137,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.17,
630
+ "grad_norm": 0.07717825472354889,
631
+ "learning_rate": 1.8832086139858777e-05,
632
+ "loss": 1.1311,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.17,
637
+ "grad_norm": 0.07542562484741211,
638
+ "learning_rate": 1.880256387520593e-05,
639
+ "loss": 1.1066,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.18,
644
+ "grad_norm": 0.07316063344478607,
645
+ "learning_rate": 1.8772696863883905e-05,
646
+ "loss": 1.0976,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.18,
651
+ "grad_norm": 0.0738874301314354,
652
+ "learning_rate": 1.8742486275614706e-05,
653
+ "loss": 1.0901,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.18,
658
+ "grad_norm": 0.07698226720094681,
659
+ "learning_rate": 1.8711933293576303e-05,
660
+ "loss": 1.1224,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.18,
665
+ "grad_norm": 0.07452582567930222,
666
+ "learning_rate": 1.8681039114356298e-05,
667
+ "loss": 1.1399,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.18,
672
+ "grad_norm": 0.07452700287103653,
673
+ "learning_rate": 1.8649804947905057e-05,
674
+ "loss": 1.1639,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.19,
679
+ "grad_norm": 0.07358838617801666,
680
+ "learning_rate": 1.861823201748833e-05,
681
+ "loss": 1.1139,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.19,
686
+ "grad_norm": 0.07469804584980011,
687
+ "learning_rate": 1.8586321559639316e-05,
688
+ "loss": 1.1103,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.19,
693
+ "grad_norm": 0.07484911382198334,
694
+ "learning_rate": 1.8554074824110285e-05,
695
+ "loss": 1.1231,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.19,
700
+ "grad_norm": 0.07320189476013184,
701
+ "learning_rate": 1.8521493073823583e-05,
702
+ "loss": 1.1405,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.19,
707
+ "grad_norm": 0.07219311594963074,
708
+ "learning_rate": 1.8488577584822197e-05,
709
+ "loss": 1.1084,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.19,
714
+ "grad_norm": 0.07267658412456512,
715
+ "learning_rate": 1.8455329646219767e-05,
716
+ "loss": 1.109,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.2,
721
+ "grad_norm": 0.07124843448400497,
722
+ "learning_rate": 1.8421750560150112e-05,
723
+ "loss": 1.0997,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.2,
728
+ "grad_norm": 0.06921572983264923,
729
+ "learning_rate": 1.8387841641716226e-05,
730
+ "loss": 1.1095,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.2,
735
+ "grad_norm": 0.07149618864059448,
736
+ "learning_rate": 1.835360421893876e-05,
737
+ "loss": 1.1078,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.2,
742
+ "grad_norm": 0.07851895689964294,
743
+ "learning_rate": 1.8319039632704042e-05,
744
+ "loss": 1.1195,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.2,
749
+ "grad_norm": 0.07615454494953156,
750
+ "learning_rate": 1.8284149236711527e-05,
751
+ "loss": 1.0754,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.21,
756
+ "grad_norm": 0.07054944336414337,
757
+ "learning_rate": 1.8248934397420802e-05,
758
+ "loss": 1.0943,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.21,
763
+ "grad_norm": 0.07253159582614899,
764
+ "learning_rate": 1.821339649399807e-05,
765
+ "loss": 1.1263,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.21,
770
+ "grad_norm": 0.0729857012629509,
771
+ "learning_rate": 1.817753691826212e-05,
772
+ "loss": 1.0977,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.21,
777
+ "grad_norm": 0.07234011590480804,
778
+ "learning_rate": 1.8141357074629838e-05,
779
+ "loss": 1.1334,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.21,
784
+ "grad_norm": 0.07030120491981506,
785
+ "learning_rate": 1.8104858380061178e-05,
786
+ "loss": 1.0767,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.22,
791
+ "grad_norm": 0.07036615908145905,
792
+ "learning_rate": 1.80680422640037e-05,
793
+ "loss": 1.0796,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.22,
798
+ "grad_norm": 0.0742933601140976,
799
+ "learning_rate": 1.8030910168336558e-05,
800
+ "loss": 1.0671,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.22,
805
+ "grad_norm": 0.07065165787935257,
806
+ "learning_rate": 1.7993463547314044e-05,
807
+ "loss": 1.1594,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.22,
812
+ "grad_norm": 0.07182008028030396,
813
+ "learning_rate": 1.7955703867508634e-05,
814
+ "loss": 1.0936,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.22,
819
+ "grad_norm": 0.06882106512784958,
820
+ "learning_rate": 1.791763260775354e-05,
821
+ "loss": 1.1017,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.23,
826
+ "grad_norm": 0.07001936435699463,
827
+ "learning_rate": 1.7879251259084803e-05,
828
+ "loss": 1.1267,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.23,
833
+ "grad_norm": 0.06916490197181702,
834
+ "learning_rate": 1.78405613246829e-05,
835
+ "loss": 1.0787,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.23,
840
+ "grad_norm": 0.07149837166070938,
841
+ "learning_rate": 1.7801564319813854e-05,
842
+ "loss": 1.1302,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.23,
847
+ "grad_norm": 0.06783504039049149,
848
+ "learning_rate": 1.776226177176991e-05,
849
+ "loss": 1.1159,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.23,
854
+ "grad_norm": 0.07285293936729431,
855
+ "learning_rate": 1.7722655219809718e-05,
856
+ "loss": 1.0758,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.24,
861
+ "grad_norm": 0.07273004204034805,
862
+ "learning_rate": 1.768274621509803e-05,
863
+ "loss": 1.1019,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.24,
868
+ "grad_norm": 0.07392899692058563,
869
+ "learning_rate": 1.7642536320644964e-05,
870
+ "loss": 1.1111,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.24,
875
+ "grad_norm": 0.0693732351064682,
876
+ "learning_rate": 1.7602027111244807e-05,
877
+ "loss": 1.1109,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.24,
882
+ "grad_norm": 0.0721542090177536,
883
+ "learning_rate": 1.7561220173414297e-05,
884
+ "loss": 1.1246,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.24,
889
+ "grad_norm": 0.07002190500497818,
890
+ "learning_rate": 1.7520117105330524e-05,
891
+ "loss": 1.073,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.25,
896
+ "grad_norm": 0.0697953850030899,
897
+ "learning_rate": 1.7478719516768324e-05,
898
+ "loss": 1.0913,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.25,
903
+ "grad_norm": 0.07040461152791977,
904
+ "learning_rate": 1.7437029029037233e-05,
905
+ "loss": 1.1445,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.25,
910
+ "grad_norm": 0.07231634110212326,
911
+ "learning_rate": 1.7395047274917994e-05,
912
+ "loss": 1.1106,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.25,
917
+ "eval_loss": 1.0988876819610596,
918
+ "eval_runtime": 708.4228,
919
+ "eval_samples_per_second": 7.162,
920
+ "eval_steps_per_second": 1.791,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.25,
925
+ "grad_norm": 0.0713375061750412,
926
+ "learning_rate": 1.7352775898598615e-05,
927
+ "loss": 1.0982,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.25,
932
+ "grad_norm": 0.06747942417860031,
933
+ "learning_rate": 1.731021655560995e-05,
934
+ "loss": 1.1017,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.26,
939
+ "grad_norm": 0.071540467441082,
940
+ "learning_rate": 1.72673709127609e-05,
941
+ "loss": 1.0859,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.26,
946
+ "grad_norm": 0.06861750036478043,
947
+ "learning_rate": 1.7224240648073097e-05,
948
+ "loss": 1.0728,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.26,
953
+ "grad_norm": 0.06919445842504501,
954
+ "learning_rate": 1.718082745071521e-05,
955
+ "loss": 1.1218,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.26,
960
+ "grad_norm": 0.07422851771116257,
961
+ "learning_rate": 1.7137133020936783e-05,
962
+ "loss": 1.0881,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.26,
967
+ "grad_norm": 0.07452652603387833,
968
+ "learning_rate": 1.7093159070001637e-05,
969
+ "loss": 1.1073,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.27,
974
+ "grad_norm": 0.07337850332260132,
975
+ "learning_rate": 1.7048907320120867e-05,
976
+ "loss": 1.1065,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.27,
981
+ "grad_norm": 0.07020066678524017,
982
+ "learning_rate": 1.700437950438537e-05,
983
+ "loss": 1.0742,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.27,
988
+ "grad_norm": 0.07053718715906143,
989
+ "learning_rate": 1.695957736669799e-05,
990
+ "loss": 1.0627,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.27,
995
+ "grad_norm": 0.07288292795419693,
996
+ "learning_rate": 1.6914502661705216e-05,
997
+ "loss": 1.0842,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.27,
1002
+ "grad_norm": 0.07197044044733047,
1003
+ "learning_rate": 1.6869157154728437e-05,
1004
+ "loss": 1.065,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.27,
1009
+ "grad_norm": 0.07109569013118744,
1010
+ "learning_rate": 1.6823542621694852e-05,
1011
+ "loss": 1.0996,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.28,
1016
+ "grad_norm": 0.07084467262029648,
1017
+ "learning_rate": 1.677766084906787e-05,
1018
+ "loss": 1.0862,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.28,
1023
+ "grad_norm": 0.07195379585027695,
1024
+ "learning_rate": 1.6731513633777173e-05,
1025
+ "loss": 1.1184,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.28,
1030
+ "grad_norm": 0.07326792180538177,
1031
+ "learning_rate": 1.668510278314833e-05,
1032
+ "loss": 1.0867,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.28,
1037
+ "grad_norm": 0.07582233846187592,
1038
+ "learning_rate": 1.6638430114832015e-05,
1039
+ "loss": 1.0721,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.28,
1044
+ "grad_norm": 0.07204006612300873,
1045
+ "learning_rate": 1.6591497456732827e-05,
1046
+ "loss": 1.0565,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.29,
1051
+ "grad_norm": 0.07225130498409271,
1052
+ "learning_rate": 1.6544306646937683e-05,
1053
+ "loss": 1.1036,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.29,
1058
+ "grad_norm": 0.07662148773670197,
1059
+ "learning_rate": 1.649685953364385e-05,
1060
+ "loss": 1.0289,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.29,
1065
+ "grad_norm": 0.07611638307571411,
1066
+ "learning_rate": 1.644915797508656e-05,
1067
+ "loss": 1.1068,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.29,
1072
+ "grad_norm": 0.07609565556049347,
1073
+ "learning_rate": 1.6401203839466212e-05,
1074
+ "loss": 1.0816,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.29,
1079
+ "grad_norm": 0.0737641304731369,
1080
+ "learning_rate": 1.6352999004875242e-05,
1081
+ "loss": 1.1016,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.3,
1086
+ "grad_norm": 0.07359515875577927,
1087
+ "learning_rate": 1.630454535922452e-05,
1088
+ "loss": 1.0787,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.3,
1093
+ "grad_norm": 0.07506351917982101,
1094
+ "learning_rate": 1.6255844800169472e-05,
1095
+ "loss": 1.0789,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.3,
1100
+ "grad_norm": 0.07777760922908783,
1101
+ "learning_rate": 1.62068992350357e-05,
1102
+ "loss": 1.096,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.3,
1107
+ "grad_norm": 0.07574637979269028,
1108
+ "learning_rate": 1.6157710580744322e-05,
1109
+ "loss": 1.1007,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.3,
1114
+ "grad_norm": 0.07857154309749603,
1115
+ "learning_rate": 1.610828076373687e-05,
1116
+ "loss": 1.0735,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.31,
1121
+ "grad_norm": 0.07402702420949936,
1122
+ "learning_rate": 1.605861171989988e-05,
1123
+ "loss": 1.1003,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.31,
1128
+ "grad_norm": 0.07439373433589935,
1129
+ "learning_rate": 1.6008705394489032e-05,
1130
+ "loss": 1.0662,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.31,
1135
+ "grad_norm": 0.07392847537994385,
1136
+ "learning_rate": 1.5958563742052987e-05,
1137
+ "loss": 1.0487,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.31,
1142
+ "grad_norm": 0.07773245126008987,
1143
+ "learning_rate": 1.5908188726356843e-05,
1144
+ "loss": 1.1107,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.31,
1149
+ "grad_norm": 0.07752656936645508,
1150
+ "learning_rate": 1.5857582320305207e-05,
1151
+ "loss": 1.0426,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.32,
1156
+ "grad_norm": 0.07541097700595856,
1157
+ "learning_rate": 1.5806746505864947e-05,
1158
+ "loss": 1.081,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.32,
1163
+ "grad_norm": 0.07938623428344727,
1164
+ "learning_rate": 1.5755683273987554e-05,
1165
+ "loss": 1.0969,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.32,
1170
+ "grad_norm": 0.07379717379808426,
1171
+ "learning_rate": 1.5704394624531184e-05,
1172
+ "loss": 1.0763,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.32,
1177
+ "grad_norm": 0.07850446552038193,
1178
+ "learning_rate": 1.5652882566182316e-05,
1179
+ "loss": 1.1029,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.32,
1184
+ "grad_norm": 0.07627106457948685,
1185
+ "learning_rate": 1.5601149116377095e-05,
1186
+ "loss": 1.0611,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.33,
1191
+ "grad_norm": 0.07577154785394669,
1192
+ "learning_rate": 1.554919630122232e-05,
1193
+ "loss": 1.0973,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.33,
1198
+ "grad_norm": 0.07844171673059464,
1199
+ "learning_rate": 1.5497026155416087e-05,
1200
+ "loss": 1.1006,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.33,
1205
+ "grad_norm": 0.08061926811933517,
1206
+ "learning_rate": 1.5444640722168114e-05,
1207
+ "loss": 1.0879,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.33,
1212
+ "grad_norm": 0.07918211817741394,
1213
+ "learning_rate": 1.53920420531197e-05,
1214
+ "loss": 1.0602,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.33,
1219
+ "grad_norm": 0.08213488012552261,
1220
+ "learning_rate": 1.5339232208263394e-05,
1221
+ "loss": 1.0798,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.34,
1226
+ "grad_norm": 0.07898285239934921,
1227
+ "learning_rate": 1.5286213255862295e-05,
1228
+ "loss": 1.0969,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.34,
1233
+ "grad_norm": 0.08233582973480225,
1234
+ "learning_rate": 1.5232987272369076e-05,
1235
+ "loss": 1.0699,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.34,
1240
+ "grad_norm": 0.08074311912059784,
1241
+ "learning_rate": 1.5179556342344643e-05,
1242
+ "loss": 1.0851,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.34,
1247
+ "grad_norm": 0.08196305483579636,
1248
+ "learning_rate": 1.51259225583765e-05,
1249
+ "loss": 1.076,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.34,
1254
+ "grad_norm": 0.08637065440416336,
1255
+ "learning_rate": 1.5072088020996791e-05,
1256
+ "loss": 1.0989,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.35,
1261
+ "grad_norm": 0.08313170820474625,
1262
+ "learning_rate": 1.5018054838600033e-05,
1263
+ "loss": 1.09,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.35,
1268
+ "grad_norm": 0.08245568722486496,
1269
+ "learning_rate": 1.496382512736056e-05,
1270
+ "loss": 1.0572,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.35,
1275
+ "grad_norm": 0.08442118763923645,
1276
+ "learning_rate": 1.490940101114961e-05,
1277
+ "loss": 1.0669,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.35,
1282
+ "grad_norm": 0.08224523812532425,
1283
+ "learning_rate": 1.4854784621452176e-05,
1284
+ "loss": 1.0842,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.35,
1289
+ "grad_norm": 0.08642537891864777,
1290
+ "learning_rate": 1.479997809728352e-05,
1291
+ "loss": 1.123,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.35,
1296
+ "grad_norm": 0.08723440766334534,
1297
+ "learning_rate": 1.4744983585105388e-05,
1298
+ "loss": 1.0649,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.36,
1303
+ "grad_norm": 0.08666212856769562,
1304
+ "learning_rate": 1.4689803238741955e-05,
1305
+ "loss": 1.0938,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.36,
1310
+ "grad_norm": 0.09213647246360779,
1311
+ "learning_rate": 1.463443921929548e-05,
1312
+ "loss": 1.0903,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.36,
1317
+ "grad_norm": 0.08998877555131912,
1318
+ "learning_rate": 1.4578893695061644e-05,
1319
+ "loss": 1.0778,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.36,
1324
+ "grad_norm": 0.09158129245042801,
1325
+ "learning_rate": 1.4523168841444657e-05,
1326
+ "loss": 1.0932,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.36,
1331
+ "grad_norm": 0.09460633993148804,
1332
+ "learning_rate": 1.4467266840872041e-05,
1333
+ "loss": 1.0691,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.37,
1338
+ "grad_norm": 0.09502755105495453,
1339
+ "learning_rate": 1.441118988270916e-05,
1340
+ "loss": 1.0684,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.37,
1345
+ "grad_norm": 0.09307122975587845,
1346
+ "learning_rate": 1.4354940163173486e-05,
1347
+ "loss": 1.0776,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.37,
1352
+ "grad_norm": 0.09580650180578232,
1353
+ "learning_rate": 1.4298519885248574e-05,
1354
+ "loss": 1.0882,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.37,
1359
+ "grad_norm": 0.09251459687948227,
1360
+ "learning_rate": 1.4241931258597781e-05,
1361
+ "loss": 1.077,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.37,
1366
+ "grad_norm": 0.09432998299598694,
1367
+ "learning_rate": 1.4185176499477742e-05,
1368
+ "loss": 1.0012,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.38,
1373
+ "grad_norm": 0.09586652368307114,
1374
+ "learning_rate": 1.4128257830651554e-05,
1375
+ "loss": 1.0334,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.38,
1380
+ "grad_norm": 0.09538242220878601,
1381
+ "learning_rate": 1.407117748130174e-05,
1382
+ "loss": 1.0731,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.38,
1387
+ "grad_norm": 0.09691152721643448,
1388
+ "learning_rate": 1.401393768694292e-05,
1389
+ "loss": 1.0412,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.38,
1394
+ "grad_norm": 0.09779084473848343,
1395
+ "learning_rate": 1.3956540689334286e-05,
1396
+ "loss": 1.0602,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.38,
1401
+ "grad_norm": 0.0998532623052597,
1402
+ "learning_rate": 1.3898988736391792e-05,
1403
+ "loss": 1.0261,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.39,
1408
+ "grad_norm": 0.10739872604608536,
1409
+ "learning_rate": 1.384128408210011e-05,
1410
+ "loss": 1.0502,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.39,
1415
+ "grad_norm": 0.11806387454271317,
1416
+ "learning_rate": 1.3783428986424366e-05,
1417
+ "loss": 1.1188,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.39,
1422
+ "grad_norm": 0.10208501666784286,
1423
+ "learning_rate": 1.3725425715221625e-05,
1424
+ "loss": 1.0465,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.39,
1429
+ "grad_norm": 0.1044783741235733,
1430
+ "learning_rate": 1.3667276540152143e-05,
1431
+ "loss": 1.0561,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.39,
1436
+ "grad_norm": 0.1070132926106453,
1437
+ "learning_rate": 1.3608983738590414e-05,
1438
+ "loss": 1.0429,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.4,
1443
+ "grad_norm": 0.11181865632534027,
1444
+ "learning_rate": 1.3550549593535965e-05,
1445
+ "loss": 1.0564,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.4,
1450
+ "grad_norm": 0.11098324507474899,
1451
+ "learning_rate": 1.3491976393523952e-05,
1452
+ "loss": 1.0632,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.4,
1457
+ "grad_norm": 0.10281454026699066,
1458
+ "learning_rate": 1.343326643253552e-05,
1459
+ "loss": 1.0637,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.4,
1464
+ "grad_norm": 0.10408665239810944,
1465
+ "learning_rate": 1.3374422009907984e-05,
1466
+ "loss": 1.0701,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.4,
1471
+ "grad_norm": 0.10533872246742249,
1472
+ "learning_rate": 1.3315445430244744e-05,
1473
+ "loss": 1.0654,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.41,
1478
+ "grad_norm": 0.10545054078102112,
1479
+ "learning_rate": 1.3256339003325054e-05,
1480
+ "loss": 1.0518,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.41,
1485
+ "grad_norm": 0.09894714504480362,
1486
+ "learning_rate": 1.3197105044013544e-05,
1487
+ "loss": 1.0671,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.41,
1492
+ "grad_norm": 0.08720172196626663,
1493
+ "learning_rate": 1.3137745872169578e-05,
1494
+ "loss": 1.0127,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.41,
1499
+ "grad_norm": 0.08827454596757889,
1500
+ "learning_rate": 1.3078263812556377e-05,
1501
+ "loss": 1.0154,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.41,
1506
+ "grad_norm": 0.0914626345038414,
1507
+ "learning_rate": 1.3018661194749986e-05,
1508
+ "loss": 1.0201,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.42,
1513
+ "grad_norm": 0.08843535929918289,
1514
+ "learning_rate": 1.295894035304803e-05,
1515
+ "loss": 1.0516,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.42,
1520
+ "grad_norm": 0.08639541268348694,
1521
+ "learning_rate": 1.28991036263783e-05,
1522
+ "loss": 1.0165,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.42,
1527
+ "grad_norm": 0.07750130444765091,
1528
+ "learning_rate": 1.2839153358207142e-05,
1529
+ "loss": 1.0223,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.42,
1534
+ "grad_norm": 0.0824190005660057,
1535
+ "learning_rate": 1.2779091896447682e-05,
1536
+ "loss": 1.0337,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.42,
1541
+ "grad_norm": 0.08451572805643082,
1542
+ "learning_rate": 1.2718921593367874e-05,
1543
+ "loss": 1.0542,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.43,
1548
+ "grad_norm": 0.0857366994023323,
1549
+ "learning_rate": 1.2658644805498361e-05,
1550
+ "loss": 1.0759,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.43,
1555
+ "grad_norm": 0.07681415975093842,
1556
+ "learning_rate": 1.2598263893540207e-05,
1557
+ "loss": 1.0506,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.43,
1562
+ "grad_norm": 0.07856535911560059,
1563
+ "learning_rate": 1.2537781222272423e-05,
1564
+ "loss": 1.0974,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.43,
1569
+ "grad_norm": 0.08015410602092743,
1570
+ "learning_rate": 1.2477199160459345e-05,
1571
+ "loss": 1.0604,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.43,
1576
+ "grad_norm": 0.08314133435487747,
1577
+ "learning_rate": 1.2416520080757892e-05,
1578
+ "loss": 1.0889,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.43,
1583
+ "grad_norm": 0.08028203994035721,
1584
+ "learning_rate": 1.2355746359624621e-05,
1585
+ "loss": 1.0281,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.44,
1590
+ "grad_norm": 0.0775797963142395,
1591
+ "learning_rate": 1.2294880377222649e-05,
1592
+ "loss": 1.078,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.44,
1597
+ "grad_norm": 0.08315123617649078,
1598
+ "learning_rate": 1.2233924517328456e-05,
1599
+ "loss": 1.0356,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.44,
1604
+ "grad_norm": 0.0795183852314949,
1605
+ "learning_rate": 1.2172881167238515e-05,
1606
+ "loss": 1.0332,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.44,
1611
+ "grad_norm": 0.0779062882065773,
1612
+ "learning_rate": 1.2111752717675788e-05,
1613
+ "loss": 0.9954,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.44,
1618
+ "grad_norm": 0.07758854329586029,
1619
+ "learning_rate": 1.205054156269611e-05,
1620
+ "loss": 1.0242,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.45,
1625
+ "grad_norm": 0.07713694125413895,
1626
+ "learning_rate": 1.1989250099594412e-05,
1627
+ "loss": 1.0686,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.45,
1632
+ "grad_norm": 0.07772821933031082,
1633
+ "learning_rate": 1.192788072881085e-05,
1634
+ "loss": 1.0338,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.45,
1639
+ "grad_norm": 0.08006665855646133,
1640
+ "learning_rate": 1.1866435853836773e-05,
1641
+ "loss": 1.0946,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.45,
1646
+ "grad_norm": 0.0821637436747551,
1647
+ "learning_rate": 1.1804917881120608e-05,
1648
+ "loss": 1.0525,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.45,
1653
+ "grad_norm": 0.07892850786447525,
1654
+ "learning_rate": 1.1743329219973609e-05,
1655
+ "loss": 1.0127,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.46,
1660
+ "grad_norm": 0.07800798863172531,
1661
+ "learning_rate": 1.1681672282475495e-05,
1662
+ "loss": 1.0254,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.46,
1667
+ "grad_norm": 0.07875402271747589,
1668
+ "learning_rate": 1.161994948337998e-05,
1669
+ "loss": 1.0319,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.46,
1674
+ "grad_norm": 0.08178096264600754,
1675
+ "learning_rate": 1.1558163240020209e-05,
1676
+ "loss": 1.0541,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.46,
1681
+ "grad_norm": 0.08126726001501083,
1682
+ "learning_rate": 1.1496315972214076e-05,
1683
+ "loss": 1.0681,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.46,
1688
+ "grad_norm": 0.08104463666677475,
1689
+ "learning_rate": 1.1434410102169462e-05,
1690
+ "loss": 0.9767,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.47,
1695
+ "grad_norm": 0.0746295303106308,
1696
+ "learning_rate": 1.1372448054389364e-05,
1697
+ "loss": 1.0586,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.47,
1702
+ "grad_norm": 0.08171354979276657,
1703
+ "learning_rate": 1.1310432255576944e-05,
1704
+ "loss": 1.0655,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.47,
1709
+ "grad_norm": 0.08069796115159988,
1710
+ "learning_rate": 1.1248365134540489e-05,
1711
+ "loss": 1.079,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.47,
1716
+ "grad_norm": 0.07922904193401337,
1717
+ "learning_rate": 1.1186249122098282e-05,
1718
+ "loss": 1.0371,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.47,
1723
+ "grad_norm": 0.07877922058105469,
1724
+ "learning_rate": 1.1124086650983415e-05,
1725
+ "loss": 1.0236,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.48,
1730
+ "grad_norm": 0.07606945931911469,
1731
+ "learning_rate": 1.1061880155748497e-05,
1732
+ "loss": 1.0255,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.48,
1737
+ "grad_norm": 0.08225277811288834,
1738
+ "learning_rate": 1.0999632072670314e-05,
1739
+ "loss": 1.0571,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.48,
1744
+ "grad_norm": 0.07907744497060776,
1745
+ "learning_rate": 1.0937344839654416e-05,
1746
+ "loss": 1.0745,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.48,
1751
+ "grad_norm": 0.07885382324457169,
1752
+ "learning_rate": 1.087502089613963e-05,
1753
+ "loss": 0.9899,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.48,
1758
+ "grad_norm": 0.08236192911863327,
1759
+ "learning_rate": 1.0812662683002528e-05,
1760
+ "loss": 1.046,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.49,
1765
+ "grad_norm": 0.08153583109378815,
1766
+ "learning_rate": 1.075027264246183e-05,
1767
+ "loss": 1.0769,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 0.49,
1772
+ "grad_norm": 0.0847182348370552,
1773
+ "learning_rate": 1.068785321798276e-05,
1774
+ "loss": 1.0695,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 0.49,
1779
+ "grad_norm": 0.07414229959249496,
1780
+ "learning_rate": 1.062540685418133e-05,
1781
+ "loss": 1.0555,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 0.49,
1786
+ "grad_norm": 0.07932449132204056,
1787
+ "learning_rate": 1.0562935996728629e-05,
1788
+ "loss": 1.0644,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 0.49,
1793
+ "grad_norm": 0.08247576653957367,
1794
+ "learning_rate": 1.0500443092255017e-05,
1795
+ "loss": 1.064,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 0.5,
1800
+ "grad_norm": 0.07860003411769867,
1801
+ "learning_rate": 1.043793058825431e-05,
1802
+ "loss": 1.0579,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 0.5,
1807
+ "grad_norm": 0.08330255001783371,
1808
+ "learning_rate": 1.0375400932987932e-05,
1809
+ "loss": 1.0218,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 0.5,
1814
+ "grad_norm": 0.08150562644004822,
1815
+ "learning_rate": 1.0312856575389016e-05,
1816
+ "loss": 1.0379,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 0.5,
1821
+ "eval_loss": 1.0509783029556274,
1822
+ "eval_runtime": 708.357,
1823
+ "eval_samples_per_second": 7.163,
1824
+ "eval_steps_per_second": 1.791,
1825
+ "step": 256
1826
+ }
1827
+ ],
1828
+ "logging_steps": 1,
1829
+ "max_steps": 512,
1830
+ "num_input_tokens_seen": 0,
1831
+ "num_train_epochs": 1,
1832
+ "save_steps": 256,
1833
+ "total_flos": 2.262770368118784e+18,
1834
+ "train_batch_size": 4,
1835
+ "trial_name": null,
1836
+ "trial_params": null
1837
+ }
checkpoint-256/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2e26a4066417fbc5c36d2c392e7d37169c1c77e260f1ed05adfc5096066476
3
+ size 5307
checkpoint-512/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.10.0
checkpoint-512/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "gate_proj",
24
+ "up_proj",
25
+ "o_proj",
26
+ "down_proj",
27
+ "q_proj",
28
+ "k_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-512/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c42467656deea5a4fc8ce10508abf42c536682da3eb27700dcdeaf23e256a91
3
+ size 671149168
checkpoint-512/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b0b21cb329fba00c0a2b811725d48c9b98987c30b389df274aa65f013ccc8b
3
+ size 336725215
checkpoint-512/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5d963c89088d566bd70575763a6d789ba667d723b01cc2191344c887860fc4
3
+ size 14575
checkpoint-512/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1f30a437ece8ee1b13ca500f5edd582366cdd86fea137834b5226896e26b8c
3
+ size 627
checkpoint-512/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-512/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-512/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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ 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|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-512/trainer_state.json ADDED
@@ -0,0 +1,3645 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9983750406239844,
5
+ "eval_steps": 128,
6
+ "global_step": 512,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 0.5149741172790527,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 1.8709,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.0,
20
+ "eval_loss": 1.8383064270019531,
21
+ "eval_runtime": 707.8127,
22
+ "eval_samples_per_second": 7.169,
23
+ "eval_steps_per_second": 1.793,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0,
28
+ "grad_norm": 0.48140937089920044,
29
+ "learning_rate": 4.000000000000001e-06,
30
+ "loss": 1.7751,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01,
35
+ "grad_norm": 0.4886001944541931,
36
+ "learning_rate": 6e-06,
37
+ "loss": 1.795,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "grad_norm": 0.46349120140075684,
43
+ "learning_rate": 8.000000000000001e-06,
44
+ "loss": 1.7569,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "grad_norm": 0.5320057272911072,
50
+ "learning_rate": 1e-05,
51
+ "loss": 1.9278,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.01,
56
+ "grad_norm": 0.48083460330963135,
57
+ "learning_rate": 1.2e-05,
58
+ "loss": 1.778,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.01,
63
+ "grad_norm": 0.503804624080658,
64
+ "learning_rate": 1.4e-05,
65
+ "loss": 1.8358,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.02,
70
+ "grad_norm": 0.5177507400512695,
71
+ "learning_rate": 1.6000000000000003e-05,
72
+ "loss": 1.8655,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.02,
77
+ "grad_norm": 0.5006410479545593,
78
+ "learning_rate": 1.8e-05,
79
+ "loss": 1.8087,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.02,
84
+ "grad_norm": 0.500285804271698,
85
+ "learning_rate": 2e-05,
86
+ "loss": 1.8254,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.02,
91
+ "grad_norm": 0.4819566607475281,
92
+ "learning_rate": 1.9999804178263253e-05,
93
+ "loss": 1.7627,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.02,
98
+ "grad_norm": 0.4860954284667969,
99
+ "learning_rate": 1.999921672072223e-05,
100
+ "loss": 1.7034,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.03,
105
+ "grad_norm": 0.5111412405967712,
106
+ "learning_rate": 1.9998237650384324e-05,
107
+ "loss": 1.7203,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.03,
112
+ "grad_norm": 0.500988245010376,
113
+ "learning_rate": 1.9996867005594193e-05,
114
+ "loss": 1.6721,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.03,
119
+ "grad_norm": 0.4903103709220886,
120
+ "learning_rate": 1.999510484003224e-05,
121
+ "loss": 1.6167,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.03,
126
+ "grad_norm": 0.4756762683391571,
127
+ "learning_rate": 1.999295122271253e-05,
128
+ "loss": 1.57,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.03,
133
+ "grad_norm": 0.4689522385597229,
134
+ "learning_rate": 1.999040623798008e-05,
135
+ "loss": 1.5461,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.04,
140
+ "grad_norm": 0.5094612836837769,
141
+ "learning_rate": 1.9987469985507553e-05,
142
+ "loss": 1.5526,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.04,
147
+ "grad_norm": 0.49769631028175354,
148
+ "learning_rate": 1.9984142580291368e-05,
149
+ "loss": 1.5115,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.04,
154
+ "grad_norm": 0.46388670802116394,
155
+ "learning_rate": 1.9980424152647174e-05,
156
+ "loss": 1.467,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.04,
161
+ "grad_norm": 0.4357146918773651,
162
+ "learning_rate": 1.9976314848204762e-05,
163
+ "loss": 1.3887,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.04,
168
+ "grad_norm": 0.440377414226532,
169
+ "learning_rate": 1.997181482790236e-05,
170
+ "loss": 1.3845,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.04,
175
+ "grad_norm": 0.4116402566432953,
176
+ "learning_rate": 1.9966924267980326e-05,
177
+ "loss": 1.4091,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.05,
182
+ "grad_norm": 0.3181552588939667,
183
+ "learning_rate": 1.996164335997425e-05,
184
+ "loss": 1.3324,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.05,
189
+ "grad_norm": 0.2932267189025879,
190
+ "learning_rate": 1.995597231070744e-05,
191
+ "loss": 1.315,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.05,
196
+ "grad_norm": 0.328800231218338,
197
+ "learning_rate": 1.994991134228285e-05,
198
+ "loss": 1.3334,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.05,
203
+ "grad_norm": 0.32027724385261536,
204
+ "learning_rate": 1.9943460692074345e-05,
205
+ "loss": 1.3161,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.05,
210
+ "grad_norm": 0.3247709274291992,
211
+ "learning_rate": 1.993662061271743e-05,
212
+ "loss": 1.2601,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.06,
217
+ "grad_norm": 0.33424896001815796,
218
+ "learning_rate": 1.9929391372099352e-05,
219
+ "loss": 1.2807,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.06,
224
+ "grad_norm": 0.28847330808639526,
225
+ "learning_rate": 1.9921773253348604e-05,
226
+ "loss": 1.2427,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.06,
231
+ "grad_norm": 0.2601753771305084,
232
+ "learning_rate": 1.991376655482383e-05,
233
+ "loss": 1.2602,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.06,
238
+ "grad_norm": 0.25505828857421875,
239
+ "learning_rate": 1.9905371590102157e-05,
240
+ "loss": 1.2539,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.06,
245
+ "grad_norm": 0.25789541006088257,
246
+ "learning_rate": 1.989658868796689e-05,
247
+ "loss": 1.2796,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.07,
252
+ "grad_norm": 0.1963696926832199,
253
+ "learning_rate": 1.988741819239467e-05,
254
+ "loss": 1.2533,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.07,
259
+ "grad_norm": 0.1652669906616211,
260
+ "learning_rate": 1.9877860462541964e-05,
261
+ "loss": 1.27,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.07,
266
+ "grad_norm": 0.15272551774978638,
267
+ "learning_rate": 1.986791587273103e-05,
268
+ "loss": 1.2092,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.07,
273
+ "grad_norm": 0.14809414744377136,
274
+ "learning_rate": 1.985758481243523e-05,
275
+ "loss": 1.2028,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.07,
280
+ "grad_norm": 0.14091093838214874,
281
+ "learning_rate": 1.98468676862638e-05,
282
+ "loss": 1.1737,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.08,
287
+ "grad_norm": 0.13234961032867432,
288
+ "learning_rate": 1.9835764913945998e-05,
289
+ "loss": 1.2242,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.08,
294
+ "grad_norm": 0.12562313675880432,
295
+ "learning_rate": 1.982427693031465e-05,
296
+ "loss": 1.1846,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.08,
301
+ "grad_norm": 0.12460777163505554,
302
+ "learning_rate": 1.981240418528914e-05,
303
+ "loss": 1.1954,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.08,
308
+ "grad_norm": 0.1261477917432785,
309
+ "learning_rate": 1.9800147143857774e-05,
310
+ "loss": 1.1944,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.08,
315
+ "grad_norm": 0.12070100754499435,
316
+ "learning_rate": 1.9787506286059584e-05,
317
+ "loss": 1.1814,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.09,
322
+ "grad_norm": 0.1318473368883133,
323
+ "learning_rate": 1.9774482106965512e-05,
324
+ "loss": 1.2289,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.09,
329
+ "grad_norm": 0.11869361251592636,
330
+ "learning_rate": 1.9761075116659037e-05,
331
+ "loss": 1.1507,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.09,
336
+ "grad_norm": 0.11668427288532257,
337
+ "learning_rate": 1.974728584021618e-05,
338
+ "loss": 1.1693,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.09,
343
+ "grad_norm": 0.12271205335855484,
344
+ "learning_rate": 1.9733114817684957e-05,
345
+ "loss": 1.219,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.09,
350
+ "grad_norm": 0.12055838108062744,
351
+ "learning_rate": 1.9718562604064213e-05,
352
+ "loss": 1.2424,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.1,
357
+ "grad_norm": 0.1191168949007988,
358
+ "learning_rate": 1.97036297692819e-05,
359
+ "loss": 1.2206,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.1,
364
+ "grad_norm": 0.11361384391784668,
365
+ "learning_rate": 1.9688316898172744e-05,
366
+ "loss": 1.1927,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.1,
371
+ "grad_norm": 0.109556645154953,
372
+ "learning_rate": 1.967262459045535e-05,
373
+ "loss": 1.2013,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.1,
378
+ "grad_norm": 0.11278169602155685,
379
+ "learning_rate": 1.9656553460708707e-05,
380
+ "loss": 1.2379,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.1,
385
+ "grad_norm": 0.11011548340320587,
386
+ "learning_rate": 1.9640104138348124e-05,
387
+ "loss": 1.1808,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.11,
392
+ "grad_norm": 0.09818632155656815,
393
+ "learning_rate": 1.9623277267600574e-05,
394
+ "loss": 1.1731,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.11,
399
+ "grad_norm": 0.1045491099357605,
400
+ "learning_rate": 1.9606073507479466e-05,
401
+ "loss": 1.1729,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.11,
406
+ "grad_norm": 0.0985143780708313,
407
+ "learning_rate": 1.9588493531758843e-05,
408
+ "loss": 1.165,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.11,
413
+ "grad_norm": 0.09513280540704727,
414
+ "learning_rate": 1.9570538028946974e-05,
415
+ "loss": 1.1765,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.11,
420
+ "grad_norm": 0.09834066778421402,
421
+ "learning_rate": 1.9552207702259412e-05,
422
+ "loss": 1.1411,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.12,
427
+ "grad_norm": 0.09748240560293198,
428
+ "learning_rate": 1.9533503269591438e-05,
429
+ "loss": 1.1995,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.12,
434
+ "grad_norm": 0.09501401335000992,
435
+ "learning_rate": 1.9514425463489946e-05,
436
+ "loss": 1.1414,
437
+ "step": 60
438
+ },
439
+ {
440
+ "epoch": 0.12,
441
+ "grad_norm": 0.09078366309404373,
442
+ "learning_rate": 1.9494975031124768e-05,
443
+ "loss": 1.1132,
444
+ "step": 61
445
+ },
446
+ {
447
+ "epoch": 0.12,
448
+ "grad_norm": 0.09064218401908875,
449
+ "learning_rate": 1.947515273425939e-05,
450
+ "loss": 1.1498,
451
+ "step": 62
452
+ },
453
+ {
454
+ "epoch": 0.12,
455
+ "grad_norm": 0.09029112011194229,
456
+ "learning_rate": 1.945495934922113e-05,
457
+ "loss": 1.158,
458
+ "step": 63
459
+ },
460
+ {
461
+ "epoch": 0.12,
462
+ "grad_norm": 0.09335145354270935,
463
+ "learning_rate": 1.9434395666870735e-05,
464
+ "loss": 1.181,
465
+ "step": 64
466
+ },
467
+ {
468
+ "epoch": 0.13,
469
+ "grad_norm": 0.08959628641605377,
470
+ "learning_rate": 1.9413462492571403e-05,
471
+ "loss": 1.1353,
472
+ "step": 65
473
+ },
474
+ {
475
+ "epoch": 0.13,
476
+ "grad_norm": 0.09235028922557831,
477
+ "learning_rate": 1.9392160646157242e-05,
478
+ "loss": 1.1566,
479
+ "step": 66
480
+ },
481
+ {
482
+ "epoch": 0.13,
483
+ "grad_norm": 0.08852320164442062,
484
+ "learning_rate": 1.937049096190117e-05,
485
+ "loss": 1.1015,
486
+ "step": 67
487
+ },
488
+ {
489
+ "epoch": 0.13,
490
+ "grad_norm": 0.09060905128717422,
491
+ "learning_rate": 1.934845428848222e-05,
492
+ "loss": 1.1312,
493
+ "step": 68
494
+ },
495
+ {
496
+ "epoch": 0.13,
497
+ "grad_norm": 0.09065355360507965,
498
+ "learning_rate": 1.9326051488952334e-05,
499
+ "loss": 1.1456,
500
+ "step": 69
501
+ },
502
+ {
503
+ "epoch": 0.14,
504
+ "grad_norm": 0.09140690416097641,
505
+ "learning_rate": 1.9303283440702524e-05,
506
+ "loss": 1.1661,
507
+ "step": 70
508
+ },
509
+ {
510
+ "epoch": 0.14,
511
+ "grad_norm": 0.08641023188829422,
512
+ "learning_rate": 1.9280151035428544e-05,
513
+ "loss": 1.1153,
514
+ "step": 71
515
+ },
516
+ {
517
+ "epoch": 0.14,
518
+ "grad_norm": 0.08729224652051926,
519
+ "learning_rate": 1.9256655179095954e-05,
520
+ "loss": 1.1956,
521
+ "step": 72
522
+ },
523
+ {
524
+ "epoch": 0.14,
525
+ "grad_norm": 0.08514908701181412,
526
+ "learning_rate": 1.9232796791904627e-05,
527
+ "loss": 1.0969,
528
+ "step": 73
529
+ },
530
+ {
531
+ "epoch": 0.14,
532
+ "grad_norm": 0.08789129555225372,
533
+ "learning_rate": 1.9208576808252725e-05,
534
+ "loss": 1.1669,
535
+ "step": 74
536
+ },
537
+ {
538
+ "epoch": 0.15,
539
+ "grad_norm": 0.0829731896519661,
540
+ "learning_rate": 1.918399617670011e-05,
541
+ "loss": 1.101,
542
+ "step": 75
543
+ },
544
+ {
545
+ "epoch": 0.15,
546
+ "grad_norm": 0.08415351063013077,
547
+ "learning_rate": 1.9159055859931163e-05,
548
+ "loss": 1.122,
549
+ "step": 76
550
+ },
551
+ {
552
+ "epoch": 0.15,
553
+ "grad_norm": 0.07933653146028519,
554
+ "learning_rate": 1.9133756834717118e-05,
555
+ "loss": 1.1175,
556
+ "step": 77
557
+ },
558
+ {
559
+ "epoch": 0.15,
560
+ "grad_norm": 0.0849999189376831,
561
+ "learning_rate": 1.9108100091877787e-05,
562
+ "loss": 1.1577,
563
+ "step": 78
564
+ },
565
+ {
566
+ "epoch": 0.15,
567
+ "grad_norm": 0.0835108831524849,
568
+ "learning_rate": 1.9082086636242757e-05,
569
+ "loss": 1.1253,
570
+ "step": 79
571
+ },
572
+ {
573
+ "epoch": 0.16,
574
+ "grad_norm": 0.07834841310977936,
575
+ "learning_rate": 1.905571748661204e-05,
576
+ "loss": 1.0963,
577
+ "step": 80
578
+ },
579
+ {
580
+ "epoch": 0.16,
581
+ "grad_norm": 0.07953493297100067,
582
+ "learning_rate": 1.902899367571617e-05,
583
+ "loss": 1.1102,
584
+ "step": 81
585
+ },
586
+ {
587
+ "epoch": 0.16,
588
+ "grad_norm": 0.07989759743213654,
589
+ "learning_rate": 1.9001916250175764e-05,
590
+ "loss": 1.1576,
591
+ "step": 82
592
+ },
593
+ {
594
+ "epoch": 0.16,
595
+ "grad_norm": 0.07849448174238205,
596
+ "learning_rate": 1.8974486270460518e-05,
597
+ "loss": 1.0963,
598
+ "step": 83
599
+ },
600
+ {
601
+ "epoch": 0.16,
602
+ "grad_norm": 0.07805287837982178,
603
+ "learning_rate": 1.894670481084769e-05,
604
+ "loss": 1.1364,
605
+ "step": 84
606
+ },
607
+ {
608
+ "epoch": 0.17,
609
+ "grad_norm": 0.07698098570108414,
610
+ "learning_rate": 1.8918572959380005e-05,
611
+ "loss": 1.1407,
612
+ "step": 85
613
+ },
614
+ {
615
+ "epoch": 0.17,
616
+ "grad_norm": 0.0766262486577034,
617
+ "learning_rate": 1.8890091817823073e-05,
618
+ "loss": 1.1225,
619
+ "step": 86
620
+ },
621
+ {
622
+ "epoch": 0.17,
623
+ "grad_norm": 0.0798678770661354,
624
+ "learning_rate": 1.8861262501622213e-05,
625
+ "loss": 1.137,
626
+ "step": 87
627
+ },
628
+ {
629
+ "epoch": 0.17,
630
+ "grad_norm": 0.07717825472354889,
631
+ "learning_rate": 1.8832086139858777e-05,
632
+ "loss": 1.1311,
633
+ "step": 88
634
+ },
635
+ {
636
+ "epoch": 0.17,
637
+ "grad_norm": 0.07542562484741211,
638
+ "learning_rate": 1.880256387520593e-05,
639
+ "loss": 1.1066,
640
+ "step": 89
641
+ },
642
+ {
643
+ "epoch": 0.18,
644
+ "grad_norm": 0.07316063344478607,
645
+ "learning_rate": 1.8772696863883905e-05,
646
+ "loss": 1.0976,
647
+ "step": 90
648
+ },
649
+ {
650
+ "epoch": 0.18,
651
+ "grad_norm": 0.0738874301314354,
652
+ "learning_rate": 1.8742486275614706e-05,
653
+ "loss": 1.0901,
654
+ "step": 91
655
+ },
656
+ {
657
+ "epoch": 0.18,
658
+ "grad_norm": 0.07698226720094681,
659
+ "learning_rate": 1.8711933293576303e-05,
660
+ "loss": 1.1224,
661
+ "step": 92
662
+ },
663
+ {
664
+ "epoch": 0.18,
665
+ "grad_norm": 0.07452582567930222,
666
+ "learning_rate": 1.8681039114356298e-05,
667
+ "loss": 1.1399,
668
+ "step": 93
669
+ },
670
+ {
671
+ "epoch": 0.18,
672
+ "grad_norm": 0.07452700287103653,
673
+ "learning_rate": 1.8649804947905057e-05,
674
+ "loss": 1.1639,
675
+ "step": 94
676
+ },
677
+ {
678
+ "epoch": 0.19,
679
+ "grad_norm": 0.07358838617801666,
680
+ "learning_rate": 1.861823201748833e-05,
681
+ "loss": 1.1139,
682
+ "step": 95
683
+ },
684
+ {
685
+ "epoch": 0.19,
686
+ "grad_norm": 0.07469804584980011,
687
+ "learning_rate": 1.8586321559639316e-05,
688
+ "loss": 1.1103,
689
+ "step": 96
690
+ },
691
+ {
692
+ "epoch": 0.19,
693
+ "grad_norm": 0.07484911382198334,
694
+ "learning_rate": 1.8554074824110285e-05,
695
+ "loss": 1.1231,
696
+ "step": 97
697
+ },
698
+ {
699
+ "epoch": 0.19,
700
+ "grad_norm": 0.07320189476013184,
701
+ "learning_rate": 1.8521493073823583e-05,
702
+ "loss": 1.1405,
703
+ "step": 98
704
+ },
705
+ {
706
+ "epoch": 0.19,
707
+ "grad_norm": 0.07219311594963074,
708
+ "learning_rate": 1.8488577584822197e-05,
709
+ "loss": 1.1084,
710
+ "step": 99
711
+ },
712
+ {
713
+ "epoch": 0.19,
714
+ "grad_norm": 0.07267658412456512,
715
+ "learning_rate": 1.8455329646219767e-05,
716
+ "loss": 1.109,
717
+ "step": 100
718
+ },
719
+ {
720
+ "epoch": 0.2,
721
+ "grad_norm": 0.07124843448400497,
722
+ "learning_rate": 1.8421750560150112e-05,
723
+ "loss": 1.0997,
724
+ "step": 101
725
+ },
726
+ {
727
+ "epoch": 0.2,
728
+ "grad_norm": 0.06921572983264923,
729
+ "learning_rate": 1.8387841641716226e-05,
730
+ "loss": 1.1095,
731
+ "step": 102
732
+ },
733
+ {
734
+ "epoch": 0.2,
735
+ "grad_norm": 0.07149618864059448,
736
+ "learning_rate": 1.835360421893876e-05,
737
+ "loss": 1.1078,
738
+ "step": 103
739
+ },
740
+ {
741
+ "epoch": 0.2,
742
+ "grad_norm": 0.07851895689964294,
743
+ "learning_rate": 1.8319039632704042e-05,
744
+ "loss": 1.1195,
745
+ "step": 104
746
+ },
747
+ {
748
+ "epoch": 0.2,
749
+ "grad_norm": 0.07615454494953156,
750
+ "learning_rate": 1.8284149236711527e-05,
751
+ "loss": 1.0754,
752
+ "step": 105
753
+ },
754
+ {
755
+ "epoch": 0.21,
756
+ "grad_norm": 0.07054944336414337,
757
+ "learning_rate": 1.8248934397420802e-05,
758
+ "loss": 1.0943,
759
+ "step": 106
760
+ },
761
+ {
762
+ "epoch": 0.21,
763
+ "grad_norm": 0.07253159582614899,
764
+ "learning_rate": 1.821339649399807e-05,
765
+ "loss": 1.1263,
766
+ "step": 107
767
+ },
768
+ {
769
+ "epoch": 0.21,
770
+ "grad_norm": 0.0729857012629509,
771
+ "learning_rate": 1.817753691826212e-05,
772
+ "loss": 1.0977,
773
+ "step": 108
774
+ },
775
+ {
776
+ "epoch": 0.21,
777
+ "grad_norm": 0.07234011590480804,
778
+ "learning_rate": 1.8141357074629838e-05,
779
+ "loss": 1.1334,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 0.21,
784
+ "grad_norm": 0.07030120491981506,
785
+ "learning_rate": 1.8104858380061178e-05,
786
+ "loss": 1.0767,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 0.22,
791
+ "grad_norm": 0.07036615908145905,
792
+ "learning_rate": 1.80680422640037e-05,
793
+ "loss": 1.0796,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 0.22,
798
+ "grad_norm": 0.0742933601140976,
799
+ "learning_rate": 1.8030910168336558e-05,
800
+ "loss": 1.0671,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 0.22,
805
+ "grad_norm": 0.07065165787935257,
806
+ "learning_rate": 1.7993463547314044e-05,
807
+ "loss": 1.1594,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 0.22,
812
+ "grad_norm": 0.07182008028030396,
813
+ "learning_rate": 1.7955703867508634e-05,
814
+ "loss": 1.0936,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 0.22,
819
+ "grad_norm": 0.06882106512784958,
820
+ "learning_rate": 1.791763260775354e-05,
821
+ "loss": 1.1017,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 0.23,
826
+ "grad_norm": 0.07001936435699463,
827
+ "learning_rate": 1.7879251259084803e-05,
828
+ "loss": 1.1267,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 0.23,
833
+ "grad_norm": 0.06916490197181702,
834
+ "learning_rate": 1.78405613246829e-05,
835
+ "loss": 1.0787,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 0.23,
840
+ "grad_norm": 0.07149837166070938,
841
+ "learning_rate": 1.7801564319813854e-05,
842
+ "loss": 1.1302,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 0.23,
847
+ "grad_norm": 0.06783504039049149,
848
+ "learning_rate": 1.776226177176991e-05,
849
+ "loss": 1.1159,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 0.23,
854
+ "grad_norm": 0.07285293936729431,
855
+ "learning_rate": 1.7722655219809718e-05,
856
+ "loss": 1.0758,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 0.24,
861
+ "grad_norm": 0.07273004204034805,
862
+ "learning_rate": 1.768274621509803e-05,
863
+ "loss": 1.1019,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 0.24,
868
+ "grad_norm": 0.07392899692058563,
869
+ "learning_rate": 1.7642536320644964e-05,
870
+ "loss": 1.1111,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 0.24,
875
+ "grad_norm": 0.0693732351064682,
876
+ "learning_rate": 1.7602027111244807e-05,
877
+ "loss": 1.1109,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 0.24,
882
+ "grad_norm": 0.0721542090177536,
883
+ "learning_rate": 1.7561220173414297e-05,
884
+ "loss": 1.1246,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 0.24,
889
+ "grad_norm": 0.07002190500497818,
890
+ "learning_rate": 1.7520117105330524e-05,
891
+ "loss": 1.073,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 0.25,
896
+ "grad_norm": 0.0697953850030899,
897
+ "learning_rate": 1.7478719516768324e-05,
898
+ "loss": 1.0913,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 0.25,
903
+ "grad_norm": 0.07040461152791977,
904
+ "learning_rate": 1.7437029029037233e-05,
905
+ "loss": 1.1445,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 0.25,
910
+ "grad_norm": 0.07231634110212326,
911
+ "learning_rate": 1.7395047274917994e-05,
912
+ "loss": 1.1106,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 0.25,
917
+ "eval_loss": 1.0988876819610596,
918
+ "eval_runtime": 708.4228,
919
+ "eval_samples_per_second": 7.162,
920
+ "eval_steps_per_second": 1.791,
921
+ "step": 128
922
+ },
923
+ {
924
+ "epoch": 0.25,
925
+ "grad_norm": 0.0713375061750412,
926
+ "learning_rate": 1.7352775898598615e-05,
927
+ "loss": 1.0982,
928
+ "step": 129
929
+ },
930
+ {
931
+ "epoch": 0.25,
932
+ "grad_norm": 0.06747942417860031,
933
+ "learning_rate": 1.731021655560995e-05,
934
+ "loss": 1.1017,
935
+ "step": 130
936
+ },
937
+ {
938
+ "epoch": 0.26,
939
+ "grad_norm": 0.071540467441082,
940
+ "learning_rate": 1.72673709127609e-05,
941
+ "loss": 1.0859,
942
+ "step": 131
943
+ },
944
+ {
945
+ "epoch": 0.26,
946
+ "grad_norm": 0.06861750036478043,
947
+ "learning_rate": 1.7224240648073097e-05,
948
+ "loss": 1.0728,
949
+ "step": 132
950
+ },
951
+ {
952
+ "epoch": 0.26,
953
+ "grad_norm": 0.06919445842504501,
954
+ "learning_rate": 1.718082745071521e-05,
955
+ "loss": 1.1218,
956
+ "step": 133
957
+ },
958
+ {
959
+ "epoch": 0.26,
960
+ "grad_norm": 0.07422851771116257,
961
+ "learning_rate": 1.7137133020936783e-05,
962
+ "loss": 1.0881,
963
+ "step": 134
964
+ },
965
+ {
966
+ "epoch": 0.26,
967
+ "grad_norm": 0.07452652603387833,
968
+ "learning_rate": 1.7093159070001637e-05,
969
+ "loss": 1.1073,
970
+ "step": 135
971
+ },
972
+ {
973
+ "epoch": 0.27,
974
+ "grad_norm": 0.07337850332260132,
975
+ "learning_rate": 1.7048907320120867e-05,
976
+ "loss": 1.1065,
977
+ "step": 136
978
+ },
979
+ {
980
+ "epoch": 0.27,
981
+ "grad_norm": 0.07020066678524017,
982
+ "learning_rate": 1.700437950438537e-05,
983
+ "loss": 1.0742,
984
+ "step": 137
985
+ },
986
+ {
987
+ "epoch": 0.27,
988
+ "grad_norm": 0.07053718715906143,
989
+ "learning_rate": 1.695957736669799e-05,
990
+ "loss": 1.0627,
991
+ "step": 138
992
+ },
993
+ {
994
+ "epoch": 0.27,
995
+ "grad_norm": 0.07288292795419693,
996
+ "learning_rate": 1.6914502661705216e-05,
997
+ "loss": 1.0842,
998
+ "step": 139
999
+ },
1000
+ {
1001
+ "epoch": 0.27,
1002
+ "grad_norm": 0.07197044044733047,
1003
+ "learning_rate": 1.6869157154728437e-05,
1004
+ "loss": 1.065,
1005
+ "step": 140
1006
+ },
1007
+ {
1008
+ "epoch": 0.27,
1009
+ "grad_norm": 0.07109569013118744,
1010
+ "learning_rate": 1.6823542621694852e-05,
1011
+ "loss": 1.0996,
1012
+ "step": 141
1013
+ },
1014
+ {
1015
+ "epoch": 0.28,
1016
+ "grad_norm": 0.07084467262029648,
1017
+ "learning_rate": 1.677766084906787e-05,
1018
+ "loss": 1.0862,
1019
+ "step": 142
1020
+ },
1021
+ {
1022
+ "epoch": 0.28,
1023
+ "grad_norm": 0.07195379585027695,
1024
+ "learning_rate": 1.6731513633777173e-05,
1025
+ "loss": 1.1184,
1026
+ "step": 143
1027
+ },
1028
+ {
1029
+ "epoch": 0.28,
1030
+ "grad_norm": 0.07326792180538177,
1031
+ "learning_rate": 1.668510278314833e-05,
1032
+ "loss": 1.0867,
1033
+ "step": 144
1034
+ },
1035
+ {
1036
+ "epoch": 0.28,
1037
+ "grad_norm": 0.07582233846187592,
1038
+ "learning_rate": 1.6638430114832015e-05,
1039
+ "loss": 1.0721,
1040
+ "step": 145
1041
+ },
1042
+ {
1043
+ "epoch": 0.28,
1044
+ "grad_norm": 0.07204006612300873,
1045
+ "learning_rate": 1.6591497456732827e-05,
1046
+ "loss": 1.0565,
1047
+ "step": 146
1048
+ },
1049
+ {
1050
+ "epoch": 0.29,
1051
+ "grad_norm": 0.07225130498409271,
1052
+ "learning_rate": 1.6544306646937683e-05,
1053
+ "loss": 1.1036,
1054
+ "step": 147
1055
+ },
1056
+ {
1057
+ "epoch": 0.29,
1058
+ "grad_norm": 0.07662148773670197,
1059
+ "learning_rate": 1.649685953364385e-05,
1060
+ "loss": 1.0289,
1061
+ "step": 148
1062
+ },
1063
+ {
1064
+ "epoch": 0.29,
1065
+ "grad_norm": 0.07611638307571411,
1066
+ "learning_rate": 1.644915797508656e-05,
1067
+ "loss": 1.1068,
1068
+ "step": 149
1069
+ },
1070
+ {
1071
+ "epoch": 0.29,
1072
+ "grad_norm": 0.07609565556049347,
1073
+ "learning_rate": 1.6401203839466212e-05,
1074
+ "loss": 1.0816,
1075
+ "step": 150
1076
+ },
1077
+ {
1078
+ "epoch": 0.29,
1079
+ "grad_norm": 0.0737641304731369,
1080
+ "learning_rate": 1.6352999004875242e-05,
1081
+ "loss": 1.1016,
1082
+ "step": 151
1083
+ },
1084
+ {
1085
+ "epoch": 0.3,
1086
+ "grad_norm": 0.07359515875577927,
1087
+ "learning_rate": 1.630454535922452e-05,
1088
+ "loss": 1.0787,
1089
+ "step": 152
1090
+ },
1091
+ {
1092
+ "epoch": 0.3,
1093
+ "grad_norm": 0.07506351917982101,
1094
+ "learning_rate": 1.6255844800169472e-05,
1095
+ "loss": 1.0789,
1096
+ "step": 153
1097
+ },
1098
+ {
1099
+ "epoch": 0.3,
1100
+ "grad_norm": 0.07777760922908783,
1101
+ "learning_rate": 1.62068992350357e-05,
1102
+ "loss": 1.096,
1103
+ "step": 154
1104
+ },
1105
+ {
1106
+ "epoch": 0.3,
1107
+ "grad_norm": 0.07574637979269028,
1108
+ "learning_rate": 1.6157710580744322e-05,
1109
+ "loss": 1.1007,
1110
+ "step": 155
1111
+ },
1112
+ {
1113
+ "epoch": 0.3,
1114
+ "grad_norm": 0.07857154309749603,
1115
+ "learning_rate": 1.610828076373687e-05,
1116
+ "loss": 1.0735,
1117
+ "step": 156
1118
+ },
1119
+ {
1120
+ "epoch": 0.31,
1121
+ "grad_norm": 0.07402702420949936,
1122
+ "learning_rate": 1.605861171989988e-05,
1123
+ "loss": 1.1003,
1124
+ "step": 157
1125
+ },
1126
+ {
1127
+ "epoch": 0.31,
1128
+ "grad_norm": 0.07439373433589935,
1129
+ "learning_rate": 1.6008705394489032e-05,
1130
+ "loss": 1.0662,
1131
+ "step": 158
1132
+ },
1133
+ {
1134
+ "epoch": 0.31,
1135
+ "grad_norm": 0.07392847537994385,
1136
+ "learning_rate": 1.5958563742052987e-05,
1137
+ "loss": 1.0487,
1138
+ "step": 159
1139
+ },
1140
+ {
1141
+ "epoch": 0.31,
1142
+ "grad_norm": 0.07773245126008987,
1143
+ "learning_rate": 1.5908188726356843e-05,
1144
+ "loss": 1.1107,
1145
+ "step": 160
1146
+ },
1147
+ {
1148
+ "epoch": 0.31,
1149
+ "grad_norm": 0.07752656936645508,
1150
+ "learning_rate": 1.5857582320305207e-05,
1151
+ "loss": 1.0426,
1152
+ "step": 161
1153
+ },
1154
+ {
1155
+ "epoch": 0.32,
1156
+ "grad_norm": 0.07541097700595856,
1157
+ "learning_rate": 1.5806746505864947e-05,
1158
+ "loss": 1.081,
1159
+ "step": 162
1160
+ },
1161
+ {
1162
+ "epoch": 0.32,
1163
+ "grad_norm": 0.07938623428344727,
1164
+ "learning_rate": 1.5755683273987554e-05,
1165
+ "loss": 1.0969,
1166
+ "step": 163
1167
+ },
1168
+ {
1169
+ "epoch": 0.32,
1170
+ "grad_norm": 0.07379717379808426,
1171
+ "learning_rate": 1.5704394624531184e-05,
1172
+ "loss": 1.0763,
1173
+ "step": 164
1174
+ },
1175
+ {
1176
+ "epoch": 0.32,
1177
+ "grad_norm": 0.07850446552038193,
1178
+ "learning_rate": 1.5652882566182316e-05,
1179
+ "loss": 1.1029,
1180
+ "step": 165
1181
+ },
1182
+ {
1183
+ "epoch": 0.32,
1184
+ "grad_norm": 0.07627106457948685,
1185
+ "learning_rate": 1.5601149116377095e-05,
1186
+ "loss": 1.0611,
1187
+ "step": 166
1188
+ },
1189
+ {
1190
+ "epoch": 0.33,
1191
+ "grad_norm": 0.07577154785394669,
1192
+ "learning_rate": 1.554919630122232e-05,
1193
+ "loss": 1.0973,
1194
+ "step": 167
1195
+ },
1196
+ {
1197
+ "epoch": 0.33,
1198
+ "grad_norm": 0.07844171673059464,
1199
+ "learning_rate": 1.5497026155416087e-05,
1200
+ "loss": 1.1006,
1201
+ "step": 168
1202
+ },
1203
+ {
1204
+ "epoch": 0.33,
1205
+ "grad_norm": 0.08061926811933517,
1206
+ "learning_rate": 1.5444640722168114e-05,
1207
+ "loss": 1.0879,
1208
+ "step": 169
1209
+ },
1210
+ {
1211
+ "epoch": 0.33,
1212
+ "grad_norm": 0.07918211817741394,
1213
+ "learning_rate": 1.53920420531197e-05,
1214
+ "loss": 1.0602,
1215
+ "step": 170
1216
+ },
1217
+ {
1218
+ "epoch": 0.33,
1219
+ "grad_norm": 0.08213488012552261,
1220
+ "learning_rate": 1.5339232208263394e-05,
1221
+ "loss": 1.0798,
1222
+ "step": 171
1223
+ },
1224
+ {
1225
+ "epoch": 0.34,
1226
+ "grad_norm": 0.07898285239934921,
1227
+ "learning_rate": 1.5286213255862295e-05,
1228
+ "loss": 1.0969,
1229
+ "step": 172
1230
+ },
1231
+ {
1232
+ "epoch": 0.34,
1233
+ "grad_norm": 0.08233582973480225,
1234
+ "learning_rate": 1.5232987272369076e-05,
1235
+ "loss": 1.0699,
1236
+ "step": 173
1237
+ },
1238
+ {
1239
+ "epoch": 0.34,
1240
+ "grad_norm": 0.08074311912059784,
1241
+ "learning_rate": 1.5179556342344643e-05,
1242
+ "loss": 1.0851,
1243
+ "step": 174
1244
+ },
1245
+ {
1246
+ "epoch": 0.34,
1247
+ "grad_norm": 0.08196305483579636,
1248
+ "learning_rate": 1.51259225583765e-05,
1249
+ "loss": 1.076,
1250
+ "step": 175
1251
+ },
1252
+ {
1253
+ "epoch": 0.34,
1254
+ "grad_norm": 0.08637065440416336,
1255
+ "learning_rate": 1.5072088020996791e-05,
1256
+ "loss": 1.0989,
1257
+ "step": 176
1258
+ },
1259
+ {
1260
+ "epoch": 0.35,
1261
+ "grad_norm": 0.08313170820474625,
1262
+ "learning_rate": 1.5018054838600033e-05,
1263
+ "loss": 1.09,
1264
+ "step": 177
1265
+ },
1266
+ {
1267
+ "epoch": 0.35,
1268
+ "grad_norm": 0.08245568722486496,
1269
+ "learning_rate": 1.496382512736056e-05,
1270
+ "loss": 1.0572,
1271
+ "step": 178
1272
+ },
1273
+ {
1274
+ "epoch": 0.35,
1275
+ "grad_norm": 0.08442118763923645,
1276
+ "learning_rate": 1.490940101114961e-05,
1277
+ "loss": 1.0669,
1278
+ "step": 179
1279
+ },
1280
+ {
1281
+ "epoch": 0.35,
1282
+ "grad_norm": 0.08224523812532425,
1283
+ "learning_rate": 1.4854784621452176e-05,
1284
+ "loss": 1.0842,
1285
+ "step": 180
1286
+ },
1287
+ {
1288
+ "epoch": 0.35,
1289
+ "grad_norm": 0.08642537891864777,
1290
+ "learning_rate": 1.479997809728352e-05,
1291
+ "loss": 1.123,
1292
+ "step": 181
1293
+ },
1294
+ {
1295
+ "epoch": 0.35,
1296
+ "grad_norm": 0.08723440766334534,
1297
+ "learning_rate": 1.4744983585105388e-05,
1298
+ "loss": 1.0649,
1299
+ "step": 182
1300
+ },
1301
+ {
1302
+ "epoch": 0.36,
1303
+ "grad_norm": 0.08666212856769562,
1304
+ "learning_rate": 1.4689803238741955e-05,
1305
+ "loss": 1.0938,
1306
+ "step": 183
1307
+ },
1308
+ {
1309
+ "epoch": 0.36,
1310
+ "grad_norm": 0.09213647246360779,
1311
+ "learning_rate": 1.463443921929548e-05,
1312
+ "loss": 1.0903,
1313
+ "step": 184
1314
+ },
1315
+ {
1316
+ "epoch": 0.36,
1317
+ "grad_norm": 0.08998877555131912,
1318
+ "learning_rate": 1.4578893695061644e-05,
1319
+ "loss": 1.0778,
1320
+ "step": 185
1321
+ },
1322
+ {
1323
+ "epoch": 0.36,
1324
+ "grad_norm": 0.09158129245042801,
1325
+ "learning_rate": 1.4523168841444657e-05,
1326
+ "loss": 1.0932,
1327
+ "step": 186
1328
+ },
1329
+ {
1330
+ "epoch": 0.36,
1331
+ "grad_norm": 0.09460633993148804,
1332
+ "learning_rate": 1.4467266840872041e-05,
1333
+ "loss": 1.0691,
1334
+ "step": 187
1335
+ },
1336
+ {
1337
+ "epoch": 0.37,
1338
+ "grad_norm": 0.09502755105495453,
1339
+ "learning_rate": 1.441118988270916e-05,
1340
+ "loss": 1.0684,
1341
+ "step": 188
1342
+ },
1343
+ {
1344
+ "epoch": 0.37,
1345
+ "grad_norm": 0.09307122975587845,
1346
+ "learning_rate": 1.4354940163173486e-05,
1347
+ "loss": 1.0776,
1348
+ "step": 189
1349
+ },
1350
+ {
1351
+ "epoch": 0.37,
1352
+ "grad_norm": 0.09580650180578232,
1353
+ "learning_rate": 1.4298519885248574e-05,
1354
+ "loss": 1.0882,
1355
+ "step": 190
1356
+ },
1357
+ {
1358
+ "epoch": 0.37,
1359
+ "grad_norm": 0.09251459687948227,
1360
+ "learning_rate": 1.4241931258597781e-05,
1361
+ "loss": 1.077,
1362
+ "step": 191
1363
+ },
1364
+ {
1365
+ "epoch": 0.37,
1366
+ "grad_norm": 0.09432998299598694,
1367
+ "learning_rate": 1.4185176499477742e-05,
1368
+ "loss": 1.0012,
1369
+ "step": 192
1370
+ },
1371
+ {
1372
+ "epoch": 0.38,
1373
+ "grad_norm": 0.09586652368307114,
1374
+ "learning_rate": 1.4128257830651554e-05,
1375
+ "loss": 1.0334,
1376
+ "step": 193
1377
+ },
1378
+ {
1379
+ "epoch": 0.38,
1380
+ "grad_norm": 0.09538242220878601,
1381
+ "learning_rate": 1.407117748130174e-05,
1382
+ "loss": 1.0731,
1383
+ "step": 194
1384
+ },
1385
+ {
1386
+ "epoch": 0.38,
1387
+ "grad_norm": 0.09691152721643448,
1388
+ "learning_rate": 1.401393768694292e-05,
1389
+ "loss": 1.0412,
1390
+ "step": 195
1391
+ },
1392
+ {
1393
+ "epoch": 0.38,
1394
+ "grad_norm": 0.09779084473848343,
1395
+ "learning_rate": 1.3956540689334286e-05,
1396
+ "loss": 1.0602,
1397
+ "step": 196
1398
+ },
1399
+ {
1400
+ "epoch": 0.38,
1401
+ "grad_norm": 0.0998532623052597,
1402
+ "learning_rate": 1.3898988736391792e-05,
1403
+ "loss": 1.0261,
1404
+ "step": 197
1405
+ },
1406
+ {
1407
+ "epoch": 0.39,
1408
+ "grad_norm": 0.10739872604608536,
1409
+ "learning_rate": 1.384128408210011e-05,
1410
+ "loss": 1.0502,
1411
+ "step": 198
1412
+ },
1413
+ {
1414
+ "epoch": 0.39,
1415
+ "grad_norm": 0.11806387454271317,
1416
+ "learning_rate": 1.3783428986424366e-05,
1417
+ "loss": 1.1188,
1418
+ "step": 199
1419
+ },
1420
+ {
1421
+ "epoch": 0.39,
1422
+ "grad_norm": 0.10208501666784286,
1423
+ "learning_rate": 1.3725425715221625e-05,
1424
+ "loss": 1.0465,
1425
+ "step": 200
1426
+ },
1427
+ {
1428
+ "epoch": 0.39,
1429
+ "grad_norm": 0.1044783741235733,
1430
+ "learning_rate": 1.3667276540152143e-05,
1431
+ "loss": 1.0561,
1432
+ "step": 201
1433
+ },
1434
+ {
1435
+ "epoch": 0.39,
1436
+ "grad_norm": 0.1070132926106453,
1437
+ "learning_rate": 1.3608983738590414e-05,
1438
+ "loss": 1.0429,
1439
+ "step": 202
1440
+ },
1441
+ {
1442
+ "epoch": 0.4,
1443
+ "grad_norm": 0.11181865632534027,
1444
+ "learning_rate": 1.3550549593535965e-05,
1445
+ "loss": 1.0564,
1446
+ "step": 203
1447
+ },
1448
+ {
1449
+ "epoch": 0.4,
1450
+ "grad_norm": 0.11098324507474899,
1451
+ "learning_rate": 1.3491976393523952e-05,
1452
+ "loss": 1.0632,
1453
+ "step": 204
1454
+ },
1455
+ {
1456
+ "epoch": 0.4,
1457
+ "grad_norm": 0.10281454026699066,
1458
+ "learning_rate": 1.343326643253552e-05,
1459
+ "loss": 1.0637,
1460
+ "step": 205
1461
+ },
1462
+ {
1463
+ "epoch": 0.4,
1464
+ "grad_norm": 0.10408665239810944,
1465
+ "learning_rate": 1.3374422009907984e-05,
1466
+ "loss": 1.0701,
1467
+ "step": 206
1468
+ },
1469
+ {
1470
+ "epoch": 0.4,
1471
+ "grad_norm": 0.10533872246742249,
1472
+ "learning_rate": 1.3315445430244744e-05,
1473
+ "loss": 1.0654,
1474
+ "step": 207
1475
+ },
1476
+ {
1477
+ "epoch": 0.41,
1478
+ "grad_norm": 0.10545054078102112,
1479
+ "learning_rate": 1.3256339003325054e-05,
1480
+ "loss": 1.0518,
1481
+ "step": 208
1482
+ },
1483
+ {
1484
+ "epoch": 0.41,
1485
+ "grad_norm": 0.09894714504480362,
1486
+ "learning_rate": 1.3197105044013544e-05,
1487
+ "loss": 1.0671,
1488
+ "step": 209
1489
+ },
1490
+ {
1491
+ "epoch": 0.41,
1492
+ "grad_norm": 0.08720172196626663,
1493
+ "learning_rate": 1.3137745872169578e-05,
1494
+ "loss": 1.0127,
1495
+ "step": 210
1496
+ },
1497
+ {
1498
+ "epoch": 0.41,
1499
+ "grad_norm": 0.08827454596757889,
1500
+ "learning_rate": 1.3078263812556377e-05,
1501
+ "loss": 1.0154,
1502
+ "step": 211
1503
+ },
1504
+ {
1505
+ "epoch": 0.41,
1506
+ "grad_norm": 0.0914626345038414,
1507
+ "learning_rate": 1.3018661194749986e-05,
1508
+ "loss": 1.0201,
1509
+ "step": 212
1510
+ },
1511
+ {
1512
+ "epoch": 0.42,
1513
+ "grad_norm": 0.08843535929918289,
1514
+ "learning_rate": 1.295894035304803e-05,
1515
+ "loss": 1.0516,
1516
+ "step": 213
1517
+ },
1518
+ {
1519
+ "epoch": 0.42,
1520
+ "grad_norm": 0.08639541268348694,
1521
+ "learning_rate": 1.28991036263783e-05,
1522
+ "loss": 1.0165,
1523
+ "step": 214
1524
+ },
1525
+ {
1526
+ "epoch": 0.42,
1527
+ "grad_norm": 0.07750130444765091,
1528
+ "learning_rate": 1.2839153358207142e-05,
1529
+ "loss": 1.0223,
1530
+ "step": 215
1531
+ },
1532
+ {
1533
+ "epoch": 0.42,
1534
+ "grad_norm": 0.0824190005660057,
1535
+ "learning_rate": 1.2779091896447682e-05,
1536
+ "loss": 1.0337,
1537
+ "step": 216
1538
+ },
1539
+ {
1540
+ "epoch": 0.42,
1541
+ "grad_norm": 0.08451572805643082,
1542
+ "learning_rate": 1.2718921593367874e-05,
1543
+ "loss": 1.0542,
1544
+ "step": 217
1545
+ },
1546
+ {
1547
+ "epoch": 0.43,
1548
+ "grad_norm": 0.0857366994023323,
1549
+ "learning_rate": 1.2658644805498361e-05,
1550
+ "loss": 1.0759,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 0.43,
1555
+ "grad_norm": 0.07681415975093842,
1556
+ "learning_rate": 1.2598263893540207e-05,
1557
+ "loss": 1.0506,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 0.43,
1562
+ "grad_norm": 0.07856535911560059,
1563
+ "learning_rate": 1.2537781222272423e-05,
1564
+ "loss": 1.0974,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 0.43,
1569
+ "grad_norm": 0.08015410602092743,
1570
+ "learning_rate": 1.2477199160459345e-05,
1571
+ "loss": 1.0604,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 0.43,
1576
+ "grad_norm": 0.08314133435487747,
1577
+ "learning_rate": 1.2416520080757892e-05,
1578
+ "loss": 1.0889,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 0.43,
1583
+ "grad_norm": 0.08028203994035721,
1584
+ "learning_rate": 1.2355746359624621e-05,
1585
+ "loss": 1.0281,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 0.44,
1590
+ "grad_norm": 0.0775797963142395,
1591
+ "learning_rate": 1.2294880377222649e-05,
1592
+ "loss": 1.078,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 0.44,
1597
+ "grad_norm": 0.08315123617649078,
1598
+ "learning_rate": 1.2233924517328456e-05,
1599
+ "loss": 1.0356,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 0.44,
1604
+ "grad_norm": 0.0795183852314949,
1605
+ "learning_rate": 1.2172881167238515e-05,
1606
+ "loss": 1.0332,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 0.44,
1611
+ "grad_norm": 0.0779062882065773,
1612
+ "learning_rate": 1.2111752717675788e-05,
1613
+ "loss": 0.9954,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 0.44,
1618
+ "grad_norm": 0.07758854329586029,
1619
+ "learning_rate": 1.205054156269611e-05,
1620
+ "loss": 1.0242,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 0.45,
1625
+ "grad_norm": 0.07713694125413895,
1626
+ "learning_rate": 1.1989250099594412e-05,
1627
+ "loss": 1.0686,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 0.45,
1632
+ "grad_norm": 0.07772821933031082,
1633
+ "learning_rate": 1.192788072881085e-05,
1634
+ "loss": 1.0338,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 0.45,
1639
+ "grad_norm": 0.08006665855646133,
1640
+ "learning_rate": 1.1866435853836773e-05,
1641
+ "loss": 1.0946,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 0.45,
1646
+ "grad_norm": 0.0821637436747551,
1647
+ "learning_rate": 1.1804917881120608e-05,
1648
+ "loss": 1.0525,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 0.45,
1653
+ "grad_norm": 0.07892850786447525,
1654
+ "learning_rate": 1.1743329219973609e-05,
1655
+ "loss": 1.0127,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 0.46,
1660
+ "grad_norm": 0.07800798863172531,
1661
+ "learning_rate": 1.1681672282475495e-05,
1662
+ "loss": 1.0254,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 0.46,
1667
+ "grad_norm": 0.07875402271747589,
1668
+ "learning_rate": 1.161994948337998e-05,
1669
+ "loss": 1.0319,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 0.46,
1674
+ "grad_norm": 0.08178096264600754,
1675
+ "learning_rate": 1.1558163240020209e-05,
1676
+ "loss": 1.0541,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 0.46,
1681
+ "grad_norm": 0.08126726001501083,
1682
+ "learning_rate": 1.1496315972214076e-05,
1683
+ "loss": 1.0681,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 0.46,
1688
+ "grad_norm": 0.08104463666677475,
1689
+ "learning_rate": 1.1434410102169462e-05,
1690
+ "loss": 0.9767,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 0.47,
1695
+ "grad_norm": 0.0746295303106308,
1696
+ "learning_rate": 1.1372448054389364e-05,
1697
+ "loss": 1.0586,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 0.47,
1702
+ "grad_norm": 0.08171354979276657,
1703
+ "learning_rate": 1.1310432255576944e-05,
1704
+ "loss": 1.0655,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 0.47,
1709
+ "grad_norm": 0.08069796115159988,
1710
+ "learning_rate": 1.1248365134540489e-05,
1711
+ "loss": 1.079,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 0.47,
1716
+ "grad_norm": 0.07922904193401337,
1717
+ "learning_rate": 1.1186249122098282e-05,
1718
+ "loss": 1.0371,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 0.47,
1723
+ "grad_norm": 0.07877922058105469,
1724
+ "learning_rate": 1.1124086650983415e-05,
1725
+ "loss": 1.0236,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 0.48,
1730
+ "grad_norm": 0.07606945931911469,
1731
+ "learning_rate": 1.1061880155748497e-05,
1732
+ "loss": 1.0255,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 0.48,
1737
+ "grad_norm": 0.08225277811288834,
1738
+ "learning_rate": 1.0999632072670314e-05,
1739
+ "loss": 1.0571,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 0.48,
1744
+ "grad_norm": 0.07907744497060776,
1745
+ "learning_rate": 1.0937344839654416e-05,
1746
+ "loss": 1.0745,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 0.48,
1751
+ "grad_norm": 0.07885382324457169,
1752
+ "learning_rate": 1.087502089613963e-05,
1753
+ "loss": 0.9899,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 0.48,
1758
+ "grad_norm": 0.08236192911863327,
1759
+ "learning_rate": 1.0812662683002528e-05,
1760
+ "loss": 1.046,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 0.49,
1765
+ "grad_norm": 0.08153583109378815,
1766
+ "learning_rate": 1.075027264246183e-05,
1767
+ "loss": 1.0769,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 0.49,
1772
+ "grad_norm": 0.0847182348370552,
1773
+ "learning_rate": 1.068785321798276e-05,
1774
+ "loss": 1.0695,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 0.49,
1779
+ "grad_norm": 0.07414229959249496,
1780
+ "learning_rate": 1.062540685418133e-05,
1781
+ "loss": 1.0555,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 0.49,
1786
+ "grad_norm": 0.07932449132204056,
1787
+ "learning_rate": 1.0562935996728629e-05,
1788
+ "loss": 1.0644,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 0.49,
1793
+ "grad_norm": 0.08247576653957367,
1794
+ "learning_rate": 1.0500443092255017e-05,
1795
+ "loss": 1.064,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 0.5,
1800
+ "grad_norm": 0.07860003411769867,
1801
+ "learning_rate": 1.043793058825431e-05,
1802
+ "loss": 1.0579,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 0.5,
1807
+ "grad_norm": 0.08330255001783371,
1808
+ "learning_rate": 1.0375400932987932e-05,
1809
+ "loss": 1.0218,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 0.5,
1814
+ "grad_norm": 0.08150562644004822,
1815
+ "learning_rate": 1.0312856575389016e-05,
1816
+ "loss": 1.0379,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 0.5,
1821
+ "eval_loss": 1.0509783029556274,
1822
+ "eval_runtime": 708.357,
1823
+ "eval_samples_per_second": 7.163,
1824
+ "eval_steps_per_second": 1.791,
1825
+ "step": 256
1826
+ },
1827
+ {
1828
+ "epoch": 0.5,
1829
+ "grad_norm": 0.08040876686573029,
1830
+ "learning_rate": 1.025029996496651e-05,
1831
+ "loss": 1.03,
1832
+ "step": 257
1833
+ },
1834
+ {
1835
+ "epoch": 0.5,
1836
+ "grad_norm": 0.07957625389099121,
1837
+ "learning_rate": 1.0187733551709236e-05,
1838
+ "loss": 1.0235,
1839
+ "step": 258
1840
+ },
1841
+ {
1842
+ "epoch": 0.51,
1843
+ "grad_norm": 0.07723429054021835,
1844
+ "learning_rate": 1.0125159785989933e-05,
1845
+ "loss": 1.0633,
1846
+ "step": 259
1847
+ },
1848
+ {
1849
+ "epoch": 0.51,
1850
+ "grad_norm": 0.079456627368927,
1851
+ "learning_rate": 1.00625811184693e-05,
1852
+ "loss": 1.0403,
1853
+ "step": 260
1854
+ },
1855
+ {
1856
+ "epoch": 0.51,
1857
+ "grad_norm": 0.07875042408704758,
1858
+ "learning_rate": 1e-05,
1859
+ "loss": 1.0393,
1860
+ "step": 261
1861
+ },
1862
+ {
1863
+ "epoch": 0.51,
1864
+ "grad_norm": 0.0797952190041542,
1865
+ "learning_rate": 9.937418881530704e-06,
1866
+ "loss": 1.0456,
1867
+ "step": 262
1868
+ },
1869
+ {
1870
+ "epoch": 0.51,
1871
+ "grad_norm": 0.08356386423110962,
1872
+ "learning_rate": 9.874840214010069e-06,
1873
+ "loss": 1.0967,
1874
+ "step": 263
1875
+ },
1876
+ {
1877
+ "epoch": 0.51,
1878
+ "grad_norm": 0.0836138129234314,
1879
+ "learning_rate": 9.812266448290767e-06,
1880
+ "loss": 1.065,
1881
+ "step": 264
1882
+ },
1883
+ {
1884
+ "epoch": 0.52,
1885
+ "grad_norm": 0.07885371893644333,
1886
+ "learning_rate": 9.749700035033492e-06,
1887
+ "loss": 1.0664,
1888
+ "step": 265
1889
+ },
1890
+ {
1891
+ "epoch": 0.52,
1892
+ "grad_norm": 0.07813183963298798,
1893
+ "learning_rate": 9.687143424610986e-06,
1894
+ "loss": 1.0277,
1895
+ "step": 266
1896
+ },
1897
+ {
1898
+ "epoch": 0.52,
1899
+ "grad_norm": 0.07894445955753326,
1900
+ "learning_rate": 9.624599067012073e-06,
1901
+ "loss": 1.0646,
1902
+ "step": 267
1903
+ },
1904
+ {
1905
+ "epoch": 0.52,
1906
+ "grad_norm": 0.08423804491758347,
1907
+ "learning_rate": 9.562069411745692e-06,
1908
+ "loss": 1.0592,
1909
+ "step": 268
1910
+ },
1911
+ {
1912
+ "epoch": 0.52,
1913
+ "grad_norm": 0.08294244855642319,
1914
+ "learning_rate": 9.499556907744985e-06,
1915
+ "loss": 1.11,
1916
+ "step": 269
1917
+ },
1918
+ {
1919
+ "epoch": 0.53,
1920
+ "grad_norm": 0.07947829365730286,
1921
+ "learning_rate": 9.437064003271373e-06,
1922
+ "loss": 1.0872,
1923
+ "step": 270
1924
+ },
1925
+ {
1926
+ "epoch": 0.53,
1927
+ "grad_norm": 0.07858666032552719,
1928
+ "learning_rate": 9.374593145818673e-06,
1929
+ "loss": 1.0711,
1930
+ "step": 271
1931
+ },
1932
+ {
1933
+ "epoch": 0.53,
1934
+ "grad_norm": 0.07969223707914352,
1935
+ "learning_rate": 9.312146782017244e-06,
1936
+ "loss": 1.0515,
1937
+ "step": 272
1938
+ },
1939
+ {
1940
+ "epoch": 0.53,
1941
+ "grad_norm": 0.08079613745212555,
1942
+ "learning_rate": 9.249727357538171e-06,
1943
+ "loss": 1.0755,
1944
+ "step": 273
1945
+ },
1946
+ {
1947
+ "epoch": 0.53,
1948
+ "grad_norm": 0.07963809370994568,
1949
+ "learning_rate": 9.187337316997475e-06,
1950
+ "loss": 1.0371,
1951
+ "step": 274
1952
+ },
1953
+ {
1954
+ "epoch": 0.54,
1955
+ "grad_norm": 0.07834453135728836,
1956
+ "learning_rate": 9.124979103860374e-06,
1957
+ "loss": 1.0512,
1958
+ "step": 275
1959
+ },
1960
+ {
1961
+ "epoch": 0.54,
1962
+ "grad_norm": 0.07958018779754639,
1963
+ "learning_rate": 9.062655160345587e-06,
1964
+ "loss": 1.0395,
1965
+ "step": 276
1966
+ },
1967
+ {
1968
+ "epoch": 0.54,
1969
+ "grad_norm": 0.08063136041164398,
1970
+ "learning_rate": 9.000367927329691e-06,
1971
+ "loss": 1.0417,
1972
+ "step": 277
1973
+ },
1974
+ {
1975
+ "epoch": 0.54,
1976
+ "grad_norm": 0.07932613044977188,
1977
+ "learning_rate": 8.938119844251507e-06,
1978
+ "loss": 1.0223,
1979
+ "step": 278
1980
+ },
1981
+ {
1982
+ "epoch": 0.54,
1983
+ "grad_norm": 0.08033180236816406,
1984
+ "learning_rate": 8.87591334901659e-06,
1985
+ "loss": 1.0549,
1986
+ "step": 279
1987
+ },
1988
+ {
1989
+ "epoch": 0.55,
1990
+ "grad_norm": 0.07867812365293503,
1991
+ "learning_rate": 8.813750877901723e-06,
1992
+ "loss": 1.0559,
1993
+ "step": 280
1994
+ },
1995
+ {
1996
+ "epoch": 0.55,
1997
+ "grad_norm": 0.07839823514223099,
1998
+ "learning_rate": 8.751634865459518e-06,
1999
+ "loss": 1.0506,
2000
+ "step": 281
2001
+ },
2002
+ {
2003
+ "epoch": 0.55,
2004
+ "grad_norm": 0.08088871091604233,
2005
+ "learning_rate": 8.68956774442306e-06,
2006
+ "loss": 1.0387,
2007
+ "step": 282
2008
+ },
2009
+ {
2010
+ "epoch": 0.55,
2011
+ "grad_norm": 0.07918152213096619,
2012
+ "learning_rate": 8.627551945610641e-06,
2013
+ "loss": 1.0213,
2014
+ "step": 283
2015
+ },
2016
+ {
2017
+ "epoch": 0.55,
2018
+ "grad_norm": 0.08179888874292374,
2019
+ "learning_rate": 8.565589897830543e-06,
2020
+ "loss": 1.0328,
2021
+ "step": 284
2022
+ },
2023
+ {
2024
+ "epoch": 0.56,
2025
+ "grad_norm": 0.07968099415302277,
2026
+ "learning_rate": 8.503684027785929e-06,
2027
+ "loss": 1.0358,
2028
+ "step": 285
2029
+ },
2030
+ {
2031
+ "epoch": 0.56,
2032
+ "grad_norm": 0.07866982370615005,
2033
+ "learning_rate": 8.441836759979796e-06,
2034
+ "loss": 1.0278,
2035
+ "step": 286
2036
+ },
2037
+ {
2038
+ "epoch": 0.56,
2039
+ "grad_norm": 0.08549748361110687,
2040
+ "learning_rate": 8.380050516620026e-06,
2041
+ "loss": 1.0062,
2042
+ "step": 287
2043
+ },
2044
+ {
2045
+ "epoch": 0.56,
2046
+ "grad_norm": 0.07923188805580139,
2047
+ "learning_rate": 8.31832771752451e-06,
2048
+ "loss": 1.0566,
2049
+ "step": 288
2050
+ },
2051
+ {
2052
+ "epoch": 0.56,
2053
+ "grad_norm": 0.07845155894756317,
2054
+ "learning_rate": 8.256670780026393e-06,
2055
+ "loss": 1.0425,
2056
+ "step": 289
2057
+ },
2058
+ {
2059
+ "epoch": 0.57,
2060
+ "grad_norm": 0.08341726660728455,
2061
+ "learning_rate": 8.195082118879397e-06,
2062
+ "loss": 1.0269,
2063
+ "step": 290
2064
+ },
2065
+ {
2066
+ "epoch": 0.57,
2067
+ "grad_norm": 0.09000853449106216,
2068
+ "learning_rate": 8.133564146163232e-06,
2069
+ "loss": 1.0602,
2070
+ "step": 291
2071
+ },
2072
+ {
2073
+ "epoch": 0.57,
2074
+ "grad_norm": 0.07995503395795822,
2075
+ "learning_rate": 8.072119271189155e-06,
2076
+ "loss": 1.0283,
2077
+ "step": 292
2078
+ },
2079
+ {
2080
+ "epoch": 0.57,
2081
+ "grad_norm": 0.08204926550388336,
2082
+ "learning_rate": 8.01074990040559e-06,
2083
+ "loss": 1.0397,
2084
+ "step": 293
2085
+ },
2086
+ {
2087
+ "epoch": 0.57,
2088
+ "grad_norm": 0.08035868406295776,
2089
+ "learning_rate": 7.949458437303892e-06,
2090
+ "loss": 1.0455,
2091
+ "step": 294
2092
+ },
2093
+ {
2094
+ "epoch": 0.58,
2095
+ "grad_norm": 0.08018406480550766,
2096
+ "learning_rate": 7.888247282324212e-06,
2097
+ "loss": 1.0796,
2098
+ "step": 295
2099
+ },
2100
+ {
2101
+ "epoch": 0.58,
2102
+ "grad_norm": 0.07843944430351257,
2103
+ "learning_rate": 7.827118832761487e-06,
2104
+ "loss": 1.0541,
2105
+ "step": 296
2106
+ },
2107
+ {
2108
+ "epoch": 0.58,
2109
+ "grad_norm": 0.07853015512228012,
2110
+ "learning_rate": 7.766075482671544e-06,
2111
+ "loss": 1.045,
2112
+ "step": 297
2113
+ },
2114
+ {
2115
+ "epoch": 0.58,
2116
+ "grad_norm": 0.08274030685424805,
2117
+ "learning_rate": 7.705119622777351e-06,
2118
+ "loss": 1.0465,
2119
+ "step": 298
2120
+ },
2121
+ {
2122
+ "epoch": 0.58,
2123
+ "grad_norm": 0.08550436049699783,
2124
+ "learning_rate": 7.644253640375382e-06,
2125
+ "loss": 0.9985,
2126
+ "step": 299
2127
+ },
2128
+ {
2129
+ "epoch": 0.58,
2130
+ "grad_norm": 0.08202614635229111,
2131
+ "learning_rate": 7.583479919242108e-06,
2132
+ "loss": 1.039,
2133
+ "step": 300
2134
+ },
2135
+ {
2136
+ "epoch": 0.59,
2137
+ "grad_norm": 0.08024229854345322,
2138
+ "learning_rate": 7.522800839540656e-06,
2139
+ "loss": 1.0158,
2140
+ "step": 301
2141
+ },
2142
+ {
2143
+ "epoch": 0.59,
2144
+ "grad_norm": 0.08370032161474228,
2145
+ "learning_rate": 7.462218777727581e-06,
2146
+ "loss": 1.0143,
2147
+ "step": 302
2148
+ },
2149
+ {
2150
+ "epoch": 0.59,
2151
+ "grad_norm": 0.0836290642619133,
2152
+ "learning_rate": 7.4017361064597925e-06,
2153
+ "loss": 1.0427,
2154
+ "step": 303
2155
+ },
2156
+ {
2157
+ "epoch": 0.59,
2158
+ "grad_norm": 0.08153602480888367,
2159
+ "learning_rate": 7.341355194501638e-06,
2160
+ "loss": 1.0573,
2161
+ "step": 304
2162
+ },
2163
+ {
2164
+ "epoch": 0.59,
2165
+ "grad_norm": 0.08701439201831818,
2166
+ "learning_rate": 7.281078406632127e-06,
2167
+ "loss": 1.0185,
2168
+ "step": 305
2169
+ },
2170
+ {
2171
+ "epoch": 0.6,
2172
+ "grad_norm": 0.08054394274950027,
2173
+ "learning_rate": 7.220908103552319e-06,
2174
+ "loss": 1.0349,
2175
+ "step": 306
2176
+ },
2177
+ {
2178
+ "epoch": 0.6,
2179
+ "grad_norm": 0.0855594277381897,
2180
+ "learning_rate": 7.160846641792858e-06,
2181
+ "loss": 1.0594,
2182
+ "step": 307
2183
+ },
2184
+ {
2185
+ "epoch": 0.6,
2186
+ "grad_norm": 0.08319972455501556,
2187
+ "learning_rate": 7.1008963736217e-06,
2188
+ "loss": 1.0537,
2189
+ "step": 308
2190
+ },
2191
+ {
2192
+ "epoch": 0.6,
2193
+ "grad_norm": 0.08150538802146912,
2194
+ "learning_rate": 7.041059646951971e-06,
2195
+ "loss": 1.025,
2196
+ "step": 309
2197
+ },
2198
+ {
2199
+ "epoch": 0.6,
2200
+ "grad_norm": 0.07885453850030899,
2201
+ "learning_rate": 6.981338805250015e-06,
2202
+ "loss": 1.013,
2203
+ "step": 310
2204
+ },
2205
+ {
2206
+ "epoch": 0.61,
2207
+ "grad_norm": 0.0796799287199974,
2208
+ "learning_rate": 6.921736187443624e-06,
2209
+ "loss": 1.0002,
2210
+ "step": 311
2211
+ },
2212
+ {
2213
+ "epoch": 0.61,
2214
+ "grad_norm": 0.08254199475049973,
2215
+ "learning_rate": 6.862254127830426e-06,
2216
+ "loss": 1.076,
2217
+ "step": 312
2218
+ },
2219
+ {
2220
+ "epoch": 0.61,
2221
+ "grad_norm": 0.08591365814208984,
2222
+ "learning_rate": 6.802894955986459e-06,
2223
+ "loss": 1.0464,
2224
+ "step": 313
2225
+ },
2226
+ {
2227
+ "epoch": 0.61,
2228
+ "grad_norm": 0.08346603810787201,
2229
+ "learning_rate": 6.74366099667495e-06,
2230
+ "loss": 1.0497,
2231
+ "step": 314
2232
+ },
2233
+ {
2234
+ "epoch": 0.61,
2235
+ "grad_norm": 0.0861155241727829,
2236
+ "learning_rate": 6.684554569755258e-06,
2237
+ "loss": 1.0272,
2238
+ "step": 315
2239
+ },
2240
+ {
2241
+ "epoch": 0.62,
2242
+ "grad_norm": 0.08690168708562851,
2243
+ "learning_rate": 6.625577990092019e-06,
2244
+ "loss": 1.0239,
2245
+ "step": 316
2246
+ },
2247
+ {
2248
+ "epoch": 0.62,
2249
+ "grad_norm": 0.08035359531641006,
2250
+ "learning_rate": 6.56673356746448e-06,
2251
+ "loss": 1.0224,
2252
+ "step": 317
2253
+ },
2254
+ {
2255
+ "epoch": 0.62,
2256
+ "grad_norm": 0.08103054761886597,
2257
+ "learning_rate": 6.508023606476052e-06,
2258
+ "loss": 1.0484,
2259
+ "step": 318
2260
+ },
2261
+ {
2262
+ "epoch": 0.62,
2263
+ "grad_norm": 0.08610061556100845,
2264
+ "learning_rate": 6.44945040646404e-06,
2265
+ "loss": 1.0345,
2266
+ "step": 319
2267
+ },
2268
+ {
2269
+ "epoch": 0.62,
2270
+ "grad_norm": 0.07808943837881088,
2271
+ "learning_rate": 6.39101626140959e-06,
2272
+ "loss": 1.0312,
2273
+ "step": 320
2274
+ },
2275
+ {
2276
+ "epoch": 0.63,
2277
+ "grad_norm": 0.08029762655496597,
2278
+ "learning_rate": 6.3327234598478605e-06,
2279
+ "loss": 1.0705,
2280
+ "step": 321
2281
+ },
2282
+ {
2283
+ "epoch": 0.63,
2284
+ "grad_norm": 0.08351495862007141,
2285
+ "learning_rate": 6.274574284778379e-06,
2286
+ "loss": 1.0243,
2287
+ "step": 322
2288
+ },
2289
+ {
2290
+ "epoch": 0.63,
2291
+ "grad_norm": 0.07923708111047745,
2292
+ "learning_rate": 6.2165710135756365e-06,
2293
+ "loss": 1.0663,
2294
+ "step": 323
2295
+ },
2296
+ {
2297
+ "epoch": 0.63,
2298
+ "grad_norm": 0.0885549783706665,
2299
+ "learning_rate": 6.158715917899892e-06,
2300
+ "loss": 1.0464,
2301
+ "step": 324
2302
+ },
2303
+ {
2304
+ "epoch": 0.63,
2305
+ "grad_norm": 0.08241602033376694,
2306
+ "learning_rate": 6.10101126360821e-06,
2307
+ "loss": 1.0619,
2308
+ "step": 325
2309
+ },
2310
+ {
2311
+ "epoch": 0.64,
2312
+ "grad_norm": 0.08293651044368744,
2313
+ "learning_rate": 6.043459310665716e-06,
2314
+ "loss": 1.0406,
2315
+ "step": 326
2316
+ },
2317
+ {
2318
+ "epoch": 0.64,
2319
+ "grad_norm": 0.08230554312467575,
2320
+ "learning_rate": 5.986062313057084e-06,
2321
+ "loss": 1.0268,
2322
+ "step": 327
2323
+ },
2324
+ {
2325
+ "epoch": 0.64,
2326
+ "grad_norm": 0.08260442316532135,
2327
+ "learning_rate": 5.928822518698263e-06,
2328
+ "loss": 1.0341,
2329
+ "step": 328
2330
+ },
2331
+ {
2332
+ "epoch": 0.64,
2333
+ "grad_norm": 0.08099180459976196,
2334
+ "learning_rate": 5.871742169348447e-06,
2335
+ "loss": 1.0127,
2336
+ "step": 329
2337
+ },
2338
+ {
2339
+ "epoch": 0.64,
2340
+ "grad_norm": 0.08358913660049438,
2341
+ "learning_rate": 5.81482350052226e-06,
2342
+ "loss": 1.0125,
2343
+ "step": 330
2344
+ },
2345
+ {
2346
+ "epoch": 0.65,
2347
+ "grad_norm": 0.07926523685455322,
2348
+ "learning_rate": 5.758068741402223e-06,
2349
+ "loss": 1.0362,
2350
+ "step": 331
2351
+ },
2352
+ {
2353
+ "epoch": 0.65,
2354
+ "grad_norm": 0.0837349146604538,
2355
+ "learning_rate": 5.701480114751432e-06,
2356
+ "loss": 1.068,
2357
+ "step": 332
2358
+ },
2359
+ {
2360
+ "epoch": 0.65,
2361
+ "grad_norm": 0.08267077058553696,
2362
+ "learning_rate": 5.645059836826518e-06,
2363
+ "loss": 1.025,
2364
+ "step": 333
2365
+ },
2366
+ {
2367
+ "epoch": 0.65,
2368
+ "grad_norm": 0.07937329262495041,
2369
+ "learning_rate": 5.588810117290843e-06,
2370
+ "loss": 1.073,
2371
+ "step": 334
2372
+ },
2373
+ {
2374
+ "epoch": 0.65,
2375
+ "grad_norm": 0.08118374645709991,
2376
+ "learning_rate": 5.532733159127963e-06,
2377
+ "loss": 1.0477,
2378
+ "step": 335
2379
+ },
2380
+ {
2381
+ "epoch": 0.66,
2382
+ "grad_norm": 0.08420372009277344,
2383
+ "learning_rate": 5.476831158555345e-06,
2384
+ "loss": 1.0384,
2385
+ "step": 336
2386
+ },
2387
+ {
2388
+ "epoch": 0.66,
2389
+ "grad_norm": 0.08201659470796585,
2390
+ "learning_rate": 5.421106304938356e-06,
2391
+ "loss": 1.0402,
2392
+ "step": 337
2393
+ },
2394
+ {
2395
+ "epoch": 0.66,
2396
+ "grad_norm": 0.08588004112243652,
2397
+ "learning_rate": 5.365560780704524e-06,
2398
+ "loss": 1.0363,
2399
+ "step": 338
2400
+ },
2401
+ {
2402
+ "epoch": 0.66,
2403
+ "grad_norm": 0.08382384479045868,
2404
+ "learning_rate": 5.310196761258048e-06,
2405
+ "loss": 1.0392,
2406
+ "step": 339
2407
+ },
2408
+ {
2409
+ "epoch": 0.66,
2410
+ "grad_norm": 0.08232959359884262,
2411
+ "learning_rate": 5.255016414894616e-06,
2412
+ "loss": 1.0476,
2413
+ "step": 340
2414
+ },
2415
+ {
2416
+ "epoch": 0.66,
2417
+ "grad_norm": 0.08402816951274872,
2418
+ "learning_rate": 5.200021902716483e-06,
2419
+ "loss": 1.0668,
2420
+ "step": 341
2421
+ },
2422
+ {
2423
+ "epoch": 0.67,
2424
+ "grad_norm": 0.0849897488951683,
2425
+ "learning_rate": 5.145215378547825e-06,
2426
+ "loss": 1.0068,
2427
+ "step": 342
2428
+ },
2429
+ {
2430
+ "epoch": 0.67,
2431
+ "grad_norm": 0.08432206511497498,
2432
+ "learning_rate": 5.0905989888503924e-06,
2433
+ "loss": 1.0815,
2434
+ "step": 343
2435
+ },
2436
+ {
2437
+ "epoch": 0.67,
2438
+ "grad_norm": 0.0807095468044281,
2439
+ "learning_rate": 5.0361748726394435e-06,
2440
+ "loss": 1.058,
2441
+ "step": 344
2442
+ },
2443
+ {
2444
+ "epoch": 0.67,
2445
+ "grad_norm": 0.0844447985291481,
2446
+ "learning_rate": 4.981945161399969e-06,
2447
+ "loss": 1.0134,
2448
+ "step": 345
2449
+ },
2450
+ {
2451
+ "epoch": 0.67,
2452
+ "grad_norm": 0.08169819414615631,
2453
+ "learning_rate": 4.927911979003214e-06,
2454
+ "loss": 1.0486,
2455
+ "step": 346
2456
+ },
2457
+ {
2458
+ "epoch": 0.68,
2459
+ "grad_norm": 0.08409695327281952,
2460
+ "learning_rate": 4.874077441623504e-06,
2461
+ "loss": 1.0711,
2462
+ "step": 347
2463
+ },
2464
+ {
2465
+ "epoch": 0.68,
2466
+ "grad_norm": 0.08292841166257858,
2467
+ "learning_rate": 4.82044365765536e-06,
2468
+ "loss": 1.0311,
2469
+ "step": 348
2470
+ },
2471
+ {
2472
+ "epoch": 0.68,
2473
+ "grad_norm": 0.084018275141716,
2474
+ "learning_rate": 4.767012727630927e-06,
2475
+ "loss": 1.0254,
2476
+ "step": 349
2477
+ },
2478
+ {
2479
+ "epoch": 0.68,
2480
+ "grad_norm": 0.08370067924261093,
2481
+ "learning_rate": 4.71378674413771e-06,
2482
+ "loss": 1.0309,
2483
+ "step": 350
2484
+ },
2485
+ {
2486
+ "epoch": 0.68,
2487
+ "grad_norm": 0.08273698389530182,
2488
+ "learning_rate": 4.6607677917366155e-06,
2489
+ "loss": 1.0068,
2490
+ "step": 351
2491
+ },
2492
+ {
2493
+ "epoch": 0.69,
2494
+ "grad_norm": 0.0803639367222786,
2495
+ "learning_rate": 4.607957946880305e-06,
2496
+ "loss": 1.0414,
2497
+ "step": 352
2498
+ },
2499
+ {
2500
+ "epoch": 0.69,
2501
+ "grad_norm": 0.08122535794973373,
2502
+ "learning_rate": 4.55535927783189e-06,
2503
+ "loss": 1.0474,
2504
+ "step": 353
2505
+ },
2506
+ {
2507
+ "epoch": 0.69,
2508
+ "grad_norm": 0.07980665564537048,
2509
+ "learning_rate": 4.502973844583914e-06,
2510
+ "loss": 1.0281,
2511
+ "step": 354
2512
+ },
2513
+ {
2514
+ "epoch": 0.69,
2515
+ "grad_norm": 0.08257856965065002,
2516
+ "learning_rate": 4.450803698777684e-06,
2517
+ "loss": 0.9825,
2518
+ "step": 355
2519
+ },
2520
+ {
2521
+ "epoch": 0.69,
2522
+ "grad_norm": 0.0826905369758606,
2523
+ "learning_rate": 4.398850883622905e-06,
2524
+ "loss": 1.0168,
2525
+ "step": 356
2526
+ },
2527
+ {
2528
+ "epoch": 0.7,
2529
+ "grad_norm": 0.0833047404885292,
2530
+ "learning_rate": 4.347117433817687e-06,
2531
+ "loss": 1.0481,
2532
+ "step": 357
2533
+ },
2534
+ {
2535
+ "epoch": 0.7,
2536
+ "grad_norm": 0.0809812918305397,
2537
+ "learning_rate": 4.295605375468818e-06,
2538
+ "loss": 1.017,
2539
+ "step": 358
2540
+ },
2541
+ {
2542
+ "epoch": 0.7,
2543
+ "grad_norm": 0.0812465101480484,
2544
+ "learning_rate": 4.244316726012446e-06,
2545
+ "loss": 1.0376,
2546
+ "step": 359
2547
+ },
2548
+ {
2549
+ "epoch": 0.7,
2550
+ "grad_norm": 0.07954216003417969,
2551
+ "learning_rate": 4.1932534941350545e-06,
2552
+ "loss": 1.0491,
2553
+ "step": 360
2554
+ },
2555
+ {
2556
+ "epoch": 0.7,
2557
+ "grad_norm": 0.08341410756111145,
2558
+ "learning_rate": 4.142417679694794e-06,
2559
+ "loss": 1.0556,
2560
+ "step": 361
2561
+ },
2562
+ {
2563
+ "epoch": 0.71,
2564
+ "grad_norm": 0.08242359757423401,
2565
+ "learning_rate": 4.091811273643157e-06,
2566
+ "loss": 1.0573,
2567
+ "step": 362
2568
+ },
2569
+ {
2570
+ "epoch": 0.71,
2571
+ "grad_norm": 0.08539704233407974,
2572
+ "learning_rate": 4.041436257947015e-06,
2573
+ "loss": 1.0458,
2574
+ "step": 363
2575
+ },
2576
+ {
2577
+ "epoch": 0.71,
2578
+ "grad_norm": 0.08542854338884354,
2579
+ "learning_rate": 3.991294605510969e-06,
2580
+ "loss": 1.052,
2581
+ "step": 364
2582
+ },
2583
+ {
2584
+ "epoch": 0.71,
2585
+ "grad_norm": 0.07968278974294662,
2586
+ "learning_rate": 3.94138828010012e-06,
2587
+ "loss": 1.0441,
2588
+ "step": 365
2589
+ },
2590
+ {
2591
+ "epoch": 0.71,
2592
+ "grad_norm": 0.08242907375097275,
2593
+ "learning_rate": 3.8917192362631285e-06,
2594
+ "loss": 1.0321,
2595
+ "step": 366
2596
+ },
2597
+ {
2598
+ "epoch": 0.72,
2599
+ "grad_norm": 0.08331603556871414,
2600
+ "learning_rate": 3.842289419255681e-06,
2601
+ "loss": 1.0296,
2602
+ "step": 367
2603
+ },
2604
+ {
2605
+ "epoch": 0.72,
2606
+ "grad_norm": 0.08717033267021179,
2607
+ "learning_rate": 3.793100764964299e-06,
2608
+ "loss": 1.0797,
2609
+ "step": 368
2610
+ },
2611
+ {
2612
+ "epoch": 0.72,
2613
+ "grad_norm": 0.08025430142879486,
2614
+ "learning_rate": 3.744155199830526e-06,
2615
+ "loss": 1.0322,
2616
+ "step": 369
2617
+ },
2618
+ {
2619
+ "epoch": 0.72,
2620
+ "grad_norm": 0.0844465121626854,
2621
+ "learning_rate": 3.69545464077548e-06,
2622
+ "loss": 1.0334,
2623
+ "step": 370
2624
+ },
2625
+ {
2626
+ "epoch": 0.72,
2627
+ "grad_norm": 0.08173581212759018,
2628
+ "learning_rate": 3.647000995124763e-06,
2629
+ "loss": 1.062,
2630
+ "step": 371
2631
+ },
2632
+ {
2633
+ "epoch": 0.73,
2634
+ "grad_norm": 0.08682363480329514,
2635
+ "learning_rate": 3.5987961605337894e-06,
2636
+ "loss": 1.0115,
2637
+ "step": 372
2638
+ },
2639
+ {
2640
+ "epoch": 0.73,
2641
+ "grad_norm": 0.09901048988103867,
2642
+ "learning_rate": 3.5508420249134432e-06,
2643
+ "loss": 1.0422,
2644
+ "step": 373
2645
+ },
2646
+ {
2647
+ "epoch": 0.73,
2648
+ "grad_norm": 0.0846165269613266,
2649
+ "learning_rate": 3.5031404663561507e-06,
2650
+ "loss": 1.0187,
2651
+ "step": 374
2652
+ },
2653
+ {
2654
+ "epoch": 0.73,
2655
+ "grad_norm": 0.08063055574893951,
2656
+ "learning_rate": 3.4556933530623193e-06,
2657
+ "loss": 1.0233,
2658
+ "step": 375
2659
+ },
2660
+ {
2661
+ "epoch": 0.73,
2662
+ "grad_norm": 0.08191438019275665,
2663
+ "learning_rate": 3.4085025432671746e-06,
2664
+ "loss": 1.0758,
2665
+ "step": 376
2666
+ },
2667
+ {
2668
+ "epoch": 0.74,
2669
+ "grad_norm": 0.08018861711025238,
2670
+ "learning_rate": 3.3615698851679866e-06,
2671
+ "loss": 1.0546,
2672
+ "step": 377
2673
+ },
2674
+ {
2675
+ "epoch": 0.74,
2676
+ "grad_norm": 0.08329375833272934,
2677
+ "learning_rate": 3.3148972168516737e-06,
2678
+ "loss": 1.0403,
2679
+ "step": 378
2680
+ },
2681
+ {
2682
+ "epoch": 0.74,
2683
+ "grad_norm": 0.08185313642024994,
2684
+ "learning_rate": 3.2684863662228307e-06,
2685
+ "loss": 1.0272,
2686
+ "step": 379
2687
+ },
2688
+ {
2689
+ "epoch": 0.74,
2690
+ "grad_norm": 0.08924821019172668,
2691
+ "learning_rate": 3.2223391509321335e-06,
2692
+ "loss": 1.0447,
2693
+ "step": 380
2694
+ },
2695
+ {
2696
+ "epoch": 0.74,
2697
+ "grad_norm": 0.08294879645109177,
2698
+ "learning_rate": 3.176457378305151e-06,
2699
+ "loss": 1.004,
2700
+ "step": 381
2701
+ },
2702
+ {
2703
+ "epoch": 0.74,
2704
+ "grad_norm": 0.08492495864629745,
2705
+ "learning_rate": 3.1308428452715643e-06,
2706
+ "loss": 1.0479,
2707
+ "step": 382
2708
+ },
2709
+ {
2710
+ "epoch": 0.75,
2711
+ "grad_norm": 0.08171503990888596,
2712
+ "learning_rate": 3.0854973382947884e-06,
2713
+ "loss": 0.9821,
2714
+ "step": 383
2715
+ },
2716
+ {
2717
+ "epoch": 0.75,
2718
+ "grad_norm": 0.08578088134527206,
2719
+ "learning_rate": 3.0404226333020117e-06,
2720
+ "loss": 1.0402,
2721
+ "step": 384
2722
+ },
2723
+ {
2724
+ "epoch": 0.75,
2725
+ "eval_loss": 1.0385833978652954,
2726
+ "eval_runtime": 708.3771,
2727
+ "eval_samples_per_second": 7.163,
2728
+ "eval_steps_per_second": 1.791,
2729
+ "step": 384
2730
+ },
2731
+ {
2732
+ "epoch": 0.75,
2733
+ "grad_norm": 0.0851321890950203,
2734
+ "learning_rate": 2.995620495614633e-06,
2735
+ "loss": 1.0501,
2736
+ "step": 385
2737
+ },
2738
+ {
2739
+ "epoch": 0.75,
2740
+ "grad_norm": 0.08435554802417755,
2741
+ "learning_rate": 2.951092679879136e-06,
2742
+ "loss": 1.0222,
2743
+ "step": 386
2744
+ },
2745
+ {
2746
+ "epoch": 0.75,
2747
+ "grad_norm": 0.08391427248716354,
2748
+ "learning_rate": 2.9068409299983634e-06,
2749
+ "loss": 1.0561,
2750
+ "step": 387
2751
+ },
2752
+ {
2753
+ "epoch": 0.76,
2754
+ "grad_norm": 0.08458521217107773,
2755
+ "learning_rate": 2.862866979063219e-06,
2756
+ "loss": 1.0279,
2757
+ "step": 388
2758
+ },
2759
+ {
2760
+ "epoch": 0.76,
2761
+ "grad_norm": 0.08274800330400467,
2762
+ "learning_rate": 2.8191725492847923e-06,
2763
+ "loss": 1.0497,
2764
+ "step": 389
2765
+ },
2766
+ {
2767
+ "epoch": 0.76,
2768
+ "grad_norm": 0.0817330926656723,
2769
+ "learning_rate": 2.7757593519269088e-06,
2770
+ "loss": 1.0518,
2771
+ "step": 390
2772
+ },
2773
+ {
2774
+ "epoch": 0.76,
2775
+ "grad_norm": 0.08396860957145691,
2776
+ "learning_rate": 2.732629087239106e-06,
2777
+ "loss": 1.0205,
2778
+ "step": 391
2779
+ },
2780
+ {
2781
+ "epoch": 0.76,
2782
+ "grad_norm": 0.0885666087269783,
2783
+ "learning_rate": 2.689783444390053e-06,
2784
+ "loss": 1.0322,
2785
+ "step": 392
2786
+ },
2787
+ {
2788
+ "epoch": 0.77,
2789
+ "grad_norm": 0.0838237777352333,
2790
+ "learning_rate": 2.647224101401389e-06,
2791
+ "loss": 1.0457,
2792
+ "step": 393
2793
+ },
2794
+ {
2795
+ "epoch": 0.77,
2796
+ "grad_norm": 0.08539842069149017,
2797
+ "learning_rate": 2.604952725082005e-06,
2798
+ "loss": 1.0324,
2799
+ "step": 394
2800
+ },
2801
+ {
2802
+ "epoch": 0.77,
2803
+ "grad_norm": 0.08621538430452347,
2804
+ "learning_rate": 2.562970970962768e-06,
2805
+ "loss": 1.0304,
2806
+ "step": 395
2807
+ },
2808
+ {
2809
+ "epoch": 0.77,
2810
+ "grad_norm": 0.08441948890686035,
2811
+ "learning_rate": 2.5212804832316783e-06,
2812
+ "loss": 1.0347,
2813
+ "step": 396
2814
+ },
2815
+ {
2816
+ "epoch": 0.77,
2817
+ "grad_norm": 0.08076242357492447,
2818
+ "learning_rate": 2.479882894669481e-06,
2819
+ "loss": 1.0287,
2820
+ "step": 397
2821
+ },
2822
+ {
2823
+ "epoch": 0.78,
2824
+ "grad_norm": 0.08226581662893295,
2825
+ "learning_rate": 2.4387798265857078e-06,
2826
+ "loss": 1.0543,
2827
+ "step": 398
2828
+ },
2829
+ {
2830
+ "epoch": 0.78,
2831
+ "grad_norm": 0.08637404441833496,
2832
+ "learning_rate": 2.397972888755197e-06,
2833
+ "loss": 1.0628,
2834
+ "step": 399
2835
+ },
2836
+ {
2837
+ "epoch": 0.78,
2838
+ "grad_norm": 0.086219921708107,
2839
+ "learning_rate": 2.3574636793550376e-06,
2840
+ "loss": 1.0006,
2841
+ "step": 400
2842
+ },
2843
+ {
2844
+ "epoch": 0.78,
2845
+ "grad_norm": 0.08456084877252579,
2846
+ "learning_rate": 2.317253784901976e-06,
2847
+ "loss": 0.9901,
2848
+ "step": 401
2849
+ },
2850
+ {
2851
+ "epoch": 0.78,
2852
+ "grad_norm": 0.08231404423713684,
2853
+ "learning_rate": 2.277344780190286e-06,
2854
+ "loss": 1.0143,
2855
+ "step": 402
2856
+ },
2857
+ {
2858
+ "epoch": 0.79,
2859
+ "grad_norm": 0.0869838073849678,
2860
+ "learning_rate": 2.237738228230091e-06,
2861
+ "loss": 1.0385,
2862
+ "step": 403
2863
+ },
2864
+ {
2865
+ "epoch": 0.79,
2866
+ "grad_norm": 0.0852610394358635,
2867
+ "learning_rate": 2.1984356801861506e-06,
2868
+ "loss": 1.0513,
2869
+ "step": 404
2870
+ },
2871
+ {
2872
+ "epoch": 0.79,
2873
+ "grad_norm": 0.08569534868001938,
2874
+ "learning_rate": 2.1594386753171035e-06,
2875
+ "loss": 1.0364,
2876
+ "step": 405
2877
+ },
2878
+ {
2879
+ "epoch": 0.79,
2880
+ "grad_norm": 0.08554627001285553,
2881
+ "learning_rate": 2.1207487409151984e-06,
2882
+ "loss": 1.0468,
2883
+ "step": 406
2884
+ },
2885
+ {
2886
+ "epoch": 0.79,
2887
+ "grad_norm": 0.08350294083356857,
2888
+ "learning_rate": 2.0823673922464625e-06,
2889
+ "loss": 1.0184,
2890
+ "step": 407
2891
+ },
2892
+ {
2893
+ "epoch": 0.8,
2894
+ "grad_norm": 0.08463279157876968,
2895
+ "learning_rate": 2.044296132491369e-06,
2896
+ "loss": 1.0686,
2897
+ "step": 408
2898
+ },
2899
+ {
2900
+ "epoch": 0.8,
2901
+ "grad_norm": 0.08454636484384537,
2902
+ "learning_rate": 2.0065364526859576e-06,
2903
+ "loss": 1.043,
2904
+ "step": 409
2905
+ },
2906
+ {
2907
+ "epoch": 0.8,
2908
+ "grad_norm": 0.08581449091434479,
2909
+ "learning_rate": 1.969089831663443e-06,
2910
+ "loss": 1.0257,
2911
+ "step": 410
2912
+ },
2913
+ {
2914
+ "epoch": 0.8,
2915
+ "grad_norm": 0.08445479720830917,
2916
+ "learning_rate": 1.931957735996304e-06,
2917
+ "loss": 1.0024,
2918
+ "step": 411
2919
+ },
2920
+ {
2921
+ "epoch": 0.8,
2922
+ "grad_norm": 0.08243846148252487,
2923
+ "learning_rate": 1.895141619938825e-06,
2924
+ "loss": 1.0211,
2925
+ "step": 412
2926
+ },
2927
+ {
2928
+ "epoch": 0.81,
2929
+ "grad_norm": 0.0819249302148819,
2930
+ "learning_rate": 1.8586429253701676e-06,
2931
+ "loss": 1.0421,
2932
+ "step": 413
2933
+ },
2934
+ {
2935
+ "epoch": 0.81,
2936
+ "grad_norm": 0.0827661082148552,
2937
+ "learning_rate": 1.822463081737883e-06,
2938
+ "loss": 1.0343,
2939
+ "step": 414
2940
+ },
2941
+ {
2942
+ "epoch": 0.81,
2943
+ "grad_norm": 0.0872969999909401,
2944
+ "learning_rate": 1.7866035060019338e-06,
2945
+ "loss": 1.0225,
2946
+ "step": 415
2947
+ },
2948
+ {
2949
+ "epoch": 0.81,
2950
+ "grad_norm": 0.08620977401733398,
2951
+ "learning_rate": 1.7510656025792005e-06,
2952
+ "loss": 1.0102,
2953
+ "step": 416
2954
+ },
2955
+ {
2956
+ "epoch": 0.81,
2957
+ "grad_norm": 0.08344931900501251,
2958
+ "learning_rate": 1.7158507632884801e-06,
2959
+ "loss": 1.0812,
2960
+ "step": 417
2961
+ },
2962
+ {
2963
+ "epoch": 0.82,
2964
+ "grad_norm": 0.08682362735271454,
2965
+ "learning_rate": 1.6809603672959618e-06,
2966
+ "loss": 1.091,
2967
+ "step": 418
2968
+ },
2969
+ {
2970
+ "epoch": 0.82,
2971
+ "grad_norm": 0.08464641869068146,
2972
+ "learning_rate": 1.6463957810612408e-06,
2973
+ "loss": 1.042,
2974
+ "step": 419
2975
+ },
2976
+ {
2977
+ "epoch": 0.82,
2978
+ "grad_norm": 0.08458367735147476,
2979
+ "learning_rate": 1.6121583582837773e-06,
2980
+ "loss": 1.0451,
2981
+ "step": 420
2982
+ },
2983
+ {
2984
+ "epoch": 0.82,
2985
+ "grad_norm": 0.08101867139339447,
2986
+ "learning_rate": 1.5782494398498882e-06,
2987
+ "loss": 0.9999,
2988
+ "step": 421
2989
+ },
2990
+ {
2991
+ "epoch": 0.82,
2992
+ "grad_norm": 0.08441881835460663,
2993
+ "learning_rate": 1.5446703537802344e-06,
2994
+ "loss": 1.094,
2995
+ "step": 422
2996
+ },
2997
+ {
2998
+ "epoch": 0.82,
2999
+ "grad_norm": 0.08229435980319977,
3000
+ "learning_rate": 1.5114224151778068e-06,
3001
+ "loss": 1.0322,
3002
+ "step": 423
3003
+ },
3004
+ {
3005
+ "epoch": 0.83,
3006
+ "grad_norm": 0.0848761573433876,
3007
+ "learning_rate": 1.4785069261764184e-06,
3008
+ "loss": 1.051,
3009
+ "step": 424
3010
+ },
3011
+ {
3012
+ "epoch": 0.83,
3013
+ "grad_norm": 0.08010521531105042,
3014
+ "learning_rate": 1.4459251758897153e-06,
3015
+ "loss": 1.0484,
3016
+ "step": 425
3017
+ },
3018
+ {
3019
+ "epoch": 0.83,
3020
+ "grad_norm": 0.08490080386400223,
3021
+ "learning_rate": 1.413678440360684e-06,
3022
+ "loss": 1.0518,
3023
+ "step": 426
3024
+ },
3025
+ {
3026
+ "epoch": 0.83,
3027
+ "grad_norm": 0.08818584680557251,
3028
+ "learning_rate": 1.3817679825116748e-06,
3029
+ "loss": 1.0199,
3030
+ "step": 427
3031
+ },
3032
+ {
3033
+ "epoch": 0.83,
3034
+ "grad_norm": 0.08122722804546356,
3035
+ "learning_rate": 1.3501950520949436e-06,
3036
+ "loss": 1.0309,
3037
+ "step": 428
3038
+ },
3039
+ {
3040
+ "epoch": 0.84,
3041
+ "grad_norm": 0.08668461441993713,
3042
+ "learning_rate": 1.3189608856437053e-06,
3043
+ "loss": 1.0309,
3044
+ "step": 429
3045
+ },
3046
+ {
3047
+ "epoch": 0.84,
3048
+ "grad_norm": 0.08044726401567459,
3049
+ "learning_rate": 1.2880667064237006e-06,
3050
+ "loss": 1.025,
3051
+ "step": 430
3052
+ },
3053
+ {
3054
+ "epoch": 0.84,
3055
+ "grad_norm": 0.08157233893871307,
3056
+ "learning_rate": 1.2575137243852965e-06,
3057
+ "loss": 1.0674,
3058
+ "step": 431
3059
+ },
3060
+ {
3061
+ "epoch": 0.84,
3062
+ "grad_norm": 0.0853031650185585,
3063
+ "learning_rate": 1.2273031361160958e-06,
3064
+ "loss": 1.0461,
3065
+ "step": 432
3066
+ },
3067
+ {
3068
+ "epoch": 0.84,
3069
+ "grad_norm": 0.08920850604772568,
3070
+ "learning_rate": 1.1974361247940702e-06,
3071
+ "loss": 1.0559,
3072
+ "step": 433
3073
+ },
3074
+ {
3075
+ "epoch": 0.85,
3076
+ "grad_norm": 0.08126967400312424,
3077
+ "learning_rate": 1.1679138601412253e-06,
3078
+ "loss": 1.0144,
3079
+ "step": 434
3080
+ },
3081
+ {
3082
+ "epoch": 0.85,
3083
+ "grad_norm": 0.08786173164844513,
3084
+ "learning_rate": 1.1387374983777888e-06,
3085
+ "loss": 1.0611,
3086
+ "step": 435
3087
+ },
3088
+ {
3089
+ "epoch": 0.85,
3090
+ "grad_norm": 0.08111479878425598,
3091
+ "learning_rate": 1.1099081821769297e-06,
3092
+ "loss": 1.0329,
3093
+ "step": 436
3094
+ },
3095
+ {
3096
+ "epoch": 0.85,
3097
+ "grad_norm": 0.08781804144382477,
3098
+ "learning_rate": 1.0814270406199967e-06,
3099
+ "loss": 1.0505,
3100
+ "step": 437
3101
+ },
3102
+ {
3103
+ "epoch": 0.85,
3104
+ "grad_norm": 0.08612725883722305,
3105
+ "learning_rate": 1.0532951891523124e-06,
3106
+ "loss": 1.0203,
3107
+ "step": 438
3108
+ },
3109
+ {
3110
+ "epoch": 0.86,
3111
+ "grad_norm": 0.08277811855077744,
3112
+ "learning_rate": 1.0255137295394813e-06,
3113
+ "loss": 1.033,
3114
+ "step": 439
3115
+ },
3116
+ {
3117
+ "epoch": 0.86,
3118
+ "grad_norm": 0.0849086195230484,
3119
+ "learning_rate": 9.980837498242357e-07,
3120
+ "loss": 1.0127,
3121
+ "step": 440
3122
+ },
3123
+ {
3124
+ "epoch": 0.86,
3125
+ "grad_norm": 0.08069565892219543,
3126
+ "learning_rate": 9.710063242838286e-07,
3127
+ "loss": 1.0368,
3128
+ "step": 441
3129
+ },
3130
+ {
3131
+ "epoch": 0.86,
3132
+ "grad_norm": 0.08577218651771545,
3133
+ "learning_rate": 9.442825133879608e-07,
3134
+ "loss": 1.03,
3135
+ "step": 442
3136
+ },
3137
+ {
3138
+ "epoch": 0.86,
3139
+ "grad_norm": 0.08074500411748886,
3140
+ "learning_rate": 9.179133637572457e-07,
3141
+ "loss": 1.0344,
3142
+ "step": 443
3143
+ },
3144
+ {
3145
+ "epoch": 0.87,
3146
+ "grad_norm": 0.08309192210435867,
3147
+ "learning_rate": 8.918999081222157e-07,
3148
+ "loss": 1.0128,
3149
+ "step": 444
3150
+ },
3151
+ {
3152
+ "epoch": 0.87,
3153
+ "grad_norm": 0.08286837488412857,
3154
+ "learning_rate": 8.66243165282884e-07,
3155
+ "loss": 1.0241,
3156
+ "step": 445
3157
+ },
3158
+ {
3159
+ "epoch": 0.87,
3160
+ "grad_norm": 0.0842629224061966,
3161
+ "learning_rate": 8.409441400688401e-07,
3162
+ "loss": 1.0243,
3163
+ "step": 446
3164
+ },
3165
+ {
3166
+ "epoch": 0.87,
3167
+ "grad_norm": 0.07928766310214996,
3168
+ "learning_rate": 8.160038232998935e-07,
3169
+ "loss": 1.0177,
3170
+ "step": 447
3171
+ },
3172
+ {
3173
+ "epoch": 0.87,
3174
+ "grad_norm": 0.08503233641386032,
3175
+ "learning_rate": 7.914231917472748e-07,
3176
+ "loss": 0.999,
3177
+ "step": 448
3178
+ },
3179
+ {
3180
+ "epoch": 0.88,
3181
+ "grad_norm": 0.08141094446182251,
3182
+ "learning_rate": 7.672032080953751e-07,
3183
+ "loss": 1.0414,
3184
+ "step": 449
3185
+ },
3186
+ {
3187
+ "epoch": 0.88,
3188
+ "grad_norm": 0.08452077209949493,
3189
+ "learning_rate": 7.433448209040495e-07,
3190
+ "loss": 1.0363,
3191
+ "step": 450
3192
+ },
3193
+ {
3194
+ "epoch": 0.88,
3195
+ "grad_norm": 0.08524196594953537,
3196
+ "learning_rate": 7.198489645714579e-07,
3197
+ "loss": 1.0299,
3198
+ "step": 451
3199
+ },
3200
+ {
3201
+ "epoch": 0.88,
3202
+ "grad_norm": 0.08539626747369766,
3203
+ "learning_rate": 6.96716559297479e-07,
3204
+ "loss": 1.0349,
3205
+ "step": 452
3206
+ },
3207
+ {
3208
+ "epoch": 0.88,
3209
+ "grad_norm": 0.08527474850416183,
3210
+ "learning_rate": 6.739485110476707e-07,
3211
+ "loss": 1.0227,
3212
+ "step": 453
3213
+ },
3214
+ {
3215
+ "epoch": 0.89,
3216
+ "grad_norm": 0.08794491738080978,
3217
+ "learning_rate": 6.515457115177804e-07,
3218
+ "loss": 1.0193,
3219
+ "step": 454
3220
+ },
3221
+ {
3222
+ "epoch": 0.89,
3223
+ "grad_norm": 0.08151602745056152,
3224
+ "learning_rate": 6.295090380988323e-07,
3225
+ "loss": 1.0322,
3226
+ "step": 455
3227
+ },
3228
+ {
3229
+ "epoch": 0.89,
3230
+ "grad_norm": 0.08208628743886948,
3231
+ "learning_rate": 6.078393538427574e-07,
3232
+ "loss": 1.0048,
3233
+ "step": 456
3234
+ },
3235
+ {
3236
+ "epoch": 0.89,
3237
+ "grad_norm": 0.08371996879577637,
3238
+ "learning_rate": 5.865375074286006e-07,
3239
+ "loss": 1.0268,
3240
+ "step": 457
3241
+ },
3242
+ {
3243
+ "epoch": 0.89,
3244
+ "grad_norm": 0.08067172765731812,
3245
+ "learning_rate": 5.656043331292682e-07,
3246
+ "loss": 1.0198,
3247
+ "step": 458
3248
+ },
3249
+ {
3250
+ "epoch": 0.9,
3251
+ "grad_norm": 0.08308243006467819,
3252
+ "learning_rate": 5.45040650778873e-07,
3253
+ "loss": 1.0508,
3254
+ "step": 459
3255
+ },
3256
+ {
3257
+ "epoch": 0.9,
3258
+ "grad_norm": 0.08296984434127808,
3259
+ "learning_rate": 5.248472657406123e-07,
3260
+ "loss": 1.038,
3261
+ "step": 460
3262
+ },
3263
+ {
3264
+ "epoch": 0.9,
3265
+ "grad_norm": 0.08200722932815552,
3266
+ "learning_rate": 5.050249688752329e-07,
3267
+ "loss": 1.0326,
3268
+ "step": 461
3269
+ },
3270
+ {
3271
+ "epoch": 0.9,
3272
+ "grad_norm": 0.08149310201406479,
3273
+ "learning_rate": 4.855745365100539e-07,
3274
+ "loss": 1.0299,
3275
+ "step": 462
3276
+ },
3277
+ {
3278
+ "epoch": 0.9,
3279
+ "grad_norm": 0.0821991041302681,
3280
+ "learning_rate": 4.664967304085655e-07,
3281
+ "loss": 1.0455,
3282
+ "step": 463
3283
+ },
3284
+ {
3285
+ "epoch": 0.9,
3286
+ "grad_norm": 0.08251185715198517,
3287
+ "learning_rate": 4.477922977405913e-07,
3288
+ "loss": 1.0434,
3289
+ "step": 464
3290
+ },
3291
+ {
3292
+ "epoch": 0.91,
3293
+ "grad_norm": 0.08696113526821136,
3294
+ "learning_rate": 4.29461971053029e-07,
3295
+ "loss": 1.0123,
3296
+ "step": 465
3297
+ },
3298
+ {
3299
+ "epoch": 0.91,
3300
+ "grad_norm": 0.08152768760919571,
3301
+ "learning_rate": 4.115064682411607e-07,
3302
+ "loss": 0.9981,
3303
+ "step": 466
3304
+ },
3305
+ {
3306
+ "epoch": 0.91,
3307
+ "grad_norm": 0.08121586591005325,
3308
+ "learning_rate": 3.939264925205355e-07,
3309
+ "loss": 1.0169,
3310
+ "step": 467
3311
+ },
3312
+ {
3313
+ "epoch": 0.91,
3314
+ "grad_norm": 0.08272110670804977,
3315
+ "learning_rate": 3.7672273239942936e-07,
3316
+ "loss": 1.0872,
3317
+ "step": 468
3318
+ },
3319
+ {
3320
+ "epoch": 0.91,
3321
+ "grad_norm": 0.08001048117876053,
3322
+ "learning_rate": 3.5989586165187884e-07,
3323
+ "loss": 1.0012,
3324
+ "step": 469
3325
+ },
3326
+ {
3327
+ "epoch": 0.92,
3328
+ "grad_norm": 0.08298242092132568,
3329
+ "learning_rate": 3.4344653929129554e-07,
3330
+ "loss": 1.0136,
3331
+ "step": 470
3332
+ },
3333
+ {
3334
+ "epoch": 0.92,
3335
+ "grad_norm": 0.0829276293516159,
3336
+ "learning_rate": 3.2737540954465244e-07,
3337
+ "loss": 1.0279,
3338
+ "step": 471
3339
+ },
3340
+ {
3341
+ "epoch": 0.92,
3342
+ "grad_norm": 0.0854070633649826,
3343
+ "learning_rate": 3.1168310182725814e-07,
3344
+ "loss": 1.0709,
3345
+ "step": 472
3346
+ },
3347
+ {
3348
+ "epoch": 0.92,
3349
+ "grad_norm": 0.08476186543703079,
3350
+ "learning_rate": 2.9637023071810155e-07,
3351
+ "loss": 1.0499,
3352
+ "step": 473
3353
+ },
3354
+ {
3355
+ "epoch": 0.92,
3356
+ "grad_norm": 0.08046039938926697,
3357
+ "learning_rate": 2.8143739593578854e-07,
3358
+ "loss": 1.0322,
3359
+ "step": 474
3360
+ },
3361
+ {
3362
+ "epoch": 0.93,
3363
+ "grad_norm": 0.08418085426092148,
3364
+ "learning_rate": 2.6688518231504535e-07,
3365
+ "loss": 1.0202,
3366
+ "step": 475
3367
+ },
3368
+ {
3369
+ "epoch": 0.93,
3370
+ "grad_norm": 0.08194521069526672,
3371
+ "learning_rate": 2.527141597838212e-07,
3372
+ "loss": 1.0059,
3373
+ "step": 476
3374
+ },
3375
+ {
3376
+ "epoch": 0.93,
3377
+ "grad_norm": 0.08417163044214249,
3378
+ "learning_rate": 2.389248833409663e-07,
3379
+ "loss": 1.0563,
3380
+ "step": 477
3381
+ },
3382
+ {
3383
+ "epoch": 0.93,
3384
+ "grad_norm": 0.08419531583786011,
3385
+ "learning_rate": 2.2551789303449034e-07,
3386
+ "loss": 1.0099,
3387
+ "step": 478
3388
+ },
3389
+ {
3390
+ "epoch": 0.93,
3391
+ "grad_norm": 0.08371371775865555,
3392
+ "learning_rate": 2.124937139404204e-07,
3393
+ "loss": 1.0209,
3394
+ "step": 479
3395
+ },
3396
+ {
3397
+ "epoch": 0.94,
3398
+ "grad_norm": 0.08230051398277283,
3399
+ "learning_rate": 1.998528561422297e-07,
3400
+ "loss": 1.0551,
3401
+ "step": 480
3402
+ },
3403
+ {
3404
+ "epoch": 0.94,
3405
+ "grad_norm": 0.08176656812429428,
3406
+ "learning_rate": 1.8759581471086363e-07,
3407
+ "loss": 1.0296,
3408
+ "step": 481
3409
+ },
3410
+ {
3411
+ "epoch": 0.94,
3412
+ "grad_norm": 0.08562692999839783,
3413
+ "learning_rate": 1.757230696853518e-07,
3414
+ "loss": 1.0499,
3415
+ "step": 482
3416
+ },
3417
+ {
3418
+ "epoch": 0.94,
3419
+ "grad_norm": 0.08376387506723404,
3420
+ "learning_rate": 1.6423508605400318e-07,
3421
+ "loss": 1.04,
3422
+ "step": 483
3423
+ },
3424
+ {
3425
+ "epoch": 0.94,
3426
+ "grad_norm": 0.08506414294242859,
3427
+ "learning_rate": 1.5313231373619953e-07,
3428
+ "loss": 1.0253,
3429
+ "step": 484
3430
+ },
3431
+ {
3432
+ "epoch": 0.95,
3433
+ "grad_norm": 0.08413960039615631,
3434
+ "learning_rate": 1.424151875647717e-07,
3435
+ "loss": 1.021,
3436
+ "step": 485
3437
+ },
3438
+ {
3439
+ "epoch": 0.95,
3440
+ "grad_norm": 0.08077908307313919,
3441
+ "learning_rate": 1.3208412726897324e-07,
3442
+ "loss": 1.0217,
3443
+ "step": 486
3444
+ },
3445
+ {
3446
+ "epoch": 0.95,
3447
+ "grad_norm": 0.08394316583871841,
3448
+ "learning_rate": 1.2213953745803587e-07,
3449
+ "loss": 0.9818,
3450
+ "step": 487
3451
+ },
3452
+ {
3453
+ "epoch": 0.95,
3454
+ "grad_norm": 0.08442597091197968,
3455
+ "learning_rate": 1.1258180760533089e-07,
3456
+ "loss": 1.0122,
3457
+ "step": 488
3458
+ },
3459
+ {
3460
+ "epoch": 0.95,
3461
+ "grad_norm": 0.08355535566806793,
3462
+ "learning_rate": 1.0341131203311039e-07,
3463
+ "loss": 1.0422,
3464
+ "step": 489
3465
+ },
3466
+ {
3467
+ "epoch": 0.96,
3468
+ "grad_norm": 0.08156078308820724,
3469
+ "learning_rate": 9.462840989784671e-08,
3470
+ "loss": 1.0425,
3471
+ "step": 490
3472
+ },
3473
+ {
3474
+ "epoch": 0.96,
3475
+ "grad_norm": 0.08547282218933105,
3476
+ "learning_rate": 8.62334451761715e-08,
3477
+ "loss": 1.0479,
3478
+ "step": 491
3479
+ },
3480
+ {
3481
+ "epoch": 0.96,
3482
+ "grad_norm": 0.08260347694158554,
3483
+ "learning_rate": 7.822674665139751e-08,
3484
+ "loss": 1.0144,
3485
+ "step": 492
3486
+ },
3487
+ {
3488
+ "epoch": 0.96,
3489
+ "grad_norm": 0.08177413791418076,
3490
+ "learning_rate": 7.060862790064793e-08,
3491
+ "loss": 1.0365,
3492
+ "step": 493
3493
+ },
3494
+ {
3495
+ "epoch": 0.96,
3496
+ "grad_norm": 0.08669156581163406,
3497
+ "learning_rate": 6.337938728257054e-08,
3498
+ "loss": 1.0332,
3499
+ "step": 494
3500
+ },
3501
+ {
3502
+ "epoch": 0.97,
3503
+ "grad_norm": 0.08690541237592697,
3504
+ "learning_rate": 5.653930792565821e-08,
3505
+ "loss": 1.0179,
3506
+ "step": 495
3507
+ },
3508
+ {
3509
+ "epoch": 0.97,
3510
+ "grad_norm": 0.085110604763031,
3511
+ "learning_rate": 5.008865771715221e-08,
3512
+ "loss": 1.0572,
3513
+ "step": 496
3514
+ },
3515
+ {
3516
+ "epoch": 0.97,
3517
+ "grad_norm": 0.08295170217752457,
3518
+ "learning_rate": 4.4027689292560626e-08,
3519
+ "loss": 1.0266,
3520
+ "step": 497
3521
+ },
3522
+ {
3523
+ "epoch": 0.97,
3524
+ "grad_norm": 0.07970304042100906,
3525
+ "learning_rate": 3.83566400257529e-08,
3526
+ "loss": 1.0388,
3527
+ "step": 498
3528
+ },
3529
+ {
3530
+ "epoch": 0.97,
3531
+ "grad_norm": 0.08482901751995087,
3532
+ "learning_rate": 3.3075732019675065e-08,
3533
+ "loss": 1.0551,
3534
+ "step": 499
3535
+ },
3536
+ {
3537
+ "epoch": 0.97,
3538
+ "grad_norm": 0.0838318020105362,
3539
+ "learning_rate": 2.8185172097641156e-08,
3540
+ "loss": 1.075,
3541
+ "step": 500
3542
+ },
3543
+ {
3544
+ "epoch": 0.98,
3545
+ "grad_norm": 0.08117860555648804,
3546
+ "learning_rate": 2.368515179523967e-08,
3547
+ "loss": 1.0418,
3548
+ "step": 501
3549
+ },
3550
+ {
3551
+ "epoch": 0.98,
3552
+ "grad_norm": 0.08278267085552216,
3553
+ "learning_rate": 1.957584735282847e-08,
3554
+ "loss": 1.0176,
3555
+ "step": 502
3556
+ },
3557
+ {
3558
+ "epoch": 0.98,
3559
+ "grad_norm": 0.08319726586341858,
3560
+ "learning_rate": 1.5857419708633636e-08,
3561
+ "loss": 1.0229,
3562
+ "step": 503
3563
+ },
3564
+ {
3565
+ "epoch": 0.98,
3566
+ "grad_norm": 0.08518896996974945,
3567
+ "learning_rate": 1.253001449244673e-08,
3568
+ "loss": 1.0313,
3569
+ "step": 504
3570
+ },
3571
+ {
3572
+ "epoch": 0.98,
3573
+ "grad_norm": 0.08542507141828537,
3574
+ "learning_rate": 9.593762019922681e-09,
3575
+ "loss": 1.0703,
3576
+ "step": 505
3577
+ },
3578
+ {
3579
+ "epoch": 0.99,
3580
+ "grad_norm": 0.08333377540111542,
3581
+ "learning_rate": 7.048777287472774e-09,
3582
+ "loss": 1.0058,
3583
+ "step": 506
3584
+ },
3585
+ {
3586
+ "epoch": 0.99,
3587
+ "grad_norm": 0.09070394933223724,
3588
+ "learning_rate": 4.895159967762686e-09,
3589
+ "loss": 1.0059,
3590
+ "step": 507
3591
+ },
3592
+ {
3593
+ "epoch": 0.99,
3594
+ "grad_norm": 0.0817839726805687,
3595
+ "learning_rate": 3.132994405808942e-09,
3596
+ "loss": 1.0301,
3597
+ "step": 508
3598
+ },
3599
+ {
3600
+ "epoch": 0.99,
3601
+ "grad_norm": 0.08134960383176804,
3602
+ "learning_rate": 1.7623496156771169e-09,
3603
+ "loss": 1.0419,
3604
+ "step": 509
3605
+ },
3606
+ {
3607
+ "epoch": 0.99,
3608
+ "grad_norm": 0.08472370356321335,
3609
+ "learning_rate": 7.832792777739962e-10,
3610
+ "loss": 1.0253,
3611
+ "step": 510
3612
+ },
3613
+ {
3614
+ "epoch": 1.0,
3615
+ "grad_norm": 0.08445168286561966,
3616
+ "learning_rate": 1.958217367514781e-10,
3617
+ "loss": 1.0475,
3618
+ "step": 511
3619
+ },
3620
+ {
3621
+ "epoch": 1.0,
3622
+ "grad_norm": 0.08768552541732788,
3623
+ "learning_rate": 0.0,
3624
+ "loss": 1.0703,
3625
+ "step": 512
3626
+ },
3627
+ {
3628
+ "epoch": 1.0,
3629
+ "eval_loss": 1.0364834070205688,
3630
+ "eval_runtime": 707.9527,
3631
+ "eval_samples_per_second": 7.167,
3632
+ "eval_steps_per_second": 1.792,
3633
+ "step": 512
3634
+ }
3635
+ ],
3636
+ "logging_steps": 1,
3637
+ "max_steps": 512,
3638
+ "num_input_tokens_seen": 0,
3639
+ "num_train_epochs": 1,
3640
+ "save_steps": 256,
3641
+ "total_flos": 4.525540736237568e+18,
3642
+ "train_batch_size": 4,
3643
+ "trial_name": null,
3644
+ "trial_params": null
3645
+ }
checkpoint-512/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2e26a4066417fbc5c36d2c392e7d37169c1c77e260f1ed05adfc5096066476
3
+ size 5307
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "quantization_config": {
21
+ "_load_in_4bit": false,
22
+ "_load_in_8bit": true,
23
+ "bnb_4bit_compute_dtype": "float32",
24
+ "bnb_4bit_quant_storage": "uint8",
25
+ "bnb_4bit_quant_type": "fp4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": false,
32
+ "load_in_8bit": true,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-05,
36
+ "rope_scaling": null,
37
+ "rope_theta": 500000.0,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.40.0.dev0",
41
+ "use_cache": false,
42
+ "vocab_size": 128256
43
+ }
merged/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 500000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.0.dev0",
26
+ "use_cache": false,
27
+ "vocab_size": 128256
28
+ }
merged/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 128001,
7
+ 128009
8
+ ],
9
+ "transformers_version": "4.40.0.dev0"
10
+ }
merged/pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a9cee455f4bdd041095ad171a4d01343e9855a4a646309fa299740bacf39083
3
+ size 4976716827
merged/pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c78ceff58914eb77816968ecf8a1151fce1df27d92e87c804af4236cb5ccfdd
3
+ size 4999825759
merged/pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c21977576baf3e878f9cdc669a1c4bd9acb61ffc6f8870b4ea1b828ed3b46c
3
+ size 4915938275
merged/pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c39822b9554e50c5580380b603d0e58dcc2c3d9eea8ee512acc7cbe9a3bac38
3
+ size 1168140398
merged/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
296
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
297
+ }
298
+ }
merged/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
merged/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
merged/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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ 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|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ 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|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }