Hugging Face's logo

kloodia
/
llama-8x8-qlora-alpaca

PEFT
TensorBoard
Safetensors
mixtral
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Metrics Community
kloodia commited on
Commit
1432f52
•
1 Parent(s): 4e3b679

Upload folder using huggingface_hub

Browse files
Files changed (45) hide show
  1. README.md +133 -0
  2. adapter_config.json +35 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-155/README.md +202 -0
  5. checkpoint-155/adapter_config.json +35 -0
  6. checkpoint-155/adapter_model.safetensors +3 -0
  7. checkpoint-155/optimizer.pt +3 -0
  8. checkpoint-155/rng_state.pth +3 -0
  9. checkpoint-155/scheduler.pt +3 -0
  10. checkpoint-155/special_tokens_map.json +23 -0
  11. checkpoint-155/tokenizer.json +0 -0
  12. checkpoint-155/tokenizer_config.json +2062 -0
  13. checkpoint-155/trainer_state.json +1106 -0
  14. checkpoint-155/training_args.bin +3 -0
  15. checkpoint-310/README.md +202 -0
  16. checkpoint-310/adapter_config.json +35 -0
  17. checkpoint-310/adapter_model.safetensors +3 -0
  18. checkpoint-310/optimizer.pt +3 -0
  19. checkpoint-310/rng_state.pth +3 -0
  20. checkpoint-310/scheduler.pt +3 -0
  21. checkpoint-310/special_tokens_map.json +23 -0
  22. checkpoint-310/tokenizer.json +0 -0
  23. checkpoint-310/tokenizer_config.json +2062 -0
  24. checkpoint-310/trainer_state.json +2191 -0
  25. checkpoint-310/training_args.bin +3 -0
  26. checkpoint-465/README.md +202 -0
  27. checkpoint-465/adapter_config.json +35 -0
  28. checkpoint-465/adapter_model.safetensors +3 -0
  29. checkpoint-465/optimizer.pt +3 -0
  30. checkpoint-465/rng_state.pth +3 -0
  31. checkpoint-465/scheduler.pt +3 -0
  32. checkpoint-465/special_tokens_map.json +23 -0
  33. checkpoint-465/tokenizer.json +0 -0
  34. checkpoint-465/tokenizer_config.json +2062 -0
  35. checkpoint-465/trainer_state.json +3276 -0
  36. checkpoint-465/training_args.bin +3 -0
  37. config.json +49 -0
  38. runs/Apr30_23-43-06_1bcd8aeb2316/events.out.tfevents.1714520588.1bcd8aeb2316.582.0 +3 -0
  39. runs/May01_00-06-11_a5f9ef2b4afc/events.out.tfevents.1714521973.a5f9ef2b4afc.223.0 +3 -0
  40. runs/May01_00-12-38_a5f9ef2b4afc/events.out.tfevents.1714522359.a5f9ef2b4afc.699.0 +3 -0
  41. runs/May01_00-19-09_a5f9ef2b4afc/events.out.tfevents.1714522750.a5f9ef2b4afc.880.0 +3 -0
  42. runs/May01_00-22-54_a5f9ef2b4afc/events.out.tfevents.1714522975.a5f9ef2b4afc.1030.0 +3 -0
  43. special_tokens_map.json +23 -0
  44. tokenizer.json +0 -0
  45. tokenizer_config.json +2062 -0
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: kloodia/llama8
6
+ model-index:
7
+ - name: qlora-out
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ [<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)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.4.0`
18
+ ```yaml
19
+ base_model: kloodia/llama8
20
+ model_type: AutoModelForCausalLM
21
+ tokenizer_type: AutoTokenizer
22
+
23
+ load_in_8bit: false
24
+ load_in_4bit: true
25
+ strict: false
26
+
27
+ datasets:
28
+ - path: yahma/alpaca-cleaned
29
+ type: alpaca
30
+ dataset_prepared_path:
31
+ val_set_size: 0
32
+ output_dir: ./qlora-out
33
+
34
+ adapter: qlora
35
+ lora_model_dir:
36
+
37
+ sequence_len: 4096
38
+ sample_packing: true
39
+ pad_to_sequence_len: true
40
+
41
+ lora_r: 32
42
+ lora_alpha: 16
43
+ lora_dropout: 0.05
44
+ lora_target_modules:
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project:
49
+ wandb_entity:
50
+ wandb_watch:
51
+ wandb_name:
52
+ wandb_log_model:
53
+
54
+ gradient_accumulation_steps: 3
55
+ micro_batch_size: 5
56
+ num_epochs: 3
57
+ optimizer: paged_adamw_32bit
58
+ lr_scheduler: cosine
59
+ learning_rate: 0.0002
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
+
75
+ warmup_steps: 10
76
+ evals_per_epoch: 4
77
+ eval_table_size:
78
+ saves_per_epoch: 1
79
+ debug:
80
+ deepspeed:
81
+ weight_decay: 0.0
82
+ fsdp:
83
+ fsdp_config:
84
+ special_tokens:
85
+ pad_token: "<|end_of_text|>"
86
+
87
+ ```
88
+
89
+ </details><br>
90
+
91
+ # qlora-out
92
+
93
+ This model is a fine-tuned version of [kloodia/llama8](https://huggingface.co/kloodia/llama8) on the None dataset.
94
+
95
+ ## Model description
96
+
97
+ More information needed
98
+
99
+ ## Intended uses & limitations
100
+
101
+ More information needed
102
+
103
+ ## Training and evaluation data
104
+
105
+ More information needed
106
+
107
+ ## Training procedure
108
+
109
+ ### Training hyperparameters
110
+
111
+ The following hyperparameters were used during training:
112
+ - learning_rate: 0.0002
113
+ - train_batch_size: 5
114
+ - eval_batch_size: 5
115
+ - seed: 42
116
+ - gradient_accumulation_steps: 3
117
+ - total_train_batch_size: 15
118
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
119
+ - lr_scheduler_type: cosine
120
+ - lr_scheduler_warmup_steps: 10
121
+ - num_epochs: 3
122
+
123
+ ### Training results
124
+
125
+
126
+
127
+ ### Framework versions
128
+
129
+ - PEFT 0.10.0
130
+ - Transformers 4.40.0.dev0
131
+ - Pytorch 2.1.2+cu118
132
+ - Datasets 2.15.0
133
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "kloodia/llama8",
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": 16,
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": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "gate",
25
+ "k_proj",
26
+ "w3",
27
+ "v_proj",
28
+ "w1",
29
+ "w2",
30
+ "q_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86460c7534ea7c070b9a52059a0705310ea17d8c246264556129379cee050e2
3
+ size 1204647330
checkpoint-155/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: kloodia/llama8
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-155/adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "kloodia/llama8",
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": 16,
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": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "gate",
25
+ "k_proj",
26
+ "w3",
27
+ "v_proj",
28
+ "w1",
29
+ "w2",
30
+ "q_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
checkpoint-155/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45508d9f091b27adce6bdb6c8a4da3f6a470756039604ebba42f189b06010739
3
+ size 1204141024
checkpoint-155/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f7a68aef99fcd24212de8b704f3bf8510d3e151c794fe5d9b76076e20c1b7c8
3
+ size 4782984698
checkpoint-155/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f092299df3fa8529d364e61bcaf429bd194f61b778972c3550d6e3156c9be90
3
+ size 14244
checkpoint-155/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a4fca79f3d8eaf30a60873b6a196e35b8da28a01b4ea00c82514527b68a4c6
3
+ size 1064
checkpoint-155/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-155/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-155/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-155/trainer_state.json ADDED
@@ -0,0 +1,1106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9957173447537473,
5
+ "eval_steps": 500,
6
+ "global_step": 155,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.15481117367744446,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.1213,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.16627414524555206,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.1341,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "grad_norm": 0.14720524847507477,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.148,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03,
34
+ "grad_norm": 0.15325099229812622,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.1435,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "grad_norm": 0.16704852879047394,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.0895,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "grad_norm": 0.11686641722917557,
49
+ "learning_rate": 0.00012,
50
+ "loss": 1.0784,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 0.09641632437705994,
56
+ "learning_rate": 0.00014,
57
+ "loss": 1.0612,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.05,
62
+ "grad_norm": 0.12384118884801865,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.0566,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "grad_norm": 0.07287071645259857,
70
+ "learning_rate": 0.00018,
71
+ "loss": 1.0442,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.06,
76
+ "grad_norm": 0.07469318807125092,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.0083,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.07,
83
+ "grad_norm": 0.08364757895469666,
84
+ "learning_rate": 0.00019999761633493753,
85
+ "loss": 1.0169,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "grad_norm": 0.07763934135437012,
91
+ "learning_rate": 0.0001999904654533872,
92
+ "loss": 1.0348,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "grad_norm": 0.06744416803121567,
98
+ "learning_rate": 0.0001999785476962552,
99
+ "loss": 1.0123,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.09,
104
+ "grad_norm": 0.07724820077419281,
105
+ "learning_rate": 0.00019996186363170035,
106
+ "loss": 1.0188,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "grad_norm": 0.0746370479464531,
112
+ "learning_rate": 0.00019994041405510705,
113
+ "loss": 1.0164,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.1,
118
+ "grad_norm": 0.055804282426834106,
119
+ "learning_rate": 0.00019991419998904747,
120
+ "loss": 1.0587,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.11,
125
+ "grad_norm": 0.054163169115781784,
126
+ "learning_rate": 0.00019988322268323268,
127
+ "loss": 1.0149,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.12,
132
+ "grad_norm": 0.05897677689790726,
133
+ "learning_rate": 0.00019984748361445308,
134
+ "loss": 1.0136,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "grad_norm": 0.05603804066777229,
140
+ "learning_rate": 0.00019980698448650804,
141
+ "loss": 0.9996,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.13,
146
+ "grad_norm": 0.06250110268592834,
147
+ "learning_rate": 0.0001997617272301248,
148
+ "loss": 1.0145,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.13,
153
+ "grad_norm": 0.05678323656320572,
154
+ "learning_rate": 0.000199711714002866,
155
+ "loss": 1.0005,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.14,
160
+ "grad_norm": 0.05278163403272629,
161
+ "learning_rate": 0.00019965694718902745,
162
+ "loss": 1.0034,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.15,
167
+ "grad_norm": 0.05601625144481659,
168
+ "learning_rate": 0.00019959742939952392,
169
+ "loss": 0.9915,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "grad_norm": 0.054547134786844254,
175
+ "learning_rate": 0.00019953316347176488,
176
+ "loss": 1.0115,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "grad_norm": 0.06417939066886902,
182
+ "learning_rate": 0.0001994641524695193,
183
+ "loss": 0.9862,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.17,
188
+ "grad_norm": 0.061326365917921066,
189
+ "learning_rate": 0.0001993903996827694,
190
+ "loss": 0.9889,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.17,
195
+ "grad_norm": 0.05376205965876579,
196
+ "learning_rate": 0.00019931190862755417,
197
+ "loss": 0.9604,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.18,
202
+ "grad_norm": 0.0678999274969101,
203
+ "learning_rate": 0.00019922868304580118,
204
+ "loss": 1.0492,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.19,
209
+ "grad_norm": 0.053755760192871094,
210
+ "learning_rate": 0.0001991407269051487,
211
+ "loss": 0.9985,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "grad_norm": 0.05401955544948578,
217
+ "learning_rate": 0.00019904804439875633,
218
+ "loss": 0.9787,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "grad_norm": 0.05666874349117279,
224
+ "learning_rate": 0.0001989506399451051,
225
+ "loss": 0.9886,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.21,
230
+ "grad_norm": 0.05425805598497391,
231
+ "learning_rate": 0.00019884851818778693,
232
+ "loss": 1.0197,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.21,
237
+ "grad_norm": 0.06086369976401329,
238
+ "learning_rate": 0.00019874168399528305,
239
+ "loss": 0.9879,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.22,
244
+ "grad_norm": 0.05577366426587105,
245
+ "learning_rate": 0.00019863014246073214,
246
+ "loss": 0.9808,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.22,
251
+ "grad_norm": 0.05853752791881561,
252
+ "learning_rate": 0.0001985138989016874,
253
+ "loss": 0.957,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.23,
258
+ "grad_norm": 0.0582735501229763,
259
+ "learning_rate": 0.00019839295885986296,
260
+ "loss": 0.9732,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "grad_norm": 0.07255622744560242,
266
+ "learning_rate": 0.00019826732810086998,
267
+ "loss": 1.0199,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.24,
272
+ "grad_norm": 0.06085599586367607,
273
+ "learning_rate": 0.00019813701261394136,
274
+ "loss": 0.9946,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.25,
279
+ "grad_norm": 0.06600817292928696,
280
+ "learning_rate": 0.00019800201861164664,
281
+ "loss": 0.9646,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.26,
286
+ "grad_norm": 0.0634196326136589,
287
+ "learning_rate": 0.00019786235252959553,
288
+ "loss": 1.0092,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.26,
293
+ "grad_norm": 0.05254920944571495,
294
+ "learning_rate": 0.00019771802102613127,
295
+ "loss": 0.9535,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.27,
300
+ "grad_norm": 0.06008182466030121,
301
+ "learning_rate": 0.00019756903098201308,
302
+ "loss": 0.9897,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "grad_norm": 0.07715290039777756,
308
+ "learning_rate": 0.00019741538950008818,
309
+ "loss": 1.0132,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.28,
314
+ "grad_norm": 0.06104297190904617,
315
+ "learning_rate": 0.0001972571039049533,
316
+ "loss": 0.9938,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.29,
321
+ "grad_norm": 0.06008582562208176,
322
+ "learning_rate": 0.0001970941817426052,
323
+ "loss": 0.9889,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.3,
328
+ "grad_norm": 0.05699775367975235,
329
+ "learning_rate": 0.00019692663078008132,
330
+ "loss": 0.9843,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.3,
335
+ "grad_norm": 0.05760645866394043,
336
+ "learning_rate": 0.00019675445900508909,
337
+ "loss": 0.9677,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.31,
342
+ "grad_norm": 0.06075143814086914,
343
+ "learning_rate": 0.00019657767462562544,
344
+ "loss": 0.9929,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.31,
349
+ "grad_norm": 0.059820640832185745,
350
+ "learning_rate": 0.00019639628606958533,
351
+ "loss": 0.9889,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.32,
356
+ "grad_norm": 0.059315863996744156,
357
+ "learning_rate": 0.00019621030198436006,
358
+ "loss": 0.9994,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.33,
363
+ "grad_norm": 0.05949851870536804,
364
+ "learning_rate": 0.00019601973123642492,
365
+ "loss": 0.9593,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.33,
370
+ "grad_norm": 0.06036762520670891,
371
+ "learning_rate": 0.00019582458291091663,
372
+ "loss": 0.9669,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.34,
377
+ "grad_norm": 0.05799931660294533,
378
+ "learning_rate": 0.00019562486631120006,
379
+ "loss": 0.9731,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.35,
384
+ "grad_norm": 0.05733400583267212,
385
+ "learning_rate": 0.00019542059095842485,
386
+ "loss": 0.9676,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.35,
391
+ "grad_norm": 0.06894834339618683,
392
+ "learning_rate": 0.00019521176659107142,
393
+ "loss": 1.0142,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.36,
398
+ "grad_norm": 0.0657154992222786,
399
+ "learning_rate": 0.00019499840316448673,
400
+ "loss": 0.9598,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.37,
405
+ "grad_norm": 0.0570225715637207,
406
+ "learning_rate": 0.00019478051085040975,
407
+ "loss": 0.9979,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.37,
412
+ "grad_norm": 0.06271913647651672,
413
+ "learning_rate": 0.00019455810003648637,
414
+ "loss": 0.9694,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.38,
419
+ "grad_norm": 0.05831892415881157,
420
+ "learning_rate": 0.0001943311813257743,
421
+ "loss": 0.9934,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.39,
426
+ "grad_norm": 0.061948519200086594,
427
+ "learning_rate": 0.00019409976553623766,
428
+ "loss": 0.9812,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.39,
433
+ "grad_norm": 0.06726415455341339,
434
+ "learning_rate": 0.00019386386370023103,
435
+ "loss": 0.9837,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.4,
440
+ "grad_norm": 0.057408351451158524,
441
+ "learning_rate": 0.00019362348706397373,
442
+ "loss": 0.9512,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.4,
447
+ "grad_norm": 0.057638928294181824,
448
+ "learning_rate": 0.00019337864708701357,
449
+ "loss": 0.9622,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.41,
454
+ "grad_norm": 0.06090644374489784,
455
+ "learning_rate": 0.00019312935544168048,
456
+ "loss": 0.9927,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.42,
461
+ "grad_norm": 0.05811937153339386,
462
+ "learning_rate": 0.00019287562401253022,
463
+ "loss": 0.9905,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.42,
468
+ "grad_norm": 0.05927939713001251,
469
+ "learning_rate": 0.00019261746489577765,
470
+ "loss": 0.9604,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.43,
475
+ "grad_norm": 0.06021604314446449,
476
+ "learning_rate": 0.0001923548903987201,
477
+ "loss": 0.9535,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.44,
482
+ "grad_norm": 0.07004135102033615,
483
+ "learning_rate": 0.00019208791303915063,
484
+ "loss": 1.0032,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.44,
489
+ "grad_norm": 0.05626143515110016,
490
+ "learning_rate": 0.0001918165455447614,
491
+ "loss": 0.9726,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.45,
496
+ "grad_norm": 0.06130916625261307,
497
+ "learning_rate": 0.00019154080085253666,
498
+ "loss": 0.9646,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.46,
503
+ "grad_norm": 0.06467108428478241,
504
+ "learning_rate": 0.0001912606921081362,
505
+ "loss": 0.9516,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.46,
510
+ "grad_norm": 0.06047213450074196,
511
+ "learning_rate": 0.0001909762326652686,
512
+ "loss": 0.9664,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "grad_norm": 0.05907664820551872,
518
+ "learning_rate": 0.00019068743608505455,
519
+ "loss": 0.9796,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.48,
524
+ "grad_norm": 0.06679921597242355,
525
+ "learning_rate": 0.00019039431613538047,
526
+ "loss": 0.9678,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.48,
531
+ "grad_norm": 0.06133173033595085,
532
+ "learning_rate": 0.0001900968867902419,
533
+ "loss": 0.9875,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.49,
538
+ "grad_norm": 0.05841493234038353,
539
+ "learning_rate": 0.00018979516222907775,
540
+ "loss": 0.9686,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.49,
545
+ "grad_norm": 0.0660431906580925,
546
+ "learning_rate": 0.00018948915683609388,
547
+ "loss": 0.9863,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.5,
552
+ "grad_norm": 0.05776617303490639,
553
+ "learning_rate": 0.00018917888519957754,
554
+ "loss": 0.9417,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "grad_norm": 0.05937017872929573,
560
+ "learning_rate": 0.00018886436211120193,
561
+ "loss": 0.9995,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.51,
566
+ "grad_norm": 0.06314114481210709,
567
+ "learning_rate": 0.000188545602565321,
568
+ "loss": 0.9806,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.52,
573
+ "grad_norm": 0.060519032180309296,
574
+ "learning_rate": 0.00018822262175825462,
575
+ "loss": 0.9741,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.53,
580
+ "grad_norm": 0.06154269725084305,
581
+ "learning_rate": 0.00018789543508756408,
582
+ "loss": 0.9793,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.53,
587
+ "grad_norm": 0.06176121160387993,
588
+ "learning_rate": 0.00018756405815131813,
589
+ "loss": 0.9453,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.54,
594
+ "grad_norm": 0.06044905260205269,
595
+ "learning_rate": 0.00018722850674734927,
596
+ "loss": 0.9462,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "grad_norm": 0.05896229296922684,
602
+ "learning_rate": 0.00018688879687250067,
603
+ "loss": 0.9963,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.55,
608
+ "grad_norm": 0.06071419641375542,
609
+ "learning_rate": 0.0001865449447218635,
610
+ "loss": 0.9914,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.56,
615
+ "grad_norm": 0.0697932317852974,
616
+ "learning_rate": 0.00018619696668800492,
617
+ "loss": 0.9726,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.57,
622
+ "grad_norm": 0.062443289905786514,
623
+ "learning_rate": 0.00018584487936018661,
624
+ "loss": 1.0084,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.57,
629
+ "grad_norm": 0.059460923075675964,
630
+ "learning_rate": 0.0001854886995235738,
631
+ "loss": 0.9404,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.58,
636
+ "grad_norm": 0.058260347694158554,
637
+ "learning_rate": 0.00018512844415843514,
638
+ "loss": 0.9796,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.58,
643
+ "grad_norm": 0.05946533381938934,
644
+ "learning_rate": 0.00018476413043933313,
645
+ "loss": 0.9418,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.59,
650
+ "grad_norm": 0.06572849303483963,
651
+ "learning_rate": 0.00018439577573430555,
652
+ "loss": 0.9785,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.6,
657
+ "grad_norm": 0.06783867627382278,
658
+ "learning_rate": 0.00018402339760403713,
659
+ "loss": 0.9747,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.6,
664
+ "grad_norm": 0.06454402953386307,
665
+ "learning_rate": 0.00018364701380102266,
666
+ "loss": 0.9779,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.61,
671
+ "grad_norm": 0.06309663504362106,
672
+ "learning_rate": 0.00018326664226872065,
673
+ "loss": 0.9643,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.62,
678
+ "grad_norm": 0.05967305600643158,
679
+ "learning_rate": 0.00018288230114069765,
680
+ "loss": 0.9752,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.62,
685
+ "grad_norm": 0.05811592936515808,
686
+ "learning_rate": 0.0001824940087397641,
687
+ "loss": 0.9551,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.63,
692
+ "grad_norm": 0.0642295628786087,
693
+ "learning_rate": 0.00018210178357710058,
694
+ "loss": 0.9522,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.64,
699
+ "grad_norm": 0.05724099278450012,
700
+ "learning_rate": 0.0001817056443513754,
701
+ "loss": 1.0051,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.64,
706
+ "grad_norm": 0.056155964732170105,
707
+ "learning_rate": 0.00018130560994785325,
708
+ "loss": 0.9778,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.65,
713
+ "grad_norm": 0.058100346475839615,
714
+ "learning_rate": 0.00018090169943749476,
715
+ "loss": 0.9825,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.66,
720
+ "grad_norm": 0.06120794638991356,
721
+ "learning_rate": 0.00018049393207604733,
722
+ "loss": 0.9839,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.66,
727
+ "grad_norm": 0.056975312530994415,
728
+ "learning_rate": 0.00018008232730312723,
729
+ "loss": 0.9968,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.67,
734
+ "grad_norm": 0.06239038705825806,
735
+ "learning_rate": 0.00017966690474129285,
736
+ "loss": 0.9906,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.67,
741
+ "grad_norm": 0.5958348512649536,
742
+ "learning_rate": 0.00017924768419510904,
743
+ "loss": 2.6531,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.68,
748
+ "grad_norm": 0.06554935872554779,
749
+ "learning_rate": 0.00017882468565020326,
750
+ "loss": 1.0164,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.69,
755
+ "grad_norm": 0.05698655918240547,
756
+ "learning_rate": 0.00017839792927231254,
757
+ "loss": 0.9516,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.69,
762
+ "grad_norm": 0.06186239421367645,
763
+ "learning_rate": 0.00017796743540632223,
764
+ "loss": 0.9933,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.7,
769
+ "grad_norm": 0.05811876431107521,
770
+ "learning_rate": 0.00017753322457529614,
771
+ "loss": 0.9552,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.71,
776
+ "grad_norm": 0.06247268617153168,
777
+ "learning_rate": 0.00017709531747949796,
778
+ "loss": 0.9316,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.71,
783
+ "grad_norm": 0.06278502196073532,
784
+ "learning_rate": 0.00017665373499540463,
785
+ "loss": 0.9867,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.72,
790
+ "grad_norm": 0.06079186499118805,
791
+ "learning_rate": 0.00017620849817471092,
792
+ "loss": 1.0233,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.73,
797
+ "grad_norm": 0.05586745962500572,
798
+ "learning_rate": 0.00017575962824332596,
799
+ "loss": 0.9454,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.73,
804
+ "grad_norm": 0.059647805988788605,
805
+ "learning_rate": 0.00017530714660036112,
806
+ "loss": 0.9718,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.74,
811
+ "grad_norm": 0.060143355280160904,
812
+ "learning_rate": 0.00017485107481711012,
813
+ "loss": 0.9927,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.75,
818
+ "grad_norm": 0.4768543541431427,
819
+ "learning_rate": 0.0001743914346360205,
820
+ "loss": 2.4526,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.75,
825
+ "grad_norm": 0.059104178100824356,
826
+ "learning_rate": 0.00017392824796965702,
827
+ "loss": 0.9366,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.76,
832
+ "grad_norm": 0.06858639419078827,
833
+ "learning_rate": 0.00017346153689965727,
834
+ "loss": 0.9783,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.76,
839
+ "grad_norm": 0.06308155506849289,
840
+ "learning_rate": 0.00017299132367567857,
841
+ "loss": 0.9688,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.77,
846
+ "grad_norm": 0.0601269006729126,
847
+ "learning_rate": 0.00017251763071433765,
848
+ "loss": 0.9937,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.78,
853
+ "grad_norm": 0.06544536352157593,
854
+ "learning_rate": 0.00017204048059814175,
855
+ "loss": 0.9351,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.78,
860
+ "grad_norm": 0.06467759609222412,
861
+ "learning_rate": 0.00017155989607441213,
862
+ "loss": 0.9918,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.79,
867
+ "grad_norm": 0.061619073152542114,
868
+ "learning_rate": 0.0001710759000541995,
869
+ "loss": 0.9872,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.8,
874
+ "grad_norm": 0.06122846156358719,
875
+ "learning_rate": 0.00017058851561119198,
876
+ "loss": 0.968,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.8,
881
+ "grad_norm": 0.08277314156293869,
882
+ "learning_rate": 0.00017009776598061495,
883
+ "loss": 0.9869,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.81,
888
+ "grad_norm": 0.07559008151292801,
889
+ "learning_rate": 0.00016960367455812336,
890
+ "loss": 0.9804,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.82,
895
+ "grad_norm": 0.06251110136508942,
896
+ "learning_rate": 0.00016910626489868649,
897
+ "loss": 0.978,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.82,
902
+ "grad_norm": 0.06253345310688019,
903
+ "learning_rate": 0.0001686055607154648,
904
+ "loss": 0.9524,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.83,
909
+ "grad_norm": 0.05948334559798241,
910
+ "learning_rate": 0.00016810158587867973,
911
+ "loss": 0.9826,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.84,
916
+ "grad_norm": 0.06356865167617798,
917
+ "learning_rate": 0.00016759436441447545,
918
+ "loss": 0.9805,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.84,
923
+ "grad_norm": 0.06536010652780533,
924
+ "learning_rate": 0.00016708392050377363,
925
+ "loss": 1.0146,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.85,
930
+ "grad_norm": 0.06137322261929512,
931
+ "learning_rate": 0.00016657027848112062,
932
+ "loss": 0.9457,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.85,
937
+ "grad_norm": 0.05955340713262558,
938
+ "learning_rate": 0.00016605346283352727,
939
+ "loss": 0.9823,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.86,
944
+ "grad_norm": 0.0602475143969059,
945
+ "learning_rate": 0.00016553349819930165,
946
+ "loss": 1.0077,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.87,
951
+ "grad_norm": 0.05905039981007576,
952
+ "learning_rate": 0.00016501040936687443,
953
+ "loss": 0.9313,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.87,
958
+ "grad_norm": 0.06087419390678406,
959
+ "learning_rate": 0.00016448422127361706,
960
+ "loss": 0.9725,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.88,
965
+ "grad_norm": 0.059714119881391525,
966
+ "learning_rate": 0.00016395495900465304,
967
+ "loss": 0.9963,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.89,
972
+ "grad_norm": 0.06461544334888458,
973
+ "learning_rate": 0.000163422647791662,
974
+ "loss": 0.957,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.89,
979
+ "grad_norm": 0.06247726082801819,
980
+ "learning_rate": 0.00016288731301167668,
981
+ "loss": 0.9742,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.9,
986
+ "grad_norm": 0.06527213007211685,
987
+ "learning_rate": 0.00016234898018587337,
988
+ "loss": 0.9789,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.91,
993
+ "grad_norm": 0.059757690876722336,
994
+ "learning_rate": 0.00016180767497835503,
995
+ "loss": 0.9309,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.91,
1000
+ "grad_norm": 0.059084221720695496,
1001
+ "learning_rate": 0.00016126342319492784,
1002
+ "loss": 0.9546,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.92,
1007
+ "grad_norm": 1.778961181640625,
1008
+ "learning_rate": 0.00016071625078187114,
1009
+ "loss": 2.6066,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.93,
1014
+ "grad_norm": 0.06468740105628967,
1015
+ "learning_rate": 0.00016016618382470012,
1016
+ "loss": 0.9472,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.93,
1021
+ "grad_norm": 0.061647091060876846,
1022
+ "learning_rate": 0.00015961324854692254,
1023
+ "loss": 0.9836,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.94,
1028
+ "grad_norm": 0.06061193719506264,
1029
+ "learning_rate": 0.0001590574713087885,
1030
+ "loss": 0.982,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.94,
1035
+ "grad_norm": 0.06635820865631104,
1036
+ "learning_rate": 0.00015849887860603374,
1037
+ "loss": 0.9873,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.95,
1042
+ "grad_norm": 0.06260058283805847,
1043
+ "learning_rate": 0.00015793749706861636,
1044
+ "loss": 0.9827,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.96,
1049
+ "grad_norm": 0.06037148833274841,
1050
+ "learning_rate": 0.00015737335345944757,
1051
+ "loss": 1.0072,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.96,
1056
+ "grad_norm": 0.06277037411928177,
1057
+ "learning_rate": 0.00015680647467311557,
1058
+ "loss": 0.9498,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.97,
1063
+ "grad_norm": 0.06306284666061401,
1064
+ "learning_rate": 0.00015623688773460357,
1065
+ "loss": 0.9866,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.98,
1070
+ "grad_norm": 0.07311715185642242,
1071
+ "learning_rate": 0.00015566461979800122,
1072
+ "loss": 0.9722,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.98,
1077
+ "grad_norm": 0.06143077090382576,
1078
+ "learning_rate": 0.00015508969814521025,
1079
+ "loss": 0.9442,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.99,
1084
+ "grad_norm": 0.067879818379879,
1085
+ "learning_rate": 0.00015451215018464387,
1086
+ "loss": 0.9416,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.0,
1091
+ "grad_norm": 0.06907378137111664,
1092
+ "learning_rate": 0.00015393200344991995,
1093
+ "loss": 0.9813,
1094
+ "step": 155
1095
+ }
1096
+ ],
1097
+ "logging_steps": 1,
1098
+ "max_steps": 465,
1099
+ "num_input_tokens_seen": 0,
1100
+ "num_train_epochs": 3,
1101
+ "save_steps": 155,
1102
+ "total_flos": 3.361969685082931e+18,
1103
+ "train_batch_size": 5,
1104
+ "trial_name": null,
1105
+ "trial_params": null
1106
+ }
checkpoint-155/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9caa97dafc13dac0cd1534819d62554d3da31f36030b46451037938d5cae432
3
+ size 5816
checkpoint-310/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: kloodia/llama8
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-310/adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "kloodia/llama8",
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": 16,
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": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "gate",
25
+ "k_proj",
26
+ "w3",
27
+ "v_proj",
28
+ "w1",
29
+ "w2",
30
+ "q_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
checkpoint-310/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59ec0b7e22f1a5d351a7a293f620e9a9c352fdf02cfde40cb60a71f2c3c21883
3
+ size 1204141024
checkpoint-310/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9264d3683fa1fb78a043ef7e5645f54943b98541d78da7b06b2ae1c839dfb0
3
+ size 4782986938
checkpoint-310/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df1afcc1c701d5c99f5a97d56ed72c4cdfc8edc3c08e5d090c6bc12e4a31d69
3
+ size 14244
checkpoint-310/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eafa4b8f0ba9a605e35777244ac5e6408c23287c644bbca7821d9cbe49d87407
3
+ size 1064
checkpoint-310/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-310/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-310/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-310/trainer_state.json ADDED
@@ -0,0 +1,2191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9700214132762313,
5
+ "eval_steps": 500,
6
+ "global_step": 310,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.15481117367744446,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.1213,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.16627414524555206,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.1341,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "grad_norm": 0.14720524847507477,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.148,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03,
34
+ "grad_norm": 0.15325099229812622,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.1435,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "grad_norm": 0.16704852879047394,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.0895,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "grad_norm": 0.11686641722917557,
49
+ "learning_rate": 0.00012,
50
+ "loss": 1.0784,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 0.09641632437705994,
56
+ "learning_rate": 0.00014,
57
+ "loss": 1.0612,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.05,
62
+ "grad_norm": 0.12384118884801865,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.0566,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "grad_norm": 0.07287071645259857,
70
+ "learning_rate": 0.00018,
71
+ "loss": 1.0442,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.06,
76
+ "grad_norm": 0.07469318807125092,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.0083,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.07,
83
+ "grad_norm": 0.08364757895469666,
84
+ "learning_rate": 0.00019999761633493753,
85
+ "loss": 1.0169,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "grad_norm": 0.07763934135437012,
91
+ "learning_rate": 0.0001999904654533872,
92
+ "loss": 1.0348,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "grad_norm": 0.06744416803121567,
98
+ "learning_rate": 0.0001999785476962552,
99
+ "loss": 1.0123,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.09,
104
+ "grad_norm": 0.07724820077419281,
105
+ "learning_rate": 0.00019996186363170035,
106
+ "loss": 1.0188,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "grad_norm": 0.0746370479464531,
112
+ "learning_rate": 0.00019994041405510705,
113
+ "loss": 1.0164,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.1,
118
+ "grad_norm": 0.055804282426834106,
119
+ "learning_rate": 0.00019991419998904747,
120
+ "loss": 1.0587,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.11,
125
+ "grad_norm": 0.054163169115781784,
126
+ "learning_rate": 0.00019988322268323268,
127
+ "loss": 1.0149,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.12,
132
+ "grad_norm": 0.05897677689790726,
133
+ "learning_rate": 0.00019984748361445308,
134
+ "loss": 1.0136,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "grad_norm": 0.05603804066777229,
140
+ "learning_rate": 0.00019980698448650804,
141
+ "loss": 0.9996,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.13,
146
+ "grad_norm": 0.06250110268592834,
147
+ "learning_rate": 0.0001997617272301248,
148
+ "loss": 1.0145,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.13,
153
+ "grad_norm": 0.05678323656320572,
154
+ "learning_rate": 0.000199711714002866,
155
+ "loss": 1.0005,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.14,
160
+ "grad_norm": 0.05278163403272629,
161
+ "learning_rate": 0.00019965694718902745,
162
+ "loss": 1.0034,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.15,
167
+ "grad_norm": 0.05601625144481659,
168
+ "learning_rate": 0.00019959742939952392,
169
+ "loss": 0.9915,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "grad_norm": 0.054547134786844254,
175
+ "learning_rate": 0.00019953316347176488,
176
+ "loss": 1.0115,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "grad_norm": 0.06417939066886902,
182
+ "learning_rate": 0.0001994641524695193,
183
+ "loss": 0.9862,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.17,
188
+ "grad_norm": 0.061326365917921066,
189
+ "learning_rate": 0.0001993903996827694,
190
+ "loss": 0.9889,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.17,
195
+ "grad_norm": 0.05376205965876579,
196
+ "learning_rate": 0.00019931190862755417,
197
+ "loss": 0.9604,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.18,
202
+ "grad_norm": 0.0678999274969101,
203
+ "learning_rate": 0.00019922868304580118,
204
+ "loss": 1.0492,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.19,
209
+ "grad_norm": 0.053755760192871094,
210
+ "learning_rate": 0.0001991407269051487,
211
+ "loss": 0.9985,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "grad_norm": 0.05401955544948578,
217
+ "learning_rate": 0.00019904804439875633,
218
+ "loss": 0.9787,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "grad_norm": 0.05666874349117279,
224
+ "learning_rate": 0.0001989506399451051,
225
+ "loss": 0.9886,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.21,
230
+ "grad_norm": 0.05425805598497391,
231
+ "learning_rate": 0.00019884851818778693,
232
+ "loss": 1.0197,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.21,
237
+ "grad_norm": 0.06086369976401329,
238
+ "learning_rate": 0.00019874168399528305,
239
+ "loss": 0.9879,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.22,
244
+ "grad_norm": 0.05577366426587105,
245
+ "learning_rate": 0.00019863014246073214,
246
+ "loss": 0.9808,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.22,
251
+ "grad_norm": 0.05853752791881561,
252
+ "learning_rate": 0.0001985138989016874,
253
+ "loss": 0.957,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.23,
258
+ "grad_norm": 0.0582735501229763,
259
+ "learning_rate": 0.00019839295885986296,
260
+ "loss": 0.9732,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "grad_norm": 0.07255622744560242,
266
+ "learning_rate": 0.00019826732810086998,
267
+ "loss": 1.0199,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.24,
272
+ "grad_norm": 0.06085599586367607,
273
+ "learning_rate": 0.00019813701261394136,
274
+ "loss": 0.9946,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.25,
279
+ "grad_norm": 0.06600817292928696,
280
+ "learning_rate": 0.00019800201861164664,
281
+ "loss": 0.9646,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.26,
286
+ "grad_norm": 0.0634196326136589,
287
+ "learning_rate": 0.00019786235252959553,
288
+ "loss": 1.0092,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.26,
293
+ "grad_norm": 0.05254920944571495,
294
+ "learning_rate": 0.00019771802102613127,
295
+ "loss": 0.9535,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.27,
300
+ "grad_norm": 0.06008182466030121,
301
+ "learning_rate": 0.00019756903098201308,
302
+ "loss": 0.9897,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "grad_norm": 0.07715290039777756,
308
+ "learning_rate": 0.00019741538950008818,
309
+ "loss": 1.0132,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.28,
314
+ "grad_norm": 0.06104297190904617,
315
+ "learning_rate": 0.0001972571039049533,
316
+ "loss": 0.9938,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.29,
321
+ "grad_norm": 0.06008582562208176,
322
+ "learning_rate": 0.0001970941817426052,
323
+ "loss": 0.9889,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.3,
328
+ "grad_norm": 0.05699775367975235,
329
+ "learning_rate": 0.00019692663078008132,
330
+ "loss": 0.9843,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.3,
335
+ "grad_norm": 0.05760645866394043,
336
+ "learning_rate": 0.00019675445900508909,
337
+ "loss": 0.9677,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.31,
342
+ "grad_norm": 0.06075143814086914,
343
+ "learning_rate": 0.00019657767462562544,
344
+ "loss": 0.9929,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.31,
349
+ "grad_norm": 0.059820640832185745,
350
+ "learning_rate": 0.00019639628606958533,
351
+ "loss": 0.9889,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.32,
356
+ "grad_norm": 0.059315863996744156,
357
+ "learning_rate": 0.00019621030198436006,
358
+ "loss": 0.9994,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.33,
363
+ "grad_norm": 0.05949851870536804,
364
+ "learning_rate": 0.00019601973123642492,
365
+ "loss": 0.9593,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.33,
370
+ "grad_norm": 0.06036762520670891,
371
+ "learning_rate": 0.00019582458291091663,
372
+ "loss": 0.9669,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.34,
377
+ "grad_norm": 0.05799931660294533,
378
+ "learning_rate": 0.00019562486631120006,
379
+ "loss": 0.9731,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.35,
384
+ "grad_norm": 0.05733400583267212,
385
+ "learning_rate": 0.00019542059095842485,
386
+ "loss": 0.9676,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.35,
391
+ "grad_norm": 0.06894834339618683,
392
+ "learning_rate": 0.00019521176659107142,
393
+ "loss": 1.0142,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.36,
398
+ "grad_norm": 0.0657154992222786,
399
+ "learning_rate": 0.00019499840316448673,
400
+ "loss": 0.9598,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.37,
405
+ "grad_norm": 0.0570225715637207,
406
+ "learning_rate": 0.00019478051085040975,
407
+ "loss": 0.9979,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.37,
412
+ "grad_norm": 0.06271913647651672,
413
+ "learning_rate": 0.00019455810003648637,
414
+ "loss": 0.9694,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.38,
419
+ "grad_norm": 0.05831892415881157,
420
+ "learning_rate": 0.0001943311813257743,
421
+ "loss": 0.9934,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.39,
426
+ "grad_norm": 0.061948519200086594,
427
+ "learning_rate": 0.00019409976553623766,
428
+ "loss": 0.9812,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.39,
433
+ "grad_norm": 0.06726415455341339,
434
+ "learning_rate": 0.00019386386370023103,
435
+ "loss": 0.9837,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.4,
440
+ "grad_norm": 0.057408351451158524,
441
+ "learning_rate": 0.00019362348706397373,
442
+ "loss": 0.9512,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.4,
447
+ "grad_norm": 0.057638928294181824,
448
+ "learning_rate": 0.00019337864708701357,
449
+ "loss": 0.9622,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.41,
454
+ "grad_norm": 0.06090644374489784,
455
+ "learning_rate": 0.00019312935544168048,
456
+ "loss": 0.9927,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.42,
461
+ "grad_norm": 0.05811937153339386,
462
+ "learning_rate": 0.00019287562401253022,
463
+ "loss": 0.9905,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.42,
468
+ "grad_norm": 0.05927939713001251,
469
+ "learning_rate": 0.00019261746489577765,
470
+ "loss": 0.9604,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.43,
475
+ "grad_norm": 0.06021604314446449,
476
+ "learning_rate": 0.0001923548903987201,
477
+ "loss": 0.9535,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.44,
482
+ "grad_norm": 0.07004135102033615,
483
+ "learning_rate": 0.00019208791303915063,
484
+ "loss": 1.0032,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.44,
489
+ "grad_norm": 0.05626143515110016,
490
+ "learning_rate": 0.0001918165455447614,
491
+ "loss": 0.9726,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.45,
496
+ "grad_norm": 0.06130916625261307,
497
+ "learning_rate": 0.00019154080085253666,
498
+ "loss": 0.9646,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.46,
503
+ "grad_norm": 0.06467108428478241,
504
+ "learning_rate": 0.0001912606921081362,
505
+ "loss": 0.9516,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.46,
510
+ "grad_norm": 0.06047213450074196,
511
+ "learning_rate": 0.0001909762326652686,
512
+ "loss": 0.9664,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "grad_norm": 0.05907664820551872,
518
+ "learning_rate": 0.00019068743608505455,
519
+ "loss": 0.9796,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.48,
524
+ "grad_norm": 0.06679921597242355,
525
+ "learning_rate": 0.00019039431613538047,
526
+ "loss": 0.9678,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.48,
531
+ "grad_norm": 0.06133173033595085,
532
+ "learning_rate": 0.0001900968867902419,
533
+ "loss": 0.9875,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.49,
538
+ "grad_norm": 0.05841493234038353,
539
+ "learning_rate": 0.00018979516222907775,
540
+ "loss": 0.9686,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.49,
545
+ "grad_norm": 0.0660431906580925,
546
+ "learning_rate": 0.00018948915683609388,
547
+ "loss": 0.9863,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.5,
552
+ "grad_norm": 0.05776617303490639,
553
+ "learning_rate": 0.00018917888519957754,
554
+ "loss": 0.9417,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "grad_norm": 0.05937017872929573,
560
+ "learning_rate": 0.00018886436211120193,
561
+ "loss": 0.9995,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.51,
566
+ "grad_norm": 0.06314114481210709,
567
+ "learning_rate": 0.000188545602565321,
568
+ "loss": 0.9806,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.52,
573
+ "grad_norm": 0.060519032180309296,
574
+ "learning_rate": 0.00018822262175825462,
575
+ "loss": 0.9741,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.53,
580
+ "grad_norm": 0.06154269725084305,
581
+ "learning_rate": 0.00018789543508756408,
582
+ "loss": 0.9793,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.53,
587
+ "grad_norm": 0.06176121160387993,
588
+ "learning_rate": 0.00018756405815131813,
589
+ "loss": 0.9453,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.54,
594
+ "grad_norm": 0.06044905260205269,
595
+ "learning_rate": 0.00018722850674734927,
596
+ "loss": 0.9462,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "grad_norm": 0.05896229296922684,
602
+ "learning_rate": 0.00018688879687250067,
603
+ "loss": 0.9963,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.55,
608
+ "grad_norm": 0.06071419641375542,
609
+ "learning_rate": 0.0001865449447218635,
610
+ "loss": 0.9914,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.56,
615
+ "grad_norm": 0.0697932317852974,
616
+ "learning_rate": 0.00018619696668800492,
617
+ "loss": 0.9726,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.57,
622
+ "grad_norm": 0.062443289905786514,
623
+ "learning_rate": 0.00018584487936018661,
624
+ "loss": 1.0084,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.57,
629
+ "grad_norm": 0.059460923075675964,
630
+ "learning_rate": 0.0001854886995235738,
631
+ "loss": 0.9404,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.58,
636
+ "grad_norm": 0.058260347694158554,
637
+ "learning_rate": 0.00018512844415843514,
638
+ "loss": 0.9796,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.58,
643
+ "grad_norm": 0.05946533381938934,
644
+ "learning_rate": 0.00018476413043933313,
645
+ "loss": 0.9418,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.59,
650
+ "grad_norm": 0.06572849303483963,
651
+ "learning_rate": 0.00018439577573430555,
652
+ "loss": 0.9785,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.6,
657
+ "grad_norm": 0.06783867627382278,
658
+ "learning_rate": 0.00018402339760403713,
659
+ "loss": 0.9747,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.6,
664
+ "grad_norm": 0.06454402953386307,
665
+ "learning_rate": 0.00018364701380102266,
666
+ "loss": 0.9779,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.61,
671
+ "grad_norm": 0.06309663504362106,
672
+ "learning_rate": 0.00018326664226872065,
673
+ "loss": 0.9643,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.62,
678
+ "grad_norm": 0.05967305600643158,
679
+ "learning_rate": 0.00018288230114069765,
680
+ "loss": 0.9752,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.62,
685
+ "grad_norm": 0.05811592936515808,
686
+ "learning_rate": 0.0001824940087397641,
687
+ "loss": 0.9551,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.63,
692
+ "grad_norm": 0.0642295628786087,
693
+ "learning_rate": 0.00018210178357710058,
694
+ "loss": 0.9522,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.64,
699
+ "grad_norm": 0.05724099278450012,
700
+ "learning_rate": 0.0001817056443513754,
701
+ "loss": 1.0051,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.64,
706
+ "grad_norm": 0.056155964732170105,
707
+ "learning_rate": 0.00018130560994785325,
708
+ "loss": 0.9778,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.65,
713
+ "grad_norm": 0.058100346475839615,
714
+ "learning_rate": 0.00018090169943749476,
715
+ "loss": 0.9825,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.66,
720
+ "grad_norm": 0.06120794638991356,
721
+ "learning_rate": 0.00018049393207604733,
722
+ "loss": 0.9839,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.66,
727
+ "grad_norm": 0.056975312530994415,
728
+ "learning_rate": 0.00018008232730312723,
729
+ "loss": 0.9968,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.67,
734
+ "grad_norm": 0.06239038705825806,
735
+ "learning_rate": 0.00017966690474129285,
736
+ "loss": 0.9906,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.67,
741
+ "grad_norm": 0.5958348512649536,
742
+ "learning_rate": 0.00017924768419510904,
743
+ "loss": 2.6531,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.68,
748
+ "grad_norm": 0.06554935872554779,
749
+ "learning_rate": 0.00017882468565020326,
750
+ "loss": 1.0164,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.69,
755
+ "grad_norm": 0.05698655918240547,
756
+ "learning_rate": 0.00017839792927231254,
757
+ "loss": 0.9516,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.69,
762
+ "grad_norm": 0.06186239421367645,
763
+ "learning_rate": 0.00017796743540632223,
764
+ "loss": 0.9933,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.7,
769
+ "grad_norm": 0.05811876431107521,
770
+ "learning_rate": 0.00017753322457529614,
771
+ "loss": 0.9552,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.71,
776
+ "grad_norm": 0.06247268617153168,
777
+ "learning_rate": 0.00017709531747949796,
778
+ "loss": 0.9316,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.71,
783
+ "grad_norm": 0.06278502196073532,
784
+ "learning_rate": 0.00017665373499540463,
785
+ "loss": 0.9867,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.72,
790
+ "grad_norm": 0.06079186499118805,
791
+ "learning_rate": 0.00017620849817471092,
792
+ "loss": 1.0233,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.73,
797
+ "grad_norm": 0.05586745962500572,
798
+ "learning_rate": 0.00017575962824332596,
799
+ "loss": 0.9454,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.73,
804
+ "grad_norm": 0.059647805988788605,
805
+ "learning_rate": 0.00017530714660036112,
806
+ "loss": 0.9718,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.74,
811
+ "grad_norm": 0.060143355280160904,
812
+ "learning_rate": 0.00017485107481711012,
813
+ "loss": 0.9927,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.75,
818
+ "grad_norm": 0.4768543541431427,
819
+ "learning_rate": 0.0001743914346360205,
820
+ "loss": 2.4526,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.75,
825
+ "grad_norm": 0.059104178100824356,
826
+ "learning_rate": 0.00017392824796965702,
827
+ "loss": 0.9366,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.76,
832
+ "grad_norm": 0.06858639419078827,
833
+ "learning_rate": 0.00017346153689965727,
834
+ "loss": 0.9783,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.76,
839
+ "grad_norm": 0.06308155506849289,
840
+ "learning_rate": 0.00017299132367567857,
841
+ "loss": 0.9688,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.77,
846
+ "grad_norm": 0.0601269006729126,
847
+ "learning_rate": 0.00017251763071433765,
848
+ "loss": 0.9937,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.78,
853
+ "grad_norm": 0.06544536352157593,
854
+ "learning_rate": 0.00017204048059814175,
855
+ "loss": 0.9351,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.78,
860
+ "grad_norm": 0.06467759609222412,
861
+ "learning_rate": 0.00017155989607441213,
862
+ "loss": 0.9918,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.79,
867
+ "grad_norm": 0.061619073152542114,
868
+ "learning_rate": 0.0001710759000541995,
869
+ "loss": 0.9872,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.8,
874
+ "grad_norm": 0.06122846156358719,
875
+ "learning_rate": 0.00017058851561119198,
876
+ "loss": 0.968,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.8,
881
+ "grad_norm": 0.08277314156293869,
882
+ "learning_rate": 0.00017009776598061495,
883
+ "loss": 0.9869,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.81,
888
+ "grad_norm": 0.07559008151292801,
889
+ "learning_rate": 0.00016960367455812336,
890
+ "loss": 0.9804,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.82,
895
+ "grad_norm": 0.06251110136508942,
896
+ "learning_rate": 0.00016910626489868649,
897
+ "loss": 0.978,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.82,
902
+ "grad_norm": 0.06253345310688019,
903
+ "learning_rate": 0.0001686055607154648,
904
+ "loss": 0.9524,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.83,
909
+ "grad_norm": 0.05948334559798241,
910
+ "learning_rate": 0.00016810158587867973,
911
+ "loss": 0.9826,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.84,
916
+ "grad_norm": 0.06356865167617798,
917
+ "learning_rate": 0.00016759436441447545,
918
+ "loss": 0.9805,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.84,
923
+ "grad_norm": 0.06536010652780533,
924
+ "learning_rate": 0.00016708392050377363,
925
+ "loss": 1.0146,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.85,
930
+ "grad_norm": 0.06137322261929512,
931
+ "learning_rate": 0.00016657027848112062,
932
+ "loss": 0.9457,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.85,
937
+ "grad_norm": 0.05955340713262558,
938
+ "learning_rate": 0.00016605346283352727,
939
+ "loss": 0.9823,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.86,
944
+ "grad_norm": 0.0602475143969059,
945
+ "learning_rate": 0.00016553349819930165,
946
+ "loss": 1.0077,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.87,
951
+ "grad_norm": 0.05905039981007576,
952
+ "learning_rate": 0.00016501040936687443,
953
+ "loss": 0.9313,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.87,
958
+ "grad_norm": 0.06087419390678406,
959
+ "learning_rate": 0.00016448422127361706,
960
+ "loss": 0.9725,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.88,
965
+ "grad_norm": 0.059714119881391525,
966
+ "learning_rate": 0.00016395495900465304,
967
+ "loss": 0.9963,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.89,
972
+ "grad_norm": 0.06461544334888458,
973
+ "learning_rate": 0.000163422647791662,
974
+ "loss": 0.957,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.89,
979
+ "grad_norm": 0.06247726082801819,
980
+ "learning_rate": 0.00016288731301167668,
981
+ "loss": 0.9742,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.9,
986
+ "grad_norm": 0.06527213007211685,
987
+ "learning_rate": 0.00016234898018587337,
988
+ "loss": 0.9789,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.91,
993
+ "grad_norm": 0.059757690876722336,
994
+ "learning_rate": 0.00016180767497835503,
995
+ "loss": 0.9309,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.91,
1000
+ "grad_norm": 0.059084221720695496,
1001
+ "learning_rate": 0.00016126342319492784,
1002
+ "loss": 0.9546,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.92,
1007
+ "grad_norm": 1.778961181640625,
1008
+ "learning_rate": 0.00016071625078187114,
1009
+ "loss": 2.6066,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.93,
1014
+ "grad_norm": 0.06468740105628967,
1015
+ "learning_rate": 0.00016016618382470012,
1016
+ "loss": 0.9472,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.93,
1021
+ "grad_norm": 0.061647091060876846,
1022
+ "learning_rate": 0.00015961324854692254,
1023
+ "loss": 0.9836,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.94,
1028
+ "grad_norm": 0.06061193719506264,
1029
+ "learning_rate": 0.0001590574713087885,
1030
+ "loss": 0.982,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.94,
1035
+ "grad_norm": 0.06635820865631104,
1036
+ "learning_rate": 0.00015849887860603374,
1037
+ "loss": 0.9873,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.95,
1042
+ "grad_norm": 0.06260058283805847,
1043
+ "learning_rate": 0.00015793749706861636,
1044
+ "loss": 0.9827,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.96,
1049
+ "grad_norm": 0.06037148833274841,
1050
+ "learning_rate": 0.00015737335345944757,
1051
+ "loss": 1.0072,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.96,
1056
+ "grad_norm": 0.06277037411928177,
1057
+ "learning_rate": 0.00015680647467311557,
1058
+ "loss": 0.9498,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.97,
1063
+ "grad_norm": 0.06306284666061401,
1064
+ "learning_rate": 0.00015623688773460357,
1065
+ "loss": 0.9866,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.98,
1070
+ "grad_norm": 0.07311715185642242,
1071
+ "learning_rate": 0.00015566461979800122,
1072
+ "loss": 0.9722,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.98,
1077
+ "grad_norm": 0.06143077090382576,
1078
+ "learning_rate": 0.00015508969814521025,
1079
+ "loss": 0.9442,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.99,
1084
+ "grad_norm": 0.067879818379879,
1085
+ "learning_rate": 0.00015451215018464387,
1086
+ "loss": 0.9416,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.0,
1091
+ "grad_norm": 0.06907378137111664,
1092
+ "learning_rate": 0.00015393200344991995,
1093
+ "loss": 0.9813,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.0,
1098
+ "grad_norm": 0.06299201399087906,
1099
+ "learning_rate": 0.0001533492855985485,
1100
+ "loss": 0.9684,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.01,
1105
+ "grad_norm": 0.059243012219667435,
1106
+ "learning_rate": 0.0001527640244106133,
1107
+ "loss": 0.9883,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.01,
1112
+ "grad_norm": 0.06446617841720581,
1113
+ "learning_rate": 0.00015217624778744718,
1114
+ "loss": 0.9836,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.02,
1119
+ "grad_norm": 0.07795852422714233,
1120
+ "learning_rate": 0.00015158598375030217,
1121
+ "loss": 0.9682,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.01,
1126
+ "grad_norm": 0.0846932977437973,
1127
+ "learning_rate": 0.0001509932604390136,
1128
+ "loss": 0.8964,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.01,
1133
+ "grad_norm": 0.06378539651632309,
1134
+ "learning_rate": 0.0001503981061106584,
1135
+ "loss": 0.8712,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.02,
1140
+ "grad_norm": 0.06959015876054764,
1141
+ "learning_rate": 0.00014980054913820814,
1142
+ "loss": 0.8538,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.03,
1147
+ "grad_norm": 0.11089441180229187,
1148
+ "learning_rate": 0.00014920061800917638,
1149
+ "loss": 0.8898,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.03,
1154
+ "grad_norm": 0.10314545780420303,
1155
+ "learning_rate": 0.0001485983413242606,
1156
+ "loss": 0.858,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.04,
1161
+ "grad_norm": 0.06961672008037567,
1162
+ "learning_rate": 0.00014799374779597867,
1163
+ "loss": 0.8605,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.04,
1168
+ "grad_norm": 0.07029856741428375,
1169
+ "learning_rate": 0.00014738686624729986,
1170
+ "loss": 0.8536,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.05,
1175
+ "grad_norm": 0.07742595672607422,
1176
+ "learning_rate": 0.0001467777256102712,
1177
+ "loss": 0.875,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.06,
1182
+ "grad_norm": 0.06792555004358292,
1183
+ "learning_rate": 0.00014616635492463776,
1184
+ "loss": 0.8829,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.06,
1189
+ "grad_norm": 0.08564931154251099,
1190
+ "learning_rate": 0.00014555278333645833,
1191
+ "loss": 0.9109,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.07,
1196
+ "grad_norm": 0.0962703675031662,
1197
+ "learning_rate": 0.00014493704009671613,
1198
+ "loss": 0.8707,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.08,
1203
+ "grad_norm": 0.09053023904561996,
1204
+ "learning_rate": 0.00014431915455992414,
1205
+ "loss": 0.9005,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.08,
1210
+ "grad_norm": 0.07491155713796616,
1211
+ "learning_rate": 0.00014369915618272567,
1212
+ "loss": 0.8805,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.09,
1217
+ "grad_norm": 0.08745575696229935,
1218
+ "learning_rate": 0.00014307707452249012,
1219
+ "loss": 0.8766,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.1,
1224
+ "grad_norm": 0.08251971006393433,
1225
+ "learning_rate": 0.0001424529392359039,
1226
+ "loss": 0.8939,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.1,
1231
+ "grad_norm": 0.07616613060235977,
1232
+ "learning_rate": 0.0001418267800775565,
1233
+ "loss": 0.8678,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.11,
1238
+ "grad_norm": 0.08193603903055191,
1239
+ "learning_rate": 0.00014119862689852223,
1240
+ "loss": 0.8473,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.12,
1245
+ "grad_norm": 0.08167202025651932,
1246
+ "learning_rate": 0.0001405685096449367,
1247
+ "loss": 0.8669,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.12,
1252
+ "grad_norm": 0.08531814068555832,
1253
+ "learning_rate": 0.00013993645835656953,
1254
+ "loss": 0.8637,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.13,
1259
+ "grad_norm": 0.08357888460159302,
1260
+ "learning_rate": 0.00013930250316539238,
1261
+ "loss": 0.846,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.13,
1266
+ "grad_norm": 0.583361804485321,
1267
+ "learning_rate": 0.0001386666742941419,
1268
+ "loss": 2.3925,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.14,
1273
+ "grad_norm": 0.08598628640174866,
1274
+ "learning_rate": 0.00013802900205487948,
1275
+ "loss": 0.8702,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.15,
1280
+ "grad_norm": 0.0913216769695282,
1281
+ "learning_rate": 0.00013738951684754585,
1282
+ "loss": 0.8492,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.15,
1287
+ "grad_norm": 0.08879151940345764,
1288
+ "learning_rate": 0.00013674824915851192,
1289
+ "loss": 0.8721,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.16,
1294
+ "grad_norm": 0.09359906613826752,
1295
+ "learning_rate": 0.0001361052295591255,
1296
+ "loss": 0.8678,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.17,
1301
+ "grad_norm": 0.09475123882293701,
1302
+ "learning_rate": 0.00013546048870425356,
1303
+ "loss": 0.8514,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.17,
1308
+ "grad_norm": 0.1002567857503891,
1309
+ "learning_rate": 0.00013481405733082116,
1310
+ "loss": 0.8688,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.18,
1315
+ "grad_norm": 0.09523095935583115,
1316
+ "learning_rate": 0.00013416596625634593,
1317
+ "loss": 0.8776,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.19,
1322
+ "grad_norm": 0.09465932101011276,
1323
+ "learning_rate": 0.00013351624637746886,
1324
+ "loss": 0.8965,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.19,
1329
+ "grad_norm": 0.09145588427782059,
1330
+ "learning_rate": 0.00013286492866848142,
1331
+ "loss": 0.8587,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.2,
1336
+ "grad_norm": 0.09743087738752365,
1337
+ "learning_rate": 0.00013221204417984908,
1338
+ "loss": 0.823,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.21,
1343
+ "grad_norm": 0.09468277543783188,
1344
+ "learning_rate": 0.00013155762403673063,
1345
+ "loss": 0.8578,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.21,
1350
+ "grad_norm": 0.09516102075576782,
1351
+ "learning_rate": 0.00013090169943749476,
1352
+ "loss": 0.8944,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.22,
1357
+ "grad_norm": 0.09514753520488739,
1358
+ "learning_rate": 0.00013024430165223244,
1359
+ "loss": 0.8175,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.22,
1364
+ "grad_norm": 0.10116668790578842,
1365
+ "learning_rate": 0.0001295854620212664,
1366
+ "loss": 0.8572,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.23,
1371
+ "grad_norm": 0.09801662713289261,
1372
+ "learning_rate": 0.00012892521195365678,
1373
+ "loss": 0.8532,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.24,
1378
+ "grad_norm": 0.09754762053489685,
1379
+ "learning_rate": 0.00012826358292570398,
1380
+ "loss": 0.8653,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.24,
1385
+ "grad_norm": 0.10124494135379791,
1386
+ "learning_rate": 0.00012760060647944795,
1387
+ "loss": 0.9007,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.25,
1392
+ "grad_norm": 0.09749335795640945,
1393
+ "learning_rate": 0.00012693631422116454,
1394
+ "loss": 0.8304,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.26,
1399
+ "grad_norm": 0.09953852742910385,
1400
+ "learning_rate": 0.0001262707378198587,
1401
+ "loss": 0.8759,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.26,
1406
+ "grad_norm": 0.10160723328590393,
1407
+ "learning_rate": 0.0001256039090057547,
1408
+ "loss": 0.8923,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.27,
1413
+ "grad_norm": 0.1000576838850975,
1414
+ "learning_rate": 0.00012493585956878354,
1415
+ "loss": 0.8397,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.28,
1420
+ "grad_norm": 0.10324119031429291,
1421
+ "learning_rate": 0.0001242666213570672,
1422
+ "loss": 0.8787,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.28,
1427
+ "grad_norm": 0.1018192246556282,
1428
+ "learning_rate": 0.00012359622627540058,
1429
+ "loss": 0.8318,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.29,
1434
+ "grad_norm": 0.10028495639562607,
1435
+ "learning_rate": 0.00012292470628373037,
1436
+ "loss": 0.8354,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.3,
1441
+ "grad_norm": 0.10520325601100922,
1442
+ "learning_rate": 0.00012225209339563145,
1443
+ "loss": 0.8586,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.3,
1448
+ "grad_norm": 0.10229421406984329,
1449
+ "learning_rate": 0.00012157841967678063,
1450
+ "loss": 0.8961,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.31,
1455
+ "grad_norm": 0.10230256617069244,
1456
+ "learning_rate": 0.00012090371724342804,
1457
+ "loss": 0.8851,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.31,
1462
+ "grad_norm": 0.10282580554485321,
1463
+ "learning_rate": 0.00012022801826086609,
1464
+ "loss": 0.8588,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.32,
1469
+ "grad_norm": 0.1008041650056839,
1470
+ "learning_rate": 0.00011955135494189588,
1471
+ "loss": 0.8462,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.33,
1476
+ "grad_norm": 0.10294941067695618,
1477
+ "learning_rate": 0.00011887375954529168,
1478
+ "loss": 0.8301,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.33,
1483
+ "grad_norm": 0.10411438345909119,
1484
+ "learning_rate": 0.00011819526437426298,
1485
+ "loss": 0.8299,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.34,
1490
+ "grad_norm": 0.10526308417320251,
1491
+ "learning_rate": 0.0001175159017749144,
1492
+ "loss": 0.8624,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.35,
1497
+ "grad_norm": 0.10539798438549042,
1498
+ "learning_rate": 0.00011683570413470383,
1499
+ "loss": 0.8473,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.35,
1504
+ "grad_norm": 0.09961718320846558,
1505
+ "learning_rate": 0.00011615470388089835,
1506
+ "loss": 0.8571,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.36,
1511
+ "grad_norm": 0.10262471437454224,
1512
+ "learning_rate": 0.00011547293347902812,
1513
+ "loss": 0.8539,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.37,
1518
+ "grad_norm": 0.10586554557085037,
1519
+ "learning_rate": 0.00011479042543133895,
1520
+ "loss": 0.8559,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.37,
1525
+ "grad_norm": 0.10486755520105362,
1526
+ "learning_rate": 0.00011410721227524255,
1527
+ "loss": 0.8726,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.38,
1532
+ "grad_norm": 0.10485829412937164,
1533
+ "learning_rate": 0.00011342332658176555,
1534
+ "loss": 0.8903,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.39,
1539
+ "grad_norm": 0.10306116938591003,
1540
+ "learning_rate": 0.00011273880095399667,
1541
+ "loss": 0.8495,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.39,
1546
+ "grad_norm": 0.10205783694982529,
1547
+ "learning_rate": 0.0001120536680255323,
1548
+ "loss": 0.86,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.4,
1553
+ "grad_norm": 0.10305880010128021,
1554
+ "learning_rate": 0.00011136796045892102,
1555
+ "loss": 0.8617,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.4,
1560
+ "grad_norm": 0.10516184568405151,
1561
+ "learning_rate": 0.00011068171094410618,
1562
+ "loss": 0.8942,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.41,
1567
+ "grad_norm": 0.10830646008253098,
1568
+ "learning_rate": 0.00010999495219686762,
1569
+ "loss": 0.8853,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.42,
1574
+ "grad_norm": 0.10334376990795135,
1575
+ "learning_rate": 0.00010930771695726201,
1576
+ "loss": 0.8183,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.42,
1581
+ "grad_norm": 0.10024702548980713,
1582
+ "learning_rate": 0.00010862003798806196,
1583
+ "loss": 0.8503,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.43,
1588
+ "grad_norm": 0.10792502015829086,
1589
+ "learning_rate": 0.00010793194807319408,
1590
+ "loss": 0.8746,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.44,
1595
+ "grad_norm": 0.10143101215362549,
1596
+ "learning_rate": 0.00010724348001617625,
1597
+ "loss": 0.8321,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.44,
1602
+ "grad_norm": 0.09850587695837021,
1603
+ "learning_rate": 0.00010655466663855349,
1604
+ "loss": 0.8649,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.45,
1609
+ "grad_norm": 0.10333626717329025,
1610
+ "learning_rate": 0.00010586554077833347,
1611
+ "loss": 0.8722,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.46,
1616
+ "grad_norm": 0.10461243987083435,
1617
+ "learning_rate": 0.00010517613528842097,
1618
+ "loss": 0.8961,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.46,
1623
+ "grad_norm": 0.10886025428771973,
1624
+ "learning_rate": 0.00010448648303505151,
1625
+ "loss": 0.8921,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.47,
1630
+ "grad_norm": 0.10471045225858688,
1631
+ "learning_rate": 0.00010379661689622477,
1632
+ "loss": 0.8647,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.48,
1637
+ "grad_norm": 0.10855681449174881,
1638
+ "learning_rate": 0.00010310656976013705,
1639
+ "loss": 0.8783,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 1.48,
1644
+ "grad_norm": 0.11153094470500946,
1645
+ "learning_rate": 0.00010241637452361323,
1646
+ "loss": 0.8732,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 1.49,
1651
+ "grad_norm": 0.10941874235868454,
1652
+ "learning_rate": 0.00010172606409053886,
1653
+ "loss": 0.8555,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 1.49,
1658
+ "grad_norm": 0.10388068854808807,
1659
+ "learning_rate": 0.0001010356713702911,
1660
+ "loss": 0.8549,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 1.5,
1665
+ "grad_norm": 0.1045478880405426,
1666
+ "learning_rate": 0.00010034522927617014,
1667
+ "loss": 0.8706,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 1.51,
1672
+ "grad_norm": 0.10188283771276474,
1673
+ "learning_rate": 9.96547707238299e-05,
1674
+ "loss": 0.8916,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 1.51,
1679
+ "grad_norm": 0.10076084733009338,
1680
+ "learning_rate": 9.896432862970892e-05,
1681
+ "loss": 0.8841,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 1.52,
1686
+ "grad_norm": 0.10353115946054459,
1687
+ "learning_rate": 9.827393590946116e-05,
1688
+ "loss": 0.8723,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 1.53,
1693
+ "grad_norm": 0.10559534281492233,
1694
+ "learning_rate": 9.75836254763868e-05,
1695
+ "loss": 0.8679,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 1.53,
1700
+ "grad_norm": 0.10226694494485855,
1701
+ "learning_rate": 9.689343023986302e-05,
1702
+ "loss": 0.8434,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 1.54,
1707
+ "grad_norm": 0.10569630563259125,
1708
+ "learning_rate": 9.620338310377525e-05,
1709
+ "loss": 0.8768,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 1.55,
1714
+ "grad_norm": 0.10112857073545456,
1715
+ "learning_rate": 9.551351696494854e-05,
1716
+ "loss": 0.8249,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 1.55,
1721
+ "grad_norm": 0.10926086455583572,
1722
+ "learning_rate": 9.482386471157904e-05,
1723
+ "loss": 0.8634,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 1.56,
1728
+ "grad_norm": 0.1026775911450386,
1729
+ "learning_rate": 9.413445922166653e-05,
1730
+ "loss": 0.8679,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 1.57,
1735
+ "grad_norm": 0.10021597146987915,
1736
+ "learning_rate": 9.344533336144652e-05,
1737
+ "loss": 0.8596,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 1.57,
1742
+ "grad_norm": 0.1025286465883255,
1743
+ "learning_rate": 9.275651998382377e-05,
1744
+ "loss": 0.8302,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 1.58,
1749
+ "grad_norm": 0.0997297540307045,
1750
+ "learning_rate": 9.206805192680593e-05,
1751
+ "loss": 0.8818,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 1.58,
1756
+ "grad_norm": 0.10259710997343063,
1757
+ "learning_rate": 9.137996201193805e-05,
1758
+ "loss": 0.8558,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 1.59,
1763
+ "grad_norm": 0.1076403483748436,
1764
+ "learning_rate": 9.069228304273802e-05,
1765
+ "loss": 0.8922,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 1.6,
1770
+ "grad_norm": 0.10561492294073105,
1771
+ "learning_rate": 9.00050478031324e-05,
1772
+ "loss": 0.8593,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 1.6,
1777
+ "grad_norm": 0.10473283380270004,
1778
+ "learning_rate": 8.931828905589385e-05,
1779
+ "loss": 0.8893,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 1.61,
1784
+ "grad_norm": 0.11126771569252014,
1785
+ "learning_rate": 8.863203954107902e-05,
1786
+ "loss": 0.8761,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 1.62,
1791
+ "grad_norm": 0.10318706929683685,
1792
+ "learning_rate": 8.79463319744677e-05,
1793
+ "loss": 0.8688,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 1.62,
1798
+ "grad_norm": 0.10156065970659256,
1799
+ "learning_rate": 8.726119904600336e-05,
1800
+ "loss": 0.8683,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 1.63,
1805
+ "grad_norm": 0.0986093133687973,
1806
+ "learning_rate": 8.657667341823448e-05,
1807
+ "loss": 0.8375,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 1.64,
1812
+ "grad_norm": 0.10292702913284302,
1813
+ "learning_rate": 8.589278772475749e-05,
1814
+ "loss": 0.8623,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 1.64,
1819
+ "grad_norm": 0.1031164601445198,
1820
+ "learning_rate": 8.520957456866107e-05,
1821
+ "loss": 0.8633,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 1.65,
1826
+ "grad_norm": 0.0997462198138237,
1827
+ "learning_rate": 8.452706652097186e-05,
1828
+ "loss": 0.8462,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 1.66,
1833
+ "grad_norm": 0.11357836425304413,
1834
+ "learning_rate": 8.384529611910163e-05,
1835
+ "loss": 0.8316,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 1.66,
1840
+ "grad_norm": 0.10290369391441345,
1841
+ "learning_rate": 8.316429586529615e-05,
1842
+ "loss": 0.8357,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 1.67,
1847
+ "grad_norm": 0.10479974746704102,
1848
+ "learning_rate": 8.248409822508561e-05,
1849
+ "loss": 0.8591,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 1.67,
1854
+ "grad_norm": 0.1035972386598587,
1855
+ "learning_rate": 8.180473562573705e-05,
1856
+ "loss": 0.8351,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 1.68,
1861
+ "grad_norm": 0.10530169308185577,
1862
+ "learning_rate": 8.112624045470835e-05,
1863
+ "loss": 0.8387,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 1.69,
1868
+ "grad_norm": 0.09917616844177246,
1869
+ "learning_rate": 8.044864505810414e-05,
1870
+ "loss": 0.8699,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 1.69,
1875
+ "grad_norm": 0.10452553629875183,
1876
+ "learning_rate": 7.977198173913394e-05,
1877
+ "loss": 0.859,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 1.7,
1882
+ "grad_norm": 0.10981190949678421,
1883
+ "learning_rate": 7.909628275657198e-05,
1884
+ "loss": 0.8443,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 1.71,
1889
+ "grad_norm": 0.10094719380140305,
1890
+ "learning_rate": 7.84215803232194e-05,
1891
+ "loss": 0.8461,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 1.71,
1896
+ "grad_norm": 0.11014903336763382,
1897
+ "learning_rate": 7.774790660436858e-05,
1898
+ "loss": 0.8409,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 1.72,
1903
+ "grad_norm": 0.10279539972543716,
1904
+ "learning_rate": 7.707529371626965e-05,
1905
+ "loss": 0.8588,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 1.73,
1910
+ "grad_norm": 0.10260649770498276,
1911
+ "learning_rate": 7.640377372459945e-05,
1912
+ "loss": 0.8702,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 1.73,
1917
+ "grad_norm": 0.10066790878772736,
1918
+ "learning_rate": 7.573337864293283e-05,
1919
+ "loss": 0.8523,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 1.74,
1924
+ "grad_norm": 0.10237132757902145,
1925
+ "learning_rate": 7.506414043121647e-05,
1926
+ "loss": 0.8676,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 1.75,
1931
+ "grad_norm": 0.10095226764678955,
1932
+ "learning_rate": 7.43960909942453e-05,
1933
+ "loss": 0.8802,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 1.75,
1938
+ "grad_norm": 0.10220375657081604,
1939
+ "learning_rate": 7.372926218014131e-05,
1940
+ "loss": 0.8347,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 1.76,
1945
+ "grad_norm": 0.09893085062503815,
1946
+ "learning_rate": 7.306368577883547e-05,
1947
+ "loss": 0.8565,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 1.76,
1952
+ "grad_norm": 0.10145033895969391,
1953
+ "learning_rate": 7.239939352055208e-05,
1954
+ "loss": 0.8565,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 1.77,
1959
+ "grad_norm": 0.10070981830358505,
1960
+ "learning_rate": 7.173641707429606e-05,
1961
+ "loss": 0.8475,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.78,
1966
+ "grad_norm": 0.10595450550317764,
1967
+ "learning_rate": 7.107478804634325e-05,
1968
+ "loss": 0.8368,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.78,
1973
+ "grad_norm": 0.1085483580827713,
1974
+ "learning_rate": 7.041453797873363e-05,
1975
+ "loss": 0.866,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 1.79,
1980
+ "grad_norm": 0.1005505919456482,
1981
+ "learning_rate": 6.975569834776758e-05,
1982
+ "loss": 0.8393,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 1.8,
1987
+ "grad_norm": 0.10384807735681534,
1988
+ "learning_rate": 6.909830056250527e-05,
1989
+ "loss": 0.8571,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 1.8,
1994
+ "grad_norm": 0.10558132082223892,
1995
+ "learning_rate": 6.844237596326941e-05,
1996
+ "loss": 0.8477,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 1.81,
2001
+ "grad_norm": 0.10049811750650406,
2002
+ "learning_rate": 6.778795582015097e-05,
2003
+ "loss": 0.8317,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 1.82,
2008
+ "grad_norm": 0.10088322311639786,
2009
+ "learning_rate": 6.713507133151857e-05,
2010
+ "loss": 0.8602,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 1.82,
2015
+ "grad_norm": 0.09972478449344635,
2016
+ "learning_rate": 6.648375362253118e-05,
2017
+ "loss": 0.8514,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 1.83,
2022
+ "grad_norm": 0.10518650710582733,
2023
+ "learning_rate": 6.583403374365405e-05,
2024
+ "loss": 0.8732,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 1.84,
2029
+ "grad_norm": 0.10432999581098557,
2030
+ "learning_rate": 6.518594266917882e-05,
2031
+ "loss": 0.9014,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 1.84,
2036
+ "grad_norm": 0.10011251270771027,
2037
+ "learning_rate": 6.453951129574644e-05,
2038
+ "loss": 0.8192,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 1.85,
2043
+ "grad_norm": 0.09896595031023026,
2044
+ "learning_rate": 6.389477044087452e-05,
2045
+ "loss": 0.8148,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 1.85,
2050
+ "grad_norm": 0.10062045603990555,
2051
+ "learning_rate": 6.325175084148809e-05,
2052
+ "loss": 0.8303,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 1.86,
2057
+ "grad_norm": 0.1033136248588562,
2058
+ "learning_rate": 6.261048315245419e-05,
2059
+ "loss": 0.8537,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 1.87,
2064
+ "grad_norm": 0.10438770055770874,
2065
+ "learning_rate": 6.197099794512056e-05,
2066
+ "loss": 0.8881,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 1.87,
2071
+ "grad_norm": 0.1036936491727829,
2072
+ "learning_rate": 6.133332570585812e-05,
2073
+ "loss": 0.85,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 1.88,
2078
+ "grad_norm": 0.10618463903665543,
2079
+ "learning_rate": 6.069749683460765e-05,
2080
+ "loss": 0.8618,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 1.89,
2085
+ "grad_norm": 0.10110071301460266,
2086
+ "learning_rate": 6.006354164343046e-05,
2087
+ "loss": 0.8632,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 1.89,
2092
+ "grad_norm": 0.10008033365011215,
2093
+ "learning_rate": 5.943149035506337e-05,
2094
+ "loss": 0.8648,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 1.9,
2099
+ "grad_norm": 0.09985347092151642,
2100
+ "learning_rate": 5.880137310147782e-05,
2101
+ "loss": 0.893,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 1.91,
2106
+ "grad_norm": 0.09989628195762634,
2107
+ "learning_rate": 5.817321992244351e-05,
2108
+ "loss": 0.8682,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 1.91,
2113
+ "grad_norm": 0.10163696855306625,
2114
+ "learning_rate": 5.754706076409613e-05,
2115
+ "loss": 0.8554,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 1.92,
2120
+ "grad_norm": 0.10319127887487411,
2121
+ "learning_rate": 5.692292547750988e-05,
2122
+ "loss": 0.8603,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 1.93,
2127
+ "grad_norm": 0.10187959671020508,
2128
+ "learning_rate": 5.630084381727434e-05,
2129
+ "loss": 0.8628,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 1.93,
2134
+ "grad_norm": 0.09999451041221619,
2135
+ "learning_rate": 5.568084544007588e-05,
2136
+ "loss": 0.8471,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 1.94,
2141
+ "grad_norm": 0.10175001621246338,
2142
+ "learning_rate": 5.506295990328385e-05,
2143
+ "loss": 0.8371,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 1.94,
2148
+ "grad_norm": 0.10206517577171326,
2149
+ "learning_rate": 5.444721666354169e-05,
2150
+ "loss": 0.8836,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 1.95,
2155
+ "grad_norm": 0.10593275725841522,
2156
+ "learning_rate": 5.383364507536229e-05,
2157
+ "loss": 0.8397,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 1.96,
2162
+ "grad_norm": 0.10138902068138123,
2163
+ "learning_rate": 5.32222743897288e-05,
2164
+ "loss": 0.8749,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 1.96,
2169
+ "grad_norm": 0.1002379059791565,
2170
+ "learning_rate": 5.261313375270014e-05,
2171
+ "loss": 0.8338,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 1.97,
2176
+ "grad_norm": 0.11006593704223633,
2177
+ "learning_rate": 5.200625220402139e-05,
2178
+ "loss": 0.8779,
2179
+ "step": 310
2180
+ }
2181
+ ],
2182
+ "logging_steps": 1,
2183
+ "max_steps": 465,
2184
+ "num_input_tokens_seen": 0,
2185
+ "num_train_epochs": 3,
2186
+ "save_steps": 155,
2187
+ "total_flos": 6.721047353232458e+18,
2188
+ "train_batch_size": 5,
2189
+ "trial_name": null,
2190
+ "trial_params": null
2191
+ }
checkpoint-310/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9caa97dafc13dac0cd1534819d62554d3da31f36030b46451037938d5cae432
3
+ size 5816
checkpoint-465/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: kloodia/llama8
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-465/adapter_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "kloodia/llama8",
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": 16,
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": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "o_proj",
24
+ "gate",
25
+ "k_proj",
26
+ "w3",
27
+ "v_proj",
28
+ "w1",
29
+ "w2",
30
+ "q_proj"
31
+ ],
32
+ "task_type": "CAUSAL_LM",
33
+ "use_dora": false,
34
+ "use_rslora": false
35
+ }
checkpoint-465/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6b7b78fcc8d68d30e8d5e40b2616b5cc23cb08b3bfbb72ce36796d60edfefa
3
+ size 1204141024
checkpoint-465/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ddad76c6bed572fe318eaf08f358efa91185620fdf4b22cf0c7ee74003c081
3
+ size 4782986938
checkpoint-465/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0e685122cf3229d613c435ddbe5bd98615f63f0167225c79a262220cab768c
3
+ size 14244
checkpoint-465/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b4695e57942b812e750f9936d8f9d7d6cb6adb663cd07a771c201ca821c797f
3
+ size 1064
checkpoint-465/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-465/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-465/tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
checkpoint-465/trainer_state.json ADDED
@@ -0,0 +1,3276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9443254817987152,
5
+ "eval_steps": 500,
6
+ "global_step": 465,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "grad_norm": 0.15481117367744446,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.1213,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01,
20
+ "grad_norm": 0.16627414524555206,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.1341,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "grad_norm": 0.14720524847507477,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.148,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03,
34
+ "grad_norm": 0.15325099229812622,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.1435,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.03,
41
+ "grad_norm": 0.16704852879047394,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.0895,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "grad_norm": 0.11686641722917557,
49
+ "learning_rate": 0.00012,
50
+ "loss": 1.0784,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.04,
55
+ "grad_norm": 0.09641632437705994,
56
+ "learning_rate": 0.00014,
57
+ "loss": 1.0612,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.05,
62
+ "grad_norm": 0.12384118884801865,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.0566,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.06,
69
+ "grad_norm": 0.07287071645259857,
70
+ "learning_rate": 0.00018,
71
+ "loss": 1.0442,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.06,
76
+ "grad_norm": 0.07469318807125092,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.0083,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.07,
83
+ "grad_norm": 0.08364757895469666,
84
+ "learning_rate": 0.00019999761633493753,
85
+ "loss": 1.0169,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.08,
90
+ "grad_norm": 0.07763934135437012,
91
+ "learning_rate": 0.0001999904654533872,
92
+ "loss": 1.0348,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.08,
97
+ "grad_norm": 0.06744416803121567,
98
+ "learning_rate": 0.0001999785476962552,
99
+ "loss": 1.0123,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.09,
104
+ "grad_norm": 0.07724820077419281,
105
+ "learning_rate": 0.00019996186363170035,
106
+ "loss": 1.0188,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1,
111
+ "grad_norm": 0.0746370479464531,
112
+ "learning_rate": 0.00019994041405510705,
113
+ "loss": 1.0164,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.1,
118
+ "grad_norm": 0.055804282426834106,
119
+ "learning_rate": 0.00019991419998904747,
120
+ "loss": 1.0587,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.11,
125
+ "grad_norm": 0.054163169115781784,
126
+ "learning_rate": 0.00019988322268323268,
127
+ "loss": 1.0149,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.12,
132
+ "grad_norm": 0.05897677689790726,
133
+ "learning_rate": 0.00019984748361445308,
134
+ "loss": 1.0136,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "grad_norm": 0.05603804066777229,
140
+ "learning_rate": 0.00019980698448650804,
141
+ "loss": 0.9996,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.13,
146
+ "grad_norm": 0.06250110268592834,
147
+ "learning_rate": 0.0001997617272301248,
148
+ "loss": 1.0145,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.13,
153
+ "grad_norm": 0.05678323656320572,
154
+ "learning_rate": 0.000199711714002866,
155
+ "loss": 1.0005,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.14,
160
+ "grad_norm": 0.05278163403272629,
161
+ "learning_rate": 0.00019965694718902745,
162
+ "loss": 1.0034,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.15,
167
+ "grad_norm": 0.05601625144481659,
168
+ "learning_rate": 0.00019959742939952392,
169
+ "loss": 0.9915,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "grad_norm": 0.054547134786844254,
175
+ "learning_rate": 0.00019953316347176488,
176
+ "loss": 1.0115,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.16,
181
+ "grad_norm": 0.06417939066886902,
182
+ "learning_rate": 0.0001994641524695193,
183
+ "loss": 0.9862,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.17,
188
+ "grad_norm": 0.061326365917921066,
189
+ "learning_rate": 0.0001993903996827694,
190
+ "loss": 0.9889,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.17,
195
+ "grad_norm": 0.05376205965876579,
196
+ "learning_rate": 0.00019931190862755417,
197
+ "loss": 0.9604,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.18,
202
+ "grad_norm": 0.0678999274969101,
203
+ "learning_rate": 0.00019922868304580118,
204
+ "loss": 1.0492,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.19,
209
+ "grad_norm": 0.053755760192871094,
210
+ "learning_rate": 0.0001991407269051487,
211
+ "loss": 0.9985,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "grad_norm": 0.05401955544948578,
217
+ "learning_rate": 0.00019904804439875633,
218
+ "loss": 0.9787,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.2,
223
+ "grad_norm": 0.05666874349117279,
224
+ "learning_rate": 0.0001989506399451051,
225
+ "loss": 0.9886,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.21,
230
+ "grad_norm": 0.05425805598497391,
231
+ "learning_rate": 0.00019884851818778693,
232
+ "loss": 1.0197,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.21,
237
+ "grad_norm": 0.06086369976401329,
238
+ "learning_rate": 0.00019874168399528305,
239
+ "loss": 0.9879,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.22,
244
+ "grad_norm": 0.05577366426587105,
245
+ "learning_rate": 0.00019863014246073214,
246
+ "loss": 0.9808,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.22,
251
+ "grad_norm": 0.05853752791881561,
252
+ "learning_rate": 0.0001985138989016874,
253
+ "loss": 0.957,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.23,
258
+ "grad_norm": 0.0582735501229763,
259
+ "learning_rate": 0.00019839295885986296,
260
+ "loss": 0.9732,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.24,
265
+ "grad_norm": 0.07255622744560242,
266
+ "learning_rate": 0.00019826732810086998,
267
+ "loss": 1.0199,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.24,
272
+ "grad_norm": 0.06085599586367607,
273
+ "learning_rate": 0.00019813701261394136,
274
+ "loss": 0.9946,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.25,
279
+ "grad_norm": 0.06600817292928696,
280
+ "learning_rate": 0.00019800201861164664,
281
+ "loss": 0.9646,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.26,
286
+ "grad_norm": 0.0634196326136589,
287
+ "learning_rate": 0.00019786235252959553,
288
+ "loss": 1.0092,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.26,
293
+ "grad_norm": 0.05254920944571495,
294
+ "learning_rate": 0.00019771802102613127,
295
+ "loss": 0.9535,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.27,
300
+ "grad_norm": 0.06008182466030121,
301
+ "learning_rate": 0.00019756903098201308,
302
+ "loss": 0.9897,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.28,
307
+ "grad_norm": 0.07715290039777756,
308
+ "learning_rate": 0.00019741538950008818,
309
+ "loss": 1.0132,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.28,
314
+ "grad_norm": 0.06104297190904617,
315
+ "learning_rate": 0.0001972571039049533,
316
+ "loss": 0.9938,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.29,
321
+ "grad_norm": 0.06008582562208176,
322
+ "learning_rate": 0.0001970941817426052,
323
+ "loss": 0.9889,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.3,
328
+ "grad_norm": 0.05699775367975235,
329
+ "learning_rate": 0.00019692663078008132,
330
+ "loss": 0.9843,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.3,
335
+ "grad_norm": 0.05760645866394043,
336
+ "learning_rate": 0.00019675445900508909,
337
+ "loss": 0.9677,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.31,
342
+ "grad_norm": 0.06075143814086914,
343
+ "learning_rate": 0.00019657767462562544,
344
+ "loss": 0.9929,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.31,
349
+ "grad_norm": 0.059820640832185745,
350
+ "learning_rate": 0.00019639628606958533,
351
+ "loss": 0.9889,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.32,
356
+ "grad_norm": 0.059315863996744156,
357
+ "learning_rate": 0.00019621030198436006,
358
+ "loss": 0.9994,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.33,
363
+ "grad_norm": 0.05949851870536804,
364
+ "learning_rate": 0.00019601973123642492,
365
+ "loss": 0.9593,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.33,
370
+ "grad_norm": 0.06036762520670891,
371
+ "learning_rate": 0.00019582458291091663,
372
+ "loss": 0.9669,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.34,
377
+ "grad_norm": 0.05799931660294533,
378
+ "learning_rate": 0.00019562486631120006,
379
+ "loss": 0.9731,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.35,
384
+ "grad_norm": 0.05733400583267212,
385
+ "learning_rate": 0.00019542059095842485,
386
+ "loss": 0.9676,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.35,
391
+ "grad_norm": 0.06894834339618683,
392
+ "learning_rate": 0.00019521176659107142,
393
+ "loss": 1.0142,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.36,
398
+ "grad_norm": 0.0657154992222786,
399
+ "learning_rate": 0.00019499840316448673,
400
+ "loss": 0.9598,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.37,
405
+ "grad_norm": 0.0570225715637207,
406
+ "learning_rate": 0.00019478051085040975,
407
+ "loss": 0.9979,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.37,
412
+ "grad_norm": 0.06271913647651672,
413
+ "learning_rate": 0.00019455810003648637,
414
+ "loss": 0.9694,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.38,
419
+ "grad_norm": 0.05831892415881157,
420
+ "learning_rate": 0.0001943311813257743,
421
+ "loss": 0.9934,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.39,
426
+ "grad_norm": 0.061948519200086594,
427
+ "learning_rate": 0.00019409976553623766,
428
+ "loss": 0.9812,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.39,
433
+ "grad_norm": 0.06726415455341339,
434
+ "learning_rate": 0.00019386386370023103,
435
+ "loss": 0.9837,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.4,
440
+ "grad_norm": 0.057408351451158524,
441
+ "learning_rate": 0.00019362348706397373,
442
+ "loss": 0.9512,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.4,
447
+ "grad_norm": 0.057638928294181824,
448
+ "learning_rate": 0.00019337864708701357,
449
+ "loss": 0.9622,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.41,
454
+ "grad_norm": 0.06090644374489784,
455
+ "learning_rate": 0.00019312935544168048,
456
+ "loss": 0.9927,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.42,
461
+ "grad_norm": 0.05811937153339386,
462
+ "learning_rate": 0.00019287562401253022,
463
+ "loss": 0.9905,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.42,
468
+ "grad_norm": 0.05927939713001251,
469
+ "learning_rate": 0.00019261746489577765,
470
+ "loss": 0.9604,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.43,
475
+ "grad_norm": 0.06021604314446449,
476
+ "learning_rate": 0.0001923548903987201,
477
+ "loss": 0.9535,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.44,
482
+ "grad_norm": 0.07004135102033615,
483
+ "learning_rate": 0.00019208791303915063,
484
+ "loss": 1.0032,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.44,
489
+ "grad_norm": 0.05626143515110016,
490
+ "learning_rate": 0.0001918165455447614,
491
+ "loss": 0.9726,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.45,
496
+ "grad_norm": 0.06130916625261307,
497
+ "learning_rate": 0.00019154080085253666,
498
+ "loss": 0.9646,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.46,
503
+ "grad_norm": 0.06467108428478241,
504
+ "learning_rate": 0.0001912606921081362,
505
+ "loss": 0.9516,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.46,
510
+ "grad_norm": 0.06047213450074196,
511
+ "learning_rate": 0.0001909762326652686,
512
+ "loss": 0.9664,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.47,
517
+ "grad_norm": 0.05907664820551872,
518
+ "learning_rate": 0.00019068743608505455,
519
+ "loss": 0.9796,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.48,
524
+ "grad_norm": 0.06679921597242355,
525
+ "learning_rate": 0.00019039431613538047,
526
+ "loss": 0.9678,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.48,
531
+ "grad_norm": 0.06133173033595085,
532
+ "learning_rate": 0.0001900968867902419,
533
+ "loss": 0.9875,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.49,
538
+ "grad_norm": 0.05841493234038353,
539
+ "learning_rate": 0.00018979516222907775,
540
+ "loss": 0.9686,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.49,
545
+ "grad_norm": 0.0660431906580925,
546
+ "learning_rate": 0.00018948915683609388,
547
+ "loss": 0.9863,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.5,
552
+ "grad_norm": 0.05776617303490639,
553
+ "learning_rate": 0.00018917888519957754,
554
+ "loss": 0.9417,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.51,
559
+ "grad_norm": 0.05937017872929573,
560
+ "learning_rate": 0.00018886436211120193,
561
+ "loss": 0.9995,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.51,
566
+ "grad_norm": 0.06314114481210709,
567
+ "learning_rate": 0.000188545602565321,
568
+ "loss": 0.9806,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.52,
573
+ "grad_norm": 0.060519032180309296,
574
+ "learning_rate": 0.00018822262175825462,
575
+ "loss": 0.9741,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.53,
580
+ "grad_norm": 0.06154269725084305,
581
+ "learning_rate": 0.00018789543508756408,
582
+ "loss": 0.9793,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.53,
587
+ "grad_norm": 0.06176121160387993,
588
+ "learning_rate": 0.00018756405815131813,
589
+ "loss": 0.9453,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.54,
594
+ "grad_norm": 0.06044905260205269,
595
+ "learning_rate": 0.00018722850674734927,
596
+ "loss": 0.9462,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.55,
601
+ "grad_norm": 0.05896229296922684,
602
+ "learning_rate": 0.00018688879687250067,
603
+ "loss": 0.9963,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.55,
608
+ "grad_norm": 0.06071419641375542,
609
+ "learning_rate": 0.0001865449447218635,
610
+ "loss": 0.9914,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.56,
615
+ "grad_norm": 0.0697932317852974,
616
+ "learning_rate": 0.00018619696668800492,
617
+ "loss": 0.9726,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.57,
622
+ "grad_norm": 0.062443289905786514,
623
+ "learning_rate": 0.00018584487936018661,
624
+ "loss": 1.0084,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.57,
629
+ "grad_norm": 0.059460923075675964,
630
+ "learning_rate": 0.0001854886995235738,
631
+ "loss": 0.9404,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.58,
636
+ "grad_norm": 0.058260347694158554,
637
+ "learning_rate": 0.00018512844415843514,
638
+ "loss": 0.9796,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.58,
643
+ "grad_norm": 0.05946533381938934,
644
+ "learning_rate": 0.00018476413043933313,
645
+ "loss": 0.9418,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.59,
650
+ "grad_norm": 0.06572849303483963,
651
+ "learning_rate": 0.00018439577573430555,
652
+ "loss": 0.9785,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.6,
657
+ "grad_norm": 0.06783867627382278,
658
+ "learning_rate": 0.00018402339760403713,
659
+ "loss": 0.9747,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.6,
664
+ "grad_norm": 0.06454402953386307,
665
+ "learning_rate": 0.00018364701380102266,
666
+ "loss": 0.9779,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.61,
671
+ "grad_norm": 0.06309663504362106,
672
+ "learning_rate": 0.00018326664226872065,
673
+ "loss": 0.9643,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.62,
678
+ "grad_norm": 0.05967305600643158,
679
+ "learning_rate": 0.00018288230114069765,
680
+ "loss": 0.9752,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.62,
685
+ "grad_norm": 0.05811592936515808,
686
+ "learning_rate": 0.0001824940087397641,
687
+ "loss": 0.9551,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.63,
692
+ "grad_norm": 0.0642295628786087,
693
+ "learning_rate": 0.00018210178357710058,
694
+ "loss": 0.9522,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.64,
699
+ "grad_norm": 0.05724099278450012,
700
+ "learning_rate": 0.0001817056443513754,
701
+ "loss": 1.0051,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.64,
706
+ "grad_norm": 0.056155964732170105,
707
+ "learning_rate": 0.00018130560994785325,
708
+ "loss": 0.9778,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.65,
713
+ "grad_norm": 0.058100346475839615,
714
+ "learning_rate": 0.00018090169943749476,
715
+ "loss": 0.9825,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.66,
720
+ "grad_norm": 0.06120794638991356,
721
+ "learning_rate": 0.00018049393207604733,
722
+ "loss": 0.9839,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.66,
727
+ "grad_norm": 0.056975312530994415,
728
+ "learning_rate": 0.00018008232730312723,
729
+ "loss": 0.9968,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.67,
734
+ "grad_norm": 0.06239038705825806,
735
+ "learning_rate": 0.00017966690474129285,
736
+ "loss": 0.9906,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.67,
741
+ "grad_norm": 0.5958348512649536,
742
+ "learning_rate": 0.00017924768419510904,
743
+ "loss": 2.6531,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.68,
748
+ "grad_norm": 0.06554935872554779,
749
+ "learning_rate": 0.00017882468565020326,
750
+ "loss": 1.0164,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.69,
755
+ "grad_norm": 0.05698655918240547,
756
+ "learning_rate": 0.00017839792927231254,
757
+ "loss": 0.9516,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.69,
762
+ "grad_norm": 0.06186239421367645,
763
+ "learning_rate": 0.00017796743540632223,
764
+ "loss": 0.9933,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.7,
769
+ "grad_norm": 0.05811876431107521,
770
+ "learning_rate": 0.00017753322457529614,
771
+ "loss": 0.9552,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.71,
776
+ "grad_norm": 0.06247268617153168,
777
+ "learning_rate": 0.00017709531747949796,
778
+ "loss": 0.9316,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.71,
783
+ "grad_norm": 0.06278502196073532,
784
+ "learning_rate": 0.00017665373499540463,
785
+ "loss": 0.9867,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.72,
790
+ "grad_norm": 0.06079186499118805,
791
+ "learning_rate": 0.00017620849817471092,
792
+ "loss": 1.0233,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.73,
797
+ "grad_norm": 0.05586745962500572,
798
+ "learning_rate": 0.00017575962824332596,
799
+ "loss": 0.9454,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.73,
804
+ "grad_norm": 0.059647805988788605,
805
+ "learning_rate": 0.00017530714660036112,
806
+ "loss": 0.9718,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.74,
811
+ "grad_norm": 0.060143355280160904,
812
+ "learning_rate": 0.00017485107481711012,
813
+ "loss": 0.9927,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.75,
818
+ "grad_norm": 0.4768543541431427,
819
+ "learning_rate": 0.0001743914346360205,
820
+ "loss": 2.4526,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.75,
825
+ "grad_norm": 0.059104178100824356,
826
+ "learning_rate": 0.00017392824796965702,
827
+ "loss": 0.9366,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.76,
832
+ "grad_norm": 0.06858639419078827,
833
+ "learning_rate": 0.00017346153689965727,
834
+ "loss": 0.9783,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.76,
839
+ "grad_norm": 0.06308155506849289,
840
+ "learning_rate": 0.00017299132367567857,
841
+ "loss": 0.9688,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.77,
846
+ "grad_norm": 0.0601269006729126,
847
+ "learning_rate": 0.00017251763071433765,
848
+ "loss": 0.9937,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.78,
853
+ "grad_norm": 0.06544536352157593,
854
+ "learning_rate": 0.00017204048059814175,
855
+ "loss": 0.9351,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.78,
860
+ "grad_norm": 0.06467759609222412,
861
+ "learning_rate": 0.00017155989607441213,
862
+ "loss": 0.9918,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.79,
867
+ "grad_norm": 0.061619073152542114,
868
+ "learning_rate": 0.0001710759000541995,
869
+ "loss": 0.9872,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.8,
874
+ "grad_norm": 0.06122846156358719,
875
+ "learning_rate": 0.00017058851561119198,
876
+ "loss": 0.968,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.8,
881
+ "grad_norm": 0.08277314156293869,
882
+ "learning_rate": 0.00017009776598061495,
883
+ "loss": 0.9869,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.81,
888
+ "grad_norm": 0.07559008151292801,
889
+ "learning_rate": 0.00016960367455812336,
890
+ "loss": 0.9804,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.82,
895
+ "grad_norm": 0.06251110136508942,
896
+ "learning_rate": 0.00016910626489868649,
897
+ "loss": 0.978,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.82,
902
+ "grad_norm": 0.06253345310688019,
903
+ "learning_rate": 0.0001686055607154648,
904
+ "loss": 0.9524,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.83,
909
+ "grad_norm": 0.05948334559798241,
910
+ "learning_rate": 0.00016810158587867973,
911
+ "loss": 0.9826,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.84,
916
+ "grad_norm": 0.06356865167617798,
917
+ "learning_rate": 0.00016759436441447545,
918
+ "loss": 0.9805,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.84,
923
+ "grad_norm": 0.06536010652780533,
924
+ "learning_rate": 0.00016708392050377363,
925
+ "loss": 1.0146,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.85,
930
+ "grad_norm": 0.06137322261929512,
931
+ "learning_rate": 0.00016657027848112062,
932
+ "loss": 0.9457,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.85,
937
+ "grad_norm": 0.05955340713262558,
938
+ "learning_rate": 0.00016605346283352727,
939
+ "loss": 0.9823,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.86,
944
+ "grad_norm": 0.0602475143969059,
945
+ "learning_rate": 0.00016553349819930165,
946
+ "loss": 1.0077,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.87,
951
+ "grad_norm": 0.05905039981007576,
952
+ "learning_rate": 0.00016501040936687443,
953
+ "loss": 0.9313,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.87,
958
+ "grad_norm": 0.06087419390678406,
959
+ "learning_rate": 0.00016448422127361706,
960
+ "loss": 0.9725,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.88,
965
+ "grad_norm": 0.059714119881391525,
966
+ "learning_rate": 0.00016395495900465304,
967
+ "loss": 0.9963,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.89,
972
+ "grad_norm": 0.06461544334888458,
973
+ "learning_rate": 0.000163422647791662,
974
+ "loss": 0.957,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.89,
979
+ "grad_norm": 0.06247726082801819,
980
+ "learning_rate": 0.00016288731301167668,
981
+ "loss": 0.9742,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.9,
986
+ "grad_norm": 0.06527213007211685,
987
+ "learning_rate": 0.00016234898018587337,
988
+ "loss": 0.9789,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.91,
993
+ "grad_norm": 0.059757690876722336,
994
+ "learning_rate": 0.00016180767497835503,
995
+ "loss": 0.9309,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.91,
1000
+ "grad_norm": 0.059084221720695496,
1001
+ "learning_rate": 0.00016126342319492784,
1002
+ "loss": 0.9546,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.92,
1007
+ "grad_norm": 1.778961181640625,
1008
+ "learning_rate": 0.00016071625078187114,
1009
+ "loss": 2.6066,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.93,
1014
+ "grad_norm": 0.06468740105628967,
1015
+ "learning_rate": 0.00016016618382470012,
1016
+ "loss": 0.9472,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.93,
1021
+ "grad_norm": 0.061647091060876846,
1022
+ "learning_rate": 0.00015961324854692254,
1023
+ "loss": 0.9836,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.94,
1028
+ "grad_norm": 0.06061193719506264,
1029
+ "learning_rate": 0.0001590574713087885,
1030
+ "loss": 0.982,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.94,
1035
+ "grad_norm": 0.06635820865631104,
1036
+ "learning_rate": 0.00015849887860603374,
1037
+ "loss": 0.9873,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.95,
1042
+ "grad_norm": 0.06260058283805847,
1043
+ "learning_rate": 0.00015793749706861636,
1044
+ "loss": 0.9827,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.96,
1049
+ "grad_norm": 0.06037148833274841,
1050
+ "learning_rate": 0.00015737335345944757,
1051
+ "loss": 1.0072,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.96,
1056
+ "grad_norm": 0.06277037411928177,
1057
+ "learning_rate": 0.00015680647467311557,
1058
+ "loss": 0.9498,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.97,
1063
+ "grad_norm": 0.06306284666061401,
1064
+ "learning_rate": 0.00015623688773460357,
1065
+ "loss": 0.9866,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.98,
1070
+ "grad_norm": 0.07311715185642242,
1071
+ "learning_rate": 0.00015566461979800122,
1072
+ "loss": 0.9722,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.98,
1077
+ "grad_norm": 0.06143077090382576,
1078
+ "learning_rate": 0.00015508969814521025,
1079
+ "loss": 0.9442,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.99,
1084
+ "grad_norm": 0.067879818379879,
1085
+ "learning_rate": 0.00015451215018464387,
1086
+ "loss": 0.9416,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.0,
1091
+ "grad_norm": 0.06907378137111664,
1092
+ "learning_rate": 0.00015393200344991995,
1093
+ "loss": 0.9813,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.0,
1098
+ "grad_norm": 0.06299201399087906,
1099
+ "learning_rate": 0.0001533492855985485,
1100
+ "loss": 0.9684,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.01,
1105
+ "grad_norm": 0.059243012219667435,
1106
+ "learning_rate": 0.0001527640244106133,
1107
+ "loss": 0.9883,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.01,
1112
+ "grad_norm": 0.06446617841720581,
1113
+ "learning_rate": 0.00015217624778744718,
1114
+ "loss": 0.9836,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.02,
1119
+ "grad_norm": 0.07795852422714233,
1120
+ "learning_rate": 0.00015158598375030217,
1121
+ "loss": 0.9682,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.01,
1126
+ "grad_norm": 0.0846932977437973,
1127
+ "learning_rate": 0.0001509932604390136,
1128
+ "loss": 0.8964,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.01,
1133
+ "grad_norm": 0.06378539651632309,
1134
+ "learning_rate": 0.0001503981061106584,
1135
+ "loss": 0.8712,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.02,
1140
+ "grad_norm": 0.06959015876054764,
1141
+ "learning_rate": 0.00014980054913820814,
1142
+ "loss": 0.8538,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.03,
1147
+ "grad_norm": 0.11089441180229187,
1148
+ "learning_rate": 0.00014920061800917638,
1149
+ "loss": 0.8898,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.03,
1154
+ "grad_norm": 0.10314545780420303,
1155
+ "learning_rate": 0.0001485983413242606,
1156
+ "loss": 0.858,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.04,
1161
+ "grad_norm": 0.06961672008037567,
1162
+ "learning_rate": 0.00014799374779597867,
1163
+ "loss": 0.8605,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.04,
1168
+ "grad_norm": 0.07029856741428375,
1169
+ "learning_rate": 0.00014738686624729986,
1170
+ "loss": 0.8536,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.05,
1175
+ "grad_norm": 0.07742595672607422,
1176
+ "learning_rate": 0.0001467777256102712,
1177
+ "loss": 0.875,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.06,
1182
+ "grad_norm": 0.06792555004358292,
1183
+ "learning_rate": 0.00014616635492463776,
1184
+ "loss": 0.8829,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.06,
1189
+ "grad_norm": 0.08564931154251099,
1190
+ "learning_rate": 0.00014555278333645833,
1191
+ "loss": 0.9109,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.07,
1196
+ "grad_norm": 0.0962703675031662,
1197
+ "learning_rate": 0.00014493704009671613,
1198
+ "loss": 0.8707,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.08,
1203
+ "grad_norm": 0.09053023904561996,
1204
+ "learning_rate": 0.00014431915455992414,
1205
+ "loss": 0.9005,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.08,
1210
+ "grad_norm": 0.07491155713796616,
1211
+ "learning_rate": 0.00014369915618272567,
1212
+ "loss": 0.8805,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.09,
1217
+ "grad_norm": 0.08745575696229935,
1218
+ "learning_rate": 0.00014307707452249012,
1219
+ "loss": 0.8766,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.1,
1224
+ "grad_norm": 0.08251971006393433,
1225
+ "learning_rate": 0.0001424529392359039,
1226
+ "loss": 0.8939,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.1,
1231
+ "grad_norm": 0.07616613060235977,
1232
+ "learning_rate": 0.0001418267800775565,
1233
+ "loss": 0.8678,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.11,
1238
+ "grad_norm": 0.08193603903055191,
1239
+ "learning_rate": 0.00014119862689852223,
1240
+ "loss": 0.8473,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.12,
1245
+ "grad_norm": 0.08167202025651932,
1246
+ "learning_rate": 0.0001405685096449367,
1247
+ "loss": 0.8669,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.12,
1252
+ "grad_norm": 0.08531814068555832,
1253
+ "learning_rate": 0.00013993645835656953,
1254
+ "loss": 0.8637,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.13,
1259
+ "grad_norm": 0.08357888460159302,
1260
+ "learning_rate": 0.00013930250316539238,
1261
+ "loss": 0.846,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.13,
1266
+ "grad_norm": 0.583361804485321,
1267
+ "learning_rate": 0.0001386666742941419,
1268
+ "loss": 2.3925,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.14,
1273
+ "grad_norm": 0.08598628640174866,
1274
+ "learning_rate": 0.00013802900205487948,
1275
+ "loss": 0.8702,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.15,
1280
+ "grad_norm": 0.0913216769695282,
1281
+ "learning_rate": 0.00013738951684754585,
1282
+ "loss": 0.8492,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.15,
1287
+ "grad_norm": 0.08879151940345764,
1288
+ "learning_rate": 0.00013674824915851192,
1289
+ "loss": 0.8721,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.16,
1294
+ "grad_norm": 0.09359906613826752,
1295
+ "learning_rate": 0.0001361052295591255,
1296
+ "loss": 0.8678,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.17,
1301
+ "grad_norm": 0.09475123882293701,
1302
+ "learning_rate": 0.00013546048870425356,
1303
+ "loss": 0.8514,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.17,
1308
+ "grad_norm": 0.1002567857503891,
1309
+ "learning_rate": 0.00013481405733082116,
1310
+ "loss": 0.8688,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.18,
1315
+ "grad_norm": 0.09523095935583115,
1316
+ "learning_rate": 0.00013416596625634593,
1317
+ "loss": 0.8776,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.19,
1322
+ "grad_norm": 0.09465932101011276,
1323
+ "learning_rate": 0.00013351624637746886,
1324
+ "loss": 0.8965,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.19,
1329
+ "grad_norm": 0.09145588427782059,
1330
+ "learning_rate": 0.00013286492866848142,
1331
+ "loss": 0.8587,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.2,
1336
+ "grad_norm": 0.09743087738752365,
1337
+ "learning_rate": 0.00013221204417984908,
1338
+ "loss": 0.823,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.21,
1343
+ "grad_norm": 0.09468277543783188,
1344
+ "learning_rate": 0.00013155762403673063,
1345
+ "loss": 0.8578,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.21,
1350
+ "grad_norm": 0.09516102075576782,
1351
+ "learning_rate": 0.00013090169943749476,
1352
+ "loss": 0.8944,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.22,
1357
+ "grad_norm": 0.09514753520488739,
1358
+ "learning_rate": 0.00013024430165223244,
1359
+ "loss": 0.8175,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.22,
1364
+ "grad_norm": 0.10116668790578842,
1365
+ "learning_rate": 0.0001295854620212664,
1366
+ "loss": 0.8572,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.23,
1371
+ "grad_norm": 0.09801662713289261,
1372
+ "learning_rate": 0.00012892521195365678,
1373
+ "loss": 0.8532,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.24,
1378
+ "grad_norm": 0.09754762053489685,
1379
+ "learning_rate": 0.00012826358292570398,
1380
+ "loss": 0.8653,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.24,
1385
+ "grad_norm": 0.10124494135379791,
1386
+ "learning_rate": 0.00012760060647944795,
1387
+ "loss": 0.9007,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.25,
1392
+ "grad_norm": 0.09749335795640945,
1393
+ "learning_rate": 0.00012693631422116454,
1394
+ "loss": 0.8304,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.26,
1399
+ "grad_norm": 0.09953852742910385,
1400
+ "learning_rate": 0.0001262707378198587,
1401
+ "loss": 0.8759,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.26,
1406
+ "grad_norm": 0.10160723328590393,
1407
+ "learning_rate": 0.0001256039090057547,
1408
+ "loss": 0.8923,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.27,
1413
+ "grad_norm": 0.1000576838850975,
1414
+ "learning_rate": 0.00012493585956878354,
1415
+ "loss": 0.8397,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.28,
1420
+ "grad_norm": 0.10324119031429291,
1421
+ "learning_rate": 0.0001242666213570672,
1422
+ "loss": 0.8787,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.28,
1427
+ "grad_norm": 0.1018192246556282,
1428
+ "learning_rate": 0.00012359622627540058,
1429
+ "loss": 0.8318,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.29,
1434
+ "grad_norm": 0.10028495639562607,
1435
+ "learning_rate": 0.00012292470628373037,
1436
+ "loss": 0.8354,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.3,
1441
+ "grad_norm": 0.10520325601100922,
1442
+ "learning_rate": 0.00012225209339563145,
1443
+ "loss": 0.8586,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.3,
1448
+ "grad_norm": 0.10229421406984329,
1449
+ "learning_rate": 0.00012157841967678063,
1450
+ "loss": 0.8961,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.31,
1455
+ "grad_norm": 0.10230256617069244,
1456
+ "learning_rate": 0.00012090371724342804,
1457
+ "loss": 0.8851,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.31,
1462
+ "grad_norm": 0.10282580554485321,
1463
+ "learning_rate": 0.00012022801826086609,
1464
+ "loss": 0.8588,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.32,
1469
+ "grad_norm": 0.1008041650056839,
1470
+ "learning_rate": 0.00011955135494189588,
1471
+ "loss": 0.8462,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.33,
1476
+ "grad_norm": 0.10294941067695618,
1477
+ "learning_rate": 0.00011887375954529168,
1478
+ "loss": 0.8301,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.33,
1483
+ "grad_norm": 0.10411438345909119,
1484
+ "learning_rate": 0.00011819526437426298,
1485
+ "loss": 0.8299,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.34,
1490
+ "grad_norm": 0.10526308417320251,
1491
+ "learning_rate": 0.0001175159017749144,
1492
+ "loss": 0.8624,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.35,
1497
+ "grad_norm": 0.10539798438549042,
1498
+ "learning_rate": 0.00011683570413470383,
1499
+ "loss": 0.8473,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.35,
1504
+ "grad_norm": 0.09961718320846558,
1505
+ "learning_rate": 0.00011615470388089835,
1506
+ "loss": 0.8571,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.36,
1511
+ "grad_norm": 0.10262471437454224,
1512
+ "learning_rate": 0.00011547293347902812,
1513
+ "loss": 0.8539,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.37,
1518
+ "grad_norm": 0.10586554557085037,
1519
+ "learning_rate": 0.00011479042543133895,
1520
+ "loss": 0.8559,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.37,
1525
+ "grad_norm": 0.10486755520105362,
1526
+ "learning_rate": 0.00011410721227524255,
1527
+ "loss": 0.8726,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.38,
1532
+ "grad_norm": 0.10485829412937164,
1533
+ "learning_rate": 0.00011342332658176555,
1534
+ "loss": 0.8903,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.39,
1539
+ "grad_norm": 0.10306116938591003,
1540
+ "learning_rate": 0.00011273880095399667,
1541
+ "loss": 0.8495,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.39,
1546
+ "grad_norm": 0.10205783694982529,
1547
+ "learning_rate": 0.0001120536680255323,
1548
+ "loss": 0.86,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.4,
1553
+ "grad_norm": 0.10305880010128021,
1554
+ "learning_rate": 0.00011136796045892102,
1555
+ "loss": 0.8617,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.4,
1560
+ "grad_norm": 0.10516184568405151,
1561
+ "learning_rate": 0.00011068171094410618,
1562
+ "loss": 0.8942,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.41,
1567
+ "grad_norm": 0.10830646008253098,
1568
+ "learning_rate": 0.00010999495219686762,
1569
+ "loss": 0.8853,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.42,
1574
+ "grad_norm": 0.10334376990795135,
1575
+ "learning_rate": 0.00010930771695726201,
1576
+ "loss": 0.8183,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.42,
1581
+ "grad_norm": 0.10024702548980713,
1582
+ "learning_rate": 0.00010862003798806196,
1583
+ "loss": 0.8503,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.43,
1588
+ "grad_norm": 0.10792502015829086,
1589
+ "learning_rate": 0.00010793194807319408,
1590
+ "loss": 0.8746,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.44,
1595
+ "grad_norm": 0.10143101215362549,
1596
+ "learning_rate": 0.00010724348001617625,
1597
+ "loss": 0.8321,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.44,
1602
+ "grad_norm": 0.09850587695837021,
1603
+ "learning_rate": 0.00010655466663855349,
1604
+ "loss": 0.8649,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.45,
1609
+ "grad_norm": 0.10333626717329025,
1610
+ "learning_rate": 0.00010586554077833347,
1611
+ "loss": 0.8722,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.46,
1616
+ "grad_norm": 0.10461243987083435,
1617
+ "learning_rate": 0.00010517613528842097,
1618
+ "loss": 0.8961,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.46,
1623
+ "grad_norm": 0.10886025428771973,
1624
+ "learning_rate": 0.00010448648303505151,
1625
+ "loss": 0.8921,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.47,
1630
+ "grad_norm": 0.10471045225858688,
1631
+ "learning_rate": 0.00010379661689622477,
1632
+ "loss": 0.8647,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.48,
1637
+ "grad_norm": 0.10855681449174881,
1638
+ "learning_rate": 0.00010310656976013705,
1639
+ "loss": 0.8783,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 1.48,
1644
+ "grad_norm": 0.11153094470500946,
1645
+ "learning_rate": 0.00010241637452361323,
1646
+ "loss": 0.8732,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 1.49,
1651
+ "grad_norm": 0.10941874235868454,
1652
+ "learning_rate": 0.00010172606409053886,
1653
+ "loss": 0.8555,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 1.49,
1658
+ "grad_norm": 0.10388068854808807,
1659
+ "learning_rate": 0.0001010356713702911,
1660
+ "loss": 0.8549,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 1.5,
1665
+ "grad_norm": 0.1045478880405426,
1666
+ "learning_rate": 0.00010034522927617014,
1667
+ "loss": 0.8706,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 1.51,
1672
+ "grad_norm": 0.10188283771276474,
1673
+ "learning_rate": 9.96547707238299e-05,
1674
+ "loss": 0.8916,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 1.51,
1679
+ "grad_norm": 0.10076084733009338,
1680
+ "learning_rate": 9.896432862970892e-05,
1681
+ "loss": 0.8841,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 1.52,
1686
+ "grad_norm": 0.10353115946054459,
1687
+ "learning_rate": 9.827393590946116e-05,
1688
+ "loss": 0.8723,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 1.53,
1693
+ "grad_norm": 0.10559534281492233,
1694
+ "learning_rate": 9.75836254763868e-05,
1695
+ "loss": 0.8679,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 1.53,
1700
+ "grad_norm": 0.10226694494485855,
1701
+ "learning_rate": 9.689343023986302e-05,
1702
+ "loss": 0.8434,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 1.54,
1707
+ "grad_norm": 0.10569630563259125,
1708
+ "learning_rate": 9.620338310377525e-05,
1709
+ "loss": 0.8768,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 1.55,
1714
+ "grad_norm": 0.10112857073545456,
1715
+ "learning_rate": 9.551351696494854e-05,
1716
+ "loss": 0.8249,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 1.55,
1721
+ "grad_norm": 0.10926086455583572,
1722
+ "learning_rate": 9.482386471157904e-05,
1723
+ "loss": 0.8634,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 1.56,
1728
+ "grad_norm": 0.1026775911450386,
1729
+ "learning_rate": 9.413445922166653e-05,
1730
+ "loss": 0.8679,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 1.57,
1735
+ "grad_norm": 0.10021597146987915,
1736
+ "learning_rate": 9.344533336144652e-05,
1737
+ "loss": 0.8596,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 1.57,
1742
+ "grad_norm": 0.1025286465883255,
1743
+ "learning_rate": 9.275651998382377e-05,
1744
+ "loss": 0.8302,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 1.58,
1749
+ "grad_norm": 0.0997297540307045,
1750
+ "learning_rate": 9.206805192680593e-05,
1751
+ "loss": 0.8818,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 1.58,
1756
+ "grad_norm": 0.10259710997343063,
1757
+ "learning_rate": 9.137996201193805e-05,
1758
+ "loss": 0.8558,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 1.59,
1763
+ "grad_norm": 0.1076403483748436,
1764
+ "learning_rate": 9.069228304273802e-05,
1765
+ "loss": 0.8922,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 1.6,
1770
+ "grad_norm": 0.10561492294073105,
1771
+ "learning_rate": 9.00050478031324e-05,
1772
+ "loss": 0.8593,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 1.6,
1777
+ "grad_norm": 0.10473283380270004,
1778
+ "learning_rate": 8.931828905589385e-05,
1779
+ "loss": 0.8893,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 1.61,
1784
+ "grad_norm": 0.11126771569252014,
1785
+ "learning_rate": 8.863203954107902e-05,
1786
+ "loss": 0.8761,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 1.62,
1791
+ "grad_norm": 0.10318706929683685,
1792
+ "learning_rate": 8.79463319744677e-05,
1793
+ "loss": 0.8688,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 1.62,
1798
+ "grad_norm": 0.10156065970659256,
1799
+ "learning_rate": 8.726119904600336e-05,
1800
+ "loss": 0.8683,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 1.63,
1805
+ "grad_norm": 0.0986093133687973,
1806
+ "learning_rate": 8.657667341823448e-05,
1807
+ "loss": 0.8375,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 1.64,
1812
+ "grad_norm": 0.10292702913284302,
1813
+ "learning_rate": 8.589278772475749e-05,
1814
+ "loss": 0.8623,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 1.64,
1819
+ "grad_norm": 0.1031164601445198,
1820
+ "learning_rate": 8.520957456866107e-05,
1821
+ "loss": 0.8633,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 1.65,
1826
+ "grad_norm": 0.0997462198138237,
1827
+ "learning_rate": 8.452706652097186e-05,
1828
+ "loss": 0.8462,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 1.66,
1833
+ "grad_norm": 0.11357836425304413,
1834
+ "learning_rate": 8.384529611910163e-05,
1835
+ "loss": 0.8316,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 1.66,
1840
+ "grad_norm": 0.10290369391441345,
1841
+ "learning_rate": 8.316429586529615e-05,
1842
+ "loss": 0.8357,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 1.67,
1847
+ "grad_norm": 0.10479974746704102,
1848
+ "learning_rate": 8.248409822508561e-05,
1849
+ "loss": 0.8591,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 1.67,
1854
+ "grad_norm": 0.1035972386598587,
1855
+ "learning_rate": 8.180473562573705e-05,
1856
+ "loss": 0.8351,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 1.68,
1861
+ "grad_norm": 0.10530169308185577,
1862
+ "learning_rate": 8.112624045470835e-05,
1863
+ "loss": 0.8387,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 1.69,
1868
+ "grad_norm": 0.09917616844177246,
1869
+ "learning_rate": 8.044864505810414e-05,
1870
+ "loss": 0.8699,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 1.69,
1875
+ "grad_norm": 0.10452553629875183,
1876
+ "learning_rate": 7.977198173913394e-05,
1877
+ "loss": 0.859,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 1.7,
1882
+ "grad_norm": 0.10981190949678421,
1883
+ "learning_rate": 7.909628275657198e-05,
1884
+ "loss": 0.8443,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 1.71,
1889
+ "grad_norm": 0.10094719380140305,
1890
+ "learning_rate": 7.84215803232194e-05,
1891
+ "loss": 0.8461,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 1.71,
1896
+ "grad_norm": 0.11014903336763382,
1897
+ "learning_rate": 7.774790660436858e-05,
1898
+ "loss": 0.8409,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 1.72,
1903
+ "grad_norm": 0.10279539972543716,
1904
+ "learning_rate": 7.707529371626965e-05,
1905
+ "loss": 0.8588,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 1.73,
1910
+ "grad_norm": 0.10260649770498276,
1911
+ "learning_rate": 7.640377372459945e-05,
1912
+ "loss": 0.8702,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 1.73,
1917
+ "grad_norm": 0.10066790878772736,
1918
+ "learning_rate": 7.573337864293283e-05,
1919
+ "loss": 0.8523,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 1.74,
1924
+ "grad_norm": 0.10237132757902145,
1925
+ "learning_rate": 7.506414043121647e-05,
1926
+ "loss": 0.8676,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 1.75,
1931
+ "grad_norm": 0.10095226764678955,
1932
+ "learning_rate": 7.43960909942453e-05,
1933
+ "loss": 0.8802,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 1.75,
1938
+ "grad_norm": 0.10220375657081604,
1939
+ "learning_rate": 7.372926218014131e-05,
1940
+ "loss": 0.8347,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 1.76,
1945
+ "grad_norm": 0.09893085062503815,
1946
+ "learning_rate": 7.306368577883547e-05,
1947
+ "loss": 0.8565,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 1.76,
1952
+ "grad_norm": 0.10145033895969391,
1953
+ "learning_rate": 7.239939352055208e-05,
1954
+ "loss": 0.8565,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 1.77,
1959
+ "grad_norm": 0.10070981830358505,
1960
+ "learning_rate": 7.173641707429606e-05,
1961
+ "loss": 0.8475,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.78,
1966
+ "grad_norm": 0.10595450550317764,
1967
+ "learning_rate": 7.107478804634325e-05,
1968
+ "loss": 0.8368,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.78,
1973
+ "grad_norm": 0.1085483580827713,
1974
+ "learning_rate": 7.041453797873363e-05,
1975
+ "loss": 0.866,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 1.79,
1980
+ "grad_norm": 0.1005505919456482,
1981
+ "learning_rate": 6.975569834776758e-05,
1982
+ "loss": 0.8393,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 1.8,
1987
+ "grad_norm": 0.10384807735681534,
1988
+ "learning_rate": 6.909830056250527e-05,
1989
+ "loss": 0.8571,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 1.8,
1994
+ "grad_norm": 0.10558132082223892,
1995
+ "learning_rate": 6.844237596326941e-05,
1996
+ "loss": 0.8477,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 1.81,
2001
+ "grad_norm": 0.10049811750650406,
2002
+ "learning_rate": 6.778795582015097e-05,
2003
+ "loss": 0.8317,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 1.82,
2008
+ "grad_norm": 0.10088322311639786,
2009
+ "learning_rate": 6.713507133151857e-05,
2010
+ "loss": 0.8602,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 1.82,
2015
+ "grad_norm": 0.09972478449344635,
2016
+ "learning_rate": 6.648375362253118e-05,
2017
+ "loss": 0.8514,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 1.83,
2022
+ "grad_norm": 0.10518650710582733,
2023
+ "learning_rate": 6.583403374365405e-05,
2024
+ "loss": 0.8732,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 1.84,
2029
+ "grad_norm": 0.10432999581098557,
2030
+ "learning_rate": 6.518594266917882e-05,
2031
+ "loss": 0.9014,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 1.84,
2036
+ "grad_norm": 0.10011251270771027,
2037
+ "learning_rate": 6.453951129574644e-05,
2038
+ "loss": 0.8192,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 1.85,
2043
+ "grad_norm": 0.09896595031023026,
2044
+ "learning_rate": 6.389477044087452e-05,
2045
+ "loss": 0.8148,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 1.85,
2050
+ "grad_norm": 0.10062045603990555,
2051
+ "learning_rate": 6.325175084148809e-05,
2052
+ "loss": 0.8303,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 1.86,
2057
+ "grad_norm": 0.1033136248588562,
2058
+ "learning_rate": 6.261048315245419e-05,
2059
+ "loss": 0.8537,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 1.87,
2064
+ "grad_norm": 0.10438770055770874,
2065
+ "learning_rate": 6.197099794512056e-05,
2066
+ "loss": 0.8881,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 1.87,
2071
+ "grad_norm": 0.1036936491727829,
2072
+ "learning_rate": 6.133332570585812e-05,
2073
+ "loss": 0.85,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 1.88,
2078
+ "grad_norm": 0.10618463903665543,
2079
+ "learning_rate": 6.069749683460765e-05,
2080
+ "loss": 0.8618,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 1.89,
2085
+ "grad_norm": 0.10110071301460266,
2086
+ "learning_rate": 6.006354164343046e-05,
2087
+ "loss": 0.8632,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 1.89,
2092
+ "grad_norm": 0.10008033365011215,
2093
+ "learning_rate": 5.943149035506337e-05,
2094
+ "loss": 0.8648,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 1.9,
2099
+ "grad_norm": 0.09985347092151642,
2100
+ "learning_rate": 5.880137310147782e-05,
2101
+ "loss": 0.893,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 1.91,
2106
+ "grad_norm": 0.09989628195762634,
2107
+ "learning_rate": 5.817321992244351e-05,
2108
+ "loss": 0.8682,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 1.91,
2113
+ "grad_norm": 0.10163696855306625,
2114
+ "learning_rate": 5.754706076409613e-05,
2115
+ "loss": 0.8554,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 1.92,
2120
+ "grad_norm": 0.10319127887487411,
2121
+ "learning_rate": 5.692292547750988e-05,
2122
+ "loss": 0.8603,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 1.93,
2127
+ "grad_norm": 0.10187959671020508,
2128
+ "learning_rate": 5.630084381727434e-05,
2129
+ "loss": 0.8628,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 1.93,
2134
+ "grad_norm": 0.09999451041221619,
2135
+ "learning_rate": 5.568084544007588e-05,
2136
+ "loss": 0.8471,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 1.94,
2141
+ "grad_norm": 0.10175001621246338,
2142
+ "learning_rate": 5.506295990328385e-05,
2143
+ "loss": 0.8371,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 1.94,
2148
+ "grad_norm": 0.10206517577171326,
2149
+ "learning_rate": 5.444721666354169e-05,
2150
+ "loss": 0.8836,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 1.95,
2155
+ "grad_norm": 0.10593275725841522,
2156
+ "learning_rate": 5.383364507536229e-05,
2157
+ "loss": 0.8397,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 1.96,
2162
+ "grad_norm": 0.10138902068138123,
2163
+ "learning_rate": 5.32222743897288e-05,
2164
+ "loss": 0.8749,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 1.96,
2169
+ "grad_norm": 0.1002379059791565,
2170
+ "learning_rate": 5.261313375270014e-05,
2171
+ "loss": 0.8338,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 1.97,
2176
+ "grad_norm": 0.11006593704223633,
2177
+ "learning_rate": 5.200625220402139e-05,
2178
+ "loss": 0.8779,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 1.98,
2183
+ "grad_norm": 0.10245108604431152,
2184
+ "learning_rate": 5.14016586757394e-05,
2185
+ "loss": 0.8585,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 1.98,
2190
+ "grad_norm": 0.10026349872350693,
2191
+ "learning_rate": 5.0799381990823636e-05,
2192
+ "loss": 0.8563,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 1.99,
2197
+ "grad_norm": 0.10075627267360687,
2198
+ "learning_rate": 5.0199450861791916e-05,
2199
+ "loss": 0.8569,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 2.0,
2204
+ "grad_norm": 0.10112147778272629,
2205
+ "learning_rate": 4.960189388934163e-05,
2206
+ "loss": 0.8453,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 2.0,
2211
+ "grad_norm": 0.10117790102958679,
2212
+ "learning_rate": 4.900673956098644e-05,
2213
+ "loss": 0.8458,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 2.01,
2218
+ "grad_norm": 0.10271448642015457,
2219
+ "learning_rate": 4.841401624969782e-05,
2220
+ "loss": 0.8801,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 2.01,
2225
+ "grad_norm": 0.10152995586395264,
2226
+ "learning_rate": 4.782375221255285e-05,
2227
+ "loss": 0.8334,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 2.02,
2232
+ "grad_norm": 0.12786038219928741,
2233
+ "learning_rate": 4.723597558938672e-05,
2234
+ "loss": 0.8573,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 2.01,
2239
+ "grad_norm": 0.12889742851257324,
2240
+ "learning_rate": 4.66507144014515e-05,
2241
+ "loss": 0.7692,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 2.01,
2246
+ "grad_norm": 0.11231512576341629,
2247
+ "learning_rate": 4.606799655008009e-05,
2248
+ "loss": 0.7609,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 2.02,
2253
+ "grad_norm": 0.10861942172050476,
2254
+ "learning_rate": 4.548784981535614e-05,
2255
+ "loss": 0.7596,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 2.03,
2260
+ "grad_norm": 0.10464295744895935,
2261
+ "learning_rate": 4.491030185478976e-05,
2262
+ "loss": 0.7382,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 2.03,
2267
+ "grad_norm": 0.11696916818618774,
2268
+ "learning_rate": 4.433538020199882e-05,
2269
+ "loss": 0.7422,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 2.04,
2274
+ "grad_norm": 0.134673073887825,
2275
+ "learning_rate": 4.376311226539644e-05,
2276
+ "loss": 0.7449,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 2.04,
2281
+ "grad_norm": 0.1342369168996811,
2282
+ "learning_rate": 4.3193525326884435e-05,
2283
+ "loss": 0.7518,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 2.05,
2288
+ "grad_norm": 0.13265672326087952,
2289
+ "learning_rate": 4.262664654055246e-05,
2290
+ "loss": 0.7285,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 2.06,
2295
+ "grad_norm": 0.1257001906633377,
2296
+ "learning_rate": 4.2062502931383664e-05,
2297
+ "loss": 0.7393,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 2.06,
2302
+ "grad_norm": 0.1159779280424118,
2303
+ "learning_rate": 4.1501121393966305e-05,
2304
+ "loss": 0.7768,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 2.07,
2309
+ "grad_norm": 0.11127850413322449,
2310
+ "learning_rate": 4.0942528691211526e-05,
2311
+ "loss": 0.7737,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 2.08,
2316
+ "grad_norm": 0.11521172523498535,
2317
+ "learning_rate": 4.038675145307747e-05,
2318
+ "loss": 0.7507,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 2.08,
2323
+ "grad_norm": 0.12056267261505127,
2324
+ "learning_rate": 3.98338161752999e-05,
2325
+ "loss": 0.7678,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 2.09,
2330
+ "grad_norm": 0.1185149997472763,
2331
+ "learning_rate": 3.9283749218128885e-05,
2332
+ "loss": 0.7329,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 2.1,
2337
+ "grad_norm": 0.12041933834552765,
2338
+ "learning_rate": 3.873657680507217e-05,
2339
+ "loss": 0.7231,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 2.1,
2344
+ "grad_norm": 0.11616391688585281,
2345
+ "learning_rate": 3.819232502164499e-05,
2346
+ "loss": 0.7554,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 2.11,
2351
+ "grad_norm": 0.11951781064271927,
2352
+ "learning_rate": 3.7651019814126654e-05,
2353
+ "loss": 0.7439,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 2.12,
2358
+ "grad_norm": 0.11885462701320648,
2359
+ "learning_rate": 3.711268698832335e-05,
2360
+ "loss": 0.7428,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 2.12,
2365
+ "grad_norm": 0.11805927753448486,
2366
+ "learning_rate": 3.6577352208338015e-05,
2367
+ "loss": 0.727,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 2.13,
2372
+ "grad_norm": 0.1328866332769394,
2373
+ "learning_rate": 3.604504099534696e-05,
2374
+ "loss": 0.7879,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 2.13,
2379
+ "grad_norm": 0.1301942765712738,
2380
+ "learning_rate": 3.5515778726382966e-05,
2381
+ "loss": 0.77,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 2.14,
2386
+ "grad_norm": 0.12639887630939484,
2387
+ "learning_rate": 3.498959063312558e-05,
2388
+ "loss": 0.7337,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 2.15,
2393
+ "grad_norm": 0.11830651760101318,
2394
+ "learning_rate": 3.446650180069837e-05,
2395
+ "loss": 0.7345,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 2.15,
2400
+ "grad_norm": 0.1206677109003067,
2401
+ "learning_rate": 3.394653716647277e-05,
2402
+ "loss": 0.7439,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 2.16,
2407
+ "grad_norm": 0.1203649565577507,
2408
+ "learning_rate": 3.342972151887941e-05,
2409
+ "loss": 0.7289,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 2.17,
2414
+ "grad_norm": 0.12418176233768463,
2415
+ "learning_rate": 3.29160794962264e-05,
2416
+ "loss": 0.7597,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 2.17,
2421
+ "grad_norm": 0.11708332598209381,
2422
+ "learning_rate": 3.2405635585524565e-05,
2423
+ "loss": 0.7551,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 2.18,
2428
+ "grad_norm": 0.12150386720895767,
2429
+ "learning_rate": 3.1898414121320276e-05,
2430
+ "loss": 0.7575,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 2.19,
2435
+ "grad_norm": 0.12156111001968384,
2436
+ "learning_rate": 3.1394439284535205e-05,
2437
+ "loss": 0.7704,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 2.19,
2442
+ "grad_norm": 0.12297102808952332,
2443
+ "learning_rate": 3.089373510131354e-05,
2444
+ "loss": 0.7158,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 2.2,
2449
+ "grad_norm": 0.12420902401208878,
2450
+ "learning_rate": 3.039632544187663e-05,
2451
+ "loss": 0.7413,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 2.21,
2456
+ "grad_norm": 0.1244964450597763,
2457
+ "learning_rate": 2.9902234019385057e-05,
2458
+ "loss": 0.7274,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 2.21,
2463
+ "grad_norm": 0.12399135529994965,
2464
+ "learning_rate": 2.941148438880803e-05,
2465
+ "loss": 0.7161,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 2.22,
2470
+ "grad_norm": 0.12398847192525864,
2471
+ "learning_rate": 2.892409994580053e-05,
2472
+ "loss": 0.7195,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 2.22,
2477
+ "grad_norm": 0.13451841473579407,
2478
+ "learning_rate": 2.84401039255879e-05,
2479
+ "loss": 0.721,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 2.23,
2484
+ "grad_norm": 0.1276804804801941,
2485
+ "learning_rate": 2.795951940185827e-05,
2486
+ "loss": 0.7416,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 2.24,
2491
+ "grad_norm": 0.12256789207458496,
2492
+ "learning_rate": 2.7482369285662378e-05,
2493
+ "loss": 0.7277,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 2.24,
2498
+ "grad_norm": 0.1256253570318222,
2499
+ "learning_rate": 2.7008676324321447e-05,
2500
+ "loss": 0.768,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 2.25,
2505
+ "grad_norm": 0.12436559796333313,
2506
+ "learning_rate": 2.653846310034277e-05,
2507
+ "loss": 0.696,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 2.26,
2512
+ "grad_norm": 0.12579728662967682,
2513
+ "learning_rate": 2.607175203034299e-05,
2514
+ "loss": 0.7419,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 2.26,
2519
+ "grad_norm": 0.12900373339653015,
2520
+ "learning_rate": 2.56085653639795e-05,
2521
+ "loss": 0.7004,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 2.27,
2526
+ "grad_norm": 0.12415504455566406,
2527
+ "learning_rate": 2.514892518288988e-05,
2528
+ "loss": 0.7466,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 2.28,
2533
+ "grad_norm": 0.1270284801721573,
2534
+ "learning_rate": 2.4692853399638917e-05,
2535
+ "loss": 0.7472,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 2.28,
2540
+ "grad_norm": 0.1287553757429123,
2541
+ "learning_rate": 2.4240371756674064e-05,
2542
+ "loss": 0.7576,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 2.29,
2547
+ "grad_norm": 0.1296914666891098,
2548
+ "learning_rate": 2.3791501825289087e-05,
2549
+ "loss": 0.7512,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 2.3,
2554
+ "grad_norm": 0.12564246356487274,
2555
+ "learning_rate": 2.3346265004595392e-05,
2556
+ "loss": 0.7335,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 2.3,
2561
+ "grad_norm": 0.12706796824932098,
2562
+ "learning_rate": 2.290468252050204e-05,
2563
+ "loss": 0.7183,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 2.31,
2568
+ "grad_norm": 0.13130119442939758,
2569
+ "learning_rate": 2.246677542470388e-05,
2570
+ "loss": 0.7354,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 2.31,
2575
+ "grad_norm": 0.12625719606876373,
2576
+ "learning_rate": 2.2032564593677774e-05,
2577
+ "loss": 0.7235,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 2.32,
2582
+ "grad_norm": 0.12731945514678955,
2583
+ "learning_rate": 2.160207072768746e-05,
2584
+ "loss": 0.7126,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 2.33,
2589
+ "grad_norm": 3.1834702491760254,
2590
+ "learning_rate": 2.117531434979675e-05,
2591
+ "loss": 0.7382,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 2.33,
2596
+ "grad_norm": 0.1251527965068817,
2597
+ "learning_rate": 2.0752315804890977e-05,
2598
+ "loss": 0.7345,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 2.34,
2603
+ "grad_norm": 0.129663348197937,
2604
+ "learning_rate": 2.033309525870717e-05,
2605
+ "loss": 0.7133,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 2.35,
2610
+ "grad_norm": 0.12960204482078552,
2611
+ "learning_rate": 1.991767269687278e-05,
2612
+ "loss": 0.7504,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 2.35,
2617
+ "grad_norm": 0.12939876317977905,
2618
+ "learning_rate": 1.9506067923952676e-05,
2619
+ "loss": 0.7437,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 2.36,
2624
+ "grad_norm": 0.1263239085674286,
2625
+ "learning_rate": 1.9098300562505266e-05,
2626
+ "loss": 0.7285,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 2.37,
2631
+ "grad_norm": 0.12983307242393494,
2632
+ "learning_rate": 1.8694390052146737e-05,
2633
+ "loss": 0.7579,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 2.37,
2638
+ "grad_norm": 0.12673123180866241,
2639
+ "learning_rate": 1.8294355648624606e-05,
2640
+ "loss": 0.7345,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 2.38,
2645
+ "grad_norm": 0.13089123368263245,
2646
+ "learning_rate": 1.789821642289945e-05,
2647
+ "loss": 0.7213,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 2.39,
2652
+ "grad_norm": 0.1273745596408844,
2653
+ "learning_rate": 1.750599126023591e-05,
2654
+ "loss": 0.7365,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 2.39,
2659
+ "grad_norm": 0.12967997789382935,
2660
+ "learning_rate": 1.7117698859302357e-05,
2661
+ "loss": 0.7481,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 2.4,
2666
+ "grad_norm": 0.1292778104543686,
2667
+ "learning_rate": 1.6733357731279377e-05,
2668
+ "loss": 0.7547,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 2.4,
2673
+ "grad_norm": 0.1291133165359497,
2674
+ "learning_rate": 1.6352986198977325e-05,
2675
+ "loss": 0.7481,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 2.41,
2680
+ "grad_norm": 0.1252090036869049,
2681
+ "learning_rate": 1.5976602395962893e-05,
2682
+ "loss": 0.7265,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 2.42,
2687
+ "grad_norm": 0.1264342963695526,
2688
+ "learning_rate": 1.560422426569449e-05,
2689
+ "loss": 0.7313,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 2.42,
2694
+ "grad_norm": 0.12565764784812927,
2695
+ "learning_rate": 1.523586956066686e-05,
2696
+ "loss": 0.7292,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 2.43,
2701
+ "grad_norm": 0.13361261785030365,
2702
+ "learning_rate": 1.4871555841564887e-05,
2703
+ "loss": 0.7329,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 2.44,
2708
+ "grad_norm": 0.1277221292257309,
2709
+ "learning_rate": 1.4511300476426227e-05,
2710
+ "loss": 0.7111,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 2.44,
2715
+ "grad_norm": 0.1327228546142578,
2716
+ "learning_rate": 1.415512063981339e-05,
2717
+ "loss": 0.7758,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 2.45,
2722
+ "grad_norm": 0.1299590766429901,
2723
+ "learning_rate": 1.3803033311995072e-05,
2724
+ "loss": 0.7231,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 2.46,
2729
+ "grad_norm": 0.12880592048168182,
2730
+ "learning_rate": 1.3455055278136519e-05,
2731
+ "loss": 0.7434,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 2.46,
2736
+ "grad_norm": 0.13756021857261658,
2737
+ "learning_rate": 1.311120312749935e-05,
2738
+ "loss": 0.778,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 2.47,
2743
+ "grad_norm": 0.12650741636753082,
2744
+ "learning_rate": 1.2771493252650723e-05,
2745
+ "loss": 0.7616,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 2.48,
2750
+ "grad_norm": 0.12972266972064972,
2751
+ "learning_rate": 1.2435941848681864e-05,
2752
+ "loss": 0.7036,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 2.48,
2757
+ "grad_norm": 0.13031339645385742,
2758
+ "learning_rate": 1.2104564912435923e-05,
2759
+ "loss": 0.7417,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 2.49,
2764
+ "grad_norm": 0.12773780524730682,
2765
+ "learning_rate": 1.1777378241745385e-05,
2766
+ "loss": 0.7425,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 2.49,
2771
+ "grad_norm": 0.1417783945798874,
2772
+ "learning_rate": 1.1454397434679021e-05,
2773
+ "loss": 0.7186,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 2.5,
2778
+ "grad_norm": 0.13104471564292908,
2779
+ "learning_rate": 1.11356378887981e-05,
2780
+ "loss": 0.7294,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 2.51,
2785
+ "grad_norm": 0.12571465969085693,
2786
+ "learning_rate": 1.0821114800422483e-05,
2787
+ "loss": 0.7552,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 2.51,
2792
+ "grad_norm": 0.12797923386096954,
2793
+ "learning_rate": 1.0510843163906148e-05,
2794
+ "loss": 0.7605,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 2.52,
2799
+ "grad_norm": 0.12988309562206268,
2800
+ "learning_rate": 1.020483777092226e-05,
2801
+ "loss": 0.7323,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 2.53,
2806
+ "grad_norm": 0.13318131864070892,
2807
+ "learning_rate": 9.903113209758096e-06,
2808
+ "loss": 0.6997,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 2.53,
2813
+ "grad_norm": 0.13210129737854004,
2814
+ "learning_rate": 9.605683864619574e-06,
2815
+ "loss": 0.7418,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 2.54,
2820
+ "grad_norm": 0.13053849339485168,
2821
+ "learning_rate": 9.31256391494546e-06,
2822
+ "loss": 0.7281,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 2.55,
2827
+ "grad_norm": 0.13355886936187744,
2828
+ "learning_rate": 9.023767334731425e-06,
2829
+ "loss": 0.7054,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 2.55,
2834
+ "grad_norm": 0.1265229880809784,
2835
+ "learning_rate": 8.739307891863813e-06,
2836
+ "loss": 0.7539,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 2.56,
2841
+ "grad_norm": 0.12536737322807312,
2842
+ "learning_rate": 8.45919914746337e-06,
2843
+ "loss": 0.738,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 2.57,
2848
+ "grad_norm": 0.12613065540790558,
2849
+ "learning_rate": 8.183454455238636e-06,
2850
+ "loss": 0.7166,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 2.57,
2855
+ "grad_norm": 0.1304968297481537,
2856
+ "learning_rate": 7.912086960849374e-06,
2857
+ "loss": 0.7254,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 2.58,
2862
+ "grad_norm": 0.13125239312648773,
2863
+ "learning_rate": 7.645109601279921e-06,
2864
+ "loss": 0.7266,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 2.58,
2869
+ "grad_norm": 0.1331733912229538,
2870
+ "learning_rate": 7.382535104222366e-06,
2871
+ "loss": 0.7227,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 2.59,
2876
+ "grad_norm": 0.1387336701154709,
2877
+ "learning_rate": 7.124375987469767e-06,
2878
+ "loss": 0.7211,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 2.6,
2883
+ "grad_norm": 0.12945106625556946,
2884
+ "learning_rate": 6.870644558319528e-06,
2885
+ "loss": 0.7451,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 2.6,
2890
+ "grad_norm": 0.12981906533241272,
2891
+ "learning_rate": 6.621352912986467e-06,
2892
+ "loss": 0.7311,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 2.61,
2897
+ "grad_norm": 0.12764017283916473,
2898
+ "learning_rate": 6.37651293602628e-06,
2899
+ "loss": 0.7324,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 2.62,
2904
+ "grad_norm": 0.13377612829208374,
2905
+ "learning_rate": 6.136136299768991e-06,
2906
+ "loss": 0.7674,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 2.62,
2911
+ "grad_norm": 0.1285420060157776,
2912
+ "learning_rate": 5.900234463762366e-06,
2913
+ "loss": 0.735,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 2.63,
2918
+ "grad_norm": 0.13313180208206177,
2919
+ "learning_rate": 5.668818674225685e-06,
2920
+ "loss": 0.7162,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 2.64,
2925
+ "grad_norm": 0.13206835091114044,
2926
+ "learning_rate": 5.44189996351363e-06,
2927
+ "loss": 0.6833,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 2.64,
2932
+ "grad_norm": 0.13363349437713623,
2933
+ "learning_rate": 5.219489149590251e-06,
2934
+ "loss": 0.7297,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 2.65,
2939
+ "grad_norm": 0.12950360774993896,
2940
+ "learning_rate": 5.0015968355132555e-06,
2941
+ "loss": 0.7252,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 2.66,
2946
+ "grad_norm": 0.13121062517166138,
2947
+ "learning_rate": 4.788233408928589e-06,
2948
+ "loss": 0.7418,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 2.66,
2953
+ "grad_norm": 0.12770456075668335,
2954
+ "learning_rate": 4.5794090415751665e-06,
2955
+ "loss": 0.7576,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 2.67,
2960
+ "grad_norm": 0.131326824426651,
2961
+ "learning_rate": 4.375133688799959e-06,
2962
+ "loss": 0.7118,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 2.67,
2967
+ "grad_norm": 0.12951110303401947,
2968
+ "learning_rate": 4.175417089083378e-06,
2969
+ "loss": 0.698,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 2.68,
2974
+ "grad_norm": 0.1384904533624649,
2975
+ "learning_rate": 3.980268763575079e-06,
2976
+ "loss": 0.7301,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 2.69,
2981
+ "grad_norm": 0.1303904801607132,
2982
+ "learning_rate": 3.789698015639953e-06,
2983
+ "loss": 0.7204,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 2.69,
2988
+ "grad_norm": 0.12909793853759766,
2989
+ "learning_rate": 3.6037139304146762e-06,
2990
+ "loss": 0.7317,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 2.7,
2995
+ "grad_norm": 0.1411372721195221,
2996
+ "learning_rate": 3.4223253743745797e-06,
2997
+ "loss": 0.7547,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 2.71,
3002
+ "grad_norm": 0.13219870626926422,
3003
+ "learning_rate": 3.245540994910934e-06,
3004
+ "loss": 0.7221,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 2.71,
3009
+ "grad_norm": 0.13125751912593842,
3010
+ "learning_rate": 3.073369219918698e-06,
3011
+ "loss": 0.7345,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 2.72,
3016
+ "grad_norm": 0.1355525255203247,
3017
+ "learning_rate": 2.905818257394799e-06,
3018
+ "loss": 0.7559,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 2.73,
3023
+ "grad_norm": 0.13062480092048645,
3024
+ "learning_rate": 2.742896095046732e-06,
3025
+ "loss": 0.7159,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 2.73,
3030
+ "grad_norm": 0.13370193541049957,
3031
+ "learning_rate": 2.5846104999118325e-06,
3032
+ "loss": 0.7429,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 2.74,
3037
+ "grad_norm": 0.12908874452114105,
3038
+ "learning_rate": 2.4309690179869503e-06,
3039
+ "loss": 0.736,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 2.75,
3044
+ "grad_norm": 0.1381196528673172,
3045
+ "learning_rate": 2.281978973868748e-06,
3046
+ "loss": 0.7746,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 2.75,
3051
+ "grad_norm": 0.13205768167972565,
3052
+ "learning_rate": 2.137647470404469e-06,
3053
+ "loss": 0.7271,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 2.76,
3058
+ "grad_norm": 0.12809865176677704,
3059
+ "learning_rate": 1.997981388353376e-06,
3060
+ "loss": 0.717,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 2.76,
3065
+ "grad_norm": 0.128739133477211,
3066
+ "learning_rate": 1.8629873860586566e-06,
3067
+ "loss": 0.7316,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 2.77,
3072
+ "grad_norm": 0.12827108800411224,
3073
+ "learning_rate": 1.7326718991300562e-06,
3074
+ "loss": 0.7438,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 2.78,
3079
+ "grad_norm": 0.12858663499355316,
3080
+ "learning_rate": 1.6070411401370334e-06,
3081
+ "loss": 0.7234,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 2.78,
3086
+ "grad_norm": 0.12598633766174316,
3087
+ "learning_rate": 1.48610109831262e-06,
3088
+ "loss": 0.7218,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 2.79,
3093
+ "grad_norm": 0.12875476479530334,
3094
+ "learning_rate": 1.3698575392678492e-06,
3095
+ "loss": 0.7265,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 2.8,
3100
+ "grad_norm": 0.12630455195903778,
3101
+ "learning_rate": 1.258316004716953e-06,
3102
+ "loss": 0.7285,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 2.8,
3107
+ "grad_norm": 0.12824952602386475,
3108
+ "learning_rate": 1.1514818122130845e-06,
3109
+ "loss": 0.7638,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 2.81,
3114
+ "grad_norm": 0.1308830827474594,
3115
+ "learning_rate": 1.0493600548948878e-06,
3116
+ "loss": 0.721,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 2.82,
3121
+ "grad_norm": 0.13186423480510712,
3122
+ "learning_rate": 9.519556012436815e-07,
3123
+ "loss": 0.7192,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 2.82,
3128
+ "grad_norm": 0.12918241322040558,
3129
+ "learning_rate": 8.592730948513206e-07,
3130
+ "loss": 0.7432,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 2.83,
3135
+ "grad_norm": 0.1293298751115799,
3136
+ "learning_rate": 7.71316954198853e-07,
3137
+ "loss": 0.7279,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 2.84,
3142
+ "grad_norm": 0.13706308603286743,
3143
+ "learning_rate": 6.880913724458538e-07,
3144
+ "loss": 0.7469,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 2.84,
3149
+ "grad_norm": 0.12963692843914032,
3150
+ "learning_rate": 6.096003172305742e-07,
3151
+ "loss": 0.729,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 2.85,
3156
+ "grad_norm": 0.12841945886611938,
3157
+ "learning_rate": 5.358475304807375e-07,
3158
+ "loss": 0.6992,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 2.85,
3163
+ "grad_norm": 0.1284615844488144,
3164
+ "learning_rate": 4.668365282351372e-07,
3165
+ "loss": 0.7064,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 2.86,
3170
+ "grad_norm": 0.13411307334899902,
3171
+ "learning_rate": 4.025706004760932e-07,
3172
+ "loss": 0.7438,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 2.87,
3177
+ "grad_norm": 0.1265999674797058,
3178
+ "learning_rate": 3.4305281097254393e-07,
3179
+ "loss": 0.7301,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 2.87,
3184
+ "grad_norm": 0.12646237015724182,
3185
+ "learning_rate": 2.882859971339857e-07,
3186
+ "loss": 0.7147,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 2.88,
3191
+ "grad_norm": 0.1304078996181488,
3192
+ "learning_rate": 2.382727698752474e-07,
3193
+ "loss": 0.7095,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 2.89,
3198
+ "grad_norm": 0.13393165171146393,
3199
+ "learning_rate": 1.9301551349195646e-07,
3200
+ "loss": 0.7446,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 2.89,
3205
+ "grad_norm": 0.13380028307437897,
3206
+ "learning_rate": 1.5251638554694136e-07,
3207
+ "loss": 0.7609,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 2.9,
3212
+ "grad_norm": 0.12786865234375,
3213
+ "learning_rate": 1.1677731676733584e-07,
3214
+ "loss": 0.7562,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 2.91,
3219
+ "grad_norm": 0.12537167966365814,
3220
+ "learning_rate": 8.580001095253032e-08,
3221
+ "loss": 0.7597,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 2.91,
3226
+ "grad_norm": 0.131139874458313,
3227
+ "learning_rate": 5.958594489295921e-08,
3228
+ "loss": 0.7327,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 2.92,
3233
+ "grad_norm": 0.13232481479644775,
3234
+ "learning_rate": 3.813636829966827e-08,
3235
+ "loss": 0.734,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 2.93,
3240
+ "grad_norm": 0.12821924686431885,
3241
+ "learning_rate": 2.145230374481777e-08,
3242
+ "loss": 0.7109,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 2.93,
3247
+ "grad_norm": 0.12980176508426666,
3248
+ "learning_rate": 9.534546612810502e-09,
3249
+ "loss": 0.7364,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 2.94,
3254
+ "grad_norm": 0.1280398666858673,
3255
+ "learning_rate": 2.3836650624997624e-09,
3256
+ "loss": 0.752,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 2.94,
3261
+ "grad_norm": 0.12958520650863647,
3262
+ "learning_rate": 0.0,
3263
+ "loss": 0.7349,
3264
+ "step": 465
3265
+ }
3266
+ ],
3267
+ "logging_steps": 1,
3268
+ "max_steps": 465,
3269
+ "num_input_tokens_seen": 0,
3270
+ "num_train_epochs": 3,
3271
+ "save_steps": 155,
3272
+ "total_flos": 1.0078679012915282e+19,
3273
+ "train_batch_size": 5,
3274
+ "trial_name": null,
3275
+ "trial_params": null
3276
+ }
checkpoint-465/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9caa97dafc13dac0cd1534819d62554d3da31f36030b46451037938d5cae432
3
+ size 5816
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kloodia/llama8",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
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": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 10,
21
+ "output_router_logits": false,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "_load_in_4bit": true,
25
+ "_load_in_8bit": false,
26
+ "bnb_4bit_compute_dtype": "bfloat16",
27
+ "bnb_4bit_quant_storage": "bfloat16",
28
+ "bnb_4bit_quant_type": "nf4",
29
+ "bnb_4bit_use_double_quant": true,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": true,
35
+ "load_in_8bit": false,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": null,
40
+ "rope_theta": 500000.0,
41
+ "router_aux_loss_coef": 0.001,
42
+ "router_jitter_noise": 0.0,
43
+ "sliding_window": null,
44
+ "tie_word_embeddings": false,
45
+ "torch_dtype": "bfloat16",
46
+ "transformers_version": "4.40.0.dev0",
47
+ "use_cache": false,
48
+ "vocab_size": 128256
49
+ }
runs/Apr30_23-43-06_1bcd8aeb2316/events.out.tfevents.1714520588.1bcd8aeb2316.582.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0ac9a67d3311bdc34007aa0492ac1a0e3fab8cb4aee81046c4a7f0bcb5e8c8
3
+ size 6462
runs/May01_00-06-11_a5f9ef2b4afc/events.out.tfevents.1714521973.a5f9ef2b4afc.223.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a952f5a74e30f77ff563c202515ffd59c36027cebbe255c21a76a93c71865f8c
3
+ size 6876
runs/May01_00-12-38_a5f9ef2b4afc/events.out.tfevents.1714522359.a5f9ef2b4afc.699.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4b03a5224ee83a2b89f190e8e80ffa1d44caecee36bbe2d05563cb1e5b3da0
3
+ size 6876
runs/May01_00-19-09_a5f9ef2b4afc/events.out.tfevents.1714522750.a5f9ef2b4afc.880.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f10d0a9b41334ec3e5daa147cb6ed7c752fab83f60f72c27f8430f7dfa7867
3
+ size 6255
runs/May01_00-22-54_a5f9ef2b4afc/events.out.tfevents.1714522975.a5f9ef2b4afc.1030.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e03b01432bb32e90b78eaa772bd160888991a8bbe507881be6ed5b02b84e51
3
+ size 104216
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 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "model_input_names": [
2056
+ "input_ids",
2057
+ "attention_mask"
2058
+ ],
2059
+ "model_max_length": 1000000000000000019884624838656,
2060
+ "pad_token": "<|end_of_text|>",
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }