alexandra-e commited on
Commit
04b35a0
·
verified ·
1 Parent(s): 9f8012c

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +152 -0
  2. adapter_config.json +34 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-118/README.md +202 -0
  5. checkpoint-118/adapter_config.json +34 -0
  6. checkpoint-118/adapter_model.safetensors +3 -0
  7. checkpoint-118/optimizer.pt +3 -0
  8. checkpoint-118/rng_state.pth +3 -0
  9. checkpoint-118/scheduler.pt +3 -0
  10. checkpoint-118/special_tokens_map.json +37 -0
  11. checkpoint-118/tokenizer.json +0 -0
  12. checkpoint-118/tokenizer_config.json +2089 -0
  13. checkpoint-118/trainer_state.json +883 -0
  14. checkpoint-118/training_args.bin +3 -0
  15. checkpoint-177/README.md +202 -0
  16. checkpoint-177/adapter_config.json +34 -0
  17. checkpoint-177/adapter_model.safetensors +3 -0
  18. checkpoint-177/optimizer.pt +3 -0
  19. checkpoint-177/rng_state.pth +3 -0
  20. checkpoint-177/scheduler.pt +3 -0
  21. checkpoint-177/special_tokens_map.json +37 -0
  22. checkpoint-177/tokenizer.json +0 -0
  23. checkpoint-177/tokenizer_config.json +2089 -0
  24. checkpoint-177/trainer_state.json +1304 -0
  25. checkpoint-177/training_args.bin +3 -0
  26. checkpoint-236/README.md +202 -0
  27. checkpoint-236/adapter_config.json +34 -0
  28. checkpoint-236/adapter_model.safetensors +3 -0
  29. checkpoint-236/optimizer.pt +3 -0
  30. checkpoint-236/rng_state.pth +3 -0
  31. checkpoint-236/scheduler.pt +3 -0
  32. checkpoint-236/special_tokens_map.json +37 -0
  33. checkpoint-236/tokenizer.json +0 -0
  34. checkpoint-236/tokenizer_config.json +2089 -0
  35. checkpoint-236/trainer_state.json +1725 -0
  36. checkpoint-236/training_args.bin +3 -0
  37. checkpoint-59/README.md +202 -0
  38. checkpoint-59/adapter_config.json +34 -0
  39. checkpoint-59/adapter_model.safetensors +3 -0
  40. checkpoint-59/optimizer.pt +3 -0
  41. checkpoint-59/rng_state.pth +3 -0
  42. checkpoint-59/scheduler.pt +3 -0
  43. checkpoint-59/special_tokens_map.json +37 -0
  44. checkpoint-59/tokenizer.json +0 -0
  45. checkpoint-59/tokenizer_config.json +2089 -0
  46. checkpoint-59/trainer_state.json +462 -0
  47. checkpoint-59/training_args.bin +3 -0
  48. config.json +46 -0
  49. special_tokens_map.json +37 -0
  50. tokenizer.json +0 -0
README.md ADDED
@@ -0,0 +1,152 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: t-bank-ai/T-lite-instruct-0.1
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: t-lite-stalin
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
15
+ <details><summary>See axolotl config</summary>
16
+
17
+ axolotl version: `0.4.1`
18
+ ```yaml
19
+ base_model: t-bank-ai/T-lite-instruct-0.1
20
+
21
+ load_in_8bit: false
22
+ load_in_4bit: true
23
+ strict: false
24
+
25
+ datasets:
26
+ - path: test.jsonl
27
+ type: completion
28
+ dataset_prepared_path: prepared_data_tlite
29
+ val_set_size: 0.1
30
+ output_dir: ./t-lite-stalin
31
+
32
+ adapter: qlora
33
+ lora_model_dir:
34
+
35
+ sequence_len: 272
36
+ sample_packing: true
37
+ eval_sample_packing: False
38
+ pad_to_sequence_len: true
39
+
40
+ lora_r: 32
41
+ lora_alpha: 16
42
+ lora_dropout: 0.05
43
+ lora_target_linear: true
44
+ lora_fan_in_fan_out:
45
+ lora_target_modules:
46
+ - gate_proj
47
+ - down_proj
48
+ - up_proj
49
+ - q_proj
50
+ - v_proj
51
+ - k_proj
52
+ - o_proj
53
+
54
+ wandb_project:
55
+ wandb_entity:
56
+ wandb_watch:
57
+ wandb_name:
58
+ wandb_log_model:
59
+
60
+ gradient_accumulation_steps: 4
61
+ micro_batch_size: 48
62
+ num_epochs: 4
63
+ optimizer: adamw_bnb_8bit
64
+ lr_scheduler: cosine
65
+ learning_rate: 0.0002
66
+
67
+ train_on_inputs: false
68
+ group_by_length: false
69
+ bf16: auto
70
+ fp16:
71
+ tf32: false
72
+
73
+ gradient_checkpointing: true
74
+ early_stopping_patience:
75
+ resume_from_checkpoint:
76
+ local_rank:
77
+ logging_steps: 1
78
+ xformers_attention:
79
+ flash_attention: true
80
+
81
+ loss_watchdog_threshold: 5.0
82
+ loss_watchdog_patience: 3
83
+
84
+ warmup_steps: 10
85
+ evals_per_epoch: 1
86
+ eval_table_size:
87
+ eval_max_new_tokens: 1000
88
+ saves_per_epoch: 1
89
+ debug:
90
+ deepspeed:
91
+ weight_decay: 0.0
92
+ fsdp:
93
+ fsdp_config:
94
+ special_tokens:
95
+ pad_token: <|eot_id|>
96
+
97
+ ```
98
+
99
+ </details><br>
100
+
101
+ # t-lite-stalin
102
+
103
+ This model is a fine-tuned version of [t-bank-ai/T-lite-instruct-0.1](https://huggingface.co/t-bank-ai/T-lite-instruct-0.1) on the None dataset.
104
+ It achieves the following results on the evaluation set:
105
+ - Loss: 1.7248
106
+
107
+ ## Model description
108
+
109
+ More information needed
110
+
111
+ ## Intended uses & limitations
112
+
113
+ More information needed
114
+
115
+ ## Training and evaluation data
116
+
117
+ More information needed
118
+
119
+ ## Training procedure
120
+
121
+ ### Training hyperparameters
122
+
123
+ The following hyperparameters were used during training:
124
+ - learning_rate: 0.0002
125
+ - train_batch_size: 48
126
+ - eval_batch_size: 48
127
+ - seed: 42
128
+ - gradient_accumulation_steps: 4
129
+ - total_train_batch_size: 192
130
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
131
+ - lr_scheduler_type: cosine
132
+ - lr_scheduler_warmup_steps: 10
133
+ - num_epochs: 4
134
+
135
+ ### Training results
136
+
137
+ | Training Loss | Epoch | Step | Validation Loss |
138
+ |:-------------:|:------:|:----:|:---------------:|
139
+ | 2.4388 | 0.0167 | 1 | 2.2736 |
140
+ | 1.7178 | 0.9874 | 59 | 1.7366 |
141
+ | 1.5568 | 1.9582 | 118 | 1.7031 |
142
+ | 1.4787 | 2.9289 | 177 | 1.7109 |
143
+ | 1.4473 | 3.8996 | 236 | 1.7248 |
144
+
145
+
146
+ ### Framework versions
147
+
148
+ - PEFT 0.12.0
149
+ - Transformers 4.44.0
150
+ - Pytorch 2.3.0+cu121
151
+ - Datasets 2.20.0
152
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "t-bank-ai/T-lite-instruct-0.1",
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
+ "down_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618e106a2d04169ada72492bc760a3b5f4f47135db66fecc1b748dfeb300526d
3
+ size 335706186
checkpoint-118/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: t-bank-ai/T-lite-instruct-0.1
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-118/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "t-bank-ai/T-lite-instruct-0.1",
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
+ "down_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-118/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880d1476b2e0ee62026e2e76376051157ac8468ad82b8f831f285ac3b37224c4
3
+ size 335604696
checkpoint-118/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a0cbba8a479c281042bf063dff482c8e39f66cb26013093a3573882fe283ad9
3
+ size 168624724
checkpoint-118/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7f65837e83e93c71bdaac27255a8cd58085d14dad81352e634c08103b257a5
3
+ size 14244
checkpoint-118/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a531c1792258b4fbd83ee816a8872d2a00e07d5af9027d0403a78a60eb050a0
3
+ size 1064
checkpoint-118/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<sep>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-118/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-118/tokenizer_config.json ADDED
@@ -0,0 +1,2089 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<pad>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<unk>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ },
2067
+ "128258": {
2068
+ "content": "<sep>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": true
2074
+ }
2075
+ },
2076
+ "bos_token": "<|begin_of_text|>",
2077
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2078
+ "clean_up_tokenization_spaces": true,
2079
+ "eos_token": "<|end_of_text|>",
2080
+ "model_input_names": [
2081
+ "input_ids",
2082
+ "attention_mask"
2083
+ ],
2084
+ "model_max_length": 8192,
2085
+ "pad_token": "<|eot_id|>",
2086
+ "sep_token": "<sep>",
2087
+ "tokenizer_class": "PreTrainedTokenizerFast",
2088
+ "unk_token": "<unk>"
2089
+ }
checkpoint-118/trainer_state.json ADDED
@@ -0,0 +1,883 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9581589958158996,
5
+ "eval_steps": 59,
6
+ "global_step": 118,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016736401673640166,
13
+ "grad_norm": 0.3126992881298065,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.4388,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.016736401673640166,
20
+ "eval_loss": 2.2736361026763916,
21
+ "eval_runtime": 44.9772,
22
+ "eval_samples_per_second": 37.419,
23
+ "eval_steps_per_second": 0.8,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.03347280334728033,
28
+ "grad_norm": 0.31262004375457764,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.3915,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0502092050209205,
35
+ "grad_norm": 0.3161173462867737,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.4118,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.06694560669456066,
42
+ "grad_norm": 0.32605665922164917,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.3872,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.08368200836820083,
49
+ "grad_norm": 0.32243478298187256,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.3368,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.100418410041841,
56
+ "grad_norm": 0.3141494393348694,
57
+ "learning_rate": 0.00012,
58
+ "loss": 2.2966,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.11715481171548117,
63
+ "grad_norm": 0.330599308013916,
64
+ "learning_rate": 0.00014,
65
+ "loss": 2.2379,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.13389121338912133,
70
+ "grad_norm": 0.33452969789505005,
71
+ "learning_rate": 0.00016,
72
+ "loss": 2.1949,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1506276150627615,
77
+ "grad_norm": 0.2835342288017273,
78
+ "learning_rate": 0.00018,
79
+ "loss": 2.156,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.16736401673640167,
84
+ "grad_norm": 0.23091256618499756,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.1109,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.18410041841004185,
91
+ "grad_norm": 0.2284015268087387,
92
+ "learning_rate": 0.00019999033847063811,
93
+ "loss": 2.0782,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.200836820083682,
98
+ "grad_norm": 0.23981927335262299,
99
+ "learning_rate": 0.00019996135574945544,
100
+ "loss": 2.053,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.2175732217573222,
105
+ "grad_norm": 0.23807936906814575,
106
+ "learning_rate": 0.00019991305743680013,
107
+ "loss": 2.0294,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.23430962343096234,
112
+ "grad_norm": 0.20766477286815643,
113
+ "learning_rate": 0.0001998454528653836,
114
+ "loss": 1.9947,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.2510460251046025,
119
+ "grad_norm": 0.1892593652009964,
120
+ "learning_rate": 0.00019975855509847686,
121
+ "loss": 1.9643,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.26778242677824265,
126
+ "grad_norm": 0.19022946059703827,
127
+ "learning_rate": 0.00019965238092738643,
128
+ "loss": 1.9275,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.28451882845188287,
133
+ "grad_norm": 0.18370254337787628,
134
+ "learning_rate": 0.00019952695086820975,
135
+ "loss": 1.9512,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.301255230125523,
140
+ "grad_norm": 0.16774943470954895,
141
+ "learning_rate": 0.0001993822891578708,
142
+ "loss": 1.8883,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.3179916317991632,
147
+ "grad_norm": 0.17572854459285736,
148
+ "learning_rate": 0.0001992184237494368,
149
+ "loss": 1.938,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.33472803347280333,
154
+ "grad_norm": 0.21952244639396667,
155
+ "learning_rate": 0.0001990353863067169,
156
+ "loss": 1.8937,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.3514644351464435,
161
+ "grad_norm": 0.2579434812068939,
162
+ "learning_rate": 0.0001988332121981436,
163
+ "loss": 1.8797,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.3682008368200837,
168
+ "grad_norm": 0.29942768812179565,
169
+ "learning_rate": 0.00019861194048993863,
170
+ "loss": 1.8766,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.38493723849372385,
175
+ "grad_norm": 0.326593279838562,
176
+ "learning_rate": 0.0001983716139385641,
177
+ "loss": 1.8567,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.401673640167364,
182
+ "grad_norm": 0.2769831418991089,
183
+ "learning_rate": 0.0001981122789824607,
184
+ "loss": 1.839,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.41841004184100417,
189
+ "grad_norm": 0.2902805507183075,
190
+ "learning_rate": 0.00019783398573307428,
191
+ "loss": 1.8622,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.4351464435146444,
196
+ "grad_norm": 0.2152428776025772,
197
+ "learning_rate": 0.00019753678796517282,
198
+ "loss": 1.8393,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.45188284518828453,
203
+ "grad_norm": 0.1541067361831665,
204
+ "learning_rate": 0.00019722074310645553,
205
+ "loss": 1.8326,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.4686192468619247,
210
+ "grad_norm": 0.12413746118545532,
211
+ "learning_rate": 0.00019688591222645607,
212
+ "loss": 1.8079,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.48535564853556484,
217
+ "grad_norm": 0.11909659206867218,
218
+ "learning_rate": 0.000196532360024742,
219
+ "loss": 1.8044,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.502092050209205,
224
+ "grad_norm": 0.16260313987731934,
225
+ "learning_rate": 0.0001961601548184129,
226
+ "loss": 1.7888,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.5188284518828452,
231
+ "grad_norm": 0.17894335091114044,
232
+ "learning_rate": 0.00019576936852889936,
233
+ "loss": 1.8263,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.5355648535564853,
238
+ "grad_norm": 0.21706554293632507,
239
+ "learning_rate": 0.00019536007666806556,
240
+ "loss": 1.8151,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.5523012552301255,
245
+ "grad_norm": 0.17296762764453888,
246
+ "learning_rate": 0.0001949323583236181,
247
+ "loss": 1.7901,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.5690376569037657,
252
+ "grad_norm": 0.1761002093553543,
253
+ "learning_rate": 0.0001944862961438239,
254
+ "loss": 1.8126,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.5857740585774058,
259
+ "grad_norm": 0.14914190769195557,
260
+ "learning_rate": 0.00019402197632153992,
261
+ "loss": 1.7797,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.602510460251046,
266
+ "grad_norm": 0.13111546635627747,
267
+ "learning_rate": 0.00019353948857755803,
268
+ "loss": 1.7916,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.6192468619246861,
273
+ "grad_norm": 0.12080994248390198,
274
+ "learning_rate": 0.00019303892614326836,
275
+ "loss": 1.7834,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.6359832635983264,
280
+ "grad_norm": 0.15622606873512268,
281
+ "learning_rate": 0.00019252038574264405,
282
+ "loss": 1.794,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.6527196652719666,
287
+ "grad_norm": 0.1345275640487671,
288
+ "learning_rate": 0.00019198396757355118,
289
+ "loss": 1.7554,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.6694560669456067,
294
+ "grad_norm": 0.18387249112129211,
295
+ "learning_rate": 0.00019142977528838762,
296
+ "loss": 1.7675,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.6861924686192469,
301
+ "grad_norm": 0.165897399187088,
302
+ "learning_rate": 0.00019085791597405404,
303
+ "loss": 1.7631,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.702928870292887,
308
+ "grad_norm": 0.13675889372825623,
309
+ "learning_rate": 0.00019026850013126157,
310
+ "loss": 1.754,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.7196652719665272,
315
+ "grad_norm": 0.16969387233257294,
316
+ "learning_rate": 0.00018966164165317966,
317
+ "loss": 1.745,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.7364016736401674,
322
+ "grad_norm": 0.16098380088806152,
323
+ "learning_rate": 0.00018903745780342839,
324
+ "loss": 1.7609,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.7531380753138075,
329
+ "grad_norm": 0.12338632345199585,
330
+ "learning_rate": 0.0001883960691934196,
331
+ "loss": 1.7584,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.7698744769874477,
336
+ "grad_norm": 0.1335158348083496,
337
+ "learning_rate": 0.00018773759975905098,
338
+ "loss": 1.7302,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.7866108786610879,
343
+ "grad_norm": 0.11967575550079346,
344
+ "learning_rate": 0.00018706217673675811,
345
+ "loss": 1.7323,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.803347280334728,
350
+ "grad_norm": 0.12446475774049759,
351
+ "learning_rate": 0.0001863699306389282,
352
+ "loss": 1.7217,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.8200836820083682,
357
+ "grad_norm": 0.13070392608642578,
358
+ "learning_rate": 0.00018566099522868119,
359
+ "loss": 1.7192,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.8368200836820083,
364
+ "grad_norm": 0.15041972696781158,
365
+ "learning_rate": 0.00018493550749402278,
366
+ "loss": 1.7386,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.8535564853556485,
371
+ "grad_norm": 0.12314204126596451,
372
+ "learning_rate": 0.00018419360762137395,
373
+ "loss": 1.7465,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.8702928870292888,
378
+ "grad_norm": 0.15009309351444244,
379
+ "learning_rate": 0.00018343543896848273,
380
+ "loss": 1.7216,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.8870292887029289,
385
+ "grad_norm": 0.12467087060213089,
386
+ "learning_rate": 0.00018266114803672318,
387
+ "loss": 1.7043,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.9037656903765691,
392
+ "grad_norm": 0.1297266036272049,
393
+ "learning_rate": 0.00018187088444278674,
394
+ "loss": 1.7069,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.9205020920502092,
399
+ "grad_norm": 0.1195509061217308,
400
+ "learning_rate": 0.00018106480088977172,
401
+ "loss": 1.7305,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.9372384937238494,
406
+ "grad_norm": 0.14450602233409882,
407
+ "learning_rate": 0.00018024305313767646,
408
+ "loss": 1.7171,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.9539748953974896,
413
+ "grad_norm": 0.16594989597797394,
414
+ "learning_rate": 0.00017940579997330165,
415
+ "loss": 1.7239,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.9707112970711297,
420
+ "grad_norm": 0.19210928678512573,
421
+ "learning_rate": 0.00017855320317956784,
422
+ "loss": 1.7081,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.9874476987447699,
427
+ "grad_norm": 0.16463987529277802,
428
+ "learning_rate": 0.00017768542750425426,
429
+ "loss": 1.7178,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.9874476987447699,
434
+ "eval_loss": 1.7365927696228027,
435
+ "eval_runtime": 44.9816,
436
+ "eval_samples_per_second": 37.415,
437
+ "eval_steps_per_second": 0.8,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.00418410041841,
442
+ "grad_norm": 0.13954801857471466,
443
+ "learning_rate": 0.0001768026406281642,
444
+ "loss": 1.6905,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.00418410041841,
449
+ "grad_norm": 0.17747963964939117,
450
+ "learning_rate": 0.00017590501313272415,
451
+ "loss": 1.6864,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.0209205020920502,
456
+ "grad_norm": 0.1328994333744049,
457
+ "learning_rate": 0.00017499271846702213,
458
+ "loss": 1.6388,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.0376569037656904,
463
+ "grad_norm": 0.12811322510242462,
464
+ "learning_rate": 0.00017406593291429217,
465
+ "loss": 1.6821,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.0543933054393306,
470
+ "grad_norm": 0.1379721611738205,
471
+ "learning_rate": 0.00017312483555785086,
472
+ "loss": 1.6364,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.0711297071129706,
477
+ "grad_norm": 0.14301170408725739,
478
+ "learning_rate": 0.00017216960824649303,
479
+ "loss": 1.646,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.0878661087866108,
484
+ "grad_norm": 0.15547165274620056,
485
+ "learning_rate": 0.00017120043555935298,
486
+ "loss": 1.6625,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.104602510460251,
491
+ "grad_norm": 0.14291325211524963,
492
+ "learning_rate": 0.0001702175047702382,
493
+ "loss": 1.6392,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.1213389121338913,
498
+ "grad_norm": 0.14325812458992004,
499
+ "learning_rate": 0.00016922100581144228,
500
+ "loss": 1.6677,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.1380753138075315,
505
+ "grad_norm": 0.14328014850616455,
506
+ "learning_rate": 0.00016821113123704424,
507
+ "loss": 1.6182,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.1548117154811715,
512
+ "grad_norm": 0.16151900589466095,
513
+ "learning_rate": 0.00016718807618570106,
514
+ "loss": 1.6492,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.1715481171548117,
519
+ "grad_norm": 0.15649794042110443,
520
+ "learning_rate": 0.00016615203834294119,
521
+ "loss": 1.6334,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.1882845188284519,
526
+ "grad_norm": 0.15963214635849,
527
+ "learning_rate": 0.00016510321790296525,
528
+ "loss": 1.6203,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.205020920502092,
533
+ "grad_norm": 0.15893195569515228,
534
+ "learning_rate": 0.00016404181752996289,
535
+ "loss": 1.6408,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.2217573221757323,
540
+ "grad_norm": 0.16694918274879456,
541
+ "learning_rate": 0.00016296804231895142,
542
+ "loss": 1.633,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.2384937238493725,
547
+ "grad_norm": 0.15804418921470642,
548
+ "learning_rate": 0.00016188209975614542,
549
+ "loss": 1.6548,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.2552301255230125,
554
+ "grad_norm": 0.14725787937641144,
555
+ "learning_rate": 0.00016078419967886402,
556
+ "loss": 1.6158,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.2719665271966527,
561
+ "grad_norm": 0.15310946106910706,
562
+ "learning_rate": 0.00015967455423498387,
563
+ "loss": 1.664,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.288702928870293,
568
+ "grad_norm": 0.14741982519626617,
569
+ "learning_rate": 0.00015855337784194577,
570
+ "loss": 1.6494,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3054393305439331,
575
+ "grad_norm": 0.1478704810142517,
576
+ "learning_rate": 0.00015742088714532247,
577
+ "loss": 1.6254,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.3221757322175733,
582
+ "grad_norm": 0.1895337849855423,
583
+ "learning_rate": 0.00015627730097695638,
584
+ "loss": 1.6018,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.3389121338912133,
589
+ "grad_norm": 0.19194994866847992,
590
+ "learning_rate": 0.00015512284031267437,
591
+ "loss": 1.6543,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.3556485355648535,
596
+ "grad_norm": 0.1553422063589096,
597
+ "learning_rate": 0.00015395772822958845,
598
+ "loss": 1.6429,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.3723849372384938,
603
+ "grad_norm": 0.19711142778396606,
604
+ "learning_rate": 0.00015278218986299074,
605
+ "loss": 1.624,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.389121338912134,
610
+ "grad_norm": 0.16961851716041565,
611
+ "learning_rate": 0.0001515964523628501,
612
+ "loss": 1.6097,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.4058577405857742,
617
+ "grad_norm": 0.20063763856887817,
618
+ "learning_rate": 0.00015040074484992,
619
+ "loss": 1.6171,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.4225941422594142,
624
+ "grad_norm": 0.16175565123558044,
625
+ "learning_rate": 0.00014919529837146528,
626
+ "loss": 1.6119,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.4393305439330544,
631
+ "grad_norm": 0.20445561408996582,
632
+ "learning_rate": 0.00014798034585661695,
633
+ "loss": 1.6089,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.4560669456066946,
638
+ "grad_norm": 0.17204363644123077,
639
+ "learning_rate": 0.0001467561220713628,
640
+ "loss": 1.6178,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.4728033472803348,
645
+ "grad_norm": 0.1780082732439041,
646
+ "learning_rate": 0.0001455228635731839,
647
+ "loss": 1.6172,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.489539748953975,
652
+ "grad_norm": 0.17321935296058655,
653
+ "learning_rate": 0.00014428080866534396,
654
+ "loss": 1.574,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.506276150627615,
659
+ "grad_norm": 0.1722816675901413,
660
+ "learning_rate": 0.00014303019735084226,
661
+ "loss": 1.6096,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.5230125523012552,
666
+ "grad_norm": 0.1621088981628418,
667
+ "learning_rate": 0.00014177127128603745,
668
+ "loss": 1.603,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.5397489539748954,
673
+ "grad_norm": 0.17485831677913666,
674
+ "learning_rate": 0.0001405042737339524,
675
+ "loss": 1.6105,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.5564853556485354,
680
+ "grad_norm": 0.16599352657794952,
681
+ "learning_rate": 0.0001392294495172681,
682
+ "loss": 1.632,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.5732217573221758,
687
+ "grad_norm": 0.1569545418024063,
688
+ "learning_rate": 0.00013794704497101655,
689
+ "loss": 1.608,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.5899581589958158,
694
+ "grad_norm": 0.15951111912727356,
695
+ "learning_rate": 0.0001366573078949813,
696
+ "loss": 1.5742,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.606694560669456,
701
+ "grad_norm": 0.1951216161251068,
702
+ "learning_rate": 0.00013536048750581494,
703
+ "loss": 1.5908,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.6234309623430963,
708
+ "grad_norm": 0.20315046608448029,
709
+ "learning_rate": 0.00013405683438888282,
710
+ "loss": 1.6081,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.6401673640167362,
715
+ "grad_norm": 0.16759882867336273,
716
+ "learning_rate": 0.00013274660044984224,
717
+ "loss": 1.6041,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.6569037656903767,
722
+ "grad_norm": 0.18749655783176422,
723
+ "learning_rate": 0.00013143003886596669,
724
+ "loss": 1.6002,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.6736401673640167,
729
+ "grad_norm": 0.1809973418712616,
730
+ "learning_rate": 0.0001301074040372242,
731
+ "loss": 1.6328,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 1.6903765690376569,
736
+ "grad_norm": 0.20419345796108246,
737
+ "learning_rate": 0.00012877895153711935,
738
+ "loss": 1.6017,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 1.707112970711297,
743
+ "grad_norm": 0.1926768571138382,
744
+ "learning_rate": 0.0001274449380633089,
745
+ "loss": 1.5793,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 1.723849372384937,
750
+ "grad_norm": 0.22891242802143097,
751
+ "learning_rate": 0.00012610562138799978,
752
+ "loss": 1.6306,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 1.7405857740585775,
757
+ "grad_norm": 0.17105843126773834,
758
+ "learning_rate": 0.00012476126030813963,
759
+ "loss": 1.5999,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 1.7573221757322175,
764
+ "grad_norm": 0.17857873439788818,
765
+ "learning_rate": 0.0001234121145954094,
766
+ "loss": 1.5867,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 1.7740585774058577,
771
+ "grad_norm": 0.1942574381828308,
772
+ "learning_rate": 0.0001220584449460274,
773
+ "loss": 1.5719,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 1.790794979079498,
778
+ "grad_norm": 0.18035678565502167,
779
+ "learning_rate": 0.00012070051293037492,
780
+ "loss": 1.5783,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 1.8075313807531381,
785
+ "grad_norm": 0.18351756036281586,
786
+ "learning_rate": 0.00011933858094245281,
787
+ "loss": 1.6121,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 1.8242677824267783,
792
+ "grad_norm": 0.17191624641418457,
793
+ "learning_rate": 0.00011797291214917881,
794
+ "loss": 1.5801,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 1.8410041841004183,
799
+ "grad_norm": 0.19317130744457245,
800
+ "learning_rate": 0.00011660377043953588,
801
+ "loss": 1.5928,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 1.8577405857740585,
806
+ "grad_norm": 0.1735094040632248,
807
+ "learning_rate": 0.0001152314203735805,
808
+ "loss": 1.5782,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 1.8744769874476988,
813
+ "grad_norm": 0.1757810264825821,
814
+ "learning_rate": 0.0001138561271313219,
815
+ "loss": 1.605,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 1.891213389121339,
820
+ "grad_norm": 0.20154766738414764,
821
+ "learning_rate": 0.00011247815646148087,
822
+ "loss": 1.5782,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 1.9079497907949792,
827
+ "grad_norm": 0.18075552582740784,
828
+ "learning_rate": 0.00011109777463013915,
829
+ "loss": 1.5905,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 1.9246861924686192,
834
+ "grad_norm": 0.1821986436843872,
835
+ "learning_rate": 0.0001097152483692886,
836
+ "loss": 1.5661,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 1.9414225941422594,
841
+ "grad_norm": 0.1858905404806137,
842
+ "learning_rate": 0.00010833084482529048,
843
+ "loss": 1.6245,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 1.9581589958158996,
848
+ "grad_norm": 0.19977439939975739,
849
+ "learning_rate": 0.00010694483150725458,
850
+ "loss": 1.5568,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 1.9581589958158996,
855
+ "eval_loss": 1.7031370401382446,
856
+ "eval_runtime": 45.0796,
857
+ "eval_samples_per_second": 37.334,
858
+ "eval_steps_per_second": 0.799,
859
+ "step": 118
860
+ }
861
+ ],
862
+ "logging_steps": 1,
863
+ "max_steps": 236,
864
+ "num_input_tokens_seen": 0,
865
+ "num_train_epochs": 4,
866
+ "save_steps": 59,
867
+ "stateful_callbacks": {
868
+ "TrainerControl": {
869
+ "args": {
870
+ "should_epoch_stop": false,
871
+ "should_evaluate": false,
872
+ "should_log": false,
873
+ "should_save": true,
874
+ "should_training_stop": false
875
+ },
876
+ "attributes": {}
877
+ }
878
+ },
879
+ "total_flos": 2.814736962945024e+17,
880
+ "train_batch_size": 48,
881
+ "trial_name": null,
882
+ "trial_params": null
883
+ }
checkpoint-118/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553af1c5dd81032ecab9996f20cecb8cd9d302493de0264d19b2265d1e75c3ef
3
+ size 6072
checkpoint-177/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: t-bank-ai/T-lite-instruct-0.1
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-177/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "t-bank-ai/T-lite-instruct-0.1",
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
+ "down_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-177/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2028706540d85f59743fff4fb20d4d7291f7df4e137cb78daf760f9952d171
3
+ size 335604696
checkpoint-177/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6752064b40d63ccf6c66c014623e21aea2594536f272dcf0b9c68b4e39557a
3
+ size 168624724
checkpoint-177/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f840582a2d7e95d0fcce69bb8106230c323a4c4b8d258881952a02128a4c632
3
+ size 14244
checkpoint-177/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd15020b8a0c14ea10a2c7fdb6c6fdd1232950922dd38a4bf8c42557942b3420
3
+ size 1064
checkpoint-177/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<sep>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-177/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-177/tokenizer_config.json ADDED
@@ -0,0 +1,2089 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<pad>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<unk>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ },
2067
+ "128258": {
2068
+ "content": "<sep>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": true
2074
+ }
2075
+ },
2076
+ "bos_token": "<|begin_of_text|>",
2077
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2078
+ "clean_up_tokenization_spaces": true,
2079
+ "eos_token": "<|end_of_text|>",
2080
+ "model_input_names": [
2081
+ "input_ids",
2082
+ "attention_mask"
2083
+ ],
2084
+ "model_max_length": 8192,
2085
+ "pad_token": "<|eot_id|>",
2086
+ "sep_token": "<sep>",
2087
+ "tokenizer_class": "PreTrainedTokenizerFast",
2088
+ "unk_token": "<unk>"
2089
+ }
checkpoint-177/trainer_state.json ADDED
@@ -0,0 +1,1304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.928870292887029,
5
+ "eval_steps": 59,
6
+ "global_step": 177,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016736401673640166,
13
+ "grad_norm": 0.3126992881298065,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.4388,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.016736401673640166,
20
+ "eval_loss": 2.2736361026763916,
21
+ "eval_runtime": 44.9772,
22
+ "eval_samples_per_second": 37.419,
23
+ "eval_steps_per_second": 0.8,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.03347280334728033,
28
+ "grad_norm": 0.31262004375457764,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.3915,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0502092050209205,
35
+ "grad_norm": 0.3161173462867737,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.4118,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.06694560669456066,
42
+ "grad_norm": 0.32605665922164917,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.3872,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.08368200836820083,
49
+ "grad_norm": 0.32243478298187256,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.3368,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.100418410041841,
56
+ "grad_norm": 0.3141494393348694,
57
+ "learning_rate": 0.00012,
58
+ "loss": 2.2966,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.11715481171548117,
63
+ "grad_norm": 0.330599308013916,
64
+ "learning_rate": 0.00014,
65
+ "loss": 2.2379,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.13389121338912133,
70
+ "grad_norm": 0.33452969789505005,
71
+ "learning_rate": 0.00016,
72
+ "loss": 2.1949,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1506276150627615,
77
+ "grad_norm": 0.2835342288017273,
78
+ "learning_rate": 0.00018,
79
+ "loss": 2.156,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.16736401673640167,
84
+ "grad_norm": 0.23091256618499756,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.1109,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.18410041841004185,
91
+ "grad_norm": 0.2284015268087387,
92
+ "learning_rate": 0.00019999033847063811,
93
+ "loss": 2.0782,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.200836820083682,
98
+ "grad_norm": 0.23981927335262299,
99
+ "learning_rate": 0.00019996135574945544,
100
+ "loss": 2.053,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.2175732217573222,
105
+ "grad_norm": 0.23807936906814575,
106
+ "learning_rate": 0.00019991305743680013,
107
+ "loss": 2.0294,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.23430962343096234,
112
+ "grad_norm": 0.20766477286815643,
113
+ "learning_rate": 0.0001998454528653836,
114
+ "loss": 1.9947,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.2510460251046025,
119
+ "grad_norm": 0.1892593652009964,
120
+ "learning_rate": 0.00019975855509847686,
121
+ "loss": 1.9643,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.26778242677824265,
126
+ "grad_norm": 0.19022946059703827,
127
+ "learning_rate": 0.00019965238092738643,
128
+ "loss": 1.9275,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.28451882845188287,
133
+ "grad_norm": 0.18370254337787628,
134
+ "learning_rate": 0.00019952695086820975,
135
+ "loss": 1.9512,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.301255230125523,
140
+ "grad_norm": 0.16774943470954895,
141
+ "learning_rate": 0.0001993822891578708,
142
+ "loss": 1.8883,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.3179916317991632,
147
+ "grad_norm": 0.17572854459285736,
148
+ "learning_rate": 0.0001992184237494368,
149
+ "loss": 1.938,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.33472803347280333,
154
+ "grad_norm": 0.21952244639396667,
155
+ "learning_rate": 0.0001990353863067169,
156
+ "loss": 1.8937,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.3514644351464435,
161
+ "grad_norm": 0.2579434812068939,
162
+ "learning_rate": 0.0001988332121981436,
163
+ "loss": 1.8797,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.3682008368200837,
168
+ "grad_norm": 0.29942768812179565,
169
+ "learning_rate": 0.00019861194048993863,
170
+ "loss": 1.8766,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.38493723849372385,
175
+ "grad_norm": 0.326593279838562,
176
+ "learning_rate": 0.0001983716139385641,
177
+ "loss": 1.8567,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.401673640167364,
182
+ "grad_norm": 0.2769831418991089,
183
+ "learning_rate": 0.0001981122789824607,
184
+ "loss": 1.839,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.41841004184100417,
189
+ "grad_norm": 0.2902805507183075,
190
+ "learning_rate": 0.00019783398573307428,
191
+ "loss": 1.8622,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.4351464435146444,
196
+ "grad_norm": 0.2152428776025772,
197
+ "learning_rate": 0.00019753678796517282,
198
+ "loss": 1.8393,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.45188284518828453,
203
+ "grad_norm": 0.1541067361831665,
204
+ "learning_rate": 0.00019722074310645553,
205
+ "loss": 1.8326,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.4686192468619247,
210
+ "grad_norm": 0.12413746118545532,
211
+ "learning_rate": 0.00019688591222645607,
212
+ "loss": 1.8079,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.48535564853556484,
217
+ "grad_norm": 0.11909659206867218,
218
+ "learning_rate": 0.000196532360024742,
219
+ "loss": 1.8044,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.502092050209205,
224
+ "grad_norm": 0.16260313987731934,
225
+ "learning_rate": 0.0001961601548184129,
226
+ "loss": 1.7888,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.5188284518828452,
231
+ "grad_norm": 0.17894335091114044,
232
+ "learning_rate": 0.00019576936852889936,
233
+ "loss": 1.8263,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.5355648535564853,
238
+ "grad_norm": 0.21706554293632507,
239
+ "learning_rate": 0.00019536007666806556,
240
+ "loss": 1.8151,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.5523012552301255,
245
+ "grad_norm": 0.17296762764453888,
246
+ "learning_rate": 0.0001949323583236181,
247
+ "loss": 1.7901,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.5690376569037657,
252
+ "grad_norm": 0.1761002093553543,
253
+ "learning_rate": 0.0001944862961438239,
254
+ "loss": 1.8126,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.5857740585774058,
259
+ "grad_norm": 0.14914190769195557,
260
+ "learning_rate": 0.00019402197632153992,
261
+ "loss": 1.7797,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.602510460251046,
266
+ "grad_norm": 0.13111546635627747,
267
+ "learning_rate": 0.00019353948857755803,
268
+ "loss": 1.7916,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.6192468619246861,
273
+ "grad_norm": 0.12080994248390198,
274
+ "learning_rate": 0.00019303892614326836,
275
+ "loss": 1.7834,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.6359832635983264,
280
+ "grad_norm": 0.15622606873512268,
281
+ "learning_rate": 0.00019252038574264405,
282
+ "loss": 1.794,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.6527196652719666,
287
+ "grad_norm": 0.1345275640487671,
288
+ "learning_rate": 0.00019198396757355118,
289
+ "loss": 1.7554,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.6694560669456067,
294
+ "grad_norm": 0.18387249112129211,
295
+ "learning_rate": 0.00019142977528838762,
296
+ "loss": 1.7675,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.6861924686192469,
301
+ "grad_norm": 0.165897399187088,
302
+ "learning_rate": 0.00019085791597405404,
303
+ "loss": 1.7631,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.702928870292887,
308
+ "grad_norm": 0.13675889372825623,
309
+ "learning_rate": 0.00019026850013126157,
310
+ "loss": 1.754,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.7196652719665272,
315
+ "grad_norm": 0.16969387233257294,
316
+ "learning_rate": 0.00018966164165317966,
317
+ "loss": 1.745,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.7364016736401674,
322
+ "grad_norm": 0.16098380088806152,
323
+ "learning_rate": 0.00018903745780342839,
324
+ "loss": 1.7609,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.7531380753138075,
329
+ "grad_norm": 0.12338632345199585,
330
+ "learning_rate": 0.0001883960691934196,
331
+ "loss": 1.7584,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.7698744769874477,
336
+ "grad_norm": 0.1335158348083496,
337
+ "learning_rate": 0.00018773759975905098,
338
+ "loss": 1.7302,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.7866108786610879,
343
+ "grad_norm": 0.11967575550079346,
344
+ "learning_rate": 0.00018706217673675811,
345
+ "loss": 1.7323,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.803347280334728,
350
+ "grad_norm": 0.12446475774049759,
351
+ "learning_rate": 0.0001863699306389282,
352
+ "loss": 1.7217,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.8200836820083682,
357
+ "grad_norm": 0.13070392608642578,
358
+ "learning_rate": 0.00018566099522868119,
359
+ "loss": 1.7192,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.8368200836820083,
364
+ "grad_norm": 0.15041972696781158,
365
+ "learning_rate": 0.00018493550749402278,
366
+ "loss": 1.7386,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.8535564853556485,
371
+ "grad_norm": 0.12314204126596451,
372
+ "learning_rate": 0.00018419360762137395,
373
+ "loss": 1.7465,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.8702928870292888,
378
+ "grad_norm": 0.15009309351444244,
379
+ "learning_rate": 0.00018343543896848273,
380
+ "loss": 1.7216,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.8870292887029289,
385
+ "grad_norm": 0.12467087060213089,
386
+ "learning_rate": 0.00018266114803672318,
387
+ "loss": 1.7043,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.9037656903765691,
392
+ "grad_norm": 0.1297266036272049,
393
+ "learning_rate": 0.00018187088444278674,
394
+ "loss": 1.7069,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.9205020920502092,
399
+ "grad_norm": 0.1195509061217308,
400
+ "learning_rate": 0.00018106480088977172,
401
+ "loss": 1.7305,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.9372384937238494,
406
+ "grad_norm": 0.14450602233409882,
407
+ "learning_rate": 0.00018024305313767646,
408
+ "loss": 1.7171,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.9539748953974896,
413
+ "grad_norm": 0.16594989597797394,
414
+ "learning_rate": 0.00017940579997330165,
415
+ "loss": 1.7239,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.9707112970711297,
420
+ "grad_norm": 0.19210928678512573,
421
+ "learning_rate": 0.00017855320317956784,
422
+ "loss": 1.7081,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.9874476987447699,
427
+ "grad_norm": 0.16463987529277802,
428
+ "learning_rate": 0.00017768542750425426,
429
+ "loss": 1.7178,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.9874476987447699,
434
+ "eval_loss": 1.7365927696228027,
435
+ "eval_runtime": 44.9816,
436
+ "eval_samples_per_second": 37.415,
437
+ "eval_steps_per_second": 0.8,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.00418410041841,
442
+ "grad_norm": 0.13954801857471466,
443
+ "learning_rate": 0.0001768026406281642,
444
+ "loss": 1.6905,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.00418410041841,
449
+ "grad_norm": 0.17747963964939117,
450
+ "learning_rate": 0.00017590501313272415,
451
+ "loss": 1.6864,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.0209205020920502,
456
+ "grad_norm": 0.1328994333744049,
457
+ "learning_rate": 0.00017499271846702213,
458
+ "loss": 1.6388,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.0376569037656904,
463
+ "grad_norm": 0.12811322510242462,
464
+ "learning_rate": 0.00017406593291429217,
465
+ "loss": 1.6821,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.0543933054393306,
470
+ "grad_norm": 0.1379721611738205,
471
+ "learning_rate": 0.00017312483555785086,
472
+ "loss": 1.6364,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.0711297071129706,
477
+ "grad_norm": 0.14301170408725739,
478
+ "learning_rate": 0.00017216960824649303,
479
+ "loss": 1.646,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.0878661087866108,
484
+ "grad_norm": 0.15547165274620056,
485
+ "learning_rate": 0.00017120043555935298,
486
+ "loss": 1.6625,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.104602510460251,
491
+ "grad_norm": 0.14291325211524963,
492
+ "learning_rate": 0.0001702175047702382,
493
+ "loss": 1.6392,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.1213389121338913,
498
+ "grad_norm": 0.14325812458992004,
499
+ "learning_rate": 0.00016922100581144228,
500
+ "loss": 1.6677,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.1380753138075315,
505
+ "grad_norm": 0.14328014850616455,
506
+ "learning_rate": 0.00016821113123704424,
507
+ "loss": 1.6182,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.1548117154811715,
512
+ "grad_norm": 0.16151900589466095,
513
+ "learning_rate": 0.00016718807618570106,
514
+ "loss": 1.6492,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.1715481171548117,
519
+ "grad_norm": 0.15649794042110443,
520
+ "learning_rate": 0.00016615203834294119,
521
+ "loss": 1.6334,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.1882845188284519,
526
+ "grad_norm": 0.15963214635849,
527
+ "learning_rate": 0.00016510321790296525,
528
+ "loss": 1.6203,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.205020920502092,
533
+ "grad_norm": 0.15893195569515228,
534
+ "learning_rate": 0.00016404181752996289,
535
+ "loss": 1.6408,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.2217573221757323,
540
+ "grad_norm": 0.16694918274879456,
541
+ "learning_rate": 0.00016296804231895142,
542
+ "loss": 1.633,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.2384937238493725,
547
+ "grad_norm": 0.15804418921470642,
548
+ "learning_rate": 0.00016188209975614542,
549
+ "loss": 1.6548,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.2552301255230125,
554
+ "grad_norm": 0.14725787937641144,
555
+ "learning_rate": 0.00016078419967886402,
556
+ "loss": 1.6158,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.2719665271966527,
561
+ "grad_norm": 0.15310946106910706,
562
+ "learning_rate": 0.00015967455423498387,
563
+ "loss": 1.664,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.288702928870293,
568
+ "grad_norm": 0.14741982519626617,
569
+ "learning_rate": 0.00015855337784194577,
570
+ "loss": 1.6494,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3054393305439331,
575
+ "grad_norm": 0.1478704810142517,
576
+ "learning_rate": 0.00015742088714532247,
577
+ "loss": 1.6254,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.3221757322175733,
582
+ "grad_norm": 0.1895337849855423,
583
+ "learning_rate": 0.00015627730097695638,
584
+ "loss": 1.6018,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.3389121338912133,
589
+ "grad_norm": 0.19194994866847992,
590
+ "learning_rate": 0.00015512284031267437,
591
+ "loss": 1.6543,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.3556485355648535,
596
+ "grad_norm": 0.1553422063589096,
597
+ "learning_rate": 0.00015395772822958845,
598
+ "loss": 1.6429,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.3723849372384938,
603
+ "grad_norm": 0.19711142778396606,
604
+ "learning_rate": 0.00015278218986299074,
605
+ "loss": 1.624,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.389121338912134,
610
+ "grad_norm": 0.16961851716041565,
611
+ "learning_rate": 0.0001515964523628501,
612
+ "loss": 1.6097,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.4058577405857742,
617
+ "grad_norm": 0.20063763856887817,
618
+ "learning_rate": 0.00015040074484992,
619
+ "loss": 1.6171,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.4225941422594142,
624
+ "grad_norm": 0.16175565123558044,
625
+ "learning_rate": 0.00014919529837146528,
626
+ "loss": 1.6119,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.4393305439330544,
631
+ "grad_norm": 0.20445561408996582,
632
+ "learning_rate": 0.00014798034585661695,
633
+ "loss": 1.6089,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.4560669456066946,
638
+ "grad_norm": 0.17204363644123077,
639
+ "learning_rate": 0.0001467561220713628,
640
+ "loss": 1.6178,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.4728033472803348,
645
+ "grad_norm": 0.1780082732439041,
646
+ "learning_rate": 0.0001455228635731839,
647
+ "loss": 1.6172,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.489539748953975,
652
+ "grad_norm": 0.17321935296058655,
653
+ "learning_rate": 0.00014428080866534396,
654
+ "loss": 1.574,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.506276150627615,
659
+ "grad_norm": 0.1722816675901413,
660
+ "learning_rate": 0.00014303019735084226,
661
+ "loss": 1.6096,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.5230125523012552,
666
+ "grad_norm": 0.1621088981628418,
667
+ "learning_rate": 0.00014177127128603745,
668
+ "loss": 1.603,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.5397489539748954,
673
+ "grad_norm": 0.17485831677913666,
674
+ "learning_rate": 0.0001405042737339524,
675
+ "loss": 1.6105,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.5564853556485354,
680
+ "grad_norm": 0.16599352657794952,
681
+ "learning_rate": 0.0001392294495172681,
682
+ "loss": 1.632,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.5732217573221758,
687
+ "grad_norm": 0.1569545418024063,
688
+ "learning_rate": 0.00013794704497101655,
689
+ "loss": 1.608,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.5899581589958158,
694
+ "grad_norm": 0.15951111912727356,
695
+ "learning_rate": 0.0001366573078949813,
696
+ "loss": 1.5742,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.606694560669456,
701
+ "grad_norm": 0.1951216161251068,
702
+ "learning_rate": 0.00013536048750581494,
703
+ "loss": 1.5908,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.6234309623430963,
708
+ "grad_norm": 0.20315046608448029,
709
+ "learning_rate": 0.00013405683438888282,
710
+ "loss": 1.6081,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.6401673640167362,
715
+ "grad_norm": 0.16759882867336273,
716
+ "learning_rate": 0.00013274660044984224,
717
+ "loss": 1.6041,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.6569037656903767,
722
+ "grad_norm": 0.18749655783176422,
723
+ "learning_rate": 0.00013143003886596669,
724
+ "loss": 1.6002,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.6736401673640167,
729
+ "grad_norm": 0.1809973418712616,
730
+ "learning_rate": 0.0001301074040372242,
731
+ "loss": 1.6328,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 1.6903765690376569,
736
+ "grad_norm": 0.20419345796108246,
737
+ "learning_rate": 0.00012877895153711935,
738
+ "loss": 1.6017,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 1.707112970711297,
743
+ "grad_norm": 0.1926768571138382,
744
+ "learning_rate": 0.0001274449380633089,
745
+ "loss": 1.5793,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 1.723849372384937,
750
+ "grad_norm": 0.22891242802143097,
751
+ "learning_rate": 0.00012610562138799978,
752
+ "loss": 1.6306,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 1.7405857740585775,
757
+ "grad_norm": 0.17105843126773834,
758
+ "learning_rate": 0.00012476126030813963,
759
+ "loss": 1.5999,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 1.7573221757322175,
764
+ "grad_norm": 0.17857873439788818,
765
+ "learning_rate": 0.0001234121145954094,
766
+ "loss": 1.5867,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 1.7740585774058577,
771
+ "grad_norm": 0.1942574381828308,
772
+ "learning_rate": 0.0001220584449460274,
773
+ "loss": 1.5719,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 1.790794979079498,
778
+ "grad_norm": 0.18035678565502167,
779
+ "learning_rate": 0.00012070051293037492,
780
+ "loss": 1.5783,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 1.8075313807531381,
785
+ "grad_norm": 0.18351756036281586,
786
+ "learning_rate": 0.00011933858094245281,
787
+ "loss": 1.6121,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 1.8242677824267783,
792
+ "grad_norm": 0.17191624641418457,
793
+ "learning_rate": 0.00011797291214917881,
794
+ "loss": 1.5801,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 1.8410041841004183,
799
+ "grad_norm": 0.19317130744457245,
800
+ "learning_rate": 0.00011660377043953588,
801
+ "loss": 1.5928,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 1.8577405857740585,
806
+ "grad_norm": 0.1735094040632248,
807
+ "learning_rate": 0.0001152314203735805,
808
+ "loss": 1.5782,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 1.8744769874476988,
813
+ "grad_norm": 0.1757810264825821,
814
+ "learning_rate": 0.0001138561271313219,
815
+ "loss": 1.605,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 1.891213389121339,
820
+ "grad_norm": 0.20154766738414764,
821
+ "learning_rate": 0.00011247815646148087,
822
+ "loss": 1.5782,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 1.9079497907949792,
827
+ "grad_norm": 0.18075552582740784,
828
+ "learning_rate": 0.00011109777463013915,
829
+ "loss": 1.5905,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 1.9246861924686192,
834
+ "grad_norm": 0.1821986436843872,
835
+ "learning_rate": 0.0001097152483692886,
836
+ "loss": 1.5661,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 1.9414225941422594,
841
+ "grad_norm": 0.1858905404806137,
842
+ "learning_rate": 0.00010833084482529048,
843
+ "loss": 1.6245,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 1.9581589958158996,
848
+ "grad_norm": 0.19977439939975739,
849
+ "learning_rate": 0.00010694483150725458,
850
+ "loss": 1.5568,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 1.9581589958158996,
855
+ "eval_loss": 1.7031370401382446,
856
+ "eval_runtime": 45.0796,
857
+ "eval_samples_per_second": 37.334,
858
+ "eval_steps_per_second": 0.799,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.9748953974895398,
863
+ "grad_norm": 0.1789984554052353,
864
+ "learning_rate": 0.00010555747623534831,
865
+ "loss": 1.5704,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.99163179916318,
870
+ "grad_norm": 0.22544507682323456,
871
+ "learning_rate": 0.00010416904708904548,
872
+ "loss": 1.6183,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 2.00836820083682,
877
+ "grad_norm": 0.17342977225780487,
878
+ "learning_rate": 0.00010277981235532541,
879
+ "loss": 1.5733,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 2.00836820083682,
884
+ "grad_norm": 0.6578261256217957,
885
+ "learning_rate": 0.00010139004047683151,
886
+ "loss": 1.6821,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 2.0251046025104604,
891
+ "grad_norm": 0.1935090273618698,
892
+ "learning_rate": 0.0001,
893
+ "loss": 1.5441,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 2.0418410041841004,
898
+ "grad_norm": 0.19911256432533264,
899
+ "learning_rate": 9.860995952316851e-05,
900
+ "loss": 1.5088,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 2.0585774058577404,
905
+ "grad_norm": 0.18341544270515442,
906
+ "learning_rate": 9.722018764467461e-05,
907
+ "loss": 1.4831,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 2.075313807531381,
912
+ "grad_norm": 0.19700396060943604,
913
+ "learning_rate": 9.583095291095453e-05,
914
+ "loss": 1.5297,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 2.092050209205021,
919
+ "grad_norm": 0.20507797598838806,
920
+ "learning_rate": 9.444252376465171e-05,
921
+ "loss": 1.4972,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 2.1087866108786613,
926
+ "grad_norm": 0.2015601396560669,
927
+ "learning_rate": 9.305516849274541e-05,
928
+ "loss": 1.4937,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 2.1255230125523012,
933
+ "grad_norm": 0.22213681042194366,
934
+ "learning_rate": 9.166915517470953e-05,
935
+ "loss": 1.4873,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 2.1422594142259412,
940
+ "grad_norm": 0.18814267218112946,
941
+ "learning_rate": 9.028475163071141e-05,
942
+ "loss": 1.4909,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 2.1589958158995817,
947
+ "grad_norm": 0.20081497728824615,
948
+ "learning_rate": 8.890222536986085e-05,
949
+ "loss": 1.5314,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 2.1757322175732217,
954
+ "grad_norm": 0.19582556188106537,
955
+ "learning_rate": 8.752184353851916e-05,
956
+ "loss": 1.4818,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.192468619246862,
961
+ "grad_norm": 0.21074539422988892,
962
+ "learning_rate": 8.614387286867814e-05,
963
+ "loss": 1.5172,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.209205020920502,
968
+ "grad_norm": 0.20774056017398834,
969
+ "learning_rate": 8.47685796264195e-05,
970
+ "loss": 1.5242,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.225941422594142,
975
+ "grad_norm": 0.20510801672935486,
976
+ "learning_rate": 8.339622956046417e-05,
977
+ "loss": 1.5028,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.2426778242677825,
982
+ "grad_norm": 0.20695893466472626,
983
+ "learning_rate": 8.202708785082121e-05,
984
+ "loss": 1.4822,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.2594142259414225,
989
+ "grad_norm": 0.19602717459201813,
990
+ "learning_rate": 8.066141905754723e-05,
991
+ "loss": 1.5104,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.276150627615063,
996
+ "grad_norm": 0.21398168802261353,
997
+ "learning_rate": 7.929948706962508e-05,
998
+ "loss": 1.497,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.292887029288703,
1003
+ "grad_norm": 0.21202580630779266,
1004
+ "learning_rate": 7.794155505397261e-05,
1005
+ "loss": 1.4967,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.309623430962343,
1010
+ "grad_norm": 0.2122480869293213,
1011
+ "learning_rate": 7.658788540459062e-05,
1012
+ "loss": 1.4908,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.3263598326359833,
1017
+ "grad_norm": 0.19832229614257812,
1018
+ "learning_rate": 7.523873969186039e-05,
1019
+ "loss": 1.4824,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.3430962343096233,
1024
+ "grad_norm": 0.19788770377635956,
1025
+ "learning_rate": 7.389437861200024e-05,
1026
+ "loss": 1.5386,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.3598326359832638,
1031
+ "grad_norm": 0.19926555454730988,
1032
+ "learning_rate": 7.25550619366911e-05,
1033
+ "loss": 1.5111,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.3765690376569037,
1038
+ "grad_norm": 0.19894631206989288,
1039
+ "learning_rate": 7.122104846288064e-05,
1040
+ "loss": 1.5104,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.393305439330544,
1045
+ "grad_norm": 0.19460007548332214,
1046
+ "learning_rate": 6.989259596277582e-05,
1047
+ "loss": 1.5079,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.410041841004184,
1052
+ "grad_norm": 0.19478248059749603,
1053
+ "learning_rate": 6.85699611340333e-05,
1054
+ "loss": 1.5008,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.426778242677824,
1059
+ "grad_norm": 0.2025572657585144,
1060
+ "learning_rate": 6.725339955015777e-05,
1061
+ "loss": 1.5012,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.4435146443514646,
1066
+ "grad_norm": 0.23313574492931366,
1067
+ "learning_rate": 6.594316561111724e-05,
1068
+ "loss": 1.487,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.4602510460251046,
1073
+ "grad_norm": 0.1957079917192459,
1074
+ "learning_rate": 6.46395124941851e-05,
1075
+ "loss": 1.4873,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.476987447698745,
1080
+ "grad_norm": 0.19845594465732574,
1081
+ "learning_rate": 6.334269210501875e-05,
1082
+ "loss": 1.4975,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.493723849372385,
1087
+ "grad_norm": 0.21137520670890808,
1088
+ "learning_rate": 6.205295502898348e-05,
1089
+ "loss": 1.4861,
1090
+ "step": 151
1091
+ },
1092
+ {
1093
+ "epoch": 2.510460251046025,
1094
+ "grad_norm": 0.19834473729133606,
1095
+ "learning_rate": 6.0770550482731924e-05,
1096
+ "loss": 1.5178,
1097
+ "step": 152
1098
+ },
1099
+ {
1100
+ "epoch": 2.5271966527196654,
1101
+ "grad_norm": 0.22226808965206146,
1102
+ "learning_rate": 5.9495726266047605e-05,
1103
+ "loss": 1.481,
1104
+ "step": 153
1105
+ },
1106
+ {
1107
+ "epoch": 2.5439330543933054,
1108
+ "grad_norm": 0.20262005925178528,
1109
+ "learning_rate": 5.8228728713962543e-05,
1110
+ "loss": 1.4899,
1111
+ "step": 154
1112
+ },
1113
+ {
1114
+ "epoch": 2.560669456066946,
1115
+ "grad_norm": 0.20117135345935822,
1116
+ "learning_rate": 5.696980264915777e-05,
1117
+ "loss": 1.493,
1118
+ "step": 155
1119
+ },
1120
+ {
1121
+ "epoch": 2.577405857740586,
1122
+ "grad_norm": 0.21935462951660156,
1123
+ "learning_rate": 5.571919133465605e-05,
1124
+ "loss": 1.535,
1125
+ "step": 156
1126
+ },
1127
+ {
1128
+ "epoch": 2.594142259414226,
1129
+ "grad_norm": 0.19787819683551788,
1130
+ "learning_rate": 5.447713642681612e-05,
1131
+ "loss": 1.4635,
1132
+ "step": 157
1133
+ },
1134
+ {
1135
+ "epoch": 2.6108786610878663,
1136
+ "grad_norm": 0.2078079879283905,
1137
+ "learning_rate": 5.324387792863719e-05,
1138
+ "loss": 1.4824,
1139
+ "step": 158
1140
+ },
1141
+ {
1142
+ "epoch": 2.6276150627615062,
1143
+ "grad_norm": 0.21869535744190216,
1144
+ "learning_rate": 5.201965414338308e-05,
1145
+ "loss": 1.474,
1146
+ "step": 159
1147
+ },
1148
+ {
1149
+ "epoch": 2.6443514644351467,
1150
+ "grad_norm": 0.2099902182817459,
1151
+ "learning_rate": 5.080470162853472e-05,
1152
+ "loss": 1.4711,
1153
+ "step": 160
1154
+ },
1155
+ {
1156
+ "epoch": 2.6610878661087867,
1157
+ "grad_norm": 0.2077307403087616,
1158
+ "learning_rate": 4.959925515008002e-05,
1159
+ "loss": 1.5137,
1160
+ "step": 161
1161
+ },
1162
+ {
1163
+ "epoch": 2.6778242677824267,
1164
+ "grad_norm": 0.20681549608707428,
1165
+ "learning_rate": 4.840354763714991e-05,
1166
+ "loss": 1.4543,
1167
+ "step": 162
1168
+ },
1169
+ {
1170
+ "epoch": 2.694560669456067,
1171
+ "grad_norm": 0.21305464208126068,
1172
+ "learning_rate": 4.7217810137009274e-05,
1173
+ "loss": 1.468,
1174
+ "step": 163
1175
+ },
1176
+ {
1177
+ "epoch": 2.711297071129707,
1178
+ "grad_norm": 0.196672260761261,
1179
+ "learning_rate": 4.604227177041156e-05,
1180
+ "loss": 1.5066,
1181
+ "step": 164
1182
+ },
1183
+ {
1184
+ "epoch": 2.7280334728033475,
1185
+ "grad_norm": 0.20596779882907867,
1186
+ "learning_rate": 4.487715968732568e-05,
1187
+ "loss": 1.4968,
1188
+ "step": 165
1189
+ },
1190
+ {
1191
+ "epoch": 2.7447698744769875,
1192
+ "grad_norm": 0.19627641141414642,
1193
+ "learning_rate": 4.372269902304363e-05,
1194
+ "loss": 1.4813,
1195
+ "step": 166
1196
+ },
1197
+ {
1198
+ "epoch": 2.7615062761506275,
1199
+ "grad_norm": 0.20364060997962952,
1200
+ "learning_rate": 4.257911285467754e-05,
1201
+ "loss": 1.4794,
1202
+ "step": 167
1203
+ },
1204
+ {
1205
+ "epoch": 2.778242677824268,
1206
+ "grad_norm": 0.20353439450263977,
1207
+ "learning_rate": 4.144662215805426e-05,
1208
+ "loss": 1.4932,
1209
+ "step": 168
1210
+ },
1211
+ {
1212
+ "epoch": 2.794979079497908,
1213
+ "grad_norm": 0.20134314894676208,
1214
+ "learning_rate": 4.0325445765016145e-05,
1215
+ "loss": 1.4657,
1216
+ "step": 169
1217
+ },
1218
+ {
1219
+ "epoch": 2.8117154811715483,
1220
+ "grad_norm": 0.20385348796844482,
1221
+ "learning_rate": 3.921580032113602e-05,
1222
+ "loss": 1.4681,
1223
+ "step": 170
1224
+ },
1225
+ {
1226
+ "epoch": 2.8284518828451883,
1227
+ "grad_norm": 0.20909759402275085,
1228
+ "learning_rate": 3.8117900243854595e-05,
1229
+ "loss": 1.4477,
1230
+ "step": 171
1231
+ },
1232
+ {
1233
+ "epoch": 2.8451882845188283,
1234
+ "grad_norm": 0.2068387120962143,
1235
+ "learning_rate": 3.7031957681048604e-05,
1236
+ "loss": 1.486,
1237
+ "step": 172
1238
+ },
1239
+ {
1240
+ "epoch": 2.8619246861924688,
1241
+ "grad_norm": 0.2067539542913437,
1242
+ "learning_rate": 3.595818247003713e-05,
1243
+ "loss": 1.4723,
1244
+ "step": 173
1245
+ },
1246
+ {
1247
+ "epoch": 2.8786610878661087,
1248
+ "grad_norm": 0.21357451379299164,
1249
+ "learning_rate": 3.489678209703475e-05,
1250
+ "loss": 1.4867,
1251
+ "step": 174
1252
+ },
1253
+ {
1254
+ "epoch": 2.895397489539749,
1255
+ "grad_norm": 0.21152114868164062,
1256
+ "learning_rate": 3.3847961657058845e-05,
1257
+ "loss": 1.5219,
1258
+ "step": 175
1259
+ },
1260
+ {
1261
+ "epoch": 2.912133891213389,
1262
+ "grad_norm": 0.20278601348400116,
1263
+ "learning_rate": 3.281192381429894e-05,
1264
+ "loss": 1.4722,
1265
+ "step": 176
1266
+ },
1267
+ {
1268
+ "epoch": 2.928870292887029,
1269
+ "grad_norm": 0.2019844502210617,
1270
+ "learning_rate": 3.178886876295578e-05,
1271
+ "loss": 1.4787,
1272
+ "step": 177
1273
+ },
1274
+ {
1275
+ "epoch": 2.928870292887029,
1276
+ "eval_loss": 1.7109203338623047,
1277
+ "eval_runtime": 44.9676,
1278
+ "eval_samples_per_second": 37.427,
1279
+ "eval_steps_per_second": 0.801,
1280
+ "step": 177
1281
+ }
1282
+ ],
1283
+ "logging_steps": 1,
1284
+ "max_steps": 236,
1285
+ "num_input_tokens_seen": 0,
1286
+ "num_train_epochs": 4,
1287
+ "save_steps": 59,
1288
+ "stateful_callbacks": {
1289
+ "TrainerControl": {
1290
+ "args": {
1291
+ "should_epoch_stop": false,
1292
+ "should_evaluate": false,
1293
+ "should_log": false,
1294
+ "should_save": true,
1295
+ "should_training_stop": false
1296
+ },
1297
+ "attributes": {}
1298
+ }
1299
+ },
1300
+ "total_flos": 4.218754220163072e+17,
1301
+ "train_batch_size": 48,
1302
+ "trial_name": null,
1303
+ "trial_params": null
1304
+ }
checkpoint-177/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553af1c5dd81032ecab9996f20cecb8cd9d302493de0264d19b2265d1e75c3ef
3
+ size 6072
checkpoint-236/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: t-bank-ai/T-lite-instruct-0.1
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-236/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "t-bank-ai/T-lite-instruct-0.1",
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
+ "down_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-236/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:932c15703f1d58eeb18d41bd58f838300c0efd111a6a21725b378be873df04c6
3
+ size 335604696
checkpoint-236/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3518e26bfd04c91603bdd51332721099767b66a833e98640e497404edaa43aed
3
+ size 168624724
checkpoint-236/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8100fcf86914fe9671143957089c08a7be55175174ed0a5abd6adc6fb7db910f
3
+ size 14244
checkpoint-236/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f16866208e697deb13629708b06bc8ca5ce26719a16eb0ea06ac15f28d39d3
3
+ size 1064
checkpoint-236/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<sep>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-236/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-236/tokenizer_config.json ADDED
@@ -0,0 +1,2089 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<pad>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<unk>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ },
2067
+ "128258": {
2068
+ "content": "<sep>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": true
2074
+ }
2075
+ },
2076
+ "bos_token": "<|begin_of_text|>",
2077
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2078
+ "clean_up_tokenization_spaces": true,
2079
+ "eos_token": "<|end_of_text|>",
2080
+ "model_input_names": [
2081
+ "input_ids",
2082
+ "attention_mask"
2083
+ ],
2084
+ "model_max_length": 8192,
2085
+ "pad_token": "<|eot_id|>",
2086
+ "sep_token": "<sep>",
2087
+ "tokenizer_class": "PreTrainedTokenizerFast",
2088
+ "unk_token": "<unk>"
2089
+ }
checkpoint-236/trainer_state.json ADDED
@@ -0,0 +1,1725 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.899581589958159,
5
+ "eval_steps": 59,
6
+ "global_step": 236,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016736401673640166,
13
+ "grad_norm": 0.3126992881298065,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.4388,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.016736401673640166,
20
+ "eval_loss": 2.2736361026763916,
21
+ "eval_runtime": 44.9772,
22
+ "eval_samples_per_second": 37.419,
23
+ "eval_steps_per_second": 0.8,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.03347280334728033,
28
+ "grad_norm": 0.31262004375457764,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.3915,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0502092050209205,
35
+ "grad_norm": 0.3161173462867737,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.4118,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.06694560669456066,
42
+ "grad_norm": 0.32605665922164917,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.3872,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.08368200836820083,
49
+ "grad_norm": 0.32243478298187256,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.3368,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.100418410041841,
56
+ "grad_norm": 0.3141494393348694,
57
+ "learning_rate": 0.00012,
58
+ "loss": 2.2966,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.11715481171548117,
63
+ "grad_norm": 0.330599308013916,
64
+ "learning_rate": 0.00014,
65
+ "loss": 2.2379,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.13389121338912133,
70
+ "grad_norm": 0.33452969789505005,
71
+ "learning_rate": 0.00016,
72
+ "loss": 2.1949,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1506276150627615,
77
+ "grad_norm": 0.2835342288017273,
78
+ "learning_rate": 0.00018,
79
+ "loss": 2.156,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.16736401673640167,
84
+ "grad_norm": 0.23091256618499756,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.1109,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.18410041841004185,
91
+ "grad_norm": 0.2284015268087387,
92
+ "learning_rate": 0.00019999033847063811,
93
+ "loss": 2.0782,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.200836820083682,
98
+ "grad_norm": 0.23981927335262299,
99
+ "learning_rate": 0.00019996135574945544,
100
+ "loss": 2.053,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.2175732217573222,
105
+ "grad_norm": 0.23807936906814575,
106
+ "learning_rate": 0.00019991305743680013,
107
+ "loss": 2.0294,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.23430962343096234,
112
+ "grad_norm": 0.20766477286815643,
113
+ "learning_rate": 0.0001998454528653836,
114
+ "loss": 1.9947,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.2510460251046025,
119
+ "grad_norm": 0.1892593652009964,
120
+ "learning_rate": 0.00019975855509847686,
121
+ "loss": 1.9643,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.26778242677824265,
126
+ "grad_norm": 0.19022946059703827,
127
+ "learning_rate": 0.00019965238092738643,
128
+ "loss": 1.9275,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.28451882845188287,
133
+ "grad_norm": 0.18370254337787628,
134
+ "learning_rate": 0.00019952695086820975,
135
+ "loss": 1.9512,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.301255230125523,
140
+ "grad_norm": 0.16774943470954895,
141
+ "learning_rate": 0.0001993822891578708,
142
+ "loss": 1.8883,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.3179916317991632,
147
+ "grad_norm": 0.17572854459285736,
148
+ "learning_rate": 0.0001992184237494368,
149
+ "loss": 1.938,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.33472803347280333,
154
+ "grad_norm": 0.21952244639396667,
155
+ "learning_rate": 0.0001990353863067169,
156
+ "loss": 1.8937,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.3514644351464435,
161
+ "grad_norm": 0.2579434812068939,
162
+ "learning_rate": 0.0001988332121981436,
163
+ "loss": 1.8797,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.3682008368200837,
168
+ "grad_norm": 0.29942768812179565,
169
+ "learning_rate": 0.00019861194048993863,
170
+ "loss": 1.8766,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.38493723849372385,
175
+ "grad_norm": 0.326593279838562,
176
+ "learning_rate": 0.0001983716139385641,
177
+ "loss": 1.8567,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.401673640167364,
182
+ "grad_norm": 0.2769831418991089,
183
+ "learning_rate": 0.0001981122789824607,
184
+ "loss": 1.839,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.41841004184100417,
189
+ "grad_norm": 0.2902805507183075,
190
+ "learning_rate": 0.00019783398573307428,
191
+ "loss": 1.8622,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.4351464435146444,
196
+ "grad_norm": 0.2152428776025772,
197
+ "learning_rate": 0.00019753678796517282,
198
+ "loss": 1.8393,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.45188284518828453,
203
+ "grad_norm": 0.1541067361831665,
204
+ "learning_rate": 0.00019722074310645553,
205
+ "loss": 1.8326,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.4686192468619247,
210
+ "grad_norm": 0.12413746118545532,
211
+ "learning_rate": 0.00019688591222645607,
212
+ "loss": 1.8079,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.48535564853556484,
217
+ "grad_norm": 0.11909659206867218,
218
+ "learning_rate": 0.000196532360024742,
219
+ "loss": 1.8044,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.502092050209205,
224
+ "grad_norm": 0.16260313987731934,
225
+ "learning_rate": 0.0001961601548184129,
226
+ "loss": 1.7888,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.5188284518828452,
231
+ "grad_norm": 0.17894335091114044,
232
+ "learning_rate": 0.00019576936852889936,
233
+ "loss": 1.8263,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.5355648535564853,
238
+ "grad_norm": 0.21706554293632507,
239
+ "learning_rate": 0.00019536007666806556,
240
+ "loss": 1.8151,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.5523012552301255,
245
+ "grad_norm": 0.17296762764453888,
246
+ "learning_rate": 0.0001949323583236181,
247
+ "loss": 1.7901,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.5690376569037657,
252
+ "grad_norm": 0.1761002093553543,
253
+ "learning_rate": 0.0001944862961438239,
254
+ "loss": 1.8126,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.5857740585774058,
259
+ "grad_norm": 0.14914190769195557,
260
+ "learning_rate": 0.00019402197632153992,
261
+ "loss": 1.7797,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.602510460251046,
266
+ "grad_norm": 0.13111546635627747,
267
+ "learning_rate": 0.00019353948857755803,
268
+ "loss": 1.7916,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.6192468619246861,
273
+ "grad_norm": 0.12080994248390198,
274
+ "learning_rate": 0.00019303892614326836,
275
+ "loss": 1.7834,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.6359832635983264,
280
+ "grad_norm": 0.15622606873512268,
281
+ "learning_rate": 0.00019252038574264405,
282
+ "loss": 1.794,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.6527196652719666,
287
+ "grad_norm": 0.1345275640487671,
288
+ "learning_rate": 0.00019198396757355118,
289
+ "loss": 1.7554,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.6694560669456067,
294
+ "grad_norm": 0.18387249112129211,
295
+ "learning_rate": 0.00019142977528838762,
296
+ "loss": 1.7675,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.6861924686192469,
301
+ "grad_norm": 0.165897399187088,
302
+ "learning_rate": 0.00019085791597405404,
303
+ "loss": 1.7631,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.702928870292887,
308
+ "grad_norm": 0.13675889372825623,
309
+ "learning_rate": 0.00019026850013126157,
310
+ "loss": 1.754,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.7196652719665272,
315
+ "grad_norm": 0.16969387233257294,
316
+ "learning_rate": 0.00018966164165317966,
317
+ "loss": 1.745,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.7364016736401674,
322
+ "grad_norm": 0.16098380088806152,
323
+ "learning_rate": 0.00018903745780342839,
324
+ "loss": 1.7609,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.7531380753138075,
329
+ "grad_norm": 0.12338632345199585,
330
+ "learning_rate": 0.0001883960691934196,
331
+ "loss": 1.7584,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.7698744769874477,
336
+ "grad_norm": 0.1335158348083496,
337
+ "learning_rate": 0.00018773759975905098,
338
+ "loss": 1.7302,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.7866108786610879,
343
+ "grad_norm": 0.11967575550079346,
344
+ "learning_rate": 0.00018706217673675811,
345
+ "loss": 1.7323,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.803347280334728,
350
+ "grad_norm": 0.12446475774049759,
351
+ "learning_rate": 0.0001863699306389282,
352
+ "loss": 1.7217,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.8200836820083682,
357
+ "grad_norm": 0.13070392608642578,
358
+ "learning_rate": 0.00018566099522868119,
359
+ "loss": 1.7192,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.8368200836820083,
364
+ "grad_norm": 0.15041972696781158,
365
+ "learning_rate": 0.00018493550749402278,
366
+ "loss": 1.7386,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.8535564853556485,
371
+ "grad_norm": 0.12314204126596451,
372
+ "learning_rate": 0.00018419360762137395,
373
+ "loss": 1.7465,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.8702928870292888,
378
+ "grad_norm": 0.15009309351444244,
379
+ "learning_rate": 0.00018343543896848273,
380
+ "loss": 1.7216,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.8870292887029289,
385
+ "grad_norm": 0.12467087060213089,
386
+ "learning_rate": 0.00018266114803672318,
387
+ "loss": 1.7043,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.9037656903765691,
392
+ "grad_norm": 0.1297266036272049,
393
+ "learning_rate": 0.00018187088444278674,
394
+ "loss": 1.7069,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.9205020920502092,
399
+ "grad_norm": 0.1195509061217308,
400
+ "learning_rate": 0.00018106480088977172,
401
+ "loss": 1.7305,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.9372384937238494,
406
+ "grad_norm": 0.14450602233409882,
407
+ "learning_rate": 0.00018024305313767646,
408
+ "loss": 1.7171,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.9539748953974896,
413
+ "grad_norm": 0.16594989597797394,
414
+ "learning_rate": 0.00017940579997330165,
415
+ "loss": 1.7239,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.9707112970711297,
420
+ "grad_norm": 0.19210928678512573,
421
+ "learning_rate": 0.00017855320317956784,
422
+ "loss": 1.7081,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.9874476987447699,
427
+ "grad_norm": 0.16463987529277802,
428
+ "learning_rate": 0.00017768542750425426,
429
+ "loss": 1.7178,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.9874476987447699,
434
+ "eval_loss": 1.7365927696228027,
435
+ "eval_runtime": 44.9816,
436
+ "eval_samples_per_second": 37.415,
437
+ "eval_steps_per_second": 0.8,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.00418410041841,
442
+ "grad_norm": 0.13954801857471466,
443
+ "learning_rate": 0.0001768026406281642,
444
+ "loss": 1.6905,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.00418410041841,
449
+ "grad_norm": 0.17747963964939117,
450
+ "learning_rate": 0.00017590501313272415,
451
+ "loss": 1.6864,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.0209205020920502,
456
+ "grad_norm": 0.1328994333744049,
457
+ "learning_rate": 0.00017499271846702213,
458
+ "loss": 1.6388,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.0376569037656904,
463
+ "grad_norm": 0.12811322510242462,
464
+ "learning_rate": 0.00017406593291429217,
465
+ "loss": 1.6821,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.0543933054393306,
470
+ "grad_norm": 0.1379721611738205,
471
+ "learning_rate": 0.00017312483555785086,
472
+ "loss": 1.6364,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.0711297071129706,
477
+ "grad_norm": 0.14301170408725739,
478
+ "learning_rate": 0.00017216960824649303,
479
+ "loss": 1.646,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.0878661087866108,
484
+ "grad_norm": 0.15547165274620056,
485
+ "learning_rate": 0.00017120043555935298,
486
+ "loss": 1.6625,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.104602510460251,
491
+ "grad_norm": 0.14291325211524963,
492
+ "learning_rate": 0.0001702175047702382,
493
+ "loss": 1.6392,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.1213389121338913,
498
+ "grad_norm": 0.14325812458992004,
499
+ "learning_rate": 0.00016922100581144228,
500
+ "loss": 1.6677,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.1380753138075315,
505
+ "grad_norm": 0.14328014850616455,
506
+ "learning_rate": 0.00016821113123704424,
507
+ "loss": 1.6182,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.1548117154811715,
512
+ "grad_norm": 0.16151900589466095,
513
+ "learning_rate": 0.00016718807618570106,
514
+ "loss": 1.6492,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.1715481171548117,
519
+ "grad_norm": 0.15649794042110443,
520
+ "learning_rate": 0.00016615203834294119,
521
+ "loss": 1.6334,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.1882845188284519,
526
+ "grad_norm": 0.15963214635849,
527
+ "learning_rate": 0.00016510321790296525,
528
+ "loss": 1.6203,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.205020920502092,
533
+ "grad_norm": 0.15893195569515228,
534
+ "learning_rate": 0.00016404181752996289,
535
+ "loss": 1.6408,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.2217573221757323,
540
+ "grad_norm": 0.16694918274879456,
541
+ "learning_rate": 0.00016296804231895142,
542
+ "loss": 1.633,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.2384937238493725,
547
+ "grad_norm": 0.15804418921470642,
548
+ "learning_rate": 0.00016188209975614542,
549
+ "loss": 1.6548,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.2552301255230125,
554
+ "grad_norm": 0.14725787937641144,
555
+ "learning_rate": 0.00016078419967886402,
556
+ "loss": 1.6158,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.2719665271966527,
561
+ "grad_norm": 0.15310946106910706,
562
+ "learning_rate": 0.00015967455423498387,
563
+ "loss": 1.664,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.288702928870293,
568
+ "grad_norm": 0.14741982519626617,
569
+ "learning_rate": 0.00015855337784194577,
570
+ "loss": 1.6494,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.3054393305439331,
575
+ "grad_norm": 0.1478704810142517,
576
+ "learning_rate": 0.00015742088714532247,
577
+ "loss": 1.6254,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.3221757322175733,
582
+ "grad_norm": 0.1895337849855423,
583
+ "learning_rate": 0.00015627730097695638,
584
+ "loss": 1.6018,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.3389121338912133,
589
+ "grad_norm": 0.19194994866847992,
590
+ "learning_rate": 0.00015512284031267437,
591
+ "loss": 1.6543,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.3556485355648535,
596
+ "grad_norm": 0.1553422063589096,
597
+ "learning_rate": 0.00015395772822958845,
598
+ "loss": 1.6429,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.3723849372384938,
603
+ "grad_norm": 0.19711142778396606,
604
+ "learning_rate": 0.00015278218986299074,
605
+ "loss": 1.624,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.389121338912134,
610
+ "grad_norm": 0.16961851716041565,
611
+ "learning_rate": 0.0001515964523628501,
612
+ "loss": 1.6097,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.4058577405857742,
617
+ "grad_norm": 0.20063763856887817,
618
+ "learning_rate": 0.00015040074484992,
619
+ "loss": 1.6171,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.4225941422594142,
624
+ "grad_norm": 0.16175565123558044,
625
+ "learning_rate": 0.00014919529837146528,
626
+ "loss": 1.6119,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.4393305439330544,
631
+ "grad_norm": 0.20445561408996582,
632
+ "learning_rate": 0.00014798034585661695,
633
+ "loss": 1.6089,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.4560669456066946,
638
+ "grad_norm": 0.17204363644123077,
639
+ "learning_rate": 0.0001467561220713628,
640
+ "loss": 1.6178,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.4728033472803348,
645
+ "grad_norm": 0.1780082732439041,
646
+ "learning_rate": 0.0001455228635731839,
647
+ "loss": 1.6172,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.489539748953975,
652
+ "grad_norm": 0.17321935296058655,
653
+ "learning_rate": 0.00014428080866534396,
654
+ "loss": 1.574,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.506276150627615,
659
+ "grad_norm": 0.1722816675901413,
660
+ "learning_rate": 0.00014303019735084226,
661
+ "loss": 1.6096,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.5230125523012552,
666
+ "grad_norm": 0.1621088981628418,
667
+ "learning_rate": 0.00014177127128603745,
668
+ "loss": 1.603,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.5397489539748954,
673
+ "grad_norm": 0.17485831677913666,
674
+ "learning_rate": 0.0001405042737339524,
675
+ "loss": 1.6105,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.5564853556485354,
680
+ "grad_norm": 0.16599352657794952,
681
+ "learning_rate": 0.0001392294495172681,
682
+ "loss": 1.632,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.5732217573221758,
687
+ "grad_norm": 0.1569545418024063,
688
+ "learning_rate": 0.00013794704497101655,
689
+ "loss": 1.608,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.5899581589958158,
694
+ "grad_norm": 0.15951111912727356,
695
+ "learning_rate": 0.0001366573078949813,
696
+ "loss": 1.5742,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.606694560669456,
701
+ "grad_norm": 0.1951216161251068,
702
+ "learning_rate": 0.00013536048750581494,
703
+ "loss": 1.5908,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.6234309623430963,
708
+ "grad_norm": 0.20315046608448029,
709
+ "learning_rate": 0.00013405683438888282,
710
+ "loss": 1.6081,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.6401673640167362,
715
+ "grad_norm": 0.16759882867336273,
716
+ "learning_rate": 0.00013274660044984224,
717
+ "loss": 1.6041,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.6569037656903767,
722
+ "grad_norm": 0.18749655783176422,
723
+ "learning_rate": 0.00013143003886596669,
724
+ "loss": 1.6002,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.6736401673640167,
729
+ "grad_norm": 0.1809973418712616,
730
+ "learning_rate": 0.0001301074040372242,
731
+ "loss": 1.6328,
732
+ "step": 101
733
+ },
734
+ {
735
+ "epoch": 1.6903765690376569,
736
+ "grad_norm": 0.20419345796108246,
737
+ "learning_rate": 0.00012877895153711935,
738
+ "loss": 1.6017,
739
+ "step": 102
740
+ },
741
+ {
742
+ "epoch": 1.707112970711297,
743
+ "grad_norm": 0.1926768571138382,
744
+ "learning_rate": 0.0001274449380633089,
745
+ "loss": 1.5793,
746
+ "step": 103
747
+ },
748
+ {
749
+ "epoch": 1.723849372384937,
750
+ "grad_norm": 0.22891242802143097,
751
+ "learning_rate": 0.00012610562138799978,
752
+ "loss": 1.6306,
753
+ "step": 104
754
+ },
755
+ {
756
+ "epoch": 1.7405857740585775,
757
+ "grad_norm": 0.17105843126773834,
758
+ "learning_rate": 0.00012476126030813963,
759
+ "loss": 1.5999,
760
+ "step": 105
761
+ },
762
+ {
763
+ "epoch": 1.7573221757322175,
764
+ "grad_norm": 0.17857873439788818,
765
+ "learning_rate": 0.0001234121145954094,
766
+ "loss": 1.5867,
767
+ "step": 106
768
+ },
769
+ {
770
+ "epoch": 1.7740585774058577,
771
+ "grad_norm": 0.1942574381828308,
772
+ "learning_rate": 0.0001220584449460274,
773
+ "loss": 1.5719,
774
+ "step": 107
775
+ },
776
+ {
777
+ "epoch": 1.790794979079498,
778
+ "grad_norm": 0.18035678565502167,
779
+ "learning_rate": 0.00012070051293037492,
780
+ "loss": 1.5783,
781
+ "step": 108
782
+ },
783
+ {
784
+ "epoch": 1.8075313807531381,
785
+ "grad_norm": 0.18351756036281586,
786
+ "learning_rate": 0.00011933858094245281,
787
+ "loss": 1.6121,
788
+ "step": 109
789
+ },
790
+ {
791
+ "epoch": 1.8242677824267783,
792
+ "grad_norm": 0.17191624641418457,
793
+ "learning_rate": 0.00011797291214917881,
794
+ "loss": 1.5801,
795
+ "step": 110
796
+ },
797
+ {
798
+ "epoch": 1.8410041841004183,
799
+ "grad_norm": 0.19317130744457245,
800
+ "learning_rate": 0.00011660377043953588,
801
+ "loss": 1.5928,
802
+ "step": 111
803
+ },
804
+ {
805
+ "epoch": 1.8577405857740585,
806
+ "grad_norm": 0.1735094040632248,
807
+ "learning_rate": 0.0001152314203735805,
808
+ "loss": 1.5782,
809
+ "step": 112
810
+ },
811
+ {
812
+ "epoch": 1.8744769874476988,
813
+ "grad_norm": 0.1757810264825821,
814
+ "learning_rate": 0.0001138561271313219,
815
+ "loss": 1.605,
816
+ "step": 113
817
+ },
818
+ {
819
+ "epoch": 1.891213389121339,
820
+ "grad_norm": 0.20154766738414764,
821
+ "learning_rate": 0.00011247815646148087,
822
+ "loss": 1.5782,
823
+ "step": 114
824
+ },
825
+ {
826
+ "epoch": 1.9079497907949792,
827
+ "grad_norm": 0.18075552582740784,
828
+ "learning_rate": 0.00011109777463013915,
829
+ "loss": 1.5905,
830
+ "step": 115
831
+ },
832
+ {
833
+ "epoch": 1.9246861924686192,
834
+ "grad_norm": 0.1821986436843872,
835
+ "learning_rate": 0.0001097152483692886,
836
+ "loss": 1.5661,
837
+ "step": 116
838
+ },
839
+ {
840
+ "epoch": 1.9414225941422594,
841
+ "grad_norm": 0.1858905404806137,
842
+ "learning_rate": 0.00010833084482529048,
843
+ "loss": 1.6245,
844
+ "step": 117
845
+ },
846
+ {
847
+ "epoch": 1.9581589958158996,
848
+ "grad_norm": 0.19977439939975739,
849
+ "learning_rate": 0.00010694483150725458,
850
+ "loss": 1.5568,
851
+ "step": 118
852
+ },
853
+ {
854
+ "epoch": 1.9581589958158996,
855
+ "eval_loss": 1.7031370401382446,
856
+ "eval_runtime": 45.0796,
857
+ "eval_samples_per_second": 37.334,
858
+ "eval_steps_per_second": 0.799,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 1.9748953974895398,
863
+ "grad_norm": 0.1789984554052353,
864
+ "learning_rate": 0.00010555747623534831,
865
+ "loss": 1.5704,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 1.99163179916318,
870
+ "grad_norm": 0.22544507682323456,
871
+ "learning_rate": 0.00010416904708904548,
872
+ "loss": 1.6183,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 2.00836820083682,
877
+ "grad_norm": 0.17342977225780487,
878
+ "learning_rate": 0.00010277981235532541,
879
+ "loss": 1.5733,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 2.00836820083682,
884
+ "grad_norm": 0.6578261256217957,
885
+ "learning_rate": 0.00010139004047683151,
886
+ "loss": 1.6821,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 2.0251046025104604,
891
+ "grad_norm": 0.1935090273618698,
892
+ "learning_rate": 0.0001,
893
+ "loss": 1.5441,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 2.0418410041841004,
898
+ "grad_norm": 0.19911256432533264,
899
+ "learning_rate": 9.860995952316851e-05,
900
+ "loss": 1.5088,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 2.0585774058577404,
905
+ "grad_norm": 0.18341544270515442,
906
+ "learning_rate": 9.722018764467461e-05,
907
+ "loss": 1.4831,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 2.075313807531381,
912
+ "grad_norm": 0.19700396060943604,
913
+ "learning_rate": 9.583095291095453e-05,
914
+ "loss": 1.5297,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 2.092050209205021,
919
+ "grad_norm": 0.20507797598838806,
920
+ "learning_rate": 9.444252376465171e-05,
921
+ "loss": 1.4972,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 2.1087866108786613,
926
+ "grad_norm": 0.2015601396560669,
927
+ "learning_rate": 9.305516849274541e-05,
928
+ "loss": 1.4937,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 2.1255230125523012,
933
+ "grad_norm": 0.22213681042194366,
934
+ "learning_rate": 9.166915517470953e-05,
935
+ "loss": 1.4873,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 2.1422594142259412,
940
+ "grad_norm": 0.18814267218112946,
941
+ "learning_rate": 9.028475163071141e-05,
942
+ "loss": 1.4909,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 2.1589958158995817,
947
+ "grad_norm": 0.20081497728824615,
948
+ "learning_rate": 8.890222536986085e-05,
949
+ "loss": 1.5314,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 2.1757322175732217,
954
+ "grad_norm": 0.19582556188106537,
955
+ "learning_rate": 8.752184353851916e-05,
956
+ "loss": 1.4818,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 2.192468619246862,
961
+ "grad_norm": 0.21074539422988892,
962
+ "learning_rate": 8.614387286867814e-05,
963
+ "loss": 1.5172,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 2.209205020920502,
968
+ "grad_norm": 0.20774056017398834,
969
+ "learning_rate": 8.47685796264195e-05,
970
+ "loss": 1.5242,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 2.225941422594142,
975
+ "grad_norm": 0.20510801672935486,
976
+ "learning_rate": 8.339622956046417e-05,
977
+ "loss": 1.5028,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 2.2426778242677825,
982
+ "grad_norm": 0.20695893466472626,
983
+ "learning_rate": 8.202708785082121e-05,
984
+ "loss": 1.4822,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 2.2594142259414225,
989
+ "grad_norm": 0.19602717459201813,
990
+ "learning_rate": 8.066141905754723e-05,
991
+ "loss": 1.5104,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 2.276150627615063,
996
+ "grad_norm": 0.21398168802261353,
997
+ "learning_rate": 7.929948706962508e-05,
998
+ "loss": 1.497,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 2.292887029288703,
1003
+ "grad_norm": 0.21202580630779266,
1004
+ "learning_rate": 7.794155505397261e-05,
1005
+ "loss": 1.4967,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 2.309623430962343,
1010
+ "grad_norm": 0.2122480869293213,
1011
+ "learning_rate": 7.658788540459062e-05,
1012
+ "loss": 1.4908,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 2.3263598326359833,
1017
+ "grad_norm": 0.19832229614257812,
1018
+ "learning_rate": 7.523873969186039e-05,
1019
+ "loss": 1.4824,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 2.3430962343096233,
1024
+ "grad_norm": 0.19788770377635956,
1025
+ "learning_rate": 7.389437861200024e-05,
1026
+ "loss": 1.5386,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 2.3598326359832638,
1031
+ "grad_norm": 0.19926555454730988,
1032
+ "learning_rate": 7.25550619366911e-05,
1033
+ "loss": 1.5111,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 2.3765690376569037,
1038
+ "grad_norm": 0.19894631206989288,
1039
+ "learning_rate": 7.122104846288064e-05,
1040
+ "loss": 1.5104,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 2.393305439330544,
1045
+ "grad_norm": 0.19460007548332214,
1046
+ "learning_rate": 6.989259596277582e-05,
1047
+ "loss": 1.5079,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 2.410041841004184,
1052
+ "grad_norm": 0.19478248059749603,
1053
+ "learning_rate": 6.85699611340333e-05,
1054
+ "loss": 1.5008,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 2.426778242677824,
1059
+ "grad_norm": 0.2025572657585144,
1060
+ "learning_rate": 6.725339955015777e-05,
1061
+ "loss": 1.5012,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 2.4435146443514646,
1066
+ "grad_norm": 0.23313574492931366,
1067
+ "learning_rate": 6.594316561111724e-05,
1068
+ "loss": 1.487,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 2.4602510460251046,
1073
+ "grad_norm": 0.1957079917192459,
1074
+ "learning_rate": 6.46395124941851e-05,
1075
+ "loss": 1.4873,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 2.476987447698745,
1080
+ "grad_norm": 0.19845594465732574,
1081
+ "learning_rate": 6.334269210501875e-05,
1082
+ "loss": 1.4975,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 2.493723849372385,
1087
+ "grad_norm": 0.21137520670890808,
1088
+ "learning_rate": 6.205295502898348e-05,
1089
+ "loss": 1.4861,
1090
+ "step": 151
1091
+ },
1092
+ {
1093
+ "epoch": 2.510460251046025,
1094
+ "grad_norm": 0.19834473729133606,
1095
+ "learning_rate": 6.0770550482731924e-05,
1096
+ "loss": 1.5178,
1097
+ "step": 152
1098
+ },
1099
+ {
1100
+ "epoch": 2.5271966527196654,
1101
+ "grad_norm": 0.22226808965206146,
1102
+ "learning_rate": 5.9495726266047605e-05,
1103
+ "loss": 1.481,
1104
+ "step": 153
1105
+ },
1106
+ {
1107
+ "epoch": 2.5439330543933054,
1108
+ "grad_norm": 0.20262005925178528,
1109
+ "learning_rate": 5.8228728713962543e-05,
1110
+ "loss": 1.4899,
1111
+ "step": 154
1112
+ },
1113
+ {
1114
+ "epoch": 2.560669456066946,
1115
+ "grad_norm": 0.20117135345935822,
1116
+ "learning_rate": 5.696980264915777e-05,
1117
+ "loss": 1.493,
1118
+ "step": 155
1119
+ },
1120
+ {
1121
+ "epoch": 2.577405857740586,
1122
+ "grad_norm": 0.21935462951660156,
1123
+ "learning_rate": 5.571919133465605e-05,
1124
+ "loss": 1.535,
1125
+ "step": 156
1126
+ },
1127
+ {
1128
+ "epoch": 2.594142259414226,
1129
+ "grad_norm": 0.19787819683551788,
1130
+ "learning_rate": 5.447713642681612e-05,
1131
+ "loss": 1.4635,
1132
+ "step": 157
1133
+ },
1134
+ {
1135
+ "epoch": 2.6108786610878663,
1136
+ "grad_norm": 0.2078079879283905,
1137
+ "learning_rate": 5.324387792863719e-05,
1138
+ "loss": 1.4824,
1139
+ "step": 158
1140
+ },
1141
+ {
1142
+ "epoch": 2.6276150627615062,
1143
+ "grad_norm": 0.21869535744190216,
1144
+ "learning_rate": 5.201965414338308e-05,
1145
+ "loss": 1.474,
1146
+ "step": 159
1147
+ },
1148
+ {
1149
+ "epoch": 2.6443514644351467,
1150
+ "grad_norm": 0.2099902182817459,
1151
+ "learning_rate": 5.080470162853472e-05,
1152
+ "loss": 1.4711,
1153
+ "step": 160
1154
+ },
1155
+ {
1156
+ "epoch": 2.6610878661087867,
1157
+ "grad_norm": 0.2077307403087616,
1158
+ "learning_rate": 4.959925515008002e-05,
1159
+ "loss": 1.5137,
1160
+ "step": 161
1161
+ },
1162
+ {
1163
+ "epoch": 2.6778242677824267,
1164
+ "grad_norm": 0.20681549608707428,
1165
+ "learning_rate": 4.840354763714991e-05,
1166
+ "loss": 1.4543,
1167
+ "step": 162
1168
+ },
1169
+ {
1170
+ "epoch": 2.694560669456067,
1171
+ "grad_norm": 0.21305464208126068,
1172
+ "learning_rate": 4.7217810137009274e-05,
1173
+ "loss": 1.468,
1174
+ "step": 163
1175
+ },
1176
+ {
1177
+ "epoch": 2.711297071129707,
1178
+ "grad_norm": 0.196672260761261,
1179
+ "learning_rate": 4.604227177041156e-05,
1180
+ "loss": 1.5066,
1181
+ "step": 164
1182
+ },
1183
+ {
1184
+ "epoch": 2.7280334728033475,
1185
+ "grad_norm": 0.20596779882907867,
1186
+ "learning_rate": 4.487715968732568e-05,
1187
+ "loss": 1.4968,
1188
+ "step": 165
1189
+ },
1190
+ {
1191
+ "epoch": 2.7447698744769875,
1192
+ "grad_norm": 0.19627641141414642,
1193
+ "learning_rate": 4.372269902304363e-05,
1194
+ "loss": 1.4813,
1195
+ "step": 166
1196
+ },
1197
+ {
1198
+ "epoch": 2.7615062761506275,
1199
+ "grad_norm": 0.20364060997962952,
1200
+ "learning_rate": 4.257911285467754e-05,
1201
+ "loss": 1.4794,
1202
+ "step": 167
1203
+ },
1204
+ {
1205
+ "epoch": 2.778242677824268,
1206
+ "grad_norm": 0.20353439450263977,
1207
+ "learning_rate": 4.144662215805426e-05,
1208
+ "loss": 1.4932,
1209
+ "step": 168
1210
+ },
1211
+ {
1212
+ "epoch": 2.794979079497908,
1213
+ "grad_norm": 0.20134314894676208,
1214
+ "learning_rate": 4.0325445765016145e-05,
1215
+ "loss": 1.4657,
1216
+ "step": 169
1217
+ },
1218
+ {
1219
+ "epoch": 2.8117154811715483,
1220
+ "grad_norm": 0.20385348796844482,
1221
+ "learning_rate": 3.921580032113602e-05,
1222
+ "loss": 1.4681,
1223
+ "step": 170
1224
+ },
1225
+ {
1226
+ "epoch": 2.8284518828451883,
1227
+ "grad_norm": 0.20909759402275085,
1228
+ "learning_rate": 3.8117900243854595e-05,
1229
+ "loss": 1.4477,
1230
+ "step": 171
1231
+ },
1232
+ {
1233
+ "epoch": 2.8451882845188283,
1234
+ "grad_norm": 0.2068387120962143,
1235
+ "learning_rate": 3.7031957681048604e-05,
1236
+ "loss": 1.486,
1237
+ "step": 172
1238
+ },
1239
+ {
1240
+ "epoch": 2.8619246861924688,
1241
+ "grad_norm": 0.2067539542913437,
1242
+ "learning_rate": 3.595818247003713e-05,
1243
+ "loss": 1.4723,
1244
+ "step": 173
1245
+ },
1246
+ {
1247
+ "epoch": 2.8786610878661087,
1248
+ "grad_norm": 0.21357451379299164,
1249
+ "learning_rate": 3.489678209703475e-05,
1250
+ "loss": 1.4867,
1251
+ "step": 174
1252
+ },
1253
+ {
1254
+ "epoch": 2.895397489539749,
1255
+ "grad_norm": 0.21152114868164062,
1256
+ "learning_rate": 3.3847961657058845e-05,
1257
+ "loss": 1.5219,
1258
+ "step": 175
1259
+ },
1260
+ {
1261
+ "epoch": 2.912133891213389,
1262
+ "grad_norm": 0.20278601348400116,
1263
+ "learning_rate": 3.281192381429894e-05,
1264
+ "loss": 1.4722,
1265
+ "step": 176
1266
+ },
1267
+ {
1268
+ "epoch": 2.928870292887029,
1269
+ "grad_norm": 0.2019844502210617,
1270
+ "learning_rate": 3.178886876295578e-05,
1271
+ "loss": 1.4787,
1272
+ "step": 177
1273
+ },
1274
+ {
1275
+ "epoch": 2.928870292887029,
1276
+ "eval_loss": 1.7109203338623047,
1277
+ "eval_runtime": 44.9676,
1278
+ "eval_samples_per_second": 37.427,
1279
+ "eval_steps_per_second": 0.801,
1280
+ "step": 177
1281
+ },
1282
+ {
1283
+ "epoch": 2.9456066945606696,
1284
+ "grad_norm": 0.21223081648349762,
1285
+ "learning_rate": 3.077899418855772e-05,
1286
+ "loss": 1.4791,
1287
+ "step": 178
1288
+ },
1289
+ {
1290
+ "epoch": 2.9623430962343096,
1291
+ "grad_norm": 0.19937600195407867,
1292
+ "learning_rate": 2.9782495229761808e-05,
1293
+ "loss": 1.4528,
1294
+ "step": 179
1295
+ },
1296
+ {
1297
+ "epoch": 2.97907949790795,
1298
+ "grad_norm": 0.2088988870382309,
1299
+ "learning_rate": 2.879956444064703e-05,
1300
+ "loss": 1.464,
1301
+ "step": 180
1302
+ },
1303
+ {
1304
+ "epoch": 2.99581589958159,
1305
+ "grad_norm": 0.2008848488330841,
1306
+ "learning_rate": 2.783039175350699e-05,
1307
+ "loss": 1.4765,
1308
+ "step": 181
1309
+ },
1310
+ {
1311
+ "epoch": 3.01255230125523,
1312
+ "grad_norm": 0.21129456162452698,
1313
+ "learning_rate": 2.6875164442149147e-05,
1314
+ "loss": 1.4819,
1315
+ "step": 182
1316
+ },
1317
+ {
1318
+ "epoch": 3.01255230125523,
1319
+ "grad_norm": 0.28596311807632446,
1320
+ "learning_rate": 2.5934067085707834e-05,
1321
+ "loss": 1.4411,
1322
+ "step": 183
1323
+ },
1324
+ {
1325
+ "epoch": 3.0292887029288704,
1326
+ "grad_norm": 0.20895494520664215,
1327
+ "learning_rate": 2.500728153297788e-05,
1328
+ "loss": 1.4452,
1329
+ "step": 184
1330
+ },
1331
+ {
1332
+ "epoch": 3.0460251046025104,
1333
+ "grad_norm": 0.21326342225074768,
1334
+ "learning_rate": 2.409498686727587e-05,
1335
+ "loss": 1.422,
1336
+ "step": 185
1337
+ },
1338
+ {
1339
+ "epoch": 3.062761506276151,
1340
+ "grad_norm": 0.20488786697387695,
1341
+ "learning_rate": 2.3197359371835802e-05,
1342
+ "loss": 1.4251,
1343
+ "step": 186
1344
+ },
1345
+ {
1346
+ "epoch": 3.079497907949791,
1347
+ "grad_norm": 0.2121814638376236,
1348
+ "learning_rate": 2.2314572495745746e-05,
1349
+ "loss": 1.4338,
1350
+ "step": 187
1351
+ },
1352
+ {
1353
+ "epoch": 3.096234309623431,
1354
+ "grad_norm": 0.21775531768798828,
1355
+ "learning_rate": 2.1446796820432167e-05,
1356
+ "loss": 1.4235,
1357
+ "step": 188
1358
+ },
1359
+ {
1360
+ "epoch": 3.1129707112970713,
1361
+ "grad_norm": 0.21480879187583923,
1362
+ "learning_rate": 2.0594200026698363e-05,
1363
+ "loss": 1.4386,
1364
+ "step": 189
1365
+ },
1366
+ {
1367
+ "epoch": 3.1297071129707112,
1368
+ "grad_norm": 0.2164095789194107,
1369
+ "learning_rate": 1.9756946862323535e-05,
1370
+ "loss": 1.4565,
1371
+ "step": 190
1372
+ },
1373
+ {
1374
+ "epoch": 3.1464435146443517,
1375
+ "grad_norm": 0.22095419466495514,
1376
+ "learning_rate": 1.8935199110228275e-05,
1377
+ "loss": 1.4234,
1378
+ "step": 191
1379
+ },
1380
+ {
1381
+ "epoch": 3.1631799163179917,
1382
+ "grad_norm": 0.2301575392484665,
1383
+ "learning_rate": 1.8129115557213262e-05,
1384
+ "loss": 1.4343,
1385
+ "step": 192
1386
+ },
1387
+ {
1388
+ "epoch": 3.1799163179916317,
1389
+ "grad_norm": 0.22277624905109406,
1390
+ "learning_rate": 1.7338851963276825e-05,
1391
+ "loss": 1.4215,
1392
+ "step": 193
1393
+ },
1394
+ {
1395
+ "epoch": 3.196652719665272,
1396
+ "grad_norm": 0.21234098076820374,
1397
+ "learning_rate": 1.656456103151728e-05,
1398
+ "loss": 1.4347,
1399
+ "step": 194
1400
+ },
1401
+ {
1402
+ "epoch": 3.213389121338912,
1403
+ "grad_norm": 0.20240473747253418,
1404
+ "learning_rate": 1.580639237862608e-05,
1405
+ "loss": 1.4181,
1406
+ "step": 195
1407
+ },
1408
+ {
1409
+ "epoch": 3.2301255230125525,
1410
+ "grad_norm": 0.21217629313468933,
1411
+ "learning_rate": 1.5064492505977234e-05,
1412
+ "loss": 1.4408,
1413
+ "step": 196
1414
+ },
1415
+ {
1416
+ "epoch": 3.2468619246861925,
1417
+ "grad_norm": 0.21164193749427795,
1418
+ "learning_rate": 1.433900477131882e-05,
1419
+ "loss": 1.3905,
1420
+ "step": 197
1421
+ },
1422
+ {
1423
+ "epoch": 3.2635983263598325,
1424
+ "grad_norm": 0.21021489799022675,
1425
+ "learning_rate": 1.363006936107183e-05,
1426
+ "loss": 1.4591,
1427
+ "step": 198
1428
+ },
1429
+ {
1430
+ "epoch": 3.280334728033473,
1431
+ "grad_norm": 0.2127666026353836,
1432
+ "learning_rate": 1.29378232632419e-05,
1433
+ "loss": 1.4024,
1434
+ "step": 199
1435
+ },
1436
+ {
1437
+ "epoch": 3.297071129707113,
1438
+ "grad_norm": 0.21527446806430817,
1439
+ "learning_rate": 1.2262400240949023e-05,
1440
+ "loss": 1.3949,
1441
+ "step": 200
1442
+ },
1443
+ {
1444
+ "epoch": 3.3138075313807533,
1445
+ "grad_norm": 0.21020054817199707,
1446
+ "learning_rate": 1.1603930806580444e-05,
1447
+ "loss": 1.4529,
1448
+ "step": 201
1449
+ },
1450
+ {
1451
+ "epoch": 3.3305439330543933,
1452
+ "grad_norm": 0.21956893801689148,
1453
+ "learning_rate": 1.0962542196571634e-05,
1454
+ "loss": 1.4209,
1455
+ "step": 202
1456
+ },
1457
+ {
1458
+ "epoch": 3.3472803347280333,
1459
+ "grad_norm": 0.2126244753599167,
1460
+ "learning_rate": 1.0338358346820353e-05,
1461
+ "loss": 1.4432,
1462
+ "step": 203
1463
+ },
1464
+ {
1465
+ "epoch": 3.3640167364016738,
1466
+ "grad_norm": 0.2158239334821701,
1467
+ "learning_rate": 9.731499868738447e-06,
1468
+ "loss": 1.4652,
1469
+ "step": 204
1470
+ },
1471
+ {
1472
+ "epoch": 3.3807531380753137,
1473
+ "grad_norm": 0.20923413336277008,
1474
+ "learning_rate": 9.142084025945984e-06,
1475
+ "loss": 1.418,
1476
+ "step": 205
1477
+ },
1478
+ {
1479
+ "epoch": 3.397489539748954,
1480
+ "grad_norm": 0.21057386696338654,
1481
+ "learning_rate": 8.570224711612385e-06,
1482
+ "loss": 1.4275,
1483
+ "step": 206
1484
+ },
1485
+ {
1486
+ "epoch": 3.414225941422594,
1487
+ "grad_norm": 0.21176937222480774,
1488
+ "learning_rate": 8.016032426448817e-06,
1489
+ "loss": 1.4464,
1490
+ "step": 207
1491
+ },
1492
+ {
1493
+ "epoch": 3.430962343096234,
1494
+ "grad_norm": 0.20800316333770752,
1495
+ "learning_rate": 7.479614257355971e-06,
1496
+ "loss": 1.4288,
1497
+ "step": 208
1498
+ },
1499
+ {
1500
+ "epoch": 3.4476987447698746,
1501
+ "grad_norm": 0.20886531472206116,
1502
+ "learning_rate": 6.961073856731648e-06,
1503
+ "loss": 1.4303,
1504
+ "step": 209
1505
+ },
1506
+ {
1507
+ "epoch": 3.4644351464435146,
1508
+ "grad_norm": 0.21240338683128357,
1509
+ "learning_rate": 6.460511422441984e-06,
1510
+ "loss": 1.4068,
1511
+ "step": 210
1512
+ },
1513
+ {
1514
+ "epoch": 3.481171548117155,
1515
+ "grad_norm": 0.20686744153499603,
1516
+ "learning_rate": 5.978023678460099e-06,
1517
+ "loss": 1.4269,
1518
+ "step": 211
1519
+ },
1520
+ {
1521
+ "epoch": 3.497907949790795,
1522
+ "grad_norm": 0.22095750272274017,
1523
+ "learning_rate": 5.5137038561761115e-06,
1524
+ "loss": 1.4563,
1525
+ "step": 212
1526
+ },
1527
+ {
1528
+ "epoch": 3.514644351464435,
1529
+ "grad_norm": 0.20569024980068207,
1530
+ "learning_rate": 5.067641676381918e-06,
1531
+ "loss": 1.4337,
1532
+ "step": 213
1533
+ },
1534
+ {
1535
+ "epoch": 3.5313807531380754,
1536
+ "grad_norm": 0.2085324376821518,
1537
+ "learning_rate": 4.639923331934471e-06,
1538
+ "loss": 1.3925,
1539
+ "step": 214
1540
+ },
1541
+ {
1542
+ "epoch": 3.5481171548117154,
1543
+ "grad_norm": 0.21414080262184143,
1544
+ "learning_rate": 4.230631471100655e-06,
1545
+ "loss": 1.4106,
1546
+ "step": 215
1547
+ },
1548
+ {
1549
+ "epoch": 3.564853556485356,
1550
+ "grad_norm": 0.21130351722240448,
1551
+ "learning_rate": 3.839845181587098e-06,
1552
+ "loss": 1.4575,
1553
+ "step": 216
1554
+ },
1555
+ {
1556
+ "epoch": 3.581589958158996,
1557
+ "grad_norm": 0.21234765648841858,
1558
+ "learning_rate": 3.467639975257997e-06,
1559
+ "loss": 1.4377,
1560
+ "step": 217
1561
+ },
1562
+ {
1563
+ "epoch": 3.598326359832636,
1564
+ "grad_norm": 0.2144404500722885,
1565
+ "learning_rate": 3.1140877735439387e-06,
1566
+ "loss": 1.4093,
1567
+ "step": 218
1568
+ },
1569
+ {
1570
+ "epoch": 3.6150627615062763,
1571
+ "grad_norm": 0.21242524683475494,
1572
+ "learning_rate": 2.7792568935444796e-06,
1573
+ "loss": 1.4033,
1574
+ "step": 219
1575
+ },
1576
+ {
1577
+ "epoch": 3.6317991631799162,
1578
+ "grad_norm": 0.20995208621025085,
1579
+ "learning_rate": 2.4632120348272003e-06,
1580
+ "loss": 1.4236,
1581
+ "step": 220
1582
+ },
1583
+ {
1584
+ "epoch": 3.6485355648535567,
1585
+ "grad_norm": 0.2147565335035324,
1586
+ "learning_rate": 2.166014266925731e-06,
1587
+ "loss": 1.454,
1588
+ "step": 221
1589
+ },
1590
+ {
1591
+ "epoch": 3.6652719665271967,
1592
+ "grad_norm": 0.2077101469039917,
1593
+ "learning_rate": 1.88772101753929e-06,
1594
+ "loss": 1.4473,
1595
+ "step": 222
1596
+ },
1597
+ {
1598
+ "epoch": 3.6820083682008367,
1599
+ "grad_norm": 0.20844031870365143,
1600
+ "learning_rate": 1.6283860614358936e-06,
1601
+ "loss": 1.4621,
1602
+ "step": 223
1603
+ },
1604
+ {
1605
+ "epoch": 3.698744769874477,
1606
+ "grad_norm": 0.21885593235492706,
1607
+ "learning_rate": 1.3880595100613792e-06,
1608
+ "loss": 1.4407,
1609
+ "step": 224
1610
+ },
1611
+ {
1612
+ "epoch": 3.715481171548117,
1613
+ "grad_norm": 0.2144600749015808,
1614
+ "learning_rate": 1.1667878018564171e-06,
1615
+ "loss": 1.4472,
1616
+ "step": 225
1617
+ },
1618
+ {
1619
+ "epoch": 3.7322175732217575,
1620
+ "grad_norm": 0.21211084723472595,
1621
+ "learning_rate": 9.64613693283123e-07,
1622
+ "loss": 1.3844,
1623
+ "step": 226
1624
+ },
1625
+ {
1626
+ "epoch": 3.7489539748953975,
1627
+ "grad_norm": 0.20910845696926117,
1628
+ "learning_rate": 7.815762505632096e-07,
1629
+ "loss": 1.4424,
1630
+ "step": 227
1631
+ },
1632
+ {
1633
+ "epoch": 3.7656903765690375,
1634
+ "grad_norm": 0.21356578171253204,
1635
+ "learning_rate": 6.177108421292266e-07,
1636
+ "loss": 1.4138,
1637
+ "step": 228
1638
+ },
1639
+ {
1640
+ "epoch": 3.782426778242678,
1641
+ "grad_norm": 0.2111985683441162,
1642
+ "learning_rate": 4.7304913179025965e-07,
1643
+ "loss": 1.452,
1644
+ "step": 229
1645
+ },
1646
+ {
1647
+ "epoch": 3.799163179916318,
1648
+ "grad_norm": 0.21008148789405823,
1649
+ "learning_rate": 3.4761907261356976e-07,
1650
+ "loss": 1.4271,
1651
+ "step": 230
1652
+ },
1653
+ {
1654
+ "epoch": 3.8158995815899583,
1655
+ "grad_norm": 0.21510553359985352,
1656
+ "learning_rate": 2.414449015231357e-07,
1657
+ "loss": 1.412,
1658
+ "step": 231
1659
+ },
1660
+ {
1661
+ "epoch": 3.8326359832635983,
1662
+ "grad_norm": 0.2134546935558319,
1663
+ "learning_rate": 1.545471346164007e-07,
1664
+ "loss": 1.446,
1665
+ "step": 232
1666
+ },
1667
+ {
1668
+ "epoch": 3.8493723849372383,
1669
+ "grad_norm": 0.2131936401128769,
1670
+ "learning_rate": 8.694256319987659e-08,
1671
+ "loss": 1.414,
1672
+ "step": 233
1673
+ },
1674
+ {
1675
+ "epoch": 3.8661087866108788,
1676
+ "grad_norm": 0.20874719321727753,
1677
+ "learning_rate": 3.8644250544594975e-08,
1678
+ "loss": 1.408,
1679
+ "step": 234
1680
+ },
1681
+ {
1682
+ "epoch": 3.8828451882845187,
1683
+ "grad_norm": 0.21611733734607697,
1684
+ "learning_rate": 9.661529361892907e-09,
1685
+ "loss": 1.4154,
1686
+ "step": 235
1687
+ },
1688
+ {
1689
+ "epoch": 3.899581589958159,
1690
+ "grad_norm": 0.20997221767902374,
1691
+ "learning_rate": 0.0,
1692
+ "loss": 1.4473,
1693
+ "step": 236
1694
+ },
1695
+ {
1696
+ "epoch": 3.899581589958159,
1697
+ "eval_loss": 1.724790096282959,
1698
+ "eval_runtime": 44.874,
1699
+ "eval_samples_per_second": 37.505,
1700
+ "eval_steps_per_second": 0.802,
1701
+ "step": 236
1702
+ }
1703
+ ],
1704
+ "logging_steps": 1,
1705
+ "max_steps": 236,
1706
+ "num_input_tokens_seen": 0,
1707
+ "num_train_epochs": 4,
1708
+ "save_steps": 59,
1709
+ "stateful_callbacks": {
1710
+ "TrainerControl": {
1711
+ "args": {
1712
+ "should_epoch_stop": false,
1713
+ "should_evaluate": false,
1714
+ "should_log": false,
1715
+ "should_save": true,
1716
+ "should_training_stop": true
1717
+ },
1718
+ "attributes": {}
1719
+ }
1720
+ },
1721
+ "total_flos": 5.623791415197696e+17,
1722
+ "train_batch_size": 48,
1723
+ "trial_name": null,
1724
+ "trial_params": null
1725
+ }
checkpoint-236/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553af1c5dd81032ecab9996f20cecb8cd9d302493de0264d19b2265d1e75c3ef
3
+ size 6072
checkpoint-59/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: t-bank-ai/T-lite-instruct-0.1
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-59/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "t-bank-ai/T-lite-instruct-0.1",
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
+ "down_proj",
24
+ "k_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "v_proj",
28
+ "q_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-59/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6a21f68c9b3d3fc77646f53cb1ff74b3073a8f0598e855bba06d307c4e4a2c
3
+ size 335604696
checkpoint-59/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87cec16672f01ae6e6f0e7ab1de3604b0d3d69a991405ca775a883f3f314067
3
+ size 168624724
checkpoint-59/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178c32c04e6775fd95c835c8eeeaccc7d25f50bfa4b1479570bdfdd4e3fb106d
3
+ size 14244
checkpoint-59/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e3f930c3916a4860045e7fa05c8394ea5c799b5f5a2914435c2d3b5d13aaa1
3
+ size 1064
checkpoint-59/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<sep>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-59/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-59/tokenizer_config.json ADDED
@@ -0,0 +1,2089 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "128256": {
2052
+ "content": "<pad>",
2053
+ "lstrip": false,
2054
+ "normalized": false,
2055
+ "rstrip": false,
2056
+ "single_word": false,
2057
+ "special": true
2058
+ },
2059
+ "128257": {
2060
+ "content": "<unk>",
2061
+ "lstrip": false,
2062
+ "normalized": false,
2063
+ "rstrip": false,
2064
+ "single_word": false,
2065
+ "special": true
2066
+ },
2067
+ "128258": {
2068
+ "content": "<sep>",
2069
+ "lstrip": false,
2070
+ "normalized": false,
2071
+ "rstrip": false,
2072
+ "single_word": false,
2073
+ "special": true
2074
+ }
2075
+ },
2076
+ "bos_token": "<|begin_of_text|>",
2077
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2078
+ "clean_up_tokenization_spaces": true,
2079
+ "eos_token": "<|end_of_text|>",
2080
+ "model_input_names": [
2081
+ "input_ids",
2082
+ "attention_mask"
2083
+ ],
2084
+ "model_max_length": 8192,
2085
+ "pad_token": "<|eot_id|>",
2086
+ "sep_token": "<sep>",
2087
+ "tokenizer_class": "PreTrainedTokenizerFast",
2088
+ "unk_token": "<unk>"
2089
+ }
checkpoint-59/trainer_state.json ADDED
@@ -0,0 +1,462 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9874476987447699,
5
+ "eval_steps": 59,
6
+ "global_step": 59,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.016736401673640166,
13
+ "grad_norm": 0.3126992881298065,
14
+ "learning_rate": 2e-05,
15
+ "loss": 2.4388,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.016736401673640166,
20
+ "eval_loss": 2.2736361026763916,
21
+ "eval_runtime": 44.9772,
22
+ "eval_samples_per_second": 37.419,
23
+ "eval_steps_per_second": 0.8,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.03347280334728033,
28
+ "grad_norm": 0.31262004375457764,
29
+ "learning_rate": 4e-05,
30
+ "loss": 2.3915,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0502092050209205,
35
+ "grad_norm": 0.3161173462867737,
36
+ "learning_rate": 6e-05,
37
+ "loss": 2.4118,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.06694560669456066,
42
+ "grad_norm": 0.32605665922164917,
43
+ "learning_rate": 8e-05,
44
+ "loss": 2.3872,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.08368200836820083,
49
+ "grad_norm": 0.32243478298187256,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.3368,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.100418410041841,
56
+ "grad_norm": 0.3141494393348694,
57
+ "learning_rate": 0.00012,
58
+ "loss": 2.2966,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.11715481171548117,
63
+ "grad_norm": 0.330599308013916,
64
+ "learning_rate": 0.00014,
65
+ "loss": 2.2379,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.13389121338912133,
70
+ "grad_norm": 0.33452969789505005,
71
+ "learning_rate": 0.00016,
72
+ "loss": 2.1949,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.1506276150627615,
77
+ "grad_norm": 0.2835342288017273,
78
+ "learning_rate": 0.00018,
79
+ "loss": 2.156,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.16736401673640167,
84
+ "grad_norm": 0.23091256618499756,
85
+ "learning_rate": 0.0002,
86
+ "loss": 2.1109,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.18410041841004185,
91
+ "grad_norm": 0.2284015268087387,
92
+ "learning_rate": 0.00019999033847063811,
93
+ "loss": 2.0782,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.200836820083682,
98
+ "grad_norm": 0.23981927335262299,
99
+ "learning_rate": 0.00019996135574945544,
100
+ "loss": 2.053,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.2175732217573222,
105
+ "grad_norm": 0.23807936906814575,
106
+ "learning_rate": 0.00019991305743680013,
107
+ "loss": 2.0294,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.23430962343096234,
112
+ "grad_norm": 0.20766477286815643,
113
+ "learning_rate": 0.0001998454528653836,
114
+ "loss": 1.9947,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.2510460251046025,
119
+ "grad_norm": 0.1892593652009964,
120
+ "learning_rate": 0.00019975855509847686,
121
+ "loss": 1.9643,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.26778242677824265,
126
+ "grad_norm": 0.19022946059703827,
127
+ "learning_rate": 0.00019965238092738643,
128
+ "loss": 1.9275,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.28451882845188287,
133
+ "grad_norm": 0.18370254337787628,
134
+ "learning_rate": 0.00019952695086820975,
135
+ "loss": 1.9512,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.301255230125523,
140
+ "grad_norm": 0.16774943470954895,
141
+ "learning_rate": 0.0001993822891578708,
142
+ "loss": 1.8883,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.3179916317991632,
147
+ "grad_norm": 0.17572854459285736,
148
+ "learning_rate": 0.0001992184237494368,
149
+ "loss": 1.938,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.33472803347280333,
154
+ "grad_norm": 0.21952244639396667,
155
+ "learning_rate": 0.0001990353863067169,
156
+ "loss": 1.8937,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.3514644351464435,
161
+ "grad_norm": 0.2579434812068939,
162
+ "learning_rate": 0.0001988332121981436,
163
+ "loss": 1.8797,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.3682008368200837,
168
+ "grad_norm": 0.29942768812179565,
169
+ "learning_rate": 0.00019861194048993863,
170
+ "loss": 1.8766,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.38493723849372385,
175
+ "grad_norm": 0.326593279838562,
176
+ "learning_rate": 0.0001983716139385641,
177
+ "loss": 1.8567,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.401673640167364,
182
+ "grad_norm": 0.2769831418991089,
183
+ "learning_rate": 0.0001981122789824607,
184
+ "loss": 1.839,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.41841004184100417,
189
+ "grad_norm": 0.2902805507183075,
190
+ "learning_rate": 0.00019783398573307428,
191
+ "loss": 1.8622,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.4351464435146444,
196
+ "grad_norm": 0.2152428776025772,
197
+ "learning_rate": 0.00019753678796517282,
198
+ "loss": 1.8393,
199
+ "step": 26
200
+ },
201
+ {
202
+ "epoch": 0.45188284518828453,
203
+ "grad_norm": 0.1541067361831665,
204
+ "learning_rate": 0.00019722074310645553,
205
+ "loss": 1.8326,
206
+ "step": 27
207
+ },
208
+ {
209
+ "epoch": 0.4686192468619247,
210
+ "grad_norm": 0.12413746118545532,
211
+ "learning_rate": 0.00019688591222645607,
212
+ "loss": 1.8079,
213
+ "step": 28
214
+ },
215
+ {
216
+ "epoch": 0.48535564853556484,
217
+ "grad_norm": 0.11909659206867218,
218
+ "learning_rate": 0.000196532360024742,
219
+ "loss": 1.8044,
220
+ "step": 29
221
+ },
222
+ {
223
+ "epoch": 0.502092050209205,
224
+ "grad_norm": 0.16260313987731934,
225
+ "learning_rate": 0.0001961601548184129,
226
+ "loss": 1.7888,
227
+ "step": 30
228
+ },
229
+ {
230
+ "epoch": 0.5188284518828452,
231
+ "grad_norm": 0.17894335091114044,
232
+ "learning_rate": 0.00019576936852889936,
233
+ "loss": 1.8263,
234
+ "step": 31
235
+ },
236
+ {
237
+ "epoch": 0.5355648535564853,
238
+ "grad_norm": 0.21706554293632507,
239
+ "learning_rate": 0.00019536007666806556,
240
+ "loss": 1.8151,
241
+ "step": 32
242
+ },
243
+ {
244
+ "epoch": 0.5523012552301255,
245
+ "grad_norm": 0.17296762764453888,
246
+ "learning_rate": 0.0001949323583236181,
247
+ "loss": 1.7901,
248
+ "step": 33
249
+ },
250
+ {
251
+ "epoch": 0.5690376569037657,
252
+ "grad_norm": 0.1761002093553543,
253
+ "learning_rate": 0.0001944862961438239,
254
+ "loss": 1.8126,
255
+ "step": 34
256
+ },
257
+ {
258
+ "epoch": 0.5857740585774058,
259
+ "grad_norm": 0.14914190769195557,
260
+ "learning_rate": 0.00019402197632153992,
261
+ "loss": 1.7797,
262
+ "step": 35
263
+ },
264
+ {
265
+ "epoch": 0.602510460251046,
266
+ "grad_norm": 0.13111546635627747,
267
+ "learning_rate": 0.00019353948857755803,
268
+ "loss": 1.7916,
269
+ "step": 36
270
+ },
271
+ {
272
+ "epoch": 0.6192468619246861,
273
+ "grad_norm": 0.12080994248390198,
274
+ "learning_rate": 0.00019303892614326836,
275
+ "loss": 1.7834,
276
+ "step": 37
277
+ },
278
+ {
279
+ "epoch": 0.6359832635983264,
280
+ "grad_norm": 0.15622606873512268,
281
+ "learning_rate": 0.00019252038574264405,
282
+ "loss": 1.794,
283
+ "step": 38
284
+ },
285
+ {
286
+ "epoch": 0.6527196652719666,
287
+ "grad_norm": 0.1345275640487671,
288
+ "learning_rate": 0.00019198396757355118,
289
+ "loss": 1.7554,
290
+ "step": 39
291
+ },
292
+ {
293
+ "epoch": 0.6694560669456067,
294
+ "grad_norm": 0.18387249112129211,
295
+ "learning_rate": 0.00019142977528838762,
296
+ "loss": 1.7675,
297
+ "step": 40
298
+ },
299
+ {
300
+ "epoch": 0.6861924686192469,
301
+ "grad_norm": 0.165897399187088,
302
+ "learning_rate": 0.00019085791597405404,
303
+ "loss": 1.7631,
304
+ "step": 41
305
+ },
306
+ {
307
+ "epoch": 0.702928870292887,
308
+ "grad_norm": 0.13675889372825623,
309
+ "learning_rate": 0.00019026850013126157,
310
+ "loss": 1.754,
311
+ "step": 42
312
+ },
313
+ {
314
+ "epoch": 0.7196652719665272,
315
+ "grad_norm": 0.16969387233257294,
316
+ "learning_rate": 0.00018966164165317966,
317
+ "loss": 1.745,
318
+ "step": 43
319
+ },
320
+ {
321
+ "epoch": 0.7364016736401674,
322
+ "grad_norm": 0.16098380088806152,
323
+ "learning_rate": 0.00018903745780342839,
324
+ "loss": 1.7609,
325
+ "step": 44
326
+ },
327
+ {
328
+ "epoch": 0.7531380753138075,
329
+ "grad_norm": 0.12338632345199585,
330
+ "learning_rate": 0.0001883960691934196,
331
+ "loss": 1.7584,
332
+ "step": 45
333
+ },
334
+ {
335
+ "epoch": 0.7698744769874477,
336
+ "grad_norm": 0.1335158348083496,
337
+ "learning_rate": 0.00018773759975905098,
338
+ "loss": 1.7302,
339
+ "step": 46
340
+ },
341
+ {
342
+ "epoch": 0.7866108786610879,
343
+ "grad_norm": 0.11967575550079346,
344
+ "learning_rate": 0.00018706217673675811,
345
+ "loss": 1.7323,
346
+ "step": 47
347
+ },
348
+ {
349
+ "epoch": 0.803347280334728,
350
+ "grad_norm": 0.12446475774049759,
351
+ "learning_rate": 0.0001863699306389282,
352
+ "loss": 1.7217,
353
+ "step": 48
354
+ },
355
+ {
356
+ "epoch": 0.8200836820083682,
357
+ "grad_norm": 0.13070392608642578,
358
+ "learning_rate": 0.00018566099522868119,
359
+ "loss": 1.7192,
360
+ "step": 49
361
+ },
362
+ {
363
+ "epoch": 0.8368200836820083,
364
+ "grad_norm": 0.15041972696781158,
365
+ "learning_rate": 0.00018493550749402278,
366
+ "loss": 1.7386,
367
+ "step": 50
368
+ },
369
+ {
370
+ "epoch": 0.8535564853556485,
371
+ "grad_norm": 0.12314204126596451,
372
+ "learning_rate": 0.00018419360762137395,
373
+ "loss": 1.7465,
374
+ "step": 51
375
+ },
376
+ {
377
+ "epoch": 0.8702928870292888,
378
+ "grad_norm": 0.15009309351444244,
379
+ "learning_rate": 0.00018343543896848273,
380
+ "loss": 1.7216,
381
+ "step": 52
382
+ },
383
+ {
384
+ "epoch": 0.8870292887029289,
385
+ "grad_norm": 0.12467087060213089,
386
+ "learning_rate": 0.00018266114803672318,
387
+ "loss": 1.7043,
388
+ "step": 53
389
+ },
390
+ {
391
+ "epoch": 0.9037656903765691,
392
+ "grad_norm": 0.1297266036272049,
393
+ "learning_rate": 0.00018187088444278674,
394
+ "loss": 1.7069,
395
+ "step": 54
396
+ },
397
+ {
398
+ "epoch": 0.9205020920502092,
399
+ "grad_norm": 0.1195509061217308,
400
+ "learning_rate": 0.00018106480088977172,
401
+ "loss": 1.7305,
402
+ "step": 55
403
+ },
404
+ {
405
+ "epoch": 0.9372384937238494,
406
+ "grad_norm": 0.14450602233409882,
407
+ "learning_rate": 0.00018024305313767646,
408
+ "loss": 1.7171,
409
+ "step": 56
410
+ },
411
+ {
412
+ "epoch": 0.9539748953974896,
413
+ "grad_norm": 0.16594989597797394,
414
+ "learning_rate": 0.00017940579997330165,
415
+ "loss": 1.7239,
416
+ "step": 57
417
+ },
418
+ {
419
+ "epoch": 0.9707112970711297,
420
+ "grad_norm": 0.19210928678512573,
421
+ "learning_rate": 0.00017855320317956784,
422
+ "loss": 1.7081,
423
+ "step": 58
424
+ },
425
+ {
426
+ "epoch": 0.9874476987447699,
427
+ "grad_norm": 0.16463987529277802,
428
+ "learning_rate": 0.00017768542750425426,
429
+ "loss": 1.7178,
430
+ "step": 59
431
+ },
432
+ {
433
+ "epoch": 0.9874476987447699,
434
+ "eval_loss": 1.7365927696228027,
435
+ "eval_runtime": 44.9816,
436
+ "eval_samples_per_second": 37.415,
437
+ "eval_steps_per_second": 0.8,
438
+ "step": 59
439
+ }
440
+ ],
441
+ "logging_steps": 1,
442
+ "max_steps": 236,
443
+ "num_input_tokens_seen": 0,
444
+ "num_train_epochs": 4,
445
+ "save_steps": 59,
446
+ "stateful_callbacks": {
447
+ "TrainerControl": {
448
+ "args": {
449
+ "should_epoch_stop": false,
450
+ "should_evaluate": false,
451
+ "should_log": false,
452
+ "should_save": true,
453
+ "should_training_stop": false
454
+ },
455
+ "attributes": {}
456
+ }
457
+ },
458
+ "total_flos": 1.409845473312768e+17,
459
+ "train_batch_size": 48,
460
+ "trial_name": null,
461
+ "trial_params": null
462
+ }
checkpoint-59/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553af1c5dd81032ecab9996f20cecb8cd9d302493de0264d19b2265d1e75c3ef
3
+ size 6072
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t-bank-ai/T-lite-instruct-0.1",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 128256,
21
+ "pretraining_tp": 1,
22
+ "quantization_config": {
23
+ "_load_in_4bit": true,
24
+ "_load_in_8bit": false,
25
+ "bnb_4bit_compute_dtype": "bfloat16",
26
+ "bnb_4bit_quant_storage": "bfloat16",
27
+ "bnb_4bit_quant_type": "nf4",
28
+ "bnb_4bit_use_double_quant": true,
29
+ "llm_int8_enable_fp32_cpu_offload": false,
30
+ "llm_int8_has_fp16_weight": false,
31
+ "llm_int8_skip_modules": null,
32
+ "llm_int8_threshold": 6.0,
33
+ "load_in_4bit": true,
34
+ "load_in_8bit": false,
35
+ "quant_method": "bitsandbytes"
36
+ },
37
+ "rms_norm_eps": 1e-05,
38
+ "rope_scaling": null,
39
+ "rope_theta": 500000.0,
40
+ "sep_token_id": 128258,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.44.0",
44
+ "use_cache": false,
45
+ "vocab_size": 128259
46
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "<sep>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff