nguyenthanhdo commited on
Commit
03de149
1 Parent(s): 0cecc6f

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. NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39.yml +72 -0
  2. README.md +172 -0
  3. adapter_config.json +34 -0
  4. adapter_model.bin +3 -0
  5. checkpoint-106/README.md +202 -0
  6. checkpoint-106/adapter_config.json +34 -0
  7. checkpoint-106/adapter_model.safetensors +3 -0
  8. checkpoint-106/optimizer.pt +3 -0
  9. checkpoint-106/rng_state.pth +3 -0
  10. checkpoint-106/scheduler.pt +3 -0
  11. checkpoint-106/special_tokens_map.json +23 -0
  12. checkpoint-106/tokenizer.json +0 -0
  13. checkpoint-106/tokenizer_config.json +2063 -0
  14. checkpoint-106/trainer_state.json +855 -0
  15. checkpoint-106/training_args.bin +3 -0
  16. checkpoint-159/README.md +202 -0
  17. checkpoint-159/adapter_config.json +34 -0
  18. checkpoint-159/adapter_model.safetensors +3 -0
  19. checkpoint-159/optimizer.pt +3 -0
  20. checkpoint-159/rng_state.pth +3 -0
  21. checkpoint-159/scheduler.pt +3 -0
  22. checkpoint-159/special_tokens_map.json +23 -0
  23. checkpoint-159/tokenizer.json +0 -0
  24. checkpoint-159/tokenizer_config.json +2063 -0
  25. checkpoint-159/trainer_state.json +1266 -0
  26. checkpoint-159/training_args.bin +3 -0
  27. checkpoint-212/README.md +202 -0
  28. checkpoint-212/adapter_config.json +34 -0
  29. checkpoint-212/adapter_model.safetensors +3 -0
  30. checkpoint-212/optimizer.pt +3 -0
  31. checkpoint-212/rng_state.pth +3 -0
  32. checkpoint-212/scheduler.pt +3 -0
  33. checkpoint-212/special_tokens_map.json +23 -0
  34. checkpoint-212/tokenizer.json +0 -0
  35. checkpoint-212/tokenizer_config.json +2063 -0
  36. checkpoint-212/trainer_state.json +1677 -0
  37. checkpoint-212/training_args.bin +3 -0
  38. checkpoint-265/README.md +202 -0
  39. checkpoint-265/adapter_config.json +34 -0
  40. checkpoint-265/adapter_model.safetensors +3 -0
  41. checkpoint-265/optimizer.pt +3 -0
  42. checkpoint-265/rng_state.pth +3 -0
  43. checkpoint-265/scheduler.pt +3 -0
  44. checkpoint-265/special_tokens_map.json +23 -0
  45. checkpoint-265/tokenizer.json +0 -0
  46. checkpoint-265/tokenizer_config.json +2063 -0
  47. checkpoint-265/trainer_state.json +2088 -0
  48. checkpoint-265/training_args.bin +3 -0
  49. checkpoint-315/README.md +202 -0
  50. checkpoint-315/adapter_config.json +34 -0
NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39.yml ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
2
+ model_type: AutoModelForCausalLM
3
+ tokenizer_type: AutoTokenizer
4
+
5
+ load_in_8bit: false
6
+ load_in_4bit: false
7
+ strict: false
8
+
9
+ datasets:
10
+ - path: /workspace/axolotl/vinh/PAL/input_output_llama3.json
11
+ type: input_output
12
+ dataset_prepared_path:
13
+ val_set_size: 0.05
14
+ eval_sample_packing: false
15
+ output_dir: /workspace/axolotl/vinh/NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39
16
+
17
+ sequence_len: 2048
18
+ sample_packing: false
19
+ pad_to_sequence_len: false
20
+
21
+ adapter: lora
22
+ lora_model_dir:
23
+ lora_r: 64
24
+ lora_alpha: 128
25
+ lora_dropout: 0.05
26
+ lora_target_linear: true
27
+ lora_fan_in_fan_out:
28
+
29
+ wandb_project:
30
+ wandb_entity:
31
+ wandb_watch:
32
+ wandb_name:
33
+ wandb_log_model:
34
+
35
+ gradient_accumulation_steps: 128
36
+ micro_batch_size: 1
37
+ num_epochs: 3
38
+ optimizer: paged_adamw_32bit
39
+ lr_scheduler: cosine
40
+ learning_rate: 2e-4
41
+
42
+ train_on_inputs: false
43
+ group_by_length: false
44
+ bf16: auto
45
+ fp16:
46
+ tf32: false
47
+
48
+ gradient_checkpointing: false
49
+ early_stopping_patience:
50
+ resume_from_checkpoint:
51
+ local_rank:
52
+ logging_steps: 1
53
+ xformers_attention:
54
+ flash_attention: true
55
+ s2_attention:
56
+
57
+ loss_watchdog_threshold: 5.0
58
+ loss_watchdog_patience: 3
59
+
60
+ warmup_steps: 10
61
+ evals_per_epoch: 10
62
+ eval_table_size:
63
+ eval_max_new_tokens: 512
64
+ saves_per_epoch: 2
65
+ save_total_limit: 20
66
+ debug:
67
+ deepspeed:
68
+ weight_decay: 0.0
69
+ fsdp:
70
+ fsdp_config:
71
+ special_tokens:
72
+ pad_token: <|end_of_text|>
README.md ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
3
+ library_name: peft
4
+ license: other
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: workspace/axolotl/vinh/NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
21
+ model_type: AutoModelForCausalLM
22
+ tokenizer_type: AutoTokenizer
23
+
24
+ load_in_8bit: false
25
+ load_in_4bit: false
26
+ strict: false
27
+
28
+ datasets:
29
+ - path: /workspace/axolotl/vinh/PAL/input_output_llama3.json
30
+ type: input_output
31
+ dataset_prepared_path:
32
+ val_set_size: 0.05
33
+ eval_sample_packing: false
34
+ output_dir: /workspace/axolotl/vinh/NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39
35
+
36
+ sequence_len: 2048
37
+ sample_packing: false
38
+ pad_to_sequence_len: false
39
+
40
+ adapter: lora
41
+ lora_model_dir:
42
+ lora_r: 64
43
+ lora_alpha: 128
44
+ lora_dropout: 0.05
45
+ lora_target_linear: true
46
+ lora_fan_in_fan_out:
47
+
48
+ wandb_project:
49
+ wandb_entity:
50
+ wandb_watch:
51
+ wandb_name:
52
+ wandb_log_model:
53
+
54
+ gradient_accumulation_steps: 128
55
+ micro_batch_size: 1
56
+ num_epochs: 3
57
+ optimizer: paged_adamw_32bit
58
+ lr_scheduler: cosine
59
+ learning_rate: 2e-4
60
+
61
+ train_on_inputs: false
62
+ group_by_length: false
63
+ bf16: auto
64
+ fp16:
65
+ tf32: false
66
+
67
+ gradient_checkpointing: false
68
+ early_stopping_patience:
69
+ resume_from_checkpoint:
70
+ local_rank:
71
+ logging_steps: 1
72
+ xformers_attention:
73
+ flash_attention: true
74
+ s2_attention:
75
+
76
+ loss_watchdog_threshold: 5.0
77
+ loss_watchdog_patience: 3
78
+
79
+ warmup_steps: 10
80
+ evals_per_epoch: 10
81
+ eval_table_size:
82
+ eval_max_new_tokens: 512
83
+ saves_per_epoch: 2
84
+ save_total_limit: 20
85
+ debug:
86
+ deepspeed:
87
+ weight_decay: 0.0
88
+ fsdp:
89
+ fsdp_config:
90
+ special_tokens:
91
+ pad_token: <|end_of_text|>
92
+
93
+ ```
94
+
95
+ </details><br>
96
+
97
+ # workspace/axolotl/vinh/NousResearch_Meta-Llama-3-8B-Instruct-lora-2024-07-01-14-28-39
98
+
99
+ This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the None dataset.
100
+ It achieves the following results on the evaluation set:
101
+ - Loss: 0.0392
102
+
103
+ ## Model description
104
+
105
+ More information needed
106
+
107
+ ## Intended uses & limitations
108
+
109
+ More information needed
110
+
111
+ ## Training and evaluation data
112
+
113
+ More information needed
114
+
115
+ ## Training procedure
116
+
117
+ ### Training hyperparameters
118
+
119
+ The following hyperparameters were used during training:
120
+ - learning_rate: 0.0002
121
+ - train_batch_size: 1
122
+ - eval_batch_size: 1
123
+ - seed: 42
124
+ - gradient_accumulation_steps: 128
125
+ - total_train_batch_size: 128
126
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
127
+ - lr_scheduler_type: cosine
128
+ - lr_scheduler_warmup_steps: 10
129
+ - num_epochs: 3
130
+
131
+ ### Training results
132
+
133
+ | Training Loss | Epoch | Step | Validation Loss |
134
+ |:-------------:|:------:|:----:|:---------------:|
135
+ | 0.5339 | 0.0095 | 1 | 0.5036 |
136
+ | 0.0879 | 0.1043 | 11 | 0.0813 |
137
+ | 0.0582 | 0.2086 | 22 | 0.0629 |
138
+ | 0.06 | 0.3129 | 33 | 0.0566 |
139
+ | 0.0593 | 0.4172 | 44 | 0.0514 |
140
+ | 0.054 | 0.5214 | 55 | 0.0483 |
141
+ | 0.0459 | 0.6257 | 66 | 0.0469 |
142
+ | 0.0397 | 0.7300 | 77 | 0.0460 |
143
+ | 0.0453 | 0.8343 | 88 | 0.0449 |
144
+ | 0.04 | 0.9386 | 99 | 0.0429 |
145
+ | 0.0338 | 1.0429 | 110 | 0.0418 |
146
+ | 0.0322 | 1.1472 | 121 | 0.0422 |
147
+ | 0.0275 | 1.2515 | 132 | 0.0416 |
148
+ | 0.0322 | 1.3558 | 143 | 0.0416 |
149
+ | 0.0266 | 1.4600 | 154 | 0.0404 |
150
+ | 0.0249 | 1.5643 | 165 | 0.0397 |
151
+ | 0.0292 | 1.6686 | 176 | 0.0393 |
152
+ | 0.031 | 1.7729 | 187 | 0.0385 |
153
+ | 0.0265 | 1.8772 | 198 | 0.0375 |
154
+ | 0.0273 | 1.9815 | 209 | 0.0375 |
155
+ | 0.0175 | 2.0858 | 220 | 0.0377 |
156
+ | 0.0168 | 2.1901 | 231 | 0.0396 |
157
+ | 0.0182 | 2.2943 | 242 | 0.0403 |
158
+ | 0.0201 | 2.3986 | 253 | 0.0397 |
159
+ | 0.0138 | 2.5029 | 264 | 0.0393 |
160
+ | 0.0173 | 2.6072 | 275 | 0.0392 |
161
+ | 0.0186 | 2.7115 | 286 | 0.0392 |
162
+ | 0.0209 | 2.8158 | 297 | 0.0392 |
163
+ | 0.0185 | 2.9201 | 308 | 0.0392 |
164
+
165
+
166
+ ### Framework versions
167
+
168
+ - PEFT 0.11.1
169
+ - Transformers 4.41.1
170
+ - Pytorch 2.1.2+cu118
171
+ - Datasets 2.19.1
172
+ - 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": "NousResearch/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "down_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:d75e9988608b4df9851c2d72bf43e8ec95c786d6e5a9e09eb319bd30038a2e38
3
+ size 335706314
checkpoint-106/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
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 0.11.1
checkpoint-106/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-106/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae33ea8c5eecfdcd17f25bae21964ba432d15a6c783adbb2d14bc19680225b1
3
+ size 335605144
checkpoint-106/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd215a1b454e84154bcc453d34bf89413e4650344a61b55cc43b4738aba4eb20
3
+ size 1342452986
checkpoint-106/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a7da83a5b4a8b0b780b2121a836b41d4ac36a7de2a2b9ebf0e7a621aed351d
3
+ size 14244
checkpoint-106/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c6ccb73029ede53fae960610ee97663cfd6cf8234ebdac5276096c0b56e952
3
+ size 1064
checkpoint-106/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-106/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-106/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-106/trainer_state.json ADDED
@@ -0,0 +1,855 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0049625953633063,
5
+ "eval_steps": 11,
6
+ "global_step": 106,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009480779201540626,
13
+ "grad_norm": 2.265625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.5339,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009480779201540626,
20
+ "eval_loss": 0.5036121606826782,
21
+ "eval_runtime": 36.0149,
22
+ "eval_samples_per_second": 19.742,
23
+ "eval_steps_per_second": 19.742,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.018961558403081252,
28
+ "grad_norm": 2.1875,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.502,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02844233760462188,
35
+ "grad_norm": 1.890625,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.4769,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.037923116806162505,
42
+ "grad_norm": 1.0234375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.2922,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.04740389600770313,
49
+ "grad_norm": 1.5234375,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.2162,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.05688467520924376,
56
+ "grad_norm": 0.59375,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.1685,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.06636545441078438,
63
+ "grad_norm": 0.359375,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.1208,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.07584623361232501,
70
+ "grad_norm": 0.32421875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.1147,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.08532701281386564,
77
+ "grad_norm": 0.302734375,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.0983,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.09480779201540626,
84
+ "grad_norm": 0.25390625,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.0827,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.10428857121694689,
91
+ "grad_norm": 0.232421875,
92
+ "learning_rate": 0.00019999469523400122,
93
+ "loss": 0.0879,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10428857121694689,
98
+ "eval_loss": 0.08134982734918594,
99
+ "eval_runtime": 35.8683,
100
+ "eval_samples_per_second": 19.823,
101
+ "eval_steps_per_second": 19.823,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.11376935041848751,
106
+ "grad_norm": 0.2265625,
107
+ "learning_rate": 0.00019997878149881574,
108
+ "loss": 0.0831,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.12325012962002814,
113
+ "grad_norm": 0.21875,
114
+ "learning_rate": 0.0001999522604828164,
115
+ "loss": 0.0756,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.13273090882156877,
120
+ "grad_norm": 0.2255859375,
121
+ "learning_rate": 0.00019991513499975882,
122
+ "loss": 0.0835,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.1422116880231094,
127
+ "grad_norm": 0.234375,
128
+ "learning_rate": 0.00019986740898848306,
129
+ "loss": 0.0732,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.15169246722465002,
134
+ "grad_norm": 0.1650390625,
135
+ "learning_rate": 0.00019980908751249555,
136
+ "loss": 0.0739,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.16117324642619066,
141
+ "grad_norm": 0.14453125,
142
+ "learning_rate": 0.00019974017675943192,
143
+ "loss": 0.0698,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.17065402562773127,
148
+ "grad_norm": 0.1767578125,
149
+ "learning_rate": 0.0001996606840404006,
150
+ "loss": 0.072,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.1801348048292719,
155
+ "grad_norm": 0.1328125,
156
+ "learning_rate": 0.00019957061778920701,
157
+ "loss": 0.0556,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.18961558403081252,
162
+ "grad_norm": 0.1455078125,
163
+ "learning_rate": 0.0001994699875614589,
164
+ "loss": 0.0685,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.19909636323235316,
169
+ "grad_norm": 0.1455078125,
170
+ "learning_rate": 0.00019935880403355253,
171
+ "loss": 0.0598,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.20857714243389378,
176
+ "grad_norm": 0.13671875,
177
+ "learning_rate": 0.00019923707900153982,
178
+ "loss": 0.0582,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.20857714243389378,
183
+ "eval_loss": 0.06287878006696701,
184
+ "eval_runtime": 35.7847,
185
+ "eval_samples_per_second": 19.869,
186
+ "eval_steps_per_second": 19.869,
187
+ "step": 22
188
+ },
189
+ {
190
+ "epoch": 0.21805792163543442,
191
+ "grad_norm": 0.15234375,
192
+ "learning_rate": 0.00019910482537987702,
193
+ "loss": 0.0644,
194
+ "step": 23
195
+ },
196
+ {
197
+ "epoch": 0.22753870083697503,
198
+ "grad_norm": 0.130859375,
199
+ "learning_rate": 0.0001989620572000544,
200
+ "loss": 0.0615,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.23701948003851567,
205
+ "grad_norm": 0.13671875,
206
+ "learning_rate": 0.00019880878960910772,
207
+ "loss": 0.0686,
208
+ "step": 25
209
+ },
210
+ {
211
+ "epoch": 0.24650025924005628,
212
+ "grad_norm": 0.14453125,
213
+ "learning_rate": 0.00019864503886801106,
214
+ "loss": 0.068,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.2559810384415969,
219
+ "grad_norm": 0.12353515625,
220
+ "learning_rate": 0.00019847082234995171,
221
+ "loss": 0.0525,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.26546181764313753,
226
+ "grad_norm": 0.10791015625,
227
+ "learning_rate": 0.00019828615853848688,
228
+ "loss": 0.0541,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.27494259684467814,
233
+ "grad_norm": 0.12060546875,
234
+ "learning_rate": 0.00019809106702558277,
235
+ "loss": 0.0522,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.2844233760462188,
240
+ "grad_norm": 0.11669921875,
241
+ "learning_rate": 0.0001978855685095358,
242
+ "loss": 0.0526,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.2939041552477594,
247
+ "grad_norm": 0.140625,
248
+ "learning_rate": 0.00019766968479277683,
249
+ "loss": 0.0626,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.30338493444930004,
254
+ "grad_norm": 0.134765625,
255
+ "learning_rate": 0.00019744343877955788,
256
+ "loss": 0.0598,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.3128657136508407,
261
+ "grad_norm": 0.1220703125,
262
+ "learning_rate": 0.00019720685447352209,
263
+ "loss": 0.06,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.3128657136508407,
268
+ "eval_loss": 0.05662544071674347,
269
+ "eval_runtime": 35.8251,
270
+ "eval_samples_per_second": 19.846,
271
+ "eval_steps_per_second": 19.846,
272
+ "step": 33
273
+ },
274
+ {
275
+ "epoch": 0.3223464928523813,
276
+ "grad_norm": 0.14453125,
277
+ "learning_rate": 0.0001969599569751571,
278
+ "loss": 0.0555,
279
+ "step": 34
280
+ },
281
+ {
282
+ "epoch": 0.33182727205392193,
283
+ "grad_norm": 0.12158203125,
284
+ "learning_rate": 0.00019670277247913205,
285
+ "loss": 0.0615,
286
+ "step": 35
287
+ },
288
+ {
289
+ "epoch": 0.34130805125546254,
290
+ "grad_norm": 0.11279296875,
291
+ "learning_rate": 0.0001964353282715183,
292
+ "loss": 0.0499,
293
+ "step": 36
294
+ },
295
+ {
296
+ "epoch": 0.3507888304570032,
297
+ "grad_norm": 0.12158203125,
298
+ "learning_rate": 0.00019615765272689461,
299
+ "loss": 0.0555,
300
+ "step": 37
301
+ },
302
+ {
303
+ "epoch": 0.3602696096585438,
304
+ "grad_norm": 0.11572265625,
305
+ "learning_rate": 0.00019586977530533677,
306
+ "loss": 0.0613,
307
+ "step": 38
308
+ },
309
+ {
310
+ "epoch": 0.36975038886008443,
311
+ "grad_norm": 0.1044921875,
312
+ "learning_rate": 0.00019557172654929196,
313
+ "loss": 0.0574,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.37923116806162505,
318
+ "grad_norm": 0.1025390625,
319
+ "learning_rate": 0.00019526353808033825,
320
+ "loss": 0.0527,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.3887119472631657,
325
+ "grad_norm": 0.1298828125,
326
+ "learning_rate": 0.00019494524259582992,
327
+ "loss": 0.0561,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.3981927264647063,
332
+ "grad_norm": 0.10302734375,
333
+ "learning_rate": 0.00019461687386542826,
334
+ "loss": 0.0487,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.40767350566624694,
339
+ "grad_norm": 0.11279296875,
340
+ "learning_rate": 0.00019427846672751873,
341
+ "loss": 0.0476,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.41715428486778755,
346
+ "grad_norm": 0.1240234375,
347
+ "learning_rate": 0.00019393005708551498,
348
+ "loss": 0.0593,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.41715428486778755,
353
+ "eval_loss": 0.051377832889556885,
354
+ "eval_runtime": 35.8632,
355
+ "eval_samples_per_second": 19.825,
356
+ "eval_steps_per_second": 19.825,
357
+ "step": 44
358
+ },
359
+ {
360
+ "epoch": 0.4266350640693282,
361
+ "grad_norm": 0.10888671875,
362
+ "learning_rate": 0.00019357168190404936,
363
+ "loss": 0.0498,
364
+ "step": 45
365
+ },
366
+ {
367
+ "epoch": 0.43611584327086883,
368
+ "grad_norm": 0.1171875,
369
+ "learning_rate": 0.00019320337920505153,
370
+ "loss": 0.0599,
371
+ "step": 46
372
+ },
373
+ {
374
+ "epoch": 0.44559662247240944,
375
+ "grad_norm": 0.11669921875,
376
+ "learning_rate": 0.00019282518806371414,
377
+ "loss": 0.0595,
378
+ "step": 47
379
+ },
380
+ {
381
+ "epoch": 0.45507740167395005,
382
+ "grad_norm": 0.123046875,
383
+ "learning_rate": 0.0001924371486043473,
384
+ "loss": 0.0648,
385
+ "step": 48
386
+ },
387
+ {
388
+ "epoch": 0.4645581808754907,
389
+ "grad_norm": 0.1025390625,
390
+ "learning_rate": 0.0001920393019961217,
391
+ "loss": 0.0506,
392
+ "step": 49
393
+ },
394
+ {
395
+ "epoch": 0.47403896007703133,
396
+ "grad_norm": 0.1171875,
397
+ "learning_rate": 0.0001916316904487005,
398
+ "loss": 0.0568,
399
+ "step": 50
400
+ },
401
+ {
402
+ "epoch": 0.48351973927857195,
403
+ "grad_norm": 0.09521484375,
404
+ "learning_rate": 0.00019121435720776122,
405
+ "loss": 0.0476,
406
+ "step": 51
407
+ },
408
+ {
409
+ "epoch": 0.49300051848011256,
410
+ "grad_norm": 0.11474609375,
411
+ "learning_rate": 0.0001907873465504076,
412
+ "loss": 0.0504,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 0.5024812976816532,
417
+ "grad_norm": 0.11572265625,
418
+ "learning_rate": 0.00019035070378047204,
419
+ "loss": 0.0486,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 0.5119620768831938,
424
+ "grad_norm": 0.10986328125,
425
+ "learning_rate": 0.00018990447522370884,
426
+ "loss": 0.0467,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 0.5214428560847345,
431
+ "grad_norm": 0.12158203125,
432
+ "learning_rate": 0.00018944870822287956,
433
+ "loss": 0.054,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 0.5214428560847345,
438
+ "eval_loss": 0.048270147293806076,
439
+ "eval_runtime": 35.8252,
440
+ "eval_samples_per_second": 19.846,
441
+ "eval_steps_per_second": 19.846,
442
+ "step": 55
443
+ },
444
+ {
445
+ "epoch": 0.5309236352862751,
446
+ "grad_norm": 0.09912109375,
447
+ "learning_rate": 0.00018898345113272998,
448
+ "loss": 0.0442,
449
+ "step": 56
450
+ },
451
+ {
452
+ "epoch": 0.5404044144878157,
453
+ "grad_norm": 0.1005859375,
454
+ "learning_rate": 0.00018850875331485995,
455
+ "loss": 0.0415,
456
+ "step": 57
457
+ },
458
+ {
459
+ "epoch": 0.5498851936893563,
460
+ "grad_norm": 0.1142578125,
461
+ "learning_rate": 0.00018802466513248632,
462
+ "loss": 0.0474,
463
+ "step": 58
464
+ },
465
+ {
466
+ "epoch": 0.559365972890897,
467
+ "grad_norm": 0.1103515625,
468
+ "learning_rate": 0.00018753123794509974,
469
+ "loss": 0.0501,
470
+ "step": 59
471
+ },
472
+ {
473
+ "epoch": 0.5688467520924376,
474
+ "grad_norm": 0.10986328125,
475
+ "learning_rate": 0.00018702852410301554,
476
+ "loss": 0.0509,
477
+ "step": 60
478
+ },
479
+ {
480
+ "epoch": 0.5783275312939782,
481
+ "grad_norm": 0.119140625,
482
+ "learning_rate": 0.0001865165769418196,
483
+ "loss": 0.054,
484
+ "step": 61
485
+ },
486
+ {
487
+ "epoch": 0.5878083104955188,
488
+ "grad_norm": 0.12353515625,
489
+ "learning_rate": 0.00018599545077670985,
490
+ "loss": 0.0496,
491
+ "step": 62
492
+ },
493
+ {
494
+ "epoch": 0.5972890896970595,
495
+ "grad_norm": 0.09619140625,
496
+ "learning_rate": 0.0001854652008967335,
497
+ "loss": 0.0479,
498
+ "step": 63
499
+ },
500
+ {
501
+ "epoch": 0.6067698688986001,
502
+ "grad_norm": 0.1123046875,
503
+ "learning_rate": 0.00018492588355892124,
504
+ "loss": 0.0508,
505
+ "step": 64
506
+ },
507
+ {
508
+ "epoch": 0.6162506481001407,
509
+ "grad_norm": 0.125,
510
+ "learning_rate": 0.00018437755598231856,
511
+ "loss": 0.0499,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 0.6257314273016814,
516
+ "grad_norm": 0.0986328125,
517
+ "learning_rate": 0.00018382027634191524,
518
+ "loss": 0.0459,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 0.6257314273016814,
523
+ "eval_loss": 0.04686620458960533,
524
+ "eval_runtime": 35.9226,
525
+ "eval_samples_per_second": 19.793,
526
+ "eval_steps_per_second": 19.793,
527
+ "step": 66
528
+ },
529
+ {
530
+ "epoch": 0.635212206503222,
531
+ "grad_norm": 0.12109375,
532
+ "learning_rate": 0.00018325410376247294,
533
+ "loss": 0.0473,
534
+ "step": 67
535
+ },
536
+ {
537
+ "epoch": 0.6446929857047626,
538
+ "grad_norm": 0.1103515625,
539
+ "learning_rate": 0.0001826790983122527,
540
+ "loss": 0.0443,
541
+ "step": 68
542
+ },
543
+ {
544
+ "epoch": 0.6541737649063032,
545
+ "grad_norm": 0.11279296875,
546
+ "learning_rate": 0.00018209532099664174,
547
+ "loss": 0.0508,
548
+ "step": 69
549
+ },
550
+ {
551
+ "epoch": 0.6636545441078439,
552
+ "grad_norm": 0.11083984375,
553
+ "learning_rate": 0.00018150283375168114,
554
+ "loss": 0.0485,
555
+ "step": 70
556
+ },
557
+ {
558
+ "epoch": 0.6731353233093845,
559
+ "grad_norm": 0.10693359375,
560
+ "learning_rate": 0.00018090169943749476,
561
+ "loss": 0.0535,
562
+ "step": 71
563
+ },
564
+ {
565
+ "epoch": 0.6826161025109251,
566
+ "grad_norm": 0.10888671875,
567
+ "learning_rate": 0.00018029198183161998,
568
+ "loss": 0.0617,
569
+ "step": 72
570
+ },
571
+ {
572
+ "epoch": 0.6920968817124658,
573
+ "grad_norm": 0.09521484375,
574
+ "learning_rate": 0.00017967374562224132,
575
+ "loss": 0.0477,
576
+ "step": 73
577
+ },
578
+ {
579
+ "epoch": 0.7015776609140064,
580
+ "grad_norm": 0.0966796875,
581
+ "learning_rate": 0.00017904705640132718,
582
+ "loss": 0.0545,
583
+ "step": 74
584
+ },
585
+ {
586
+ "epoch": 0.711058440115547,
587
+ "grad_norm": 0.09423828125,
588
+ "learning_rate": 0.00017841198065767107,
589
+ "loss": 0.0396,
590
+ "step": 75
591
+ },
592
+ {
593
+ "epoch": 0.7205392193170876,
594
+ "grad_norm": 0.0947265625,
595
+ "learning_rate": 0.00017776858576983712,
596
+ "loss": 0.0483,
597
+ "step": 76
598
+ },
599
+ {
600
+ "epoch": 0.7300199985186282,
601
+ "grad_norm": 0.09326171875,
602
+ "learning_rate": 0.0001771169399990119,
603
+ "loss": 0.0397,
604
+ "step": 77
605
+ },
606
+ {
607
+ "epoch": 0.7300199985186282,
608
+ "eval_loss": 0.046032145619392395,
609
+ "eval_runtime": 35.9702,
610
+ "eval_samples_per_second": 19.766,
611
+ "eval_steps_per_second": 19.766,
612
+ "step": 77
613
+ },
614
+ {
615
+ "epoch": 0.7395007777201689,
616
+ "grad_norm": 0.09423828125,
617
+ "learning_rate": 0.00017645711248176195,
618
+ "loss": 0.0414,
619
+ "step": 78
620
+ },
621
+ {
622
+ "epoch": 0.7489815569217095,
623
+ "grad_norm": 0.10107421875,
624
+ "learning_rate": 0.00017578917322269886,
625
+ "loss": 0.0447,
626
+ "step": 79
627
+ },
628
+ {
629
+ "epoch": 0.7584623361232501,
630
+ "grad_norm": 0.0966796875,
631
+ "learning_rate": 0.00017511319308705198,
632
+ "loss": 0.0404,
633
+ "step": 80
634
+ },
635
+ {
636
+ "epoch": 0.7679431153247908,
637
+ "grad_norm": 0.099609375,
638
+ "learning_rate": 0.0001744292437931502,
639
+ "loss": 0.0409,
640
+ "step": 81
641
+ },
642
+ {
643
+ "epoch": 0.7774238945263314,
644
+ "grad_norm": 0.12890625,
645
+ "learning_rate": 0.00017373739790481262,
646
+ "loss": 0.0482,
647
+ "step": 82
648
+ },
649
+ {
650
+ "epoch": 0.786904673727872,
651
+ "grad_norm": 0.09375,
652
+ "learning_rate": 0.00017303772882365016,
653
+ "loss": 0.0356,
654
+ "step": 83
655
+ },
656
+ {
657
+ "epoch": 0.7963854529294127,
658
+ "grad_norm": 0.1103515625,
659
+ "learning_rate": 0.00017233031078127788,
660
+ "loss": 0.0467,
661
+ "step": 84
662
+ },
663
+ {
664
+ "epoch": 0.8058662321309532,
665
+ "grad_norm": 0.11767578125,
666
+ "learning_rate": 0.00017161521883143934,
667
+ "loss": 0.0537,
668
+ "step": 85
669
+ },
670
+ {
671
+ "epoch": 0.8153470113324939,
672
+ "grad_norm": 0.095703125,
673
+ "learning_rate": 0.00017089252884204377,
674
+ "loss": 0.0477,
675
+ "step": 86
676
+ },
677
+ {
678
+ "epoch": 0.8248277905340345,
679
+ "grad_norm": 0.09521484375,
680
+ "learning_rate": 0.0001701623174871168,
681
+ "loss": 0.0466,
682
+ "step": 87
683
+ },
684
+ {
685
+ "epoch": 0.8343085697355751,
686
+ "grad_norm": 0.09326171875,
687
+ "learning_rate": 0.0001694246622386658,
688
+ "loss": 0.0453,
689
+ "step": 88
690
+ },
691
+ {
692
+ "epoch": 0.8343085697355751,
693
+ "eval_loss": 0.04489152505993843,
694
+ "eval_runtime": 36.0012,
695
+ "eval_samples_per_second": 19.749,
696
+ "eval_steps_per_second": 19.749,
697
+ "step": 88
698
+ },
699
+ {
700
+ "epoch": 0.8437893489371158,
701
+ "grad_norm": 0.08349609375,
702
+ "learning_rate": 0.00016867964135846043,
703
+ "loss": 0.039,
704
+ "step": 89
705
+ },
706
+ {
707
+ "epoch": 0.8532701281386564,
708
+ "grad_norm": 0.10400390625,
709
+ "learning_rate": 0.00016792733388972932,
710
+ "loss": 0.0521,
711
+ "step": 90
712
+ },
713
+ {
714
+ "epoch": 0.862750907340197,
715
+ "grad_norm": 0.0849609375,
716
+ "learning_rate": 0.0001671678196487741,
717
+ "loss": 0.0481,
718
+ "step": 91
719
+ },
720
+ {
721
+ "epoch": 0.8722316865417377,
722
+ "grad_norm": 0.09814453125,
723
+ "learning_rate": 0.00016640117921650117,
724
+ "loss": 0.0509,
725
+ "step": 92
726
+ },
727
+ {
728
+ "epoch": 0.8817124657432783,
729
+ "grad_norm": 0.0927734375,
730
+ "learning_rate": 0.00016562749392987254,
731
+ "loss": 0.0413,
732
+ "step": 93
733
+ },
734
+ {
735
+ "epoch": 0.8911932449448189,
736
+ "grad_norm": 0.08740234375,
737
+ "learning_rate": 0.0001648468458732762,
738
+ "loss": 0.0405,
739
+ "step": 94
740
+ },
741
+ {
742
+ "epoch": 0.9006740241463596,
743
+ "grad_norm": 0.09228515625,
744
+ "learning_rate": 0.00016405931786981755,
745
+ "loss": 0.0458,
746
+ "step": 95
747
+ },
748
+ {
749
+ "epoch": 0.9101548033479001,
750
+ "grad_norm": 0.1005859375,
751
+ "learning_rate": 0.00016326499347253207,
752
+ "loss": 0.0457,
753
+ "step": 96
754
+ },
755
+ {
756
+ "epoch": 0.9196355825494408,
757
+ "grad_norm": 0.09619140625,
758
+ "learning_rate": 0.00016246395695552085,
759
+ "loss": 0.0439,
760
+ "step": 97
761
+ },
762
+ {
763
+ "epoch": 0.9291163617509814,
764
+ "grad_norm": 0.08740234375,
765
+ "learning_rate": 0.00016165629330500952,
766
+ "loss": 0.0389,
767
+ "step": 98
768
+ },
769
+ {
770
+ "epoch": 0.938597140952522,
771
+ "grad_norm": 0.08935546875,
772
+ "learning_rate": 0.0001608420882103315,
773
+ "loss": 0.04,
774
+ "step": 99
775
+ },
776
+ {
777
+ "epoch": 0.938597140952522,
778
+ "eval_loss": 0.04293662682175636,
779
+ "eval_runtime": 36.2853,
780
+ "eval_samples_per_second": 19.595,
781
+ "eval_steps_per_second": 19.595,
782
+ "step": 99
783
+ },
784
+ {
785
+ "epoch": 0.9480779201540627,
786
+ "grad_norm": 0.09326171875,
787
+ "learning_rate": 0.00016002142805483685,
788
+ "loss": 0.0418,
789
+ "step": 100
790
+ },
791
+ {
792
+ "epoch": 0.9575586993556033,
793
+ "grad_norm": 0.0830078125,
794
+ "learning_rate": 0.0001591943999067273,
795
+ "loss": 0.0406,
796
+ "step": 101
797
+ },
798
+ {
799
+ "epoch": 0.9670394785571439,
800
+ "grad_norm": 0.09375,
801
+ "learning_rate": 0.00015836109150981886,
802
+ "loss": 0.0418,
803
+ "step": 102
804
+ },
805
+ {
806
+ "epoch": 0.9765202577586846,
807
+ "grad_norm": 0.09765625,
808
+ "learning_rate": 0.00015752159127423263,
809
+ "loss": 0.0395,
810
+ "step": 103
811
+ },
812
+ {
813
+ "epoch": 0.9860010369602251,
814
+ "grad_norm": 0.08154296875,
815
+ "learning_rate": 0.0001566759882670146,
816
+ "loss": 0.0375,
817
+ "step": 104
818
+ },
819
+ {
820
+ "epoch": 0.9954818161617658,
821
+ "grad_norm": 0.1005859375,
822
+ "learning_rate": 0.00015582437220268647,
823
+ "loss": 0.0463,
824
+ "step": 105
825
+ },
826
+ {
827
+ "epoch": 1.0049625953633063,
828
+ "grad_norm": 0.07666015625,
829
+ "learning_rate": 0.0001549668334337271,
830
+ "loss": 0.0346,
831
+ "step": 106
832
+ }
833
+ ],
834
+ "logging_steps": 1,
835
+ "max_steps": 315,
836
+ "num_input_tokens_seen": 0,
837
+ "num_train_epochs": 3,
838
+ "save_steps": 53,
839
+ "stateful_callbacks": {
840
+ "TrainerControl": {
841
+ "args": {
842
+ "should_epoch_stop": false,
843
+ "should_evaluate": false,
844
+ "should_log": false,
845
+ "should_save": true,
846
+ "should_training_stop": false
847
+ },
848
+ "attributes": {}
849
+ }
850
+ },
851
+ "total_flos": 1.8985173725321626e+17,
852
+ "train_batch_size": 1,
853
+ "trial_name": null,
854
+ "trial_params": null
855
+ }
checkpoint-106/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c51879fef6458d108abda667041e5749acf5fcdaa68cbc3d11f59cd677f2e93
3
+ size 6072
checkpoint-159/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
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 0.11.1
checkpoint-159/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-159/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b814ed90ca42a7b08780d05a3c98df901b28ce6cb8eb6a6cb10f2c667f6739ea
3
+ size 335605144
checkpoint-159/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bf46ecb98cbf39d66b219f887a932e437763e9fca8548c9e354038ab2089630
3
+ size 1342452986
checkpoint-159/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a07934b6fd86594dbda051fbdd2ee9e76acec22a0dfc7cf0e899fd3c7f0a4fd
3
+ size 14244
checkpoint-159/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19809e3e9f97211f78c8259943f11fd298a3c4adde59e98dc5f42c9c642f8a96
3
+ size 1064
checkpoint-159/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-159/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-159/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-159/trainer_state.json ADDED
@@ -0,0 +1,1266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.5074438930449596,
5
+ "eval_steps": 11,
6
+ "global_step": 159,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009480779201540626,
13
+ "grad_norm": 2.265625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.5339,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009480779201540626,
20
+ "eval_loss": 0.5036121606826782,
21
+ "eval_runtime": 36.0149,
22
+ "eval_samples_per_second": 19.742,
23
+ "eval_steps_per_second": 19.742,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.018961558403081252,
28
+ "grad_norm": 2.1875,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.502,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02844233760462188,
35
+ "grad_norm": 1.890625,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.4769,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.037923116806162505,
42
+ "grad_norm": 1.0234375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.2922,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.04740389600770313,
49
+ "grad_norm": 1.5234375,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.2162,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.05688467520924376,
56
+ "grad_norm": 0.59375,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.1685,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.06636545441078438,
63
+ "grad_norm": 0.359375,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.1208,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.07584623361232501,
70
+ "grad_norm": 0.32421875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.1147,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.08532701281386564,
77
+ "grad_norm": 0.302734375,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.0983,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.09480779201540626,
84
+ "grad_norm": 0.25390625,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.0827,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.10428857121694689,
91
+ "grad_norm": 0.232421875,
92
+ "learning_rate": 0.00019999469523400122,
93
+ "loss": 0.0879,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10428857121694689,
98
+ "eval_loss": 0.08134982734918594,
99
+ "eval_runtime": 35.8683,
100
+ "eval_samples_per_second": 19.823,
101
+ "eval_steps_per_second": 19.823,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.11376935041848751,
106
+ "grad_norm": 0.2265625,
107
+ "learning_rate": 0.00019997878149881574,
108
+ "loss": 0.0831,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.12325012962002814,
113
+ "grad_norm": 0.21875,
114
+ "learning_rate": 0.0001999522604828164,
115
+ "loss": 0.0756,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.13273090882156877,
120
+ "grad_norm": 0.2255859375,
121
+ "learning_rate": 0.00019991513499975882,
122
+ "loss": 0.0835,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.1422116880231094,
127
+ "grad_norm": 0.234375,
128
+ "learning_rate": 0.00019986740898848306,
129
+ "loss": 0.0732,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.15169246722465002,
134
+ "grad_norm": 0.1650390625,
135
+ "learning_rate": 0.00019980908751249555,
136
+ "loss": 0.0739,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.16117324642619066,
141
+ "grad_norm": 0.14453125,
142
+ "learning_rate": 0.00019974017675943192,
143
+ "loss": 0.0698,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.17065402562773127,
148
+ "grad_norm": 0.1767578125,
149
+ "learning_rate": 0.0001996606840404006,
150
+ "loss": 0.072,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.1801348048292719,
155
+ "grad_norm": 0.1328125,
156
+ "learning_rate": 0.00019957061778920701,
157
+ "loss": 0.0556,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.18961558403081252,
162
+ "grad_norm": 0.1455078125,
163
+ "learning_rate": 0.0001994699875614589,
164
+ "loss": 0.0685,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.19909636323235316,
169
+ "grad_norm": 0.1455078125,
170
+ "learning_rate": 0.00019935880403355253,
171
+ "loss": 0.0598,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.20857714243389378,
176
+ "grad_norm": 0.13671875,
177
+ "learning_rate": 0.00019923707900153982,
178
+ "loss": 0.0582,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.20857714243389378,
183
+ "eval_loss": 0.06287878006696701,
184
+ "eval_runtime": 35.7847,
185
+ "eval_samples_per_second": 19.869,
186
+ "eval_steps_per_second": 19.869,
187
+ "step": 22
188
+ },
189
+ {
190
+ "epoch": 0.21805792163543442,
191
+ "grad_norm": 0.15234375,
192
+ "learning_rate": 0.00019910482537987702,
193
+ "loss": 0.0644,
194
+ "step": 23
195
+ },
196
+ {
197
+ "epoch": 0.22753870083697503,
198
+ "grad_norm": 0.130859375,
199
+ "learning_rate": 0.0001989620572000544,
200
+ "loss": 0.0615,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.23701948003851567,
205
+ "grad_norm": 0.13671875,
206
+ "learning_rate": 0.00019880878960910772,
207
+ "loss": 0.0686,
208
+ "step": 25
209
+ },
210
+ {
211
+ "epoch": 0.24650025924005628,
212
+ "grad_norm": 0.14453125,
213
+ "learning_rate": 0.00019864503886801106,
214
+ "loss": 0.068,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.2559810384415969,
219
+ "grad_norm": 0.12353515625,
220
+ "learning_rate": 0.00019847082234995171,
221
+ "loss": 0.0525,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.26546181764313753,
226
+ "grad_norm": 0.10791015625,
227
+ "learning_rate": 0.00019828615853848688,
228
+ "loss": 0.0541,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.27494259684467814,
233
+ "grad_norm": 0.12060546875,
234
+ "learning_rate": 0.00019809106702558277,
235
+ "loss": 0.0522,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.2844233760462188,
240
+ "grad_norm": 0.11669921875,
241
+ "learning_rate": 0.0001978855685095358,
242
+ "loss": 0.0526,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.2939041552477594,
247
+ "grad_norm": 0.140625,
248
+ "learning_rate": 0.00019766968479277683,
249
+ "loss": 0.0626,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.30338493444930004,
254
+ "grad_norm": 0.134765625,
255
+ "learning_rate": 0.00019744343877955788,
256
+ "loss": 0.0598,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.3128657136508407,
261
+ "grad_norm": 0.1220703125,
262
+ "learning_rate": 0.00019720685447352209,
263
+ "loss": 0.06,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.3128657136508407,
268
+ "eval_loss": 0.05662544071674347,
269
+ "eval_runtime": 35.8251,
270
+ "eval_samples_per_second": 19.846,
271
+ "eval_steps_per_second": 19.846,
272
+ "step": 33
273
+ },
274
+ {
275
+ "epoch": 0.3223464928523813,
276
+ "grad_norm": 0.14453125,
277
+ "learning_rate": 0.0001969599569751571,
278
+ "loss": 0.0555,
279
+ "step": 34
280
+ },
281
+ {
282
+ "epoch": 0.33182727205392193,
283
+ "grad_norm": 0.12158203125,
284
+ "learning_rate": 0.00019670277247913205,
285
+ "loss": 0.0615,
286
+ "step": 35
287
+ },
288
+ {
289
+ "epoch": 0.34130805125546254,
290
+ "grad_norm": 0.11279296875,
291
+ "learning_rate": 0.0001964353282715183,
292
+ "loss": 0.0499,
293
+ "step": 36
294
+ },
295
+ {
296
+ "epoch": 0.3507888304570032,
297
+ "grad_norm": 0.12158203125,
298
+ "learning_rate": 0.00019615765272689461,
299
+ "loss": 0.0555,
300
+ "step": 37
301
+ },
302
+ {
303
+ "epoch": 0.3602696096585438,
304
+ "grad_norm": 0.11572265625,
305
+ "learning_rate": 0.00019586977530533677,
306
+ "loss": 0.0613,
307
+ "step": 38
308
+ },
309
+ {
310
+ "epoch": 0.36975038886008443,
311
+ "grad_norm": 0.1044921875,
312
+ "learning_rate": 0.00019557172654929196,
313
+ "loss": 0.0574,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.37923116806162505,
318
+ "grad_norm": 0.1025390625,
319
+ "learning_rate": 0.00019526353808033825,
320
+ "loss": 0.0527,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.3887119472631657,
325
+ "grad_norm": 0.1298828125,
326
+ "learning_rate": 0.00019494524259582992,
327
+ "loss": 0.0561,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.3981927264647063,
332
+ "grad_norm": 0.10302734375,
333
+ "learning_rate": 0.00019461687386542826,
334
+ "loss": 0.0487,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.40767350566624694,
339
+ "grad_norm": 0.11279296875,
340
+ "learning_rate": 0.00019427846672751873,
341
+ "loss": 0.0476,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.41715428486778755,
346
+ "grad_norm": 0.1240234375,
347
+ "learning_rate": 0.00019393005708551498,
348
+ "loss": 0.0593,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.41715428486778755,
353
+ "eval_loss": 0.051377832889556885,
354
+ "eval_runtime": 35.8632,
355
+ "eval_samples_per_second": 19.825,
356
+ "eval_steps_per_second": 19.825,
357
+ "step": 44
358
+ },
359
+ {
360
+ "epoch": 0.4266350640693282,
361
+ "grad_norm": 0.10888671875,
362
+ "learning_rate": 0.00019357168190404936,
363
+ "loss": 0.0498,
364
+ "step": 45
365
+ },
366
+ {
367
+ "epoch": 0.43611584327086883,
368
+ "grad_norm": 0.1171875,
369
+ "learning_rate": 0.00019320337920505153,
370
+ "loss": 0.0599,
371
+ "step": 46
372
+ },
373
+ {
374
+ "epoch": 0.44559662247240944,
375
+ "grad_norm": 0.11669921875,
376
+ "learning_rate": 0.00019282518806371414,
377
+ "loss": 0.0595,
378
+ "step": 47
379
+ },
380
+ {
381
+ "epoch": 0.45507740167395005,
382
+ "grad_norm": 0.123046875,
383
+ "learning_rate": 0.0001924371486043473,
384
+ "loss": 0.0648,
385
+ "step": 48
386
+ },
387
+ {
388
+ "epoch": 0.4645581808754907,
389
+ "grad_norm": 0.1025390625,
390
+ "learning_rate": 0.0001920393019961217,
391
+ "loss": 0.0506,
392
+ "step": 49
393
+ },
394
+ {
395
+ "epoch": 0.47403896007703133,
396
+ "grad_norm": 0.1171875,
397
+ "learning_rate": 0.0001916316904487005,
398
+ "loss": 0.0568,
399
+ "step": 50
400
+ },
401
+ {
402
+ "epoch": 0.48351973927857195,
403
+ "grad_norm": 0.09521484375,
404
+ "learning_rate": 0.00019121435720776122,
405
+ "loss": 0.0476,
406
+ "step": 51
407
+ },
408
+ {
409
+ "epoch": 0.49300051848011256,
410
+ "grad_norm": 0.11474609375,
411
+ "learning_rate": 0.0001907873465504076,
412
+ "loss": 0.0504,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 0.5024812976816532,
417
+ "grad_norm": 0.11572265625,
418
+ "learning_rate": 0.00019035070378047204,
419
+ "loss": 0.0486,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 0.5119620768831938,
424
+ "grad_norm": 0.10986328125,
425
+ "learning_rate": 0.00018990447522370884,
426
+ "loss": 0.0467,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 0.5214428560847345,
431
+ "grad_norm": 0.12158203125,
432
+ "learning_rate": 0.00018944870822287956,
433
+ "loss": 0.054,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 0.5214428560847345,
438
+ "eval_loss": 0.048270147293806076,
439
+ "eval_runtime": 35.8252,
440
+ "eval_samples_per_second": 19.846,
441
+ "eval_steps_per_second": 19.846,
442
+ "step": 55
443
+ },
444
+ {
445
+ "epoch": 0.5309236352862751,
446
+ "grad_norm": 0.09912109375,
447
+ "learning_rate": 0.00018898345113272998,
448
+ "loss": 0.0442,
449
+ "step": 56
450
+ },
451
+ {
452
+ "epoch": 0.5404044144878157,
453
+ "grad_norm": 0.1005859375,
454
+ "learning_rate": 0.00018850875331485995,
455
+ "loss": 0.0415,
456
+ "step": 57
457
+ },
458
+ {
459
+ "epoch": 0.5498851936893563,
460
+ "grad_norm": 0.1142578125,
461
+ "learning_rate": 0.00018802466513248632,
462
+ "loss": 0.0474,
463
+ "step": 58
464
+ },
465
+ {
466
+ "epoch": 0.559365972890897,
467
+ "grad_norm": 0.1103515625,
468
+ "learning_rate": 0.00018753123794509974,
469
+ "loss": 0.0501,
470
+ "step": 59
471
+ },
472
+ {
473
+ "epoch": 0.5688467520924376,
474
+ "grad_norm": 0.10986328125,
475
+ "learning_rate": 0.00018702852410301554,
476
+ "loss": 0.0509,
477
+ "step": 60
478
+ },
479
+ {
480
+ "epoch": 0.5783275312939782,
481
+ "grad_norm": 0.119140625,
482
+ "learning_rate": 0.0001865165769418196,
483
+ "loss": 0.054,
484
+ "step": 61
485
+ },
486
+ {
487
+ "epoch": 0.5878083104955188,
488
+ "grad_norm": 0.12353515625,
489
+ "learning_rate": 0.00018599545077670985,
490
+ "loss": 0.0496,
491
+ "step": 62
492
+ },
493
+ {
494
+ "epoch": 0.5972890896970595,
495
+ "grad_norm": 0.09619140625,
496
+ "learning_rate": 0.0001854652008967335,
497
+ "loss": 0.0479,
498
+ "step": 63
499
+ },
500
+ {
501
+ "epoch": 0.6067698688986001,
502
+ "grad_norm": 0.1123046875,
503
+ "learning_rate": 0.00018492588355892124,
504
+ "loss": 0.0508,
505
+ "step": 64
506
+ },
507
+ {
508
+ "epoch": 0.6162506481001407,
509
+ "grad_norm": 0.125,
510
+ "learning_rate": 0.00018437755598231856,
511
+ "loss": 0.0499,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 0.6257314273016814,
516
+ "grad_norm": 0.0986328125,
517
+ "learning_rate": 0.00018382027634191524,
518
+ "loss": 0.0459,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 0.6257314273016814,
523
+ "eval_loss": 0.04686620458960533,
524
+ "eval_runtime": 35.9226,
525
+ "eval_samples_per_second": 19.793,
526
+ "eval_steps_per_second": 19.793,
527
+ "step": 66
528
+ },
529
+ {
530
+ "epoch": 0.635212206503222,
531
+ "grad_norm": 0.12109375,
532
+ "learning_rate": 0.00018325410376247294,
533
+ "loss": 0.0473,
534
+ "step": 67
535
+ },
536
+ {
537
+ "epoch": 0.6446929857047626,
538
+ "grad_norm": 0.1103515625,
539
+ "learning_rate": 0.0001826790983122527,
540
+ "loss": 0.0443,
541
+ "step": 68
542
+ },
543
+ {
544
+ "epoch": 0.6541737649063032,
545
+ "grad_norm": 0.11279296875,
546
+ "learning_rate": 0.00018209532099664174,
547
+ "loss": 0.0508,
548
+ "step": 69
549
+ },
550
+ {
551
+ "epoch": 0.6636545441078439,
552
+ "grad_norm": 0.11083984375,
553
+ "learning_rate": 0.00018150283375168114,
554
+ "loss": 0.0485,
555
+ "step": 70
556
+ },
557
+ {
558
+ "epoch": 0.6731353233093845,
559
+ "grad_norm": 0.10693359375,
560
+ "learning_rate": 0.00018090169943749476,
561
+ "loss": 0.0535,
562
+ "step": 71
563
+ },
564
+ {
565
+ "epoch": 0.6826161025109251,
566
+ "grad_norm": 0.10888671875,
567
+ "learning_rate": 0.00018029198183161998,
568
+ "loss": 0.0617,
569
+ "step": 72
570
+ },
571
+ {
572
+ "epoch": 0.6920968817124658,
573
+ "grad_norm": 0.09521484375,
574
+ "learning_rate": 0.00017967374562224132,
575
+ "loss": 0.0477,
576
+ "step": 73
577
+ },
578
+ {
579
+ "epoch": 0.7015776609140064,
580
+ "grad_norm": 0.0966796875,
581
+ "learning_rate": 0.00017904705640132718,
582
+ "loss": 0.0545,
583
+ "step": 74
584
+ },
585
+ {
586
+ "epoch": 0.711058440115547,
587
+ "grad_norm": 0.09423828125,
588
+ "learning_rate": 0.00017841198065767107,
589
+ "loss": 0.0396,
590
+ "step": 75
591
+ },
592
+ {
593
+ "epoch": 0.7205392193170876,
594
+ "grad_norm": 0.0947265625,
595
+ "learning_rate": 0.00017776858576983712,
596
+ "loss": 0.0483,
597
+ "step": 76
598
+ },
599
+ {
600
+ "epoch": 0.7300199985186282,
601
+ "grad_norm": 0.09326171875,
602
+ "learning_rate": 0.0001771169399990119,
603
+ "loss": 0.0397,
604
+ "step": 77
605
+ },
606
+ {
607
+ "epoch": 0.7300199985186282,
608
+ "eval_loss": 0.046032145619392395,
609
+ "eval_runtime": 35.9702,
610
+ "eval_samples_per_second": 19.766,
611
+ "eval_steps_per_second": 19.766,
612
+ "step": 77
613
+ },
614
+ {
615
+ "epoch": 0.7395007777201689,
616
+ "grad_norm": 0.09423828125,
617
+ "learning_rate": 0.00017645711248176195,
618
+ "loss": 0.0414,
619
+ "step": 78
620
+ },
621
+ {
622
+ "epoch": 0.7489815569217095,
623
+ "grad_norm": 0.10107421875,
624
+ "learning_rate": 0.00017578917322269886,
625
+ "loss": 0.0447,
626
+ "step": 79
627
+ },
628
+ {
629
+ "epoch": 0.7584623361232501,
630
+ "grad_norm": 0.0966796875,
631
+ "learning_rate": 0.00017511319308705198,
632
+ "loss": 0.0404,
633
+ "step": 80
634
+ },
635
+ {
636
+ "epoch": 0.7679431153247908,
637
+ "grad_norm": 0.099609375,
638
+ "learning_rate": 0.0001744292437931502,
639
+ "loss": 0.0409,
640
+ "step": 81
641
+ },
642
+ {
643
+ "epoch": 0.7774238945263314,
644
+ "grad_norm": 0.12890625,
645
+ "learning_rate": 0.00017373739790481262,
646
+ "loss": 0.0482,
647
+ "step": 82
648
+ },
649
+ {
650
+ "epoch": 0.786904673727872,
651
+ "grad_norm": 0.09375,
652
+ "learning_rate": 0.00017303772882365016,
653
+ "loss": 0.0356,
654
+ "step": 83
655
+ },
656
+ {
657
+ "epoch": 0.7963854529294127,
658
+ "grad_norm": 0.1103515625,
659
+ "learning_rate": 0.00017233031078127788,
660
+ "loss": 0.0467,
661
+ "step": 84
662
+ },
663
+ {
664
+ "epoch": 0.8058662321309532,
665
+ "grad_norm": 0.11767578125,
666
+ "learning_rate": 0.00017161521883143934,
667
+ "loss": 0.0537,
668
+ "step": 85
669
+ },
670
+ {
671
+ "epoch": 0.8153470113324939,
672
+ "grad_norm": 0.095703125,
673
+ "learning_rate": 0.00017089252884204377,
674
+ "loss": 0.0477,
675
+ "step": 86
676
+ },
677
+ {
678
+ "epoch": 0.8248277905340345,
679
+ "grad_norm": 0.09521484375,
680
+ "learning_rate": 0.0001701623174871168,
681
+ "loss": 0.0466,
682
+ "step": 87
683
+ },
684
+ {
685
+ "epoch": 0.8343085697355751,
686
+ "grad_norm": 0.09326171875,
687
+ "learning_rate": 0.0001694246622386658,
688
+ "loss": 0.0453,
689
+ "step": 88
690
+ },
691
+ {
692
+ "epoch": 0.8343085697355751,
693
+ "eval_loss": 0.04489152505993843,
694
+ "eval_runtime": 36.0012,
695
+ "eval_samples_per_second": 19.749,
696
+ "eval_steps_per_second": 19.749,
697
+ "step": 88
698
+ },
699
+ {
700
+ "epoch": 0.8437893489371158,
701
+ "grad_norm": 0.08349609375,
702
+ "learning_rate": 0.00016867964135846043,
703
+ "loss": 0.039,
704
+ "step": 89
705
+ },
706
+ {
707
+ "epoch": 0.8532701281386564,
708
+ "grad_norm": 0.10400390625,
709
+ "learning_rate": 0.00016792733388972932,
710
+ "loss": 0.0521,
711
+ "step": 90
712
+ },
713
+ {
714
+ "epoch": 0.862750907340197,
715
+ "grad_norm": 0.0849609375,
716
+ "learning_rate": 0.0001671678196487741,
717
+ "loss": 0.0481,
718
+ "step": 91
719
+ },
720
+ {
721
+ "epoch": 0.8722316865417377,
722
+ "grad_norm": 0.09814453125,
723
+ "learning_rate": 0.00016640117921650117,
724
+ "loss": 0.0509,
725
+ "step": 92
726
+ },
727
+ {
728
+ "epoch": 0.8817124657432783,
729
+ "grad_norm": 0.0927734375,
730
+ "learning_rate": 0.00016562749392987254,
731
+ "loss": 0.0413,
732
+ "step": 93
733
+ },
734
+ {
735
+ "epoch": 0.8911932449448189,
736
+ "grad_norm": 0.08740234375,
737
+ "learning_rate": 0.0001648468458732762,
738
+ "loss": 0.0405,
739
+ "step": 94
740
+ },
741
+ {
742
+ "epoch": 0.9006740241463596,
743
+ "grad_norm": 0.09228515625,
744
+ "learning_rate": 0.00016405931786981755,
745
+ "loss": 0.0458,
746
+ "step": 95
747
+ },
748
+ {
749
+ "epoch": 0.9101548033479001,
750
+ "grad_norm": 0.1005859375,
751
+ "learning_rate": 0.00016326499347253207,
752
+ "loss": 0.0457,
753
+ "step": 96
754
+ },
755
+ {
756
+ "epoch": 0.9196355825494408,
757
+ "grad_norm": 0.09619140625,
758
+ "learning_rate": 0.00016246395695552085,
759
+ "loss": 0.0439,
760
+ "step": 97
761
+ },
762
+ {
763
+ "epoch": 0.9291163617509814,
764
+ "grad_norm": 0.08740234375,
765
+ "learning_rate": 0.00016165629330500952,
766
+ "loss": 0.0389,
767
+ "step": 98
768
+ },
769
+ {
770
+ "epoch": 0.938597140952522,
771
+ "grad_norm": 0.08935546875,
772
+ "learning_rate": 0.0001608420882103315,
773
+ "loss": 0.04,
774
+ "step": 99
775
+ },
776
+ {
777
+ "epoch": 0.938597140952522,
778
+ "eval_loss": 0.04293662682175636,
779
+ "eval_runtime": 36.2853,
780
+ "eval_samples_per_second": 19.595,
781
+ "eval_steps_per_second": 19.595,
782
+ "step": 99
783
+ },
784
+ {
785
+ "epoch": 0.9480779201540627,
786
+ "grad_norm": 0.09326171875,
787
+ "learning_rate": 0.00016002142805483685,
788
+ "loss": 0.0418,
789
+ "step": 100
790
+ },
791
+ {
792
+ "epoch": 0.9575586993556033,
793
+ "grad_norm": 0.0830078125,
794
+ "learning_rate": 0.0001591943999067273,
795
+ "loss": 0.0406,
796
+ "step": 101
797
+ },
798
+ {
799
+ "epoch": 0.9670394785571439,
800
+ "grad_norm": 0.09375,
801
+ "learning_rate": 0.00015836109150981886,
802
+ "loss": 0.0418,
803
+ "step": 102
804
+ },
805
+ {
806
+ "epoch": 0.9765202577586846,
807
+ "grad_norm": 0.09765625,
808
+ "learning_rate": 0.00015752159127423263,
809
+ "loss": 0.0395,
810
+ "step": 103
811
+ },
812
+ {
813
+ "epoch": 0.9860010369602251,
814
+ "grad_norm": 0.08154296875,
815
+ "learning_rate": 0.0001566759882670146,
816
+ "loss": 0.0375,
817
+ "step": 104
818
+ },
819
+ {
820
+ "epoch": 0.9954818161617658,
821
+ "grad_norm": 0.1005859375,
822
+ "learning_rate": 0.00015582437220268647,
823
+ "loss": 0.0463,
824
+ "step": 105
825
+ },
826
+ {
827
+ "epoch": 1.0049625953633063,
828
+ "grad_norm": 0.07666015625,
829
+ "learning_rate": 0.0001549668334337271,
830
+ "loss": 0.0346,
831
+ "step": 106
832
+ },
833
+ {
834
+ "epoch": 1.0144433745648471,
835
+ "grad_norm": 0.07763671875,
836
+ "learning_rate": 0.0001541034629409865,
837
+ "loss": 0.0322,
838
+ "step": 107
839
+ },
840
+ {
841
+ "epoch": 1.0239241537663877,
842
+ "grad_norm": 0.08154296875,
843
+ "learning_rate": 0.00015323435232403337,
844
+ "loss": 0.0328,
845
+ "step": 108
846
+ },
847
+ {
848
+ "epoch": 1.0334049329679282,
849
+ "grad_norm": 0.06591796875,
850
+ "learning_rate": 0.00015235959379143678,
851
+ "loss": 0.0299,
852
+ "step": 109
853
+ },
854
+ {
855
+ "epoch": 1.042885712169469,
856
+ "grad_norm": 0.08544921875,
857
+ "learning_rate": 0.0001514792801509831,
858
+ "loss": 0.0338,
859
+ "step": 110
860
+ },
861
+ {
862
+ "epoch": 1.042885712169469,
863
+ "eval_loss": 0.04179221764206886,
864
+ "eval_runtime": 35.8658,
865
+ "eval_samples_per_second": 19.824,
866
+ "eval_steps_per_second": 19.824,
867
+ "step": 110
868
+ },
869
+ {
870
+ "epoch": 1.0523664913710096,
871
+ "grad_norm": 0.0830078125,
872
+ "learning_rate": 0.00015059350479982965,
873
+ "loss": 0.0281,
874
+ "step": 111
875
+ },
876
+ {
877
+ "epoch": 1.0618472705725501,
878
+ "grad_norm": 0.083984375,
879
+ "learning_rate": 0.0001497023617145958,
880
+ "loss": 0.03,
881
+ "step": 112
882
+ },
883
+ {
884
+ "epoch": 1.071328049774091,
885
+ "grad_norm": 0.0771484375,
886
+ "learning_rate": 0.0001488059454413923,
887
+ "loss": 0.0286,
888
+ "step": 113
889
+ },
890
+ {
891
+ "epoch": 1.0808088289756315,
892
+ "grad_norm": 0.0966796875,
893
+ "learning_rate": 0.00014790435108579048,
894
+ "loss": 0.0311,
895
+ "step": 114
896
+ },
897
+ {
898
+ "epoch": 1.090289608177172,
899
+ "grad_norm": 0.0869140625,
900
+ "learning_rate": 0.000146997674302732,
901
+ "loss": 0.0291,
902
+ "step": 115
903
+ },
904
+ {
905
+ "epoch": 1.0997703873787126,
906
+ "grad_norm": 0.08984375,
907
+ "learning_rate": 0.00014608601128638027,
908
+ "loss": 0.0281,
909
+ "step": 116
910
+ },
911
+ {
912
+ "epoch": 1.1092511665802534,
913
+ "grad_norm": 0.08837890625,
914
+ "learning_rate": 0.00014516945875991472,
915
+ "loss": 0.0322,
916
+ "step": 117
917
+ },
918
+ {
919
+ "epoch": 1.118731945781794,
920
+ "grad_norm": 0.083984375,
921
+ "learning_rate": 0.00014424811396526892,
922
+ "loss": 0.026,
923
+ "step": 118
924
+ },
925
+ {
926
+ "epoch": 1.1282127249833347,
927
+ "grad_norm": 0.08837890625,
928
+ "learning_rate": 0.00014332207465281364,
929
+ "loss": 0.0317,
930
+ "step": 119
931
+ },
932
+ {
933
+ "epoch": 1.1376935041848752,
934
+ "grad_norm": 0.09912109375,
935
+ "learning_rate": 0.0001423914390709861,
936
+ "loss": 0.0341,
937
+ "step": 120
938
+ },
939
+ {
940
+ "epoch": 1.1471742833864158,
941
+ "grad_norm": 0.095703125,
942
+ "learning_rate": 0.00014145630595586607,
943
+ "loss": 0.0322,
944
+ "step": 121
945
+ },
946
+ {
947
+ "epoch": 1.1471742833864158,
948
+ "eval_loss": 0.04224802553653717,
949
+ "eval_runtime": 35.7541,
950
+ "eval_samples_per_second": 19.886,
951
+ "eval_steps_per_second": 19.886,
952
+ "step": 121
953
+ },
954
+ {
955
+ "epoch": 1.1566550625879564,
956
+ "grad_norm": 0.07763671875,
957
+ "learning_rate": 0.00014051677452070065,
958
+ "loss": 0.0279,
959
+ "step": 122
960
+ },
961
+ {
962
+ "epoch": 1.1661358417894971,
963
+ "grad_norm": 0.08837890625,
964
+ "learning_rate": 0.00013957294444537808,
965
+ "loss": 0.0276,
966
+ "step": 123
967
+ },
968
+ {
969
+ "epoch": 1.1756166209910377,
970
+ "grad_norm": 0.099609375,
971
+ "learning_rate": 0.0001386249158658522,
972
+ "loss": 0.0399,
973
+ "step": 124
974
+ },
975
+ {
976
+ "epoch": 1.1850974001925783,
977
+ "grad_norm": 0.0888671875,
978
+ "learning_rate": 0.00013767278936351854,
979
+ "loss": 0.0327,
980
+ "step": 125
981
+ },
982
+ {
983
+ "epoch": 1.194578179394119,
984
+ "grad_norm": 0.078125,
985
+ "learning_rate": 0.00013671666595454295,
986
+ "loss": 0.0257,
987
+ "step": 126
988
+ },
989
+ {
990
+ "epoch": 1.2040589585956596,
991
+ "grad_norm": 0.078125,
992
+ "learning_rate": 0.00013575664707914448,
993
+ "loss": 0.0268,
994
+ "step": 127
995
+ },
996
+ {
997
+ "epoch": 1.2135397377972001,
998
+ "grad_norm": 0.0966796875,
999
+ "learning_rate": 0.0001347928345908329,
1000
+ "loss": 0.0368,
1001
+ "step": 128
1002
+ },
1003
+ {
1004
+ "epoch": 1.223020516998741,
1005
+ "grad_norm": 0.076171875,
1006
+ "learning_rate": 0.00013382533074560255,
1007
+ "loss": 0.0286,
1008
+ "step": 129
1009
+ },
1010
+ {
1011
+ "epoch": 1.2325012962002815,
1012
+ "grad_norm": 0.0888671875,
1013
+ "learning_rate": 0.0001328542381910835,
1014
+ "loss": 0.0304,
1015
+ "step": 130
1016
+ },
1017
+ {
1018
+ "epoch": 1.241982075401822,
1019
+ "grad_norm": 0.087890625,
1020
+ "learning_rate": 0.00013187965995565098,
1021
+ "loss": 0.0304,
1022
+ "step": 131
1023
+ },
1024
+ {
1025
+ "epoch": 1.2514628546033628,
1026
+ "grad_norm": 0.0732421875,
1027
+ "learning_rate": 0.00013090169943749476,
1028
+ "loss": 0.0275,
1029
+ "step": 132
1030
+ },
1031
+ {
1032
+ "epoch": 1.2514628546033628,
1033
+ "eval_loss": 0.04160289093852043,
1034
+ "eval_runtime": 35.8932,
1035
+ "eval_samples_per_second": 19.809,
1036
+ "eval_steps_per_second": 19.809,
1037
+ "step": 132
1038
+ },
1039
+ {
1040
+ "epoch": 1.2609436338049034,
1041
+ "grad_norm": 0.08203125,
1042
+ "learning_rate": 0.00012992046039364893,
1043
+ "loss": 0.0293,
1044
+ "step": 133
1045
+ },
1046
+ {
1047
+ "epoch": 1.270424413006444,
1048
+ "grad_norm": 0.087890625,
1049
+ "learning_rate": 0.0001289360469289838,
1050
+ "loss": 0.03,
1051
+ "step": 134
1052
+ },
1053
+ {
1054
+ "epoch": 1.2799051922079845,
1055
+ "grad_norm": 0.08203125,
1056
+ "learning_rate": 0.00012794856348516095,
1057
+ "loss": 0.028,
1058
+ "step": 135
1059
+ },
1060
+ {
1061
+ "epoch": 1.2893859714095253,
1062
+ "grad_norm": 0.0869140625,
1063
+ "learning_rate": 0.00012695811482955227,
1064
+ "loss": 0.0293,
1065
+ "step": 136
1066
+ },
1067
+ {
1068
+ "epoch": 1.2988667506110658,
1069
+ "grad_norm": 0.09228515625,
1070
+ "learning_rate": 0.00012596480604412484,
1071
+ "loss": 0.0341,
1072
+ "step": 137
1073
+ },
1074
+ {
1075
+ "epoch": 1.3083475298126066,
1076
+ "grad_norm": 0.07470703125,
1077
+ "learning_rate": 0.000124968742514292,
1078
+ "loss": 0.0259,
1079
+ "step": 138
1080
+ },
1081
+ {
1082
+ "epoch": 1.3178283090141472,
1083
+ "grad_norm": 0.10009765625,
1084
+ "learning_rate": 0.00012397002991773275,
1085
+ "loss": 0.0298,
1086
+ "step": 139
1087
+ },
1088
+ {
1089
+ "epoch": 1.3273090882156877,
1090
+ "grad_norm": 0.08837890625,
1091
+ "learning_rate": 0.0001229687742131796,
1092
+ "loss": 0.0285,
1093
+ "step": 140
1094
+ },
1095
+ {
1096
+ "epoch": 1.3367898674172283,
1097
+ "grad_norm": 0.091796875,
1098
+ "learning_rate": 0.00012196508162917677,
1099
+ "loss": 0.034,
1100
+ "step": 141
1101
+ },
1102
+ {
1103
+ "epoch": 1.346270646618769,
1104
+ "grad_norm": 0.0986328125,
1105
+ "learning_rate": 0.00012095905865281025,
1106
+ "loss": 0.0314,
1107
+ "step": 142
1108
+ },
1109
+ {
1110
+ "epoch": 1.3557514258203096,
1111
+ "grad_norm": 0.0947265625,
1112
+ "learning_rate": 0.00011995081201840956,
1113
+ "loss": 0.0322,
1114
+ "step": 143
1115
+ },
1116
+ {
1117
+ "epoch": 1.3557514258203096,
1118
+ "eval_loss": 0.041649721562862396,
1119
+ "eval_runtime": 35.8396,
1120
+ "eval_samples_per_second": 19.838,
1121
+ "eval_steps_per_second": 19.838,
1122
+ "step": 143
1123
+ },
1124
+ {
1125
+ "epoch": 1.3652322050218502,
1126
+ "grad_norm": 0.083984375,
1127
+ "learning_rate": 0.00011894044869622403,
1128
+ "loss": 0.0303,
1129
+ "step": 144
1130
+ },
1131
+ {
1132
+ "epoch": 1.374712984223391,
1133
+ "grad_norm": 0.07373046875,
1134
+ "learning_rate": 0.00011792807588107357,
1135
+ "loss": 0.0259,
1136
+ "step": 145
1137
+ },
1138
+ {
1139
+ "epoch": 1.3841937634249315,
1140
+ "grad_norm": 0.08740234375,
1141
+ "learning_rate": 0.00011691380098097597,
1142
+ "loss": 0.0334,
1143
+ "step": 146
1144
+ },
1145
+ {
1146
+ "epoch": 1.393674542626472,
1147
+ "grad_norm": 0.068359375,
1148
+ "learning_rate": 0.0001158977316057513,
1149
+ "loss": 0.0245,
1150
+ "step": 147
1151
+ },
1152
+ {
1153
+ "epoch": 1.4031553218280126,
1154
+ "grad_norm": 0.09423828125,
1155
+ "learning_rate": 0.00011487997555560503,
1156
+ "loss": 0.0322,
1157
+ "step": 148
1158
+ },
1159
+ {
1160
+ "epoch": 1.4126361010295534,
1161
+ "grad_norm": 0.0947265625,
1162
+ "learning_rate": 0.00011386064080969094,
1163
+ "loss": 0.0338,
1164
+ "step": 149
1165
+ },
1166
+ {
1167
+ "epoch": 1.422116880231094,
1168
+ "grad_norm": 0.09326171875,
1169
+ "learning_rate": 0.00011283983551465511,
1170
+ "loss": 0.0278,
1171
+ "step": 150
1172
+ },
1173
+ {
1174
+ "epoch": 1.4315976594326347,
1175
+ "grad_norm": 0.087890625,
1176
+ "learning_rate": 0.0001118176679731619,
1177
+ "loss": 0.0305,
1178
+ "step": 151
1179
+ },
1180
+ {
1181
+ "epoch": 1.4410784386341753,
1182
+ "grad_norm": 0.083984375,
1183
+ "learning_rate": 0.00011079424663240372,
1184
+ "loss": 0.0311,
1185
+ "step": 152
1186
+ },
1187
+ {
1188
+ "epoch": 1.4505592178357158,
1189
+ "grad_norm": 0.08154296875,
1190
+ "learning_rate": 0.00010976968007259519,
1191
+ "loss": 0.0298,
1192
+ "step": 153
1193
+ },
1194
+ {
1195
+ "epoch": 1.4600399970372564,
1196
+ "grad_norm": 0.072265625,
1197
+ "learning_rate": 0.00010874407699545328,
1198
+ "loss": 0.0266,
1199
+ "step": 154
1200
+ },
1201
+ {
1202
+ "epoch": 1.4600399970372564,
1203
+ "eval_loss": 0.04042724519968033,
1204
+ "eval_runtime": 36.0075,
1205
+ "eval_samples_per_second": 19.746,
1206
+ "eval_steps_per_second": 19.746,
1207
+ "step": 154
1208
+ },
1209
+ {
1210
+ "epoch": 1.4695207762387972,
1211
+ "grad_norm": 0.083984375,
1212
+ "learning_rate": 0.00010771754621266466,
1213
+ "loss": 0.0335,
1214
+ "step": 155
1215
+ },
1216
+ {
1217
+ "epoch": 1.4790015554403377,
1218
+ "grad_norm": 0.07470703125,
1219
+ "learning_rate": 0.00010669019663434117,
1220
+ "loss": 0.0268,
1221
+ "step": 156
1222
+ },
1223
+ {
1224
+ "epoch": 1.4884823346418785,
1225
+ "grad_norm": 0.0849609375,
1226
+ "learning_rate": 0.00010566213725746506,
1227
+ "loss": 0.0334,
1228
+ "step": 157
1229
+ },
1230
+ {
1231
+ "epoch": 1.497963113843419,
1232
+ "grad_norm": 0.0751953125,
1233
+ "learning_rate": 0.00010463347715432488,
1234
+ "loss": 0.0283,
1235
+ "step": 158
1236
+ },
1237
+ {
1238
+ "epoch": 1.5074438930449596,
1239
+ "grad_norm": 0.07421875,
1240
+ "learning_rate": 0.00010360432546094341,
1241
+ "loss": 0.0284,
1242
+ "step": 159
1243
+ }
1244
+ ],
1245
+ "logging_steps": 1,
1246
+ "max_steps": 315,
1247
+ "num_input_tokens_seen": 0,
1248
+ "num_train_epochs": 3,
1249
+ "save_steps": 53,
1250
+ "stateful_callbacks": {
1251
+ "TrainerControl": {
1252
+ "args": {
1253
+ "should_epoch_stop": false,
1254
+ "should_evaluate": false,
1255
+ "should_log": false,
1256
+ "should_save": true,
1257
+ "should_training_stop": false
1258
+ },
1259
+ "attributes": {}
1260
+ }
1261
+ },
1262
+ "total_flos": 2.8497058955054285e+17,
1263
+ "train_batch_size": 1,
1264
+ "trial_name": null,
1265
+ "trial_params": null
1266
+ }
checkpoint-159/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c51879fef6458d108abda667041e5749acf5fcdaa68cbc3d11f59cd677f2e93
3
+ size 6072
checkpoint-212/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
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 0.11.1
checkpoint-212/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-212/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e733a97c1ac02f9195e5ddce0f58371d40a4dbcac317df122145c4444823cd0
3
+ size 335605144
checkpoint-212/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0144874f7a2a7ce90d5578f70d8cfa3aa3c2a0b74dd657b4d7c2ec25c67fdf77
3
+ size 1342452986
checkpoint-212/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1bdd5b23fb49070f9a99ab4851de295ace145e5a60adf0ae552896051705539
3
+ size 14244
checkpoint-212/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a214afa28cba8a61e5d4cc1d5f61fa340ffd678157072501b9e9dc32eae8fe12
3
+ size 1064
checkpoint-212/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-212/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-212/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-212/trainer_state.json ADDED
@@ -0,0 +1,1677 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0099251907266127,
5
+ "eval_steps": 11,
6
+ "global_step": 212,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009480779201540626,
13
+ "grad_norm": 2.265625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.5339,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009480779201540626,
20
+ "eval_loss": 0.5036121606826782,
21
+ "eval_runtime": 36.0149,
22
+ "eval_samples_per_second": 19.742,
23
+ "eval_steps_per_second": 19.742,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.018961558403081252,
28
+ "grad_norm": 2.1875,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.502,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02844233760462188,
35
+ "grad_norm": 1.890625,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.4769,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.037923116806162505,
42
+ "grad_norm": 1.0234375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.2922,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.04740389600770313,
49
+ "grad_norm": 1.5234375,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.2162,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.05688467520924376,
56
+ "grad_norm": 0.59375,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.1685,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.06636545441078438,
63
+ "grad_norm": 0.359375,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.1208,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.07584623361232501,
70
+ "grad_norm": 0.32421875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.1147,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.08532701281386564,
77
+ "grad_norm": 0.302734375,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.0983,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.09480779201540626,
84
+ "grad_norm": 0.25390625,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.0827,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.10428857121694689,
91
+ "grad_norm": 0.232421875,
92
+ "learning_rate": 0.00019999469523400122,
93
+ "loss": 0.0879,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10428857121694689,
98
+ "eval_loss": 0.08134982734918594,
99
+ "eval_runtime": 35.8683,
100
+ "eval_samples_per_second": 19.823,
101
+ "eval_steps_per_second": 19.823,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.11376935041848751,
106
+ "grad_norm": 0.2265625,
107
+ "learning_rate": 0.00019997878149881574,
108
+ "loss": 0.0831,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.12325012962002814,
113
+ "grad_norm": 0.21875,
114
+ "learning_rate": 0.0001999522604828164,
115
+ "loss": 0.0756,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.13273090882156877,
120
+ "grad_norm": 0.2255859375,
121
+ "learning_rate": 0.00019991513499975882,
122
+ "loss": 0.0835,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.1422116880231094,
127
+ "grad_norm": 0.234375,
128
+ "learning_rate": 0.00019986740898848306,
129
+ "loss": 0.0732,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.15169246722465002,
134
+ "grad_norm": 0.1650390625,
135
+ "learning_rate": 0.00019980908751249555,
136
+ "loss": 0.0739,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.16117324642619066,
141
+ "grad_norm": 0.14453125,
142
+ "learning_rate": 0.00019974017675943192,
143
+ "loss": 0.0698,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.17065402562773127,
148
+ "grad_norm": 0.1767578125,
149
+ "learning_rate": 0.0001996606840404006,
150
+ "loss": 0.072,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.1801348048292719,
155
+ "grad_norm": 0.1328125,
156
+ "learning_rate": 0.00019957061778920701,
157
+ "loss": 0.0556,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.18961558403081252,
162
+ "grad_norm": 0.1455078125,
163
+ "learning_rate": 0.0001994699875614589,
164
+ "loss": 0.0685,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.19909636323235316,
169
+ "grad_norm": 0.1455078125,
170
+ "learning_rate": 0.00019935880403355253,
171
+ "loss": 0.0598,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.20857714243389378,
176
+ "grad_norm": 0.13671875,
177
+ "learning_rate": 0.00019923707900153982,
178
+ "loss": 0.0582,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.20857714243389378,
183
+ "eval_loss": 0.06287878006696701,
184
+ "eval_runtime": 35.7847,
185
+ "eval_samples_per_second": 19.869,
186
+ "eval_steps_per_second": 19.869,
187
+ "step": 22
188
+ },
189
+ {
190
+ "epoch": 0.21805792163543442,
191
+ "grad_norm": 0.15234375,
192
+ "learning_rate": 0.00019910482537987702,
193
+ "loss": 0.0644,
194
+ "step": 23
195
+ },
196
+ {
197
+ "epoch": 0.22753870083697503,
198
+ "grad_norm": 0.130859375,
199
+ "learning_rate": 0.0001989620572000544,
200
+ "loss": 0.0615,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.23701948003851567,
205
+ "grad_norm": 0.13671875,
206
+ "learning_rate": 0.00019880878960910772,
207
+ "loss": 0.0686,
208
+ "step": 25
209
+ },
210
+ {
211
+ "epoch": 0.24650025924005628,
212
+ "grad_norm": 0.14453125,
213
+ "learning_rate": 0.00019864503886801106,
214
+ "loss": 0.068,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.2559810384415969,
219
+ "grad_norm": 0.12353515625,
220
+ "learning_rate": 0.00019847082234995171,
221
+ "loss": 0.0525,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.26546181764313753,
226
+ "grad_norm": 0.10791015625,
227
+ "learning_rate": 0.00019828615853848688,
228
+ "loss": 0.0541,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.27494259684467814,
233
+ "grad_norm": 0.12060546875,
234
+ "learning_rate": 0.00019809106702558277,
235
+ "loss": 0.0522,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.2844233760462188,
240
+ "grad_norm": 0.11669921875,
241
+ "learning_rate": 0.0001978855685095358,
242
+ "loss": 0.0526,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.2939041552477594,
247
+ "grad_norm": 0.140625,
248
+ "learning_rate": 0.00019766968479277683,
249
+ "loss": 0.0626,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.30338493444930004,
254
+ "grad_norm": 0.134765625,
255
+ "learning_rate": 0.00019744343877955788,
256
+ "loss": 0.0598,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.3128657136508407,
261
+ "grad_norm": 0.1220703125,
262
+ "learning_rate": 0.00019720685447352209,
263
+ "loss": 0.06,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.3128657136508407,
268
+ "eval_loss": 0.05662544071674347,
269
+ "eval_runtime": 35.8251,
270
+ "eval_samples_per_second": 19.846,
271
+ "eval_steps_per_second": 19.846,
272
+ "step": 33
273
+ },
274
+ {
275
+ "epoch": 0.3223464928523813,
276
+ "grad_norm": 0.14453125,
277
+ "learning_rate": 0.0001969599569751571,
278
+ "loss": 0.0555,
279
+ "step": 34
280
+ },
281
+ {
282
+ "epoch": 0.33182727205392193,
283
+ "grad_norm": 0.12158203125,
284
+ "learning_rate": 0.00019670277247913205,
285
+ "loss": 0.0615,
286
+ "step": 35
287
+ },
288
+ {
289
+ "epoch": 0.34130805125546254,
290
+ "grad_norm": 0.11279296875,
291
+ "learning_rate": 0.0001964353282715183,
292
+ "loss": 0.0499,
293
+ "step": 36
294
+ },
295
+ {
296
+ "epoch": 0.3507888304570032,
297
+ "grad_norm": 0.12158203125,
298
+ "learning_rate": 0.00019615765272689461,
299
+ "loss": 0.0555,
300
+ "step": 37
301
+ },
302
+ {
303
+ "epoch": 0.3602696096585438,
304
+ "grad_norm": 0.11572265625,
305
+ "learning_rate": 0.00019586977530533677,
306
+ "loss": 0.0613,
307
+ "step": 38
308
+ },
309
+ {
310
+ "epoch": 0.36975038886008443,
311
+ "grad_norm": 0.1044921875,
312
+ "learning_rate": 0.00019557172654929196,
313
+ "loss": 0.0574,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.37923116806162505,
318
+ "grad_norm": 0.1025390625,
319
+ "learning_rate": 0.00019526353808033825,
320
+ "loss": 0.0527,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.3887119472631657,
325
+ "grad_norm": 0.1298828125,
326
+ "learning_rate": 0.00019494524259582992,
327
+ "loss": 0.0561,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.3981927264647063,
332
+ "grad_norm": 0.10302734375,
333
+ "learning_rate": 0.00019461687386542826,
334
+ "loss": 0.0487,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.40767350566624694,
339
+ "grad_norm": 0.11279296875,
340
+ "learning_rate": 0.00019427846672751873,
341
+ "loss": 0.0476,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.41715428486778755,
346
+ "grad_norm": 0.1240234375,
347
+ "learning_rate": 0.00019393005708551498,
348
+ "loss": 0.0593,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.41715428486778755,
353
+ "eval_loss": 0.051377832889556885,
354
+ "eval_runtime": 35.8632,
355
+ "eval_samples_per_second": 19.825,
356
+ "eval_steps_per_second": 19.825,
357
+ "step": 44
358
+ },
359
+ {
360
+ "epoch": 0.4266350640693282,
361
+ "grad_norm": 0.10888671875,
362
+ "learning_rate": 0.00019357168190404936,
363
+ "loss": 0.0498,
364
+ "step": 45
365
+ },
366
+ {
367
+ "epoch": 0.43611584327086883,
368
+ "grad_norm": 0.1171875,
369
+ "learning_rate": 0.00019320337920505153,
370
+ "loss": 0.0599,
371
+ "step": 46
372
+ },
373
+ {
374
+ "epoch": 0.44559662247240944,
375
+ "grad_norm": 0.11669921875,
376
+ "learning_rate": 0.00019282518806371414,
377
+ "loss": 0.0595,
378
+ "step": 47
379
+ },
380
+ {
381
+ "epoch": 0.45507740167395005,
382
+ "grad_norm": 0.123046875,
383
+ "learning_rate": 0.0001924371486043473,
384
+ "loss": 0.0648,
385
+ "step": 48
386
+ },
387
+ {
388
+ "epoch": 0.4645581808754907,
389
+ "grad_norm": 0.1025390625,
390
+ "learning_rate": 0.0001920393019961217,
391
+ "loss": 0.0506,
392
+ "step": 49
393
+ },
394
+ {
395
+ "epoch": 0.47403896007703133,
396
+ "grad_norm": 0.1171875,
397
+ "learning_rate": 0.0001916316904487005,
398
+ "loss": 0.0568,
399
+ "step": 50
400
+ },
401
+ {
402
+ "epoch": 0.48351973927857195,
403
+ "grad_norm": 0.09521484375,
404
+ "learning_rate": 0.00019121435720776122,
405
+ "loss": 0.0476,
406
+ "step": 51
407
+ },
408
+ {
409
+ "epoch": 0.49300051848011256,
410
+ "grad_norm": 0.11474609375,
411
+ "learning_rate": 0.0001907873465504076,
412
+ "loss": 0.0504,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 0.5024812976816532,
417
+ "grad_norm": 0.11572265625,
418
+ "learning_rate": 0.00019035070378047204,
419
+ "loss": 0.0486,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 0.5119620768831938,
424
+ "grad_norm": 0.10986328125,
425
+ "learning_rate": 0.00018990447522370884,
426
+ "loss": 0.0467,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 0.5214428560847345,
431
+ "grad_norm": 0.12158203125,
432
+ "learning_rate": 0.00018944870822287956,
433
+ "loss": 0.054,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 0.5214428560847345,
438
+ "eval_loss": 0.048270147293806076,
439
+ "eval_runtime": 35.8252,
440
+ "eval_samples_per_second": 19.846,
441
+ "eval_steps_per_second": 19.846,
442
+ "step": 55
443
+ },
444
+ {
445
+ "epoch": 0.5309236352862751,
446
+ "grad_norm": 0.09912109375,
447
+ "learning_rate": 0.00018898345113272998,
448
+ "loss": 0.0442,
449
+ "step": 56
450
+ },
451
+ {
452
+ "epoch": 0.5404044144878157,
453
+ "grad_norm": 0.1005859375,
454
+ "learning_rate": 0.00018850875331485995,
455
+ "loss": 0.0415,
456
+ "step": 57
457
+ },
458
+ {
459
+ "epoch": 0.5498851936893563,
460
+ "grad_norm": 0.1142578125,
461
+ "learning_rate": 0.00018802466513248632,
462
+ "loss": 0.0474,
463
+ "step": 58
464
+ },
465
+ {
466
+ "epoch": 0.559365972890897,
467
+ "grad_norm": 0.1103515625,
468
+ "learning_rate": 0.00018753123794509974,
469
+ "loss": 0.0501,
470
+ "step": 59
471
+ },
472
+ {
473
+ "epoch": 0.5688467520924376,
474
+ "grad_norm": 0.10986328125,
475
+ "learning_rate": 0.00018702852410301554,
476
+ "loss": 0.0509,
477
+ "step": 60
478
+ },
479
+ {
480
+ "epoch": 0.5783275312939782,
481
+ "grad_norm": 0.119140625,
482
+ "learning_rate": 0.0001865165769418196,
483
+ "loss": 0.054,
484
+ "step": 61
485
+ },
486
+ {
487
+ "epoch": 0.5878083104955188,
488
+ "grad_norm": 0.12353515625,
489
+ "learning_rate": 0.00018599545077670985,
490
+ "loss": 0.0496,
491
+ "step": 62
492
+ },
493
+ {
494
+ "epoch": 0.5972890896970595,
495
+ "grad_norm": 0.09619140625,
496
+ "learning_rate": 0.0001854652008967335,
497
+ "loss": 0.0479,
498
+ "step": 63
499
+ },
500
+ {
501
+ "epoch": 0.6067698688986001,
502
+ "grad_norm": 0.1123046875,
503
+ "learning_rate": 0.00018492588355892124,
504
+ "loss": 0.0508,
505
+ "step": 64
506
+ },
507
+ {
508
+ "epoch": 0.6162506481001407,
509
+ "grad_norm": 0.125,
510
+ "learning_rate": 0.00018437755598231856,
511
+ "loss": 0.0499,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 0.6257314273016814,
516
+ "grad_norm": 0.0986328125,
517
+ "learning_rate": 0.00018382027634191524,
518
+ "loss": 0.0459,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 0.6257314273016814,
523
+ "eval_loss": 0.04686620458960533,
524
+ "eval_runtime": 35.9226,
525
+ "eval_samples_per_second": 19.793,
526
+ "eval_steps_per_second": 19.793,
527
+ "step": 66
528
+ },
529
+ {
530
+ "epoch": 0.635212206503222,
531
+ "grad_norm": 0.12109375,
532
+ "learning_rate": 0.00018325410376247294,
533
+ "loss": 0.0473,
534
+ "step": 67
535
+ },
536
+ {
537
+ "epoch": 0.6446929857047626,
538
+ "grad_norm": 0.1103515625,
539
+ "learning_rate": 0.0001826790983122527,
540
+ "loss": 0.0443,
541
+ "step": 68
542
+ },
543
+ {
544
+ "epoch": 0.6541737649063032,
545
+ "grad_norm": 0.11279296875,
546
+ "learning_rate": 0.00018209532099664174,
547
+ "loss": 0.0508,
548
+ "step": 69
549
+ },
550
+ {
551
+ "epoch": 0.6636545441078439,
552
+ "grad_norm": 0.11083984375,
553
+ "learning_rate": 0.00018150283375168114,
554
+ "loss": 0.0485,
555
+ "step": 70
556
+ },
557
+ {
558
+ "epoch": 0.6731353233093845,
559
+ "grad_norm": 0.10693359375,
560
+ "learning_rate": 0.00018090169943749476,
561
+ "loss": 0.0535,
562
+ "step": 71
563
+ },
564
+ {
565
+ "epoch": 0.6826161025109251,
566
+ "grad_norm": 0.10888671875,
567
+ "learning_rate": 0.00018029198183161998,
568
+ "loss": 0.0617,
569
+ "step": 72
570
+ },
571
+ {
572
+ "epoch": 0.6920968817124658,
573
+ "grad_norm": 0.09521484375,
574
+ "learning_rate": 0.00017967374562224132,
575
+ "loss": 0.0477,
576
+ "step": 73
577
+ },
578
+ {
579
+ "epoch": 0.7015776609140064,
580
+ "grad_norm": 0.0966796875,
581
+ "learning_rate": 0.00017904705640132718,
582
+ "loss": 0.0545,
583
+ "step": 74
584
+ },
585
+ {
586
+ "epoch": 0.711058440115547,
587
+ "grad_norm": 0.09423828125,
588
+ "learning_rate": 0.00017841198065767107,
589
+ "loss": 0.0396,
590
+ "step": 75
591
+ },
592
+ {
593
+ "epoch": 0.7205392193170876,
594
+ "grad_norm": 0.0947265625,
595
+ "learning_rate": 0.00017776858576983712,
596
+ "loss": 0.0483,
597
+ "step": 76
598
+ },
599
+ {
600
+ "epoch": 0.7300199985186282,
601
+ "grad_norm": 0.09326171875,
602
+ "learning_rate": 0.0001771169399990119,
603
+ "loss": 0.0397,
604
+ "step": 77
605
+ },
606
+ {
607
+ "epoch": 0.7300199985186282,
608
+ "eval_loss": 0.046032145619392395,
609
+ "eval_runtime": 35.9702,
610
+ "eval_samples_per_second": 19.766,
611
+ "eval_steps_per_second": 19.766,
612
+ "step": 77
613
+ },
614
+ {
615
+ "epoch": 0.7395007777201689,
616
+ "grad_norm": 0.09423828125,
617
+ "learning_rate": 0.00017645711248176195,
618
+ "loss": 0.0414,
619
+ "step": 78
620
+ },
621
+ {
622
+ "epoch": 0.7489815569217095,
623
+ "grad_norm": 0.10107421875,
624
+ "learning_rate": 0.00017578917322269886,
625
+ "loss": 0.0447,
626
+ "step": 79
627
+ },
628
+ {
629
+ "epoch": 0.7584623361232501,
630
+ "grad_norm": 0.0966796875,
631
+ "learning_rate": 0.00017511319308705198,
632
+ "loss": 0.0404,
633
+ "step": 80
634
+ },
635
+ {
636
+ "epoch": 0.7679431153247908,
637
+ "grad_norm": 0.099609375,
638
+ "learning_rate": 0.0001744292437931502,
639
+ "loss": 0.0409,
640
+ "step": 81
641
+ },
642
+ {
643
+ "epoch": 0.7774238945263314,
644
+ "grad_norm": 0.12890625,
645
+ "learning_rate": 0.00017373739790481262,
646
+ "loss": 0.0482,
647
+ "step": 82
648
+ },
649
+ {
650
+ "epoch": 0.786904673727872,
651
+ "grad_norm": 0.09375,
652
+ "learning_rate": 0.00017303772882365016,
653
+ "loss": 0.0356,
654
+ "step": 83
655
+ },
656
+ {
657
+ "epoch": 0.7963854529294127,
658
+ "grad_norm": 0.1103515625,
659
+ "learning_rate": 0.00017233031078127788,
660
+ "loss": 0.0467,
661
+ "step": 84
662
+ },
663
+ {
664
+ "epoch": 0.8058662321309532,
665
+ "grad_norm": 0.11767578125,
666
+ "learning_rate": 0.00017161521883143934,
667
+ "loss": 0.0537,
668
+ "step": 85
669
+ },
670
+ {
671
+ "epoch": 0.8153470113324939,
672
+ "grad_norm": 0.095703125,
673
+ "learning_rate": 0.00017089252884204377,
674
+ "loss": 0.0477,
675
+ "step": 86
676
+ },
677
+ {
678
+ "epoch": 0.8248277905340345,
679
+ "grad_norm": 0.09521484375,
680
+ "learning_rate": 0.0001701623174871168,
681
+ "loss": 0.0466,
682
+ "step": 87
683
+ },
684
+ {
685
+ "epoch": 0.8343085697355751,
686
+ "grad_norm": 0.09326171875,
687
+ "learning_rate": 0.0001694246622386658,
688
+ "loss": 0.0453,
689
+ "step": 88
690
+ },
691
+ {
692
+ "epoch": 0.8343085697355751,
693
+ "eval_loss": 0.04489152505993843,
694
+ "eval_runtime": 36.0012,
695
+ "eval_samples_per_second": 19.749,
696
+ "eval_steps_per_second": 19.749,
697
+ "step": 88
698
+ },
699
+ {
700
+ "epoch": 0.8437893489371158,
701
+ "grad_norm": 0.08349609375,
702
+ "learning_rate": 0.00016867964135846043,
703
+ "loss": 0.039,
704
+ "step": 89
705
+ },
706
+ {
707
+ "epoch": 0.8532701281386564,
708
+ "grad_norm": 0.10400390625,
709
+ "learning_rate": 0.00016792733388972932,
710
+ "loss": 0.0521,
711
+ "step": 90
712
+ },
713
+ {
714
+ "epoch": 0.862750907340197,
715
+ "grad_norm": 0.0849609375,
716
+ "learning_rate": 0.0001671678196487741,
717
+ "loss": 0.0481,
718
+ "step": 91
719
+ },
720
+ {
721
+ "epoch": 0.8722316865417377,
722
+ "grad_norm": 0.09814453125,
723
+ "learning_rate": 0.00016640117921650117,
724
+ "loss": 0.0509,
725
+ "step": 92
726
+ },
727
+ {
728
+ "epoch": 0.8817124657432783,
729
+ "grad_norm": 0.0927734375,
730
+ "learning_rate": 0.00016562749392987254,
731
+ "loss": 0.0413,
732
+ "step": 93
733
+ },
734
+ {
735
+ "epoch": 0.8911932449448189,
736
+ "grad_norm": 0.08740234375,
737
+ "learning_rate": 0.0001648468458732762,
738
+ "loss": 0.0405,
739
+ "step": 94
740
+ },
741
+ {
742
+ "epoch": 0.9006740241463596,
743
+ "grad_norm": 0.09228515625,
744
+ "learning_rate": 0.00016405931786981755,
745
+ "loss": 0.0458,
746
+ "step": 95
747
+ },
748
+ {
749
+ "epoch": 0.9101548033479001,
750
+ "grad_norm": 0.1005859375,
751
+ "learning_rate": 0.00016326499347253207,
752
+ "loss": 0.0457,
753
+ "step": 96
754
+ },
755
+ {
756
+ "epoch": 0.9196355825494408,
757
+ "grad_norm": 0.09619140625,
758
+ "learning_rate": 0.00016246395695552085,
759
+ "loss": 0.0439,
760
+ "step": 97
761
+ },
762
+ {
763
+ "epoch": 0.9291163617509814,
764
+ "grad_norm": 0.08740234375,
765
+ "learning_rate": 0.00016165629330500952,
766
+ "loss": 0.0389,
767
+ "step": 98
768
+ },
769
+ {
770
+ "epoch": 0.938597140952522,
771
+ "grad_norm": 0.08935546875,
772
+ "learning_rate": 0.0001608420882103315,
773
+ "loss": 0.04,
774
+ "step": 99
775
+ },
776
+ {
777
+ "epoch": 0.938597140952522,
778
+ "eval_loss": 0.04293662682175636,
779
+ "eval_runtime": 36.2853,
780
+ "eval_samples_per_second": 19.595,
781
+ "eval_steps_per_second": 19.595,
782
+ "step": 99
783
+ },
784
+ {
785
+ "epoch": 0.9480779201540627,
786
+ "grad_norm": 0.09326171875,
787
+ "learning_rate": 0.00016002142805483685,
788
+ "loss": 0.0418,
789
+ "step": 100
790
+ },
791
+ {
792
+ "epoch": 0.9575586993556033,
793
+ "grad_norm": 0.0830078125,
794
+ "learning_rate": 0.0001591943999067273,
795
+ "loss": 0.0406,
796
+ "step": 101
797
+ },
798
+ {
799
+ "epoch": 0.9670394785571439,
800
+ "grad_norm": 0.09375,
801
+ "learning_rate": 0.00015836109150981886,
802
+ "loss": 0.0418,
803
+ "step": 102
804
+ },
805
+ {
806
+ "epoch": 0.9765202577586846,
807
+ "grad_norm": 0.09765625,
808
+ "learning_rate": 0.00015752159127423263,
809
+ "loss": 0.0395,
810
+ "step": 103
811
+ },
812
+ {
813
+ "epoch": 0.9860010369602251,
814
+ "grad_norm": 0.08154296875,
815
+ "learning_rate": 0.0001566759882670146,
816
+ "loss": 0.0375,
817
+ "step": 104
818
+ },
819
+ {
820
+ "epoch": 0.9954818161617658,
821
+ "grad_norm": 0.1005859375,
822
+ "learning_rate": 0.00015582437220268647,
823
+ "loss": 0.0463,
824
+ "step": 105
825
+ },
826
+ {
827
+ "epoch": 1.0049625953633063,
828
+ "grad_norm": 0.07666015625,
829
+ "learning_rate": 0.0001549668334337271,
830
+ "loss": 0.0346,
831
+ "step": 106
832
+ },
833
+ {
834
+ "epoch": 1.0144433745648471,
835
+ "grad_norm": 0.07763671875,
836
+ "learning_rate": 0.0001541034629409865,
837
+ "loss": 0.0322,
838
+ "step": 107
839
+ },
840
+ {
841
+ "epoch": 1.0239241537663877,
842
+ "grad_norm": 0.08154296875,
843
+ "learning_rate": 0.00015323435232403337,
844
+ "loss": 0.0328,
845
+ "step": 108
846
+ },
847
+ {
848
+ "epoch": 1.0334049329679282,
849
+ "grad_norm": 0.06591796875,
850
+ "learning_rate": 0.00015235959379143678,
851
+ "loss": 0.0299,
852
+ "step": 109
853
+ },
854
+ {
855
+ "epoch": 1.042885712169469,
856
+ "grad_norm": 0.08544921875,
857
+ "learning_rate": 0.0001514792801509831,
858
+ "loss": 0.0338,
859
+ "step": 110
860
+ },
861
+ {
862
+ "epoch": 1.042885712169469,
863
+ "eval_loss": 0.04179221764206886,
864
+ "eval_runtime": 35.8658,
865
+ "eval_samples_per_second": 19.824,
866
+ "eval_steps_per_second": 19.824,
867
+ "step": 110
868
+ },
869
+ {
870
+ "epoch": 1.0523664913710096,
871
+ "grad_norm": 0.0830078125,
872
+ "learning_rate": 0.00015059350479982965,
873
+ "loss": 0.0281,
874
+ "step": 111
875
+ },
876
+ {
877
+ "epoch": 1.0618472705725501,
878
+ "grad_norm": 0.083984375,
879
+ "learning_rate": 0.0001497023617145958,
880
+ "loss": 0.03,
881
+ "step": 112
882
+ },
883
+ {
884
+ "epoch": 1.071328049774091,
885
+ "grad_norm": 0.0771484375,
886
+ "learning_rate": 0.0001488059454413923,
887
+ "loss": 0.0286,
888
+ "step": 113
889
+ },
890
+ {
891
+ "epoch": 1.0808088289756315,
892
+ "grad_norm": 0.0966796875,
893
+ "learning_rate": 0.00014790435108579048,
894
+ "loss": 0.0311,
895
+ "step": 114
896
+ },
897
+ {
898
+ "epoch": 1.090289608177172,
899
+ "grad_norm": 0.0869140625,
900
+ "learning_rate": 0.000146997674302732,
901
+ "loss": 0.0291,
902
+ "step": 115
903
+ },
904
+ {
905
+ "epoch": 1.0997703873787126,
906
+ "grad_norm": 0.08984375,
907
+ "learning_rate": 0.00014608601128638027,
908
+ "loss": 0.0281,
909
+ "step": 116
910
+ },
911
+ {
912
+ "epoch": 1.1092511665802534,
913
+ "grad_norm": 0.08837890625,
914
+ "learning_rate": 0.00014516945875991472,
915
+ "loss": 0.0322,
916
+ "step": 117
917
+ },
918
+ {
919
+ "epoch": 1.118731945781794,
920
+ "grad_norm": 0.083984375,
921
+ "learning_rate": 0.00014424811396526892,
922
+ "loss": 0.026,
923
+ "step": 118
924
+ },
925
+ {
926
+ "epoch": 1.1282127249833347,
927
+ "grad_norm": 0.08837890625,
928
+ "learning_rate": 0.00014332207465281364,
929
+ "loss": 0.0317,
930
+ "step": 119
931
+ },
932
+ {
933
+ "epoch": 1.1376935041848752,
934
+ "grad_norm": 0.09912109375,
935
+ "learning_rate": 0.0001423914390709861,
936
+ "loss": 0.0341,
937
+ "step": 120
938
+ },
939
+ {
940
+ "epoch": 1.1471742833864158,
941
+ "grad_norm": 0.095703125,
942
+ "learning_rate": 0.00014145630595586607,
943
+ "loss": 0.0322,
944
+ "step": 121
945
+ },
946
+ {
947
+ "epoch": 1.1471742833864158,
948
+ "eval_loss": 0.04224802553653717,
949
+ "eval_runtime": 35.7541,
950
+ "eval_samples_per_second": 19.886,
951
+ "eval_steps_per_second": 19.886,
952
+ "step": 121
953
+ },
954
+ {
955
+ "epoch": 1.1566550625879564,
956
+ "grad_norm": 0.07763671875,
957
+ "learning_rate": 0.00014051677452070065,
958
+ "loss": 0.0279,
959
+ "step": 122
960
+ },
961
+ {
962
+ "epoch": 1.1661358417894971,
963
+ "grad_norm": 0.08837890625,
964
+ "learning_rate": 0.00013957294444537808,
965
+ "loss": 0.0276,
966
+ "step": 123
967
+ },
968
+ {
969
+ "epoch": 1.1756166209910377,
970
+ "grad_norm": 0.099609375,
971
+ "learning_rate": 0.0001386249158658522,
972
+ "loss": 0.0399,
973
+ "step": 124
974
+ },
975
+ {
976
+ "epoch": 1.1850974001925783,
977
+ "grad_norm": 0.0888671875,
978
+ "learning_rate": 0.00013767278936351854,
979
+ "loss": 0.0327,
980
+ "step": 125
981
+ },
982
+ {
983
+ "epoch": 1.194578179394119,
984
+ "grad_norm": 0.078125,
985
+ "learning_rate": 0.00013671666595454295,
986
+ "loss": 0.0257,
987
+ "step": 126
988
+ },
989
+ {
990
+ "epoch": 1.2040589585956596,
991
+ "grad_norm": 0.078125,
992
+ "learning_rate": 0.00013575664707914448,
993
+ "loss": 0.0268,
994
+ "step": 127
995
+ },
996
+ {
997
+ "epoch": 1.2135397377972001,
998
+ "grad_norm": 0.0966796875,
999
+ "learning_rate": 0.0001347928345908329,
1000
+ "loss": 0.0368,
1001
+ "step": 128
1002
+ },
1003
+ {
1004
+ "epoch": 1.223020516998741,
1005
+ "grad_norm": 0.076171875,
1006
+ "learning_rate": 0.00013382533074560255,
1007
+ "loss": 0.0286,
1008
+ "step": 129
1009
+ },
1010
+ {
1011
+ "epoch": 1.2325012962002815,
1012
+ "grad_norm": 0.0888671875,
1013
+ "learning_rate": 0.0001328542381910835,
1014
+ "loss": 0.0304,
1015
+ "step": 130
1016
+ },
1017
+ {
1018
+ "epoch": 1.241982075401822,
1019
+ "grad_norm": 0.087890625,
1020
+ "learning_rate": 0.00013187965995565098,
1021
+ "loss": 0.0304,
1022
+ "step": 131
1023
+ },
1024
+ {
1025
+ "epoch": 1.2514628546033628,
1026
+ "grad_norm": 0.0732421875,
1027
+ "learning_rate": 0.00013090169943749476,
1028
+ "loss": 0.0275,
1029
+ "step": 132
1030
+ },
1031
+ {
1032
+ "epoch": 1.2514628546033628,
1033
+ "eval_loss": 0.04160289093852043,
1034
+ "eval_runtime": 35.8932,
1035
+ "eval_samples_per_second": 19.809,
1036
+ "eval_steps_per_second": 19.809,
1037
+ "step": 132
1038
+ },
1039
+ {
1040
+ "epoch": 1.2609436338049034,
1041
+ "grad_norm": 0.08203125,
1042
+ "learning_rate": 0.00012992046039364893,
1043
+ "loss": 0.0293,
1044
+ "step": 133
1045
+ },
1046
+ {
1047
+ "epoch": 1.270424413006444,
1048
+ "grad_norm": 0.087890625,
1049
+ "learning_rate": 0.0001289360469289838,
1050
+ "loss": 0.03,
1051
+ "step": 134
1052
+ },
1053
+ {
1054
+ "epoch": 1.2799051922079845,
1055
+ "grad_norm": 0.08203125,
1056
+ "learning_rate": 0.00012794856348516095,
1057
+ "loss": 0.028,
1058
+ "step": 135
1059
+ },
1060
+ {
1061
+ "epoch": 1.2893859714095253,
1062
+ "grad_norm": 0.0869140625,
1063
+ "learning_rate": 0.00012695811482955227,
1064
+ "loss": 0.0293,
1065
+ "step": 136
1066
+ },
1067
+ {
1068
+ "epoch": 1.2988667506110658,
1069
+ "grad_norm": 0.09228515625,
1070
+ "learning_rate": 0.00012596480604412484,
1071
+ "loss": 0.0341,
1072
+ "step": 137
1073
+ },
1074
+ {
1075
+ "epoch": 1.3083475298126066,
1076
+ "grad_norm": 0.07470703125,
1077
+ "learning_rate": 0.000124968742514292,
1078
+ "loss": 0.0259,
1079
+ "step": 138
1080
+ },
1081
+ {
1082
+ "epoch": 1.3178283090141472,
1083
+ "grad_norm": 0.10009765625,
1084
+ "learning_rate": 0.00012397002991773275,
1085
+ "loss": 0.0298,
1086
+ "step": 139
1087
+ },
1088
+ {
1089
+ "epoch": 1.3273090882156877,
1090
+ "grad_norm": 0.08837890625,
1091
+ "learning_rate": 0.0001229687742131796,
1092
+ "loss": 0.0285,
1093
+ "step": 140
1094
+ },
1095
+ {
1096
+ "epoch": 1.3367898674172283,
1097
+ "grad_norm": 0.091796875,
1098
+ "learning_rate": 0.00012196508162917677,
1099
+ "loss": 0.034,
1100
+ "step": 141
1101
+ },
1102
+ {
1103
+ "epoch": 1.346270646618769,
1104
+ "grad_norm": 0.0986328125,
1105
+ "learning_rate": 0.00012095905865281025,
1106
+ "loss": 0.0314,
1107
+ "step": 142
1108
+ },
1109
+ {
1110
+ "epoch": 1.3557514258203096,
1111
+ "grad_norm": 0.0947265625,
1112
+ "learning_rate": 0.00011995081201840956,
1113
+ "loss": 0.0322,
1114
+ "step": 143
1115
+ },
1116
+ {
1117
+ "epoch": 1.3557514258203096,
1118
+ "eval_loss": 0.041649721562862396,
1119
+ "eval_runtime": 35.8396,
1120
+ "eval_samples_per_second": 19.838,
1121
+ "eval_steps_per_second": 19.838,
1122
+ "step": 143
1123
+ },
1124
+ {
1125
+ "epoch": 1.3652322050218502,
1126
+ "grad_norm": 0.083984375,
1127
+ "learning_rate": 0.00011894044869622403,
1128
+ "loss": 0.0303,
1129
+ "step": 144
1130
+ },
1131
+ {
1132
+ "epoch": 1.374712984223391,
1133
+ "grad_norm": 0.07373046875,
1134
+ "learning_rate": 0.00011792807588107357,
1135
+ "loss": 0.0259,
1136
+ "step": 145
1137
+ },
1138
+ {
1139
+ "epoch": 1.3841937634249315,
1140
+ "grad_norm": 0.08740234375,
1141
+ "learning_rate": 0.00011691380098097597,
1142
+ "loss": 0.0334,
1143
+ "step": 146
1144
+ },
1145
+ {
1146
+ "epoch": 1.393674542626472,
1147
+ "grad_norm": 0.068359375,
1148
+ "learning_rate": 0.0001158977316057513,
1149
+ "loss": 0.0245,
1150
+ "step": 147
1151
+ },
1152
+ {
1153
+ "epoch": 1.4031553218280126,
1154
+ "grad_norm": 0.09423828125,
1155
+ "learning_rate": 0.00011487997555560503,
1156
+ "loss": 0.0322,
1157
+ "step": 148
1158
+ },
1159
+ {
1160
+ "epoch": 1.4126361010295534,
1161
+ "grad_norm": 0.0947265625,
1162
+ "learning_rate": 0.00011386064080969094,
1163
+ "loss": 0.0338,
1164
+ "step": 149
1165
+ },
1166
+ {
1167
+ "epoch": 1.422116880231094,
1168
+ "grad_norm": 0.09326171875,
1169
+ "learning_rate": 0.00011283983551465511,
1170
+ "loss": 0.0278,
1171
+ "step": 150
1172
+ },
1173
+ {
1174
+ "epoch": 1.4315976594326347,
1175
+ "grad_norm": 0.087890625,
1176
+ "learning_rate": 0.0001118176679731619,
1177
+ "loss": 0.0305,
1178
+ "step": 151
1179
+ },
1180
+ {
1181
+ "epoch": 1.4410784386341753,
1182
+ "grad_norm": 0.083984375,
1183
+ "learning_rate": 0.00011079424663240372,
1184
+ "loss": 0.0311,
1185
+ "step": 152
1186
+ },
1187
+ {
1188
+ "epoch": 1.4505592178357158,
1189
+ "grad_norm": 0.08154296875,
1190
+ "learning_rate": 0.00010976968007259519,
1191
+ "loss": 0.0298,
1192
+ "step": 153
1193
+ },
1194
+ {
1195
+ "epoch": 1.4600399970372564,
1196
+ "grad_norm": 0.072265625,
1197
+ "learning_rate": 0.00010874407699545328,
1198
+ "loss": 0.0266,
1199
+ "step": 154
1200
+ },
1201
+ {
1202
+ "epoch": 1.4600399970372564,
1203
+ "eval_loss": 0.04042724519968033,
1204
+ "eval_runtime": 36.0075,
1205
+ "eval_samples_per_second": 19.746,
1206
+ "eval_steps_per_second": 19.746,
1207
+ "step": 154
1208
+ },
1209
+ {
1210
+ "epoch": 1.4695207762387972,
1211
+ "grad_norm": 0.083984375,
1212
+ "learning_rate": 0.00010771754621266466,
1213
+ "loss": 0.0335,
1214
+ "step": 155
1215
+ },
1216
+ {
1217
+ "epoch": 1.4790015554403377,
1218
+ "grad_norm": 0.07470703125,
1219
+ "learning_rate": 0.00010669019663434117,
1220
+ "loss": 0.0268,
1221
+ "step": 156
1222
+ },
1223
+ {
1224
+ "epoch": 1.4884823346418785,
1225
+ "grad_norm": 0.0849609375,
1226
+ "learning_rate": 0.00010566213725746506,
1227
+ "loss": 0.0334,
1228
+ "step": 157
1229
+ },
1230
+ {
1231
+ "epoch": 1.497963113843419,
1232
+ "grad_norm": 0.0751953125,
1233
+ "learning_rate": 0.00010463347715432488,
1234
+ "loss": 0.0283,
1235
+ "step": 158
1236
+ },
1237
+ {
1238
+ "epoch": 1.5074438930449596,
1239
+ "grad_norm": 0.07421875,
1240
+ "learning_rate": 0.00010360432546094341,
1241
+ "loss": 0.0284,
1242
+ "step": 159
1243
+ },
1244
+ {
1245
+ "epoch": 1.5169246722465002,
1246
+ "grad_norm": 0.08154296875,
1247
+ "learning_rate": 0.00010257479136549889,
1248
+ "loss": 0.0306,
1249
+ "step": 160
1250
+ },
1251
+ {
1252
+ "epoch": 1.5264054514480407,
1253
+ "grad_norm": 0.091796875,
1254
+ "learning_rate": 0.00010154498409674051,
1255
+ "loss": 0.0347,
1256
+ "step": 161
1257
+ },
1258
+ {
1259
+ "epoch": 1.5358862306495815,
1260
+ "grad_norm": 0.087890625,
1261
+ "learning_rate": 0.00010051501291240008,
1262
+ "loss": 0.0343,
1263
+ "step": 162
1264
+ },
1265
+ {
1266
+ "epoch": 1.5453670098511223,
1267
+ "grad_norm": 0.08544921875,
1268
+ "learning_rate": 9.948498708759993e-05,
1269
+ "loss": 0.0313,
1270
+ "step": 163
1271
+ },
1272
+ {
1273
+ "epoch": 1.5548477890526629,
1274
+ "grad_norm": 0.0791015625,
1275
+ "learning_rate": 9.845501590325948e-05,
1276
+ "loss": 0.0284,
1277
+ "step": 164
1278
+ },
1279
+ {
1280
+ "epoch": 1.5643285682542034,
1281
+ "grad_norm": 0.076171875,
1282
+ "learning_rate": 9.742520863450115e-05,
1283
+ "loss": 0.0249,
1284
+ "step": 165
1285
+ },
1286
+ {
1287
+ "epoch": 1.5643285682542034,
1288
+ "eval_loss": 0.03973715007305145,
1289
+ "eval_runtime": 35.8478,
1290
+ "eval_samples_per_second": 19.834,
1291
+ "eval_steps_per_second": 19.834,
1292
+ "step": 165
1293
+ },
1294
+ {
1295
+ "epoch": 1.573809347455744,
1296
+ "grad_norm": 0.076171875,
1297
+ "learning_rate": 9.639567453905661e-05,
1298
+ "loss": 0.0294,
1299
+ "step": 166
1300
+ },
1301
+ {
1302
+ "epoch": 1.5832901266572845,
1303
+ "grad_norm": 0.0703125,
1304
+ "learning_rate": 9.536652284567513e-05,
1305
+ "loss": 0.0248,
1306
+ "step": 167
1307
+ },
1308
+ {
1309
+ "epoch": 1.5927709058588253,
1310
+ "grad_norm": 0.08251953125,
1311
+ "learning_rate": 9.433786274253495e-05,
1312
+ "loss": 0.03,
1313
+ "step": 168
1314
+ },
1315
+ {
1316
+ "epoch": 1.6022516850603659,
1317
+ "grad_norm": 0.07373046875,
1318
+ "learning_rate": 9.330980336565887e-05,
1319
+ "loss": 0.0269,
1320
+ "step": 169
1321
+ },
1322
+ {
1323
+ "epoch": 1.6117324642619066,
1324
+ "grad_norm": 0.10791015625,
1325
+ "learning_rate": 9.228245378733537e-05,
1326
+ "loss": 0.0323,
1327
+ "step": 170
1328
+ },
1329
+ {
1330
+ "epoch": 1.6212132434634472,
1331
+ "grad_norm": 0.08837890625,
1332
+ "learning_rate": 9.125592300454676e-05,
1333
+ "loss": 0.0328,
1334
+ "step": 171
1335
+ },
1336
+ {
1337
+ "epoch": 1.6306940226649878,
1338
+ "grad_norm": 0.076171875,
1339
+ "learning_rate": 9.023031992740488e-05,
1340
+ "loss": 0.0245,
1341
+ "step": 172
1342
+ },
1343
+ {
1344
+ "epoch": 1.6401748018665283,
1345
+ "grad_norm": 0.0791015625,
1346
+ "learning_rate": 8.920575336759629e-05,
1347
+ "loss": 0.0291,
1348
+ "step": 173
1349
+ },
1350
+ {
1351
+ "epoch": 1.6496555810680689,
1352
+ "grad_norm": 0.10107421875,
1353
+ "learning_rate": 8.818233202683814e-05,
1354
+ "loss": 0.0324,
1355
+ "step": 174
1356
+ },
1357
+ {
1358
+ "epoch": 1.6591363602696096,
1359
+ "grad_norm": 0.0859375,
1360
+ "learning_rate": 8.71601644853449e-05,
1361
+ "loss": 0.0294,
1362
+ "step": 175
1363
+ },
1364
+ {
1365
+ "epoch": 1.6686171394711504,
1366
+ "grad_norm": 0.0849609375,
1367
+ "learning_rate": 8.613935919030907e-05,
1368
+ "loss": 0.0292,
1369
+ "step": 176
1370
+ },
1371
+ {
1372
+ "epoch": 1.6686171394711504,
1373
+ "eval_loss": 0.03933083638548851,
1374
+ "eval_runtime": 36.0124,
1375
+ "eval_samples_per_second": 19.743,
1376
+ "eval_steps_per_second": 19.743,
1377
+ "step": 176
1378
+ },
1379
+ {
1380
+ "epoch": 1.678097918672691,
1381
+ "grad_norm": 0.07666015625,
1382
+ "learning_rate": 8.512002444439502e-05,
1383
+ "loss": 0.028,
1384
+ "step": 177
1385
+ },
1386
+ {
1387
+ "epoch": 1.6875786978742315,
1388
+ "grad_norm": 0.08984375,
1389
+ "learning_rate": 8.410226839424871e-05,
1390
+ "loss": 0.0312,
1391
+ "step": 178
1392
+ },
1393
+ {
1394
+ "epoch": 1.697059477075772,
1395
+ "grad_norm": 0.0732421875,
1396
+ "learning_rate": 8.308619901902406e-05,
1397
+ "loss": 0.0253,
1398
+ "step": 179
1399
+ },
1400
+ {
1401
+ "epoch": 1.7065402562773127,
1402
+ "grad_norm": 0.083984375,
1403
+ "learning_rate": 8.207192411892646e-05,
1404
+ "loss": 0.0278,
1405
+ "step": 180
1406
+ },
1407
+ {
1408
+ "epoch": 1.7160210354788534,
1409
+ "grad_norm": 0.08642578125,
1410
+ "learning_rate": 8.1059551303776e-05,
1411
+ "loss": 0.0275,
1412
+ "step": 181
1413
+ },
1414
+ {
1415
+ "epoch": 1.7255018146803942,
1416
+ "grad_norm": 0.07568359375,
1417
+ "learning_rate": 8.004918798159045e-05,
1418
+ "loss": 0.0265,
1419
+ "step": 182
1420
+ },
1421
+ {
1422
+ "epoch": 1.7349825938819348,
1423
+ "grad_norm": 0.076171875,
1424
+ "learning_rate": 7.904094134718976e-05,
1425
+ "loss": 0.0285,
1426
+ "step": 183
1427
+ },
1428
+ {
1429
+ "epoch": 1.7444633730834753,
1430
+ "grad_norm": 0.09228515625,
1431
+ "learning_rate": 7.803491837082324e-05,
1432
+ "loss": 0.0349,
1433
+ "step": 184
1434
+ },
1435
+ {
1436
+ "epoch": 1.7539441522850159,
1437
+ "grad_norm": 0.09521484375,
1438
+ "learning_rate": 7.703122578682046e-05,
1439
+ "loss": 0.0325,
1440
+ "step": 185
1441
+ },
1442
+ {
1443
+ "epoch": 1.7634249314865564,
1444
+ "grad_norm": 0.0751953125,
1445
+ "learning_rate": 7.602997008226726e-05,
1446
+ "loss": 0.0283,
1447
+ "step": 186
1448
+ },
1449
+ {
1450
+ "epoch": 1.7729057106880972,
1451
+ "grad_norm": 0.0869140625,
1452
+ "learning_rate": 7.5031257485708e-05,
1453
+ "loss": 0.031,
1454
+ "step": 187
1455
+ },
1456
+ {
1457
+ "epoch": 1.7729057106880972,
1458
+ "eval_loss": 0.03848842531442642,
1459
+ "eval_runtime": 35.9251,
1460
+ "eval_samples_per_second": 19.791,
1461
+ "eval_steps_per_second": 19.791,
1462
+ "step": 187
1463
+ },
1464
+ {
1465
+ "epoch": 1.7823864898896378,
1466
+ "grad_norm": 0.07861328125,
1467
+ "learning_rate": 7.403519395587521e-05,
1468
+ "loss": 0.03,
1469
+ "step": 188
1470
+ },
1471
+ {
1472
+ "epoch": 1.7918672690911785,
1473
+ "grad_norm": 0.07177734375,
1474
+ "learning_rate": 7.304188517044774e-05,
1475
+ "loss": 0.0281,
1476
+ "step": 189
1477
+ },
1478
+ {
1479
+ "epoch": 1.801348048292719,
1480
+ "grad_norm": 0.07568359375,
1481
+ "learning_rate": 7.205143651483906e-05,
1482
+ "loss": 0.0253,
1483
+ "step": 190
1484
+ },
1485
+ {
1486
+ "epoch": 1.8108288274942597,
1487
+ "grad_norm": 0.06787109375,
1488
+ "learning_rate": 7.106395307101621e-05,
1489
+ "loss": 0.0264,
1490
+ "step": 191
1491
+ },
1492
+ {
1493
+ "epoch": 1.8203096066958002,
1494
+ "grad_norm": 0.07177734375,
1495
+ "learning_rate": 7.007953960635109e-05,
1496
+ "loss": 0.0268,
1497
+ "step": 192
1498
+ },
1499
+ {
1500
+ "epoch": 1.8297903858973408,
1501
+ "grad_norm": 0.08740234375,
1502
+ "learning_rate": 6.909830056250527e-05,
1503
+ "loss": 0.0308,
1504
+ "step": 193
1505
+ },
1506
+ {
1507
+ "epoch": 1.8392711650988816,
1508
+ "grad_norm": 0.07275390625,
1509
+ "learning_rate": 6.812034004434903e-05,
1510
+ "loss": 0.0275,
1511
+ "step": 194
1512
+ },
1513
+ {
1514
+ "epoch": 1.8487519443004223,
1515
+ "grad_norm": 0.07568359375,
1516
+ "learning_rate": 6.714576180891654e-05,
1517
+ "loss": 0.0253,
1518
+ "step": 195
1519
+ },
1520
+ {
1521
+ "epoch": 1.858232723501963,
1522
+ "grad_norm": 0.07177734375,
1523
+ "learning_rate": 6.617466925439746e-05,
1524
+ "loss": 0.0262,
1525
+ "step": 196
1526
+ },
1527
+ {
1528
+ "epoch": 1.8677135027035034,
1529
+ "grad_norm": 0.06787109375,
1530
+ "learning_rate": 6.520716540916709e-05,
1531
+ "loss": 0.0257,
1532
+ "step": 197
1533
+ },
1534
+ {
1535
+ "epoch": 1.877194281905044,
1536
+ "grad_norm": 0.0751953125,
1537
+ "learning_rate": 6.424335292085553e-05,
1538
+ "loss": 0.0265,
1539
+ "step": 198
1540
+ },
1541
+ {
1542
+ "epoch": 1.877194281905044,
1543
+ "eval_loss": 0.037521231919527054,
1544
+ "eval_runtime": 36.0213,
1545
+ "eval_samples_per_second": 19.738,
1546
+ "eval_steps_per_second": 19.738,
1547
+ "step": 198
1548
+ },
1549
+ {
1550
+ "epoch": 1.8866750611065846,
1551
+ "grad_norm": 0.10107421875,
1552
+ "learning_rate": 6.32833340454571e-05,
1553
+ "loss": 0.0269,
1554
+ "step": 199
1555
+ },
1556
+ {
1557
+ "epoch": 1.8961558403081253,
1558
+ "grad_norm": 0.0751953125,
1559
+ "learning_rate": 6.232721063648148e-05,
1560
+ "loss": 0.0279,
1561
+ "step": 200
1562
+ },
1563
+ {
1564
+ "epoch": 1.905636619509666,
1565
+ "grad_norm": 0.0791015625,
1566
+ "learning_rate": 6.137508413414784e-05,
1567
+ "loss": 0.0301,
1568
+ "step": 201
1569
+ },
1570
+ {
1571
+ "epoch": 1.9151173987112067,
1572
+ "grad_norm": 0.0791015625,
1573
+ "learning_rate": 6.0427055554621913e-05,
1574
+ "loss": 0.0289,
1575
+ "step": 202
1576
+ },
1577
+ {
1578
+ "epoch": 1.9245981779127472,
1579
+ "grad_norm": 0.08349609375,
1580
+ "learning_rate": 5.948322547929939e-05,
1581
+ "loss": 0.0239,
1582
+ "step": 203
1583
+ },
1584
+ {
1585
+ "epoch": 1.9340789571142878,
1586
+ "grad_norm": 0.07373046875,
1587
+ "learning_rate": 5.854369404413398e-05,
1588
+ "loss": 0.023,
1589
+ "step": 204
1590
+ },
1591
+ {
1592
+ "epoch": 1.9435597363158283,
1593
+ "grad_norm": 0.080078125,
1594
+ "learning_rate": 5.7608560929013946e-05,
1595
+ "loss": 0.0274,
1596
+ "step": 205
1597
+ },
1598
+ {
1599
+ "epoch": 1.9530405155173691,
1600
+ "grad_norm": 0.08447265625,
1601
+ "learning_rate": 5.667792534718639e-05,
1602
+ "loss": 0.0308,
1603
+ "step": 206
1604
+ },
1605
+ {
1606
+ "epoch": 1.9625212947189097,
1607
+ "grad_norm": 0.0732421875,
1608
+ "learning_rate": 5.5751886034731115e-05,
1609
+ "loss": 0.0253,
1610
+ "step": 207
1611
+ },
1612
+ {
1613
+ "epoch": 1.9720020739204505,
1614
+ "grad_norm": 0.0732421875,
1615
+ "learning_rate": 5.483054124008528e-05,
1616
+ "loss": 0.0261,
1617
+ "step": 208
1618
+ },
1619
+ {
1620
+ "epoch": 1.981482853121991,
1621
+ "grad_norm": 0.07763671875,
1622
+ "learning_rate": 5.391398871361972e-05,
1623
+ "loss": 0.0273,
1624
+ "step": 209
1625
+ },
1626
+ {
1627
+ "epoch": 1.981482853121991,
1628
+ "eval_loss": 0.037543829530477524,
1629
+ "eval_runtime": 36.1289,
1630
+ "eval_samples_per_second": 19.68,
1631
+ "eval_steps_per_second": 19.68,
1632
+ "step": 209
1633
+ },
1634
+ {
1635
+ "epoch": 1.9909636323235316,
1636
+ "grad_norm": 0.07958984375,
1637
+ "learning_rate": 5.300232569726804e-05,
1638
+ "loss": 0.0284,
1639
+ "step": 210
1640
+ },
1641
+ {
1642
+ "epoch": 2.000444411525072,
1643
+ "grad_norm": 0.08544921875,
1644
+ "learning_rate": 5.2095648914209525e-05,
1645
+ "loss": 0.0338,
1646
+ "step": 211
1647
+ },
1648
+ {
1649
+ "epoch": 2.0099251907266127,
1650
+ "grad_norm": 0.06298828125,
1651
+ "learning_rate": 5.119405455860772e-05,
1652
+ "loss": 0.0198,
1653
+ "step": 212
1654
+ }
1655
+ ],
1656
+ "logging_steps": 1,
1657
+ "max_steps": 315,
1658
+ "num_input_tokens_seen": 0,
1659
+ "num_train_epochs": 3,
1660
+ "save_steps": 53,
1661
+ "stateful_callbacks": {
1662
+ "TrainerControl": {
1663
+ "args": {
1664
+ "should_epoch_stop": false,
1665
+ "should_evaluate": false,
1666
+ "should_log": false,
1667
+ "should_save": true,
1668
+ "should_training_stop": false
1669
+ },
1670
+ "attributes": {}
1671
+ }
1672
+ },
1673
+ "total_flos": 3.796062460921774e+17,
1674
+ "train_batch_size": 1,
1675
+ "trial_name": null,
1676
+ "trial_params": null
1677
+ }
checkpoint-212/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c51879fef6458d108abda667041e5749acf5fcdaa68cbc3d11f59cd677f2e93
3
+ size 6072
checkpoint-265/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
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 0.11.1
checkpoint-265/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-265/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39afb5390f451a35ade3915302c300354c2dc49046acf94d2605ec5bc387a208
3
+ size 335605144
checkpoint-265/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44206a2ce6805b8dfe694fce0ac4695295717a4eb24e99a5a4b4a7b2e2458789
3
+ size 1342453434
checkpoint-265/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2684837b23b307d7fca3b152356819680fd90890f91256acbf8c359c7179284f
3
+ size 14244
checkpoint-265/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:180da771da4514ced7b8aa789fc9f0fe493376eeccc8ade7d6e8771efc347274
3
+ size 1064
checkpoint-265/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-265/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-265/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-265/trainer_state.json ADDED
@@ -0,0 +1,2088 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.512406488408266,
5
+ "eval_steps": 11,
6
+ "global_step": 265,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009480779201540626,
13
+ "grad_norm": 2.265625,
14
+ "learning_rate": 2e-05,
15
+ "loss": 0.5339,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.009480779201540626,
20
+ "eval_loss": 0.5036121606826782,
21
+ "eval_runtime": 36.0149,
22
+ "eval_samples_per_second": 19.742,
23
+ "eval_steps_per_second": 19.742,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.018961558403081252,
28
+ "grad_norm": 2.1875,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.502,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.02844233760462188,
35
+ "grad_norm": 1.890625,
36
+ "learning_rate": 6e-05,
37
+ "loss": 0.4769,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.037923116806162505,
42
+ "grad_norm": 1.0234375,
43
+ "learning_rate": 8e-05,
44
+ "loss": 0.2922,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.04740389600770313,
49
+ "grad_norm": 1.5234375,
50
+ "learning_rate": 0.0001,
51
+ "loss": 0.2162,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.05688467520924376,
56
+ "grad_norm": 0.59375,
57
+ "learning_rate": 0.00012,
58
+ "loss": 0.1685,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.06636545441078438,
63
+ "grad_norm": 0.359375,
64
+ "learning_rate": 0.00014,
65
+ "loss": 0.1208,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.07584623361232501,
70
+ "grad_norm": 0.32421875,
71
+ "learning_rate": 0.00016,
72
+ "loss": 0.1147,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.08532701281386564,
77
+ "grad_norm": 0.302734375,
78
+ "learning_rate": 0.00018,
79
+ "loss": 0.0983,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.09480779201540626,
84
+ "grad_norm": 0.25390625,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.0827,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.10428857121694689,
91
+ "grad_norm": 0.232421875,
92
+ "learning_rate": 0.00019999469523400122,
93
+ "loss": 0.0879,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.10428857121694689,
98
+ "eval_loss": 0.08134982734918594,
99
+ "eval_runtime": 35.8683,
100
+ "eval_samples_per_second": 19.823,
101
+ "eval_steps_per_second": 19.823,
102
+ "step": 11
103
+ },
104
+ {
105
+ "epoch": 0.11376935041848751,
106
+ "grad_norm": 0.2265625,
107
+ "learning_rate": 0.00019997878149881574,
108
+ "loss": 0.0831,
109
+ "step": 12
110
+ },
111
+ {
112
+ "epoch": 0.12325012962002814,
113
+ "grad_norm": 0.21875,
114
+ "learning_rate": 0.0001999522604828164,
115
+ "loss": 0.0756,
116
+ "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.13273090882156877,
120
+ "grad_norm": 0.2255859375,
121
+ "learning_rate": 0.00019991513499975882,
122
+ "loss": 0.0835,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.1422116880231094,
127
+ "grad_norm": 0.234375,
128
+ "learning_rate": 0.00019986740898848306,
129
+ "loss": 0.0732,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.15169246722465002,
134
+ "grad_norm": 0.1650390625,
135
+ "learning_rate": 0.00019980908751249555,
136
+ "loss": 0.0739,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.16117324642619066,
141
+ "grad_norm": 0.14453125,
142
+ "learning_rate": 0.00019974017675943192,
143
+ "loss": 0.0698,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.17065402562773127,
148
+ "grad_norm": 0.1767578125,
149
+ "learning_rate": 0.0001996606840404006,
150
+ "loss": 0.072,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.1801348048292719,
155
+ "grad_norm": 0.1328125,
156
+ "learning_rate": 0.00019957061778920701,
157
+ "loss": 0.0556,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.18961558403081252,
162
+ "grad_norm": 0.1455078125,
163
+ "learning_rate": 0.0001994699875614589,
164
+ "loss": 0.0685,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.19909636323235316,
169
+ "grad_norm": 0.1455078125,
170
+ "learning_rate": 0.00019935880403355253,
171
+ "loss": 0.0598,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.20857714243389378,
176
+ "grad_norm": 0.13671875,
177
+ "learning_rate": 0.00019923707900153982,
178
+ "loss": 0.0582,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.20857714243389378,
183
+ "eval_loss": 0.06287878006696701,
184
+ "eval_runtime": 35.7847,
185
+ "eval_samples_per_second": 19.869,
186
+ "eval_steps_per_second": 19.869,
187
+ "step": 22
188
+ },
189
+ {
190
+ "epoch": 0.21805792163543442,
191
+ "grad_norm": 0.15234375,
192
+ "learning_rate": 0.00019910482537987702,
193
+ "loss": 0.0644,
194
+ "step": 23
195
+ },
196
+ {
197
+ "epoch": 0.22753870083697503,
198
+ "grad_norm": 0.130859375,
199
+ "learning_rate": 0.0001989620572000544,
200
+ "loss": 0.0615,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.23701948003851567,
205
+ "grad_norm": 0.13671875,
206
+ "learning_rate": 0.00019880878960910772,
207
+ "loss": 0.0686,
208
+ "step": 25
209
+ },
210
+ {
211
+ "epoch": 0.24650025924005628,
212
+ "grad_norm": 0.14453125,
213
+ "learning_rate": 0.00019864503886801106,
214
+ "loss": 0.068,
215
+ "step": 26
216
+ },
217
+ {
218
+ "epoch": 0.2559810384415969,
219
+ "grad_norm": 0.12353515625,
220
+ "learning_rate": 0.00019847082234995171,
221
+ "loss": 0.0525,
222
+ "step": 27
223
+ },
224
+ {
225
+ "epoch": 0.26546181764313753,
226
+ "grad_norm": 0.10791015625,
227
+ "learning_rate": 0.00019828615853848688,
228
+ "loss": 0.0541,
229
+ "step": 28
230
+ },
231
+ {
232
+ "epoch": 0.27494259684467814,
233
+ "grad_norm": 0.12060546875,
234
+ "learning_rate": 0.00019809106702558277,
235
+ "loss": 0.0522,
236
+ "step": 29
237
+ },
238
+ {
239
+ "epoch": 0.2844233760462188,
240
+ "grad_norm": 0.11669921875,
241
+ "learning_rate": 0.0001978855685095358,
242
+ "loss": 0.0526,
243
+ "step": 30
244
+ },
245
+ {
246
+ "epoch": 0.2939041552477594,
247
+ "grad_norm": 0.140625,
248
+ "learning_rate": 0.00019766968479277683,
249
+ "loss": 0.0626,
250
+ "step": 31
251
+ },
252
+ {
253
+ "epoch": 0.30338493444930004,
254
+ "grad_norm": 0.134765625,
255
+ "learning_rate": 0.00019744343877955788,
256
+ "loss": 0.0598,
257
+ "step": 32
258
+ },
259
+ {
260
+ "epoch": 0.3128657136508407,
261
+ "grad_norm": 0.1220703125,
262
+ "learning_rate": 0.00019720685447352209,
263
+ "loss": 0.06,
264
+ "step": 33
265
+ },
266
+ {
267
+ "epoch": 0.3128657136508407,
268
+ "eval_loss": 0.05662544071674347,
269
+ "eval_runtime": 35.8251,
270
+ "eval_samples_per_second": 19.846,
271
+ "eval_steps_per_second": 19.846,
272
+ "step": 33
273
+ },
274
+ {
275
+ "epoch": 0.3223464928523813,
276
+ "grad_norm": 0.14453125,
277
+ "learning_rate": 0.0001969599569751571,
278
+ "loss": 0.0555,
279
+ "step": 34
280
+ },
281
+ {
282
+ "epoch": 0.33182727205392193,
283
+ "grad_norm": 0.12158203125,
284
+ "learning_rate": 0.00019670277247913205,
285
+ "loss": 0.0615,
286
+ "step": 35
287
+ },
288
+ {
289
+ "epoch": 0.34130805125546254,
290
+ "grad_norm": 0.11279296875,
291
+ "learning_rate": 0.0001964353282715183,
292
+ "loss": 0.0499,
293
+ "step": 36
294
+ },
295
+ {
296
+ "epoch": 0.3507888304570032,
297
+ "grad_norm": 0.12158203125,
298
+ "learning_rate": 0.00019615765272689461,
299
+ "loss": 0.0555,
300
+ "step": 37
301
+ },
302
+ {
303
+ "epoch": 0.3602696096585438,
304
+ "grad_norm": 0.11572265625,
305
+ "learning_rate": 0.00019586977530533677,
306
+ "loss": 0.0613,
307
+ "step": 38
308
+ },
309
+ {
310
+ "epoch": 0.36975038886008443,
311
+ "grad_norm": 0.1044921875,
312
+ "learning_rate": 0.00019557172654929196,
313
+ "loss": 0.0574,
314
+ "step": 39
315
+ },
316
+ {
317
+ "epoch": 0.37923116806162505,
318
+ "grad_norm": 0.1025390625,
319
+ "learning_rate": 0.00019526353808033825,
320
+ "loss": 0.0527,
321
+ "step": 40
322
+ },
323
+ {
324
+ "epoch": 0.3887119472631657,
325
+ "grad_norm": 0.1298828125,
326
+ "learning_rate": 0.00019494524259582992,
327
+ "loss": 0.0561,
328
+ "step": 41
329
+ },
330
+ {
331
+ "epoch": 0.3981927264647063,
332
+ "grad_norm": 0.10302734375,
333
+ "learning_rate": 0.00019461687386542826,
334
+ "loss": 0.0487,
335
+ "step": 42
336
+ },
337
+ {
338
+ "epoch": 0.40767350566624694,
339
+ "grad_norm": 0.11279296875,
340
+ "learning_rate": 0.00019427846672751873,
341
+ "loss": 0.0476,
342
+ "step": 43
343
+ },
344
+ {
345
+ "epoch": 0.41715428486778755,
346
+ "grad_norm": 0.1240234375,
347
+ "learning_rate": 0.00019393005708551498,
348
+ "loss": 0.0593,
349
+ "step": 44
350
+ },
351
+ {
352
+ "epoch": 0.41715428486778755,
353
+ "eval_loss": 0.051377832889556885,
354
+ "eval_runtime": 35.8632,
355
+ "eval_samples_per_second": 19.825,
356
+ "eval_steps_per_second": 19.825,
357
+ "step": 44
358
+ },
359
+ {
360
+ "epoch": 0.4266350640693282,
361
+ "grad_norm": 0.10888671875,
362
+ "learning_rate": 0.00019357168190404936,
363
+ "loss": 0.0498,
364
+ "step": 45
365
+ },
366
+ {
367
+ "epoch": 0.43611584327086883,
368
+ "grad_norm": 0.1171875,
369
+ "learning_rate": 0.00019320337920505153,
370
+ "loss": 0.0599,
371
+ "step": 46
372
+ },
373
+ {
374
+ "epoch": 0.44559662247240944,
375
+ "grad_norm": 0.11669921875,
376
+ "learning_rate": 0.00019282518806371414,
377
+ "loss": 0.0595,
378
+ "step": 47
379
+ },
380
+ {
381
+ "epoch": 0.45507740167395005,
382
+ "grad_norm": 0.123046875,
383
+ "learning_rate": 0.0001924371486043473,
384
+ "loss": 0.0648,
385
+ "step": 48
386
+ },
387
+ {
388
+ "epoch": 0.4645581808754907,
389
+ "grad_norm": 0.1025390625,
390
+ "learning_rate": 0.0001920393019961217,
391
+ "loss": 0.0506,
392
+ "step": 49
393
+ },
394
+ {
395
+ "epoch": 0.47403896007703133,
396
+ "grad_norm": 0.1171875,
397
+ "learning_rate": 0.0001916316904487005,
398
+ "loss": 0.0568,
399
+ "step": 50
400
+ },
401
+ {
402
+ "epoch": 0.48351973927857195,
403
+ "grad_norm": 0.09521484375,
404
+ "learning_rate": 0.00019121435720776122,
405
+ "loss": 0.0476,
406
+ "step": 51
407
+ },
408
+ {
409
+ "epoch": 0.49300051848011256,
410
+ "grad_norm": 0.11474609375,
411
+ "learning_rate": 0.0001907873465504076,
412
+ "loss": 0.0504,
413
+ "step": 52
414
+ },
415
+ {
416
+ "epoch": 0.5024812976816532,
417
+ "grad_norm": 0.11572265625,
418
+ "learning_rate": 0.00019035070378047204,
419
+ "loss": 0.0486,
420
+ "step": 53
421
+ },
422
+ {
423
+ "epoch": 0.5119620768831938,
424
+ "grad_norm": 0.10986328125,
425
+ "learning_rate": 0.00018990447522370884,
426
+ "loss": 0.0467,
427
+ "step": 54
428
+ },
429
+ {
430
+ "epoch": 0.5214428560847345,
431
+ "grad_norm": 0.12158203125,
432
+ "learning_rate": 0.00018944870822287956,
433
+ "loss": 0.054,
434
+ "step": 55
435
+ },
436
+ {
437
+ "epoch": 0.5214428560847345,
438
+ "eval_loss": 0.048270147293806076,
439
+ "eval_runtime": 35.8252,
440
+ "eval_samples_per_second": 19.846,
441
+ "eval_steps_per_second": 19.846,
442
+ "step": 55
443
+ },
444
+ {
445
+ "epoch": 0.5309236352862751,
446
+ "grad_norm": 0.09912109375,
447
+ "learning_rate": 0.00018898345113272998,
448
+ "loss": 0.0442,
449
+ "step": 56
450
+ },
451
+ {
452
+ "epoch": 0.5404044144878157,
453
+ "grad_norm": 0.1005859375,
454
+ "learning_rate": 0.00018850875331485995,
455
+ "loss": 0.0415,
456
+ "step": 57
457
+ },
458
+ {
459
+ "epoch": 0.5498851936893563,
460
+ "grad_norm": 0.1142578125,
461
+ "learning_rate": 0.00018802466513248632,
462
+ "loss": 0.0474,
463
+ "step": 58
464
+ },
465
+ {
466
+ "epoch": 0.559365972890897,
467
+ "grad_norm": 0.1103515625,
468
+ "learning_rate": 0.00018753123794509974,
469
+ "loss": 0.0501,
470
+ "step": 59
471
+ },
472
+ {
473
+ "epoch": 0.5688467520924376,
474
+ "grad_norm": 0.10986328125,
475
+ "learning_rate": 0.00018702852410301554,
476
+ "loss": 0.0509,
477
+ "step": 60
478
+ },
479
+ {
480
+ "epoch": 0.5783275312939782,
481
+ "grad_norm": 0.119140625,
482
+ "learning_rate": 0.0001865165769418196,
483
+ "loss": 0.054,
484
+ "step": 61
485
+ },
486
+ {
487
+ "epoch": 0.5878083104955188,
488
+ "grad_norm": 0.12353515625,
489
+ "learning_rate": 0.00018599545077670985,
490
+ "loss": 0.0496,
491
+ "step": 62
492
+ },
493
+ {
494
+ "epoch": 0.5972890896970595,
495
+ "grad_norm": 0.09619140625,
496
+ "learning_rate": 0.0001854652008967335,
497
+ "loss": 0.0479,
498
+ "step": 63
499
+ },
500
+ {
501
+ "epoch": 0.6067698688986001,
502
+ "grad_norm": 0.1123046875,
503
+ "learning_rate": 0.00018492588355892124,
504
+ "loss": 0.0508,
505
+ "step": 64
506
+ },
507
+ {
508
+ "epoch": 0.6162506481001407,
509
+ "grad_norm": 0.125,
510
+ "learning_rate": 0.00018437755598231856,
511
+ "loss": 0.0499,
512
+ "step": 65
513
+ },
514
+ {
515
+ "epoch": 0.6257314273016814,
516
+ "grad_norm": 0.0986328125,
517
+ "learning_rate": 0.00018382027634191524,
518
+ "loss": 0.0459,
519
+ "step": 66
520
+ },
521
+ {
522
+ "epoch": 0.6257314273016814,
523
+ "eval_loss": 0.04686620458960533,
524
+ "eval_runtime": 35.9226,
525
+ "eval_samples_per_second": 19.793,
526
+ "eval_steps_per_second": 19.793,
527
+ "step": 66
528
+ },
529
+ {
530
+ "epoch": 0.635212206503222,
531
+ "grad_norm": 0.12109375,
532
+ "learning_rate": 0.00018325410376247294,
533
+ "loss": 0.0473,
534
+ "step": 67
535
+ },
536
+ {
537
+ "epoch": 0.6446929857047626,
538
+ "grad_norm": 0.1103515625,
539
+ "learning_rate": 0.0001826790983122527,
540
+ "loss": 0.0443,
541
+ "step": 68
542
+ },
543
+ {
544
+ "epoch": 0.6541737649063032,
545
+ "grad_norm": 0.11279296875,
546
+ "learning_rate": 0.00018209532099664174,
547
+ "loss": 0.0508,
548
+ "step": 69
549
+ },
550
+ {
551
+ "epoch": 0.6636545441078439,
552
+ "grad_norm": 0.11083984375,
553
+ "learning_rate": 0.00018150283375168114,
554
+ "loss": 0.0485,
555
+ "step": 70
556
+ },
557
+ {
558
+ "epoch": 0.6731353233093845,
559
+ "grad_norm": 0.10693359375,
560
+ "learning_rate": 0.00018090169943749476,
561
+ "loss": 0.0535,
562
+ "step": 71
563
+ },
564
+ {
565
+ "epoch": 0.6826161025109251,
566
+ "grad_norm": 0.10888671875,
567
+ "learning_rate": 0.00018029198183161998,
568
+ "loss": 0.0617,
569
+ "step": 72
570
+ },
571
+ {
572
+ "epoch": 0.6920968817124658,
573
+ "grad_norm": 0.09521484375,
574
+ "learning_rate": 0.00017967374562224132,
575
+ "loss": 0.0477,
576
+ "step": 73
577
+ },
578
+ {
579
+ "epoch": 0.7015776609140064,
580
+ "grad_norm": 0.0966796875,
581
+ "learning_rate": 0.00017904705640132718,
582
+ "loss": 0.0545,
583
+ "step": 74
584
+ },
585
+ {
586
+ "epoch": 0.711058440115547,
587
+ "grad_norm": 0.09423828125,
588
+ "learning_rate": 0.00017841198065767107,
589
+ "loss": 0.0396,
590
+ "step": 75
591
+ },
592
+ {
593
+ "epoch": 0.7205392193170876,
594
+ "grad_norm": 0.0947265625,
595
+ "learning_rate": 0.00017776858576983712,
596
+ "loss": 0.0483,
597
+ "step": 76
598
+ },
599
+ {
600
+ "epoch": 0.7300199985186282,
601
+ "grad_norm": 0.09326171875,
602
+ "learning_rate": 0.0001771169399990119,
603
+ "loss": 0.0397,
604
+ "step": 77
605
+ },
606
+ {
607
+ "epoch": 0.7300199985186282,
608
+ "eval_loss": 0.046032145619392395,
609
+ "eval_runtime": 35.9702,
610
+ "eval_samples_per_second": 19.766,
611
+ "eval_steps_per_second": 19.766,
612
+ "step": 77
613
+ },
614
+ {
615
+ "epoch": 0.7395007777201689,
616
+ "grad_norm": 0.09423828125,
617
+ "learning_rate": 0.00017645711248176195,
618
+ "loss": 0.0414,
619
+ "step": 78
620
+ },
621
+ {
622
+ "epoch": 0.7489815569217095,
623
+ "grad_norm": 0.10107421875,
624
+ "learning_rate": 0.00017578917322269886,
625
+ "loss": 0.0447,
626
+ "step": 79
627
+ },
628
+ {
629
+ "epoch": 0.7584623361232501,
630
+ "grad_norm": 0.0966796875,
631
+ "learning_rate": 0.00017511319308705198,
632
+ "loss": 0.0404,
633
+ "step": 80
634
+ },
635
+ {
636
+ "epoch": 0.7679431153247908,
637
+ "grad_norm": 0.099609375,
638
+ "learning_rate": 0.0001744292437931502,
639
+ "loss": 0.0409,
640
+ "step": 81
641
+ },
642
+ {
643
+ "epoch": 0.7774238945263314,
644
+ "grad_norm": 0.12890625,
645
+ "learning_rate": 0.00017373739790481262,
646
+ "loss": 0.0482,
647
+ "step": 82
648
+ },
649
+ {
650
+ "epoch": 0.786904673727872,
651
+ "grad_norm": 0.09375,
652
+ "learning_rate": 0.00017303772882365016,
653
+ "loss": 0.0356,
654
+ "step": 83
655
+ },
656
+ {
657
+ "epoch": 0.7963854529294127,
658
+ "grad_norm": 0.1103515625,
659
+ "learning_rate": 0.00017233031078127788,
660
+ "loss": 0.0467,
661
+ "step": 84
662
+ },
663
+ {
664
+ "epoch": 0.8058662321309532,
665
+ "grad_norm": 0.11767578125,
666
+ "learning_rate": 0.00017161521883143934,
667
+ "loss": 0.0537,
668
+ "step": 85
669
+ },
670
+ {
671
+ "epoch": 0.8153470113324939,
672
+ "grad_norm": 0.095703125,
673
+ "learning_rate": 0.00017089252884204377,
674
+ "loss": 0.0477,
675
+ "step": 86
676
+ },
677
+ {
678
+ "epoch": 0.8248277905340345,
679
+ "grad_norm": 0.09521484375,
680
+ "learning_rate": 0.0001701623174871168,
681
+ "loss": 0.0466,
682
+ "step": 87
683
+ },
684
+ {
685
+ "epoch": 0.8343085697355751,
686
+ "grad_norm": 0.09326171875,
687
+ "learning_rate": 0.0001694246622386658,
688
+ "loss": 0.0453,
689
+ "step": 88
690
+ },
691
+ {
692
+ "epoch": 0.8343085697355751,
693
+ "eval_loss": 0.04489152505993843,
694
+ "eval_runtime": 36.0012,
695
+ "eval_samples_per_second": 19.749,
696
+ "eval_steps_per_second": 19.749,
697
+ "step": 88
698
+ },
699
+ {
700
+ "epoch": 0.8437893489371158,
701
+ "grad_norm": 0.08349609375,
702
+ "learning_rate": 0.00016867964135846043,
703
+ "loss": 0.039,
704
+ "step": 89
705
+ },
706
+ {
707
+ "epoch": 0.8532701281386564,
708
+ "grad_norm": 0.10400390625,
709
+ "learning_rate": 0.00016792733388972932,
710
+ "loss": 0.0521,
711
+ "step": 90
712
+ },
713
+ {
714
+ "epoch": 0.862750907340197,
715
+ "grad_norm": 0.0849609375,
716
+ "learning_rate": 0.0001671678196487741,
717
+ "loss": 0.0481,
718
+ "step": 91
719
+ },
720
+ {
721
+ "epoch": 0.8722316865417377,
722
+ "grad_norm": 0.09814453125,
723
+ "learning_rate": 0.00016640117921650117,
724
+ "loss": 0.0509,
725
+ "step": 92
726
+ },
727
+ {
728
+ "epoch": 0.8817124657432783,
729
+ "grad_norm": 0.0927734375,
730
+ "learning_rate": 0.00016562749392987254,
731
+ "loss": 0.0413,
732
+ "step": 93
733
+ },
734
+ {
735
+ "epoch": 0.8911932449448189,
736
+ "grad_norm": 0.08740234375,
737
+ "learning_rate": 0.0001648468458732762,
738
+ "loss": 0.0405,
739
+ "step": 94
740
+ },
741
+ {
742
+ "epoch": 0.9006740241463596,
743
+ "grad_norm": 0.09228515625,
744
+ "learning_rate": 0.00016405931786981755,
745
+ "loss": 0.0458,
746
+ "step": 95
747
+ },
748
+ {
749
+ "epoch": 0.9101548033479001,
750
+ "grad_norm": 0.1005859375,
751
+ "learning_rate": 0.00016326499347253207,
752
+ "loss": 0.0457,
753
+ "step": 96
754
+ },
755
+ {
756
+ "epoch": 0.9196355825494408,
757
+ "grad_norm": 0.09619140625,
758
+ "learning_rate": 0.00016246395695552085,
759
+ "loss": 0.0439,
760
+ "step": 97
761
+ },
762
+ {
763
+ "epoch": 0.9291163617509814,
764
+ "grad_norm": 0.08740234375,
765
+ "learning_rate": 0.00016165629330500952,
766
+ "loss": 0.0389,
767
+ "step": 98
768
+ },
769
+ {
770
+ "epoch": 0.938597140952522,
771
+ "grad_norm": 0.08935546875,
772
+ "learning_rate": 0.0001608420882103315,
773
+ "loss": 0.04,
774
+ "step": 99
775
+ },
776
+ {
777
+ "epoch": 0.938597140952522,
778
+ "eval_loss": 0.04293662682175636,
779
+ "eval_runtime": 36.2853,
780
+ "eval_samples_per_second": 19.595,
781
+ "eval_steps_per_second": 19.595,
782
+ "step": 99
783
+ },
784
+ {
785
+ "epoch": 0.9480779201540627,
786
+ "grad_norm": 0.09326171875,
787
+ "learning_rate": 0.00016002142805483685,
788
+ "loss": 0.0418,
789
+ "step": 100
790
+ },
791
+ {
792
+ "epoch": 0.9575586993556033,
793
+ "grad_norm": 0.0830078125,
794
+ "learning_rate": 0.0001591943999067273,
795
+ "loss": 0.0406,
796
+ "step": 101
797
+ },
798
+ {
799
+ "epoch": 0.9670394785571439,
800
+ "grad_norm": 0.09375,
801
+ "learning_rate": 0.00015836109150981886,
802
+ "loss": 0.0418,
803
+ "step": 102
804
+ },
805
+ {
806
+ "epoch": 0.9765202577586846,
807
+ "grad_norm": 0.09765625,
808
+ "learning_rate": 0.00015752159127423263,
809
+ "loss": 0.0395,
810
+ "step": 103
811
+ },
812
+ {
813
+ "epoch": 0.9860010369602251,
814
+ "grad_norm": 0.08154296875,
815
+ "learning_rate": 0.0001566759882670146,
816
+ "loss": 0.0375,
817
+ "step": 104
818
+ },
819
+ {
820
+ "epoch": 0.9954818161617658,
821
+ "grad_norm": 0.1005859375,
822
+ "learning_rate": 0.00015582437220268647,
823
+ "loss": 0.0463,
824
+ "step": 105
825
+ },
826
+ {
827
+ "epoch": 1.0049625953633063,
828
+ "grad_norm": 0.07666015625,
829
+ "learning_rate": 0.0001549668334337271,
830
+ "loss": 0.0346,
831
+ "step": 106
832
+ },
833
+ {
834
+ "epoch": 1.0144433745648471,
835
+ "grad_norm": 0.07763671875,
836
+ "learning_rate": 0.0001541034629409865,
837
+ "loss": 0.0322,
838
+ "step": 107
839
+ },
840
+ {
841
+ "epoch": 1.0239241537663877,
842
+ "grad_norm": 0.08154296875,
843
+ "learning_rate": 0.00015323435232403337,
844
+ "loss": 0.0328,
845
+ "step": 108
846
+ },
847
+ {
848
+ "epoch": 1.0334049329679282,
849
+ "grad_norm": 0.06591796875,
850
+ "learning_rate": 0.00015235959379143678,
851
+ "loss": 0.0299,
852
+ "step": 109
853
+ },
854
+ {
855
+ "epoch": 1.042885712169469,
856
+ "grad_norm": 0.08544921875,
857
+ "learning_rate": 0.0001514792801509831,
858
+ "loss": 0.0338,
859
+ "step": 110
860
+ },
861
+ {
862
+ "epoch": 1.042885712169469,
863
+ "eval_loss": 0.04179221764206886,
864
+ "eval_runtime": 35.8658,
865
+ "eval_samples_per_second": 19.824,
866
+ "eval_steps_per_second": 19.824,
867
+ "step": 110
868
+ },
869
+ {
870
+ "epoch": 1.0523664913710096,
871
+ "grad_norm": 0.0830078125,
872
+ "learning_rate": 0.00015059350479982965,
873
+ "loss": 0.0281,
874
+ "step": 111
875
+ },
876
+ {
877
+ "epoch": 1.0618472705725501,
878
+ "grad_norm": 0.083984375,
879
+ "learning_rate": 0.0001497023617145958,
880
+ "loss": 0.03,
881
+ "step": 112
882
+ },
883
+ {
884
+ "epoch": 1.071328049774091,
885
+ "grad_norm": 0.0771484375,
886
+ "learning_rate": 0.0001488059454413923,
887
+ "loss": 0.0286,
888
+ "step": 113
889
+ },
890
+ {
891
+ "epoch": 1.0808088289756315,
892
+ "grad_norm": 0.0966796875,
893
+ "learning_rate": 0.00014790435108579048,
894
+ "loss": 0.0311,
895
+ "step": 114
896
+ },
897
+ {
898
+ "epoch": 1.090289608177172,
899
+ "grad_norm": 0.0869140625,
900
+ "learning_rate": 0.000146997674302732,
901
+ "loss": 0.0291,
902
+ "step": 115
903
+ },
904
+ {
905
+ "epoch": 1.0997703873787126,
906
+ "grad_norm": 0.08984375,
907
+ "learning_rate": 0.00014608601128638027,
908
+ "loss": 0.0281,
909
+ "step": 116
910
+ },
911
+ {
912
+ "epoch": 1.1092511665802534,
913
+ "grad_norm": 0.08837890625,
914
+ "learning_rate": 0.00014516945875991472,
915
+ "loss": 0.0322,
916
+ "step": 117
917
+ },
918
+ {
919
+ "epoch": 1.118731945781794,
920
+ "grad_norm": 0.083984375,
921
+ "learning_rate": 0.00014424811396526892,
922
+ "loss": 0.026,
923
+ "step": 118
924
+ },
925
+ {
926
+ "epoch": 1.1282127249833347,
927
+ "grad_norm": 0.08837890625,
928
+ "learning_rate": 0.00014332207465281364,
929
+ "loss": 0.0317,
930
+ "step": 119
931
+ },
932
+ {
933
+ "epoch": 1.1376935041848752,
934
+ "grad_norm": 0.09912109375,
935
+ "learning_rate": 0.0001423914390709861,
936
+ "loss": 0.0341,
937
+ "step": 120
938
+ },
939
+ {
940
+ "epoch": 1.1471742833864158,
941
+ "grad_norm": 0.095703125,
942
+ "learning_rate": 0.00014145630595586607,
943
+ "loss": 0.0322,
944
+ "step": 121
945
+ },
946
+ {
947
+ "epoch": 1.1471742833864158,
948
+ "eval_loss": 0.04224802553653717,
949
+ "eval_runtime": 35.7541,
950
+ "eval_samples_per_second": 19.886,
951
+ "eval_steps_per_second": 19.886,
952
+ "step": 121
953
+ },
954
+ {
955
+ "epoch": 1.1566550625879564,
956
+ "grad_norm": 0.07763671875,
957
+ "learning_rate": 0.00014051677452070065,
958
+ "loss": 0.0279,
959
+ "step": 122
960
+ },
961
+ {
962
+ "epoch": 1.1661358417894971,
963
+ "grad_norm": 0.08837890625,
964
+ "learning_rate": 0.00013957294444537808,
965
+ "loss": 0.0276,
966
+ "step": 123
967
+ },
968
+ {
969
+ "epoch": 1.1756166209910377,
970
+ "grad_norm": 0.099609375,
971
+ "learning_rate": 0.0001386249158658522,
972
+ "loss": 0.0399,
973
+ "step": 124
974
+ },
975
+ {
976
+ "epoch": 1.1850974001925783,
977
+ "grad_norm": 0.0888671875,
978
+ "learning_rate": 0.00013767278936351854,
979
+ "loss": 0.0327,
980
+ "step": 125
981
+ },
982
+ {
983
+ "epoch": 1.194578179394119,
984
+ "grad_norm": 0.078125,
985
+ "learning_rate": 0.00013671666595454295,
986
+ "loss": 0.0257,
987
+ "step": 126
988
+ },
989
+ {
990
+ "epoch": 1.2040589585956596,
991
+ "grad_norm": 0.078125,
992
+ "learning_rate": 0.00013575664707914448,
993
+ "loss": 0.0268,
994
+ "step": 127
995
+ },
996
+ {
997
+ "epoch": 1.2135397377972001,
998
+ "grad_norm": 0.0966796875,
999
+ "learning_rate": 0.0001347928345908329,
1000
+ "loss": 0.0368,
1001
+ "step": 128
1002
+ },
1003
+ {
1004
+ "epoch": 1.223020516998741,
1005
+ "grad_norm": 0.076171875,
1006
+ "learning_rate": 0.00013382533074560255,
1007
+ "loss": 0.0286,
1008
+ "step": 129
1009
+ },
1010
+ {
1011
+ "epoch": 1.2325012962002815,
1012
+ "grad_norm": 0.0888671875,
1013
+ "learning_rate": 0.0001328542381910835,
1014
+ "loss": 0.0304,
1015
+ "step": 130
1016
+ },
1017
+ {
1018
+ "epoch": 1.241982075401822,
1019
+ "grad_norm": 0.087890625,
1020
+ "learning_rate": 0.00013187965995565098,
1021
+ "loss": 0.0304,
1022
+ "step": 131
1023
+ },
1024
+ {
1025
+ "epoch": 1.2514628546033628,
1026
+ "grad_norm": 0.0732421875,
1027
+ "learning_rate": 0.00013090169943749476,
1028
+ "loss": 0.0275,
1029
+ "step": 132
1030
+ },
1031
+ {
1032
+ "epoch": 1.2514628546033628,
1033
+ "eval_loss": 0.04160289093852043,
1034
+ "eval_runtime": 35.8932,
1035
+ "eval_samples_per_second": 19.809,
1036
+ "eval_steps_per_second": 19.809,
1037
+ "step": 132
1038
+ },
1039
+ {
1040
+ "epoch": 1.2609436338049034,
1041
+ "grad_norm": 0.08203125,
1042
+ "learning_rate": 0.00012992046039364893,
1043
+ "loss": 0.0293,
1044
+ "step": 133
1045
+ },
1046
+ {
1047
+ "epoch": 1.270424413006444,
1048
+ "grad_norm": 0.087890625,
1049
+ "learning_rate": 0.0001289360469289838,
1050
+ "loss": 0.03,
1051
+ "step": 134
1052
+ },
1053
+ {
1054
+ "epoch": 1.2799051922079845,
1055
+ "grad_norm": 0.08203125,
1056
+ "learning_rate": 0.00012794856348516095,
1057
+ "loss": 0.028,
1058
+ "step": 135
1059
+ },
1060
+ {
1061
+ "epoch": 1.2893859714095253,
1062
+ "grad_norm": 0.0869140625,
1063
+ "learning_rate": 0.00012695811482955227,
1064
+ "loss": 0.0293,
1065
+ "step": 136
1066
+ },
1067
+ {
1068
+ "epoch": 1.2988667506110658,
1069
+ "grad_norm": 0.09228515625,
1070
+ "learning_rate": 0.00012596480604412484,
1071
+ "loss": 0.0341,
1072
+ "step": 137
1073
+ },
1074
+ {
1075
+ "epoch": 1.3083475298126066,
1076
+ "grad_norm": 0.07470703125,
1077
+ "learning_rate": 0.000124968742514292,
1078
+ "loss": 0.0259,
1079
+ "step": 138
1080
+ },
1081
+ {
1082
+ "epoch": 1.3178283090141472,
1083
+ "grad_norm": 0.10009765625,
1084
+ "learning_rate": 0.00012397002991773275,
1085
+ "loss": 0.0298,
1086
+ "step": 139
1087
+ },
1088
+ {
1089
+ "epoch": 1.3273090882156877,
1090
+ "grad_norm": 0.08837890625,
1091
+ "learning_rate": 0.0001229687742131796,
1092
+ "loss": 0.0285,
1093
+ "step": 140
1094
+ },
1095
+ {
1096
+ "epoch": 1.3367898674172283,
1097
+ "grad_norm": 0.091796875,
1098
+ "learning_rate": 0.00012196508162917677,
1099
+ "loss": 0.034,
1100
+ "step": 141
1101
+ },
1102
+ {
1103
+ "epoch": 1.346270646618769,
1104
+ "grad_norm": 0.0986328125,
1105
+ "learning_rate": 0.00012095905865281025,
1106
+ "loss": 0.0314,
1107
+ "step": 142
1108
+ },
1109
+ {
1110
+ "epoch": 1.3557514258203096,
1111
+ "grad_norm": 0.0947265625,
1112
+ "learning_rate": 0.00011995081201840956,
1113
+ "loss": 0.0322,
1114
+ "step": 143
1115
+ },
1116
+ {
1117
+ "epoch": 1.3557514258203096,
1118
+ "eval_loss": 0.041649721562862396,
1119
+ "eval_runtime": 35.8396,
1120
+ "eval_samples_per_second": 19.838,
1121
+ "eval_steps_per_second": 19.838,
1122
+ "step": 143
1123
+ },
1124
+ {
1125
+ "epoch": 1.3652322050218502,
1126
+ "grad_norm": 0.083984375,
1127
+ "learning_rate": 0.00011894044869622403,
1128
+ "loss": 0.0303,
1129
+ "step": 144
1130
+ },
1131
+ {
1132
+ "epoch": 1.374712984223391,
1133
+ "grad_norm": 0.07373046875,
1134
+ "learning_rate": 0.00011792807588107357,
1135
+ "loss": 0.0259,
1136
+ "step": 145
1137
+ },
1138
+ {
1139
+ "epoch": 1.3841937634249315,
1140
+ "grad_norm": 0.08740234375,
1141
+ "learning_rate": 0.00011691380098097597,
1142
+ "loss": 0.0334,
1143
+ "step": 146
1144
+ },
1145
+ {
1146
+ "epoch": 1.393674542626472,
1147
+ "grad_norm": 0.068359375,
1148
+ "learning_rate": 0.0001158977316057513,
1149
+ "loss": 0.0245,
1150
+ "step": 147
1151
+ },
1152
+ {
1153
+ "epoch": 1.4031553218280126,
1154
+ "grad_norm": 0.09423828125,
1155
+ "learning_rate": 0.00011487997555560503,
1156
+ "loss": 0.0322,
1157
+ "step": 148
1158
+ },
1159
+ {
1160
+ "epoch": 1.4126361010295534,
1161
+ "grad_norm": 0.0947265625,
1162
+ "learning_rate": 0.00011386064080969094,
1163
+ "loss": 0.0338,
1164
+ "step": 149
1165
+ },
1166
+ {
1167
+ "epoch": 1.422116880231094,
1168
+ "grad_norm": 0.09326171875,
1169
+ "learning_rate": 0.00011283983551465511,
1170
+ "loss": 0.0278,
1171
+ "step": 150
1172
+ },
1173
+ {
1174
+ "epoch": 1.4315976594326347,
1175
+ "grad_norm": 0.087890625,
1176
+ "learning_rate": 0.0001118176679731619,
1177
+ "loss": 0.0305,
1178
+ "step": 151
1179
+ },
1180
+ {
1181
+ "epoch": 1.4410784386341753,
1182
+ "grad_norm": 0.083984375,
1183
+ "learning_rate": 0.00011079424663240372,
1184
+ "loss": 0.0311,
1185
+ "step": 152
1186
+ },
1187
+ {
1188
+ "epoch": 1.4505592178357158,
1189
+ "grad_norm": 0.08154296875,
1190
+ "learning_rate": 0.00010976968007259519,
1191
+ "loss": 0.0298,
1192
+ "step": 153
1193
+ },
1194
+ {
1195
+ "epoch": 1.4600399970372564,
1196
+ "grad_norm": 0.072265625,
1197
+ "learning_rate": 0.00010874407699545328,
1198
+ "loss": 0.0266,
1199
+ "step": 154
1200
+ },
1201
+ {
1202
+ "epoch": 1.4600399970372564,
1203
+ "eval_loss": 0.04042724519968033,
1204
+ "eval_runtime": 36.0075,
1205
+ "eval_samples_per_second": 19.746,
1206
+ "eval_steps_per_second": 19.746,
1207
+ "step": 154
1208
+ },
1209
+ {
1210
+ "epoch": 1.4695207762387972,
1211
+ "grad_norm": 0.083984375,
1212
+ "learning_rate": 0.00010771754621266466,
1213
+ "loss": 0.0335,
1214
+ "step": 155
1215
+ },
1216
+ {
1217
+ "epoch": 1.4790015554403377,
1218
+ "grad_norm": 0.07470703125,
1219
+ "learning_rate": 0.00010669019663434117,
1220
+ "loss": 0.0268,
1221
+ "step": 156
1222
+ },
1223
+ {
1224
+ "epoch": 1.4884823346418785,
1225
+ "grad_norm": 0.0849609375,
1226
+ "learning_rate": 0.00010566213725746506,
1227
+ "loss": 0.0334,
1228
+ "step": 157
1229
+ },
1230
+ {
1231
+ "epoch": 1.497963113843419,
1232
+ "grad_norm": 0.0751953125,
1233
+ "learning_rate": 0.00010463347715432488,
1234
+ "loss": 0.0283,
1235
+ "step": 158
1236
+ },
1237
+ {
1238
+ "epoch": 1.5074438930449596,
1239
+ "grad_norm": 0.07421875,
1240
+ "learning_rate": 0.00010360432546094341,
1241
+ "loss": 0.0284,
1242
+ "step": 159
1243
+ },
1244
+ {
1245
+ "epoch": 1.5169246722465002,
1246
+ "grad_norm": 0.08154296875,
1247
+ "learning_rate": 0.00010257479136549889,
1248
+ "loss": 0.0306,
1249
+ "step": 160
1250
+ },
1251
+ {
1252
+ "epoch": 1.5264054514480407,
1253
+ "grad_norm": 0.091796875,
1254
+ "learning_rate": 0.00010154498409674051,
1255
+ "loss": 0.0347,
1256
+ "step": 161
1257
+ },
1258
+ {
1259
+ "epoch": 1.5358862306495815,
1260
+ "grad_norm": 0.087890625,
1261
+ "learning_rate": 0.00010051501291240008,
1262
+ "loss": 0.0343,
1263
+ "step": 162
1264
+ },
1265
+ {
1266
+ "epoch": 1.5453670098511223,
1267
+ "grad_norm": 0.08544921875,
1268
+ "learning_rate": 9.948498708759993e-05,
1269
+ "loss": 0.0313,
1270
+ "step": 163
1271
+ },
1272
+ {
1273
+ "epoch": 1.5548477890526629,
1274
+ "grad_norm": 0.0791015625,
1275
+ "learning_rate": 9.845501590325948e-05,
1276
+ "loss": 0.0284,
1277
+ "step": 164
1278
+ },
1279
+ {
1280
+ "epoch": 1.5643285682542034,
1281
+ "grad_norm": 0.076171875,
1282
+ "learning_rate": 9.742520863450115e-05,
1283
+ "loss": 0.0249,
1284
+ "step": 165
1285
+ },
1286
+ {
1287
+ "epoch": 1.5643285682542034,
1288
+ "eval_loss": 0.03973715007305145,
1289
+ "eval_runtime": 35.8478,
1290
+ "eval_samples_per_second": 19.834,
1291
+ "eval_steps_per_second": 19.834,
1292
+ "step": 165
1293
+ },
1294
+ {
1295
+ "epoch": 1.573809347455744,
1296
+ "grad_norm": 0.076171875,
1297
+ "learning_rate": 9.639567453905661e-05,
1298
+ "loss": 0.0294,
1299
+ "step": 166
1300
+ },
1301
+ {
1302
+ "epoch": 1.5832901266572845,
1303
+ "grad_norm": 0.0703125,
1304
+ "learning_rate": 9.536652284567513e-05,
1305
+ "loss": 0.0248,
1306
+ "step": 167
1307
+ },
1308
+ {
1309
+ "epoch": 1.5927709058588253,
1310
+ "grad_norm": 0.08251953125,
1311
+ "learning_rate": 9.433786274253495e-05,
1312
+ "loss": 0.03,
1313
+ "step": 168
1314
+ },
1315
+ {
1316
+ "epoch": 1.6022516850603659,
1317
+ "grad_norm": 0.07373046875,
1318
+ "learning_rate": 9.330980336565887e-05,
1319
+ "loss": 0.0269,
1320
+ "step": 169
1321
+ },
1322
+ {
1323
+ "epoch": 1.6117324642619066,
1324
+ "grad_norm": 0.10791015625,
1325
+ "learning_rate": 9.228245378733537e-05,
1326
+ "loss": 0.0323,
1327
+ "step": 170
1328
+ },
1329
+ {
1330
+ "epoch": 1.6212132434634472,
1331
+ "grad_norm": 0.08837890625,
1332
+ "learning_rate": 9.125592300454676e-05,
1333
+ "loss": 0.0328,
1334
+ "step": 171
1335
+ },
1336
+ {
1337
+ "epoch": 1.6306940226649878,
1338
+ "grad_norm": 0.076171875,
1339
+ "learning_rate": 9.023031992740488e-05,
1340
+ "loss": 0.0245,
1341
+ "step": 172
1342
+ },
1343
+ {
1344
+ "epoch": 1.6401748018665283,
1345
+ "grad_norm": 0.0791015625,
1346
+ "learning_rate": 8.920575336759629e-05,
1347
+ "loss": 0.0291,
1348
+ "step": 173
1349
+ },
1350
+ {
1351
+ "epoch": 1.6496555810680689,
1352
+ "grad_norm": 0.10107421875,
1353
+ "learning_rate": 8.818233202683814e-05,
1354
+ "loss": 0.0324,
1355
+ "step": 174
1356
+ },
1357
+ {
1358
+ "epoch": 1.6591363602696096,
1359
+ "grad_norm": 0.0859375,
1360
+ "learning_rate": 8.71601644853449e-05,
1361
+ "loss": 0.0294,
1362
+ "step": 175
1363
+ },
1364
+ {
1365
+ "epoch": 1.6686171394711504,
1366
+ "grad_norm": 0.0849609375,
1367
+ "learning_rate": 8.613935919030907e-05,
1368
+ "loss": 0.0292,
1369
+ "step": 176
1370
+ },
1371
+ {
1372
+ "epoch": 1.6686171394711504,
1373
+ "eval_loss": 0.03933083638548851,
1374
+ "eval_runtime": 36.0124,
1375
+ "eval_samples_per_second": 19.743,
1376
+ "eval_steps_per_second": 19.743,
1377
+ "step": 176
1378
+ },
1379
+ {
1380
+ "epoch": 1.678097918672691,
1381
+ "grad_norm": 0.07666015625,
1382
+ "learning_rate": 8.512002444439502e-05,
1383
+ "loss": 0.028,
1384
+ "step": 177
1385
+ },
1386
+ {
1387
+ "epoch": 1.6875786978742315,
1388
+ "grad_norm": 0.08984375,
1389
+ "learning_rate": 8.410226839424871e-05,
1390
+ "loss": 0.0312,
1391
+ "step": 178
1392
+ },
1393
+ {
1394
+ "epoch": 1.697059477075772,
1395
+ "grad_norm": 0.0732421875,
1396
+ "learning_rate": 8.308619901902406e-05,
1397
+ "loss": 0.0253,
1398
+ "step": 179
1399
+ },
1400
+ {
1401
+ "epoch": 1.7065402562773127,
1402
+ "grad_norm": 0.083984375,
1403
+ "learning_rate": 8.207192411892646e-05,
1404
+ "loss": 0.0278,
1405
+ "step": 180
1406
+ },
1407
+ {
1408
+ "epoch": 1.7160210354788534,
1409
+ "grad_norm": 0.08642578125,
1410
+ "learning_rate": 8.1059551303776e-05,
1411
+ "loss": 0.0275,
1412
+ "step": 181
1413
+ },
1414
+ {
1415
+ "epoch": 1.7255018146803942,
1416
+ "grad_norm": 0.07568359375,
1417
+ "learning_rate": 8.004918798159045e-05,
1418
+ "loss": 0.0265,
1419
+ "step": 182
1420
+ },
1421
+ {
1422
+ "epoch": 1.7349825938819348,
1423
+ "grad_norm": 0.076171875,
1424
+ "learning_rate": 7.904094134718976e-05,
1425
+ "loss": 0.0285,
1426
+ "step": 183
1427
+ },
1428
+ {
1429
+ "epoch": 1.7444633730834753,
1430
+ "grad_norm": 0.09228515625,
1431
+ "learning_rate": 7.803491837082324e-05,
1432
+ "loss": 0.0349,
1433
+ "step": 184
1434
+ },
1435
+ {
1436
+ "epoch": 1.7539441522850159,
1437
+ "grad_norm": 0.09521484375,
1438
+ "learning_rate": 7.703122578682046e-05,
1439
+ "loss": 0.0325,
1440
+ "step": 185
1441
+ },
1442
+ {
1443
+ "epoch": 1.7634249314865564,
1444
+ "grad_norm": 0.0751953125,
1445
+ "learning_rate": 7.602997008226726e-05,
1446
+ "loss": 0.0283,
1447
+ "step": 186
1448
+ },
1449
+ {
1450
+ "epoch": 1.7729057106880972,
1451
+ "grad_norm": 0.0869140625,
1452
+ "learning_rate": 7.5031257485708e-05,
1453
+ "loss": 0.031,
1454
+ "step": 187
1455
+ },
1456
+ {
1457
+ "epoch": 1.7729057106880972,
1458
+ "eval_loss": 0.03848842531442642,
1459
+ "eval_runtime": 35.9251,
1460
+ "eval_samples_per_second": 19.791,
1461
+ "eval_steps_per_second": 19.791,
1462
+ "step": 187
1463
+ },
1464
+ {
1465
+ "epoch": 1.7823864898896378,
1466
+ "grad_norm": 0.07861328125,
1467
+ "learning_rate": 7.403519395587521e-05,
1468
+ "loss": 0.03,
1469
+ "step": 188
1470
+ },
1471
+ {
1472
+ "epoch": 1.7918672690911785,
1473
+ "grad_norm": 0.07177734375,
1474
+ "learning_rate": 7.304188517044774e-05,
1475
+ "loss": 0.0281,
1476
+ "step": 189
1477
+ },
1478
+ {
1479
+ "epoch": 1.801348048292719,
1480
+ "grad_norm": 0.07568359375,
1481
+ "learning_rate": 7.205143651483906e-05,
1482
+ "loss": 0.0253,
1483
+ "step": 190
1484
+ },
1485
+ {
1486
+ "epoch": 1.8108288274942597,
1487
+ "grad_norm": 0.06787109375,
1488
+ "learning_rate": 7.106395307101621e-05,
1489
+ "loss": 0.0264,
1490
+ "step": 191
1491
+ },
1492
+ {
1493
+ "epoch": 1.8203096066958002,
1494
+ "grad_norm": 0.07177734375,
1495
+ "learning_rate": 7.007953960635109e-05,
1496
+ "loss": 0.0268,
1497
+ "step": 192
1498
+ },
1499
+ {
1500
+ "epoch": 1.8297903858973408,
1501
+ "grad_norm": 0.08740234375,
1502
+ "learning_rate": 6.909830056250527e-05,
1503
+ "loss": 0.0308,
1504
+ "step": 193
1505
+ },
1506
+ {
1507
+ "epoch": 1.8392711650988816,
1508
+ "grad_norm": 0.07275390625,
1509
+ "learning_rate": 6.812034004434903e-05,
1510
+ "loss": 0.0275,
1511
+ "step": 194
1512
+ },
1513
+ {
1514
+ "epoch": 1.8487519443004223,
1515
+ "grad_norm": 0.07568359375,
1516
+ "learning_rate": 6.714576180891654e-05,
1517
+ "loss": 0.0253,
1518
+ "step": 195
1519
+ },
1520
+ {
1521
+ "epoch": 1.858232723501963,
1522
+ "grad_norm": 0.07177734375,
1523
+ "learning_rate": 6.617466925439746e-05,
1524
+ "loss": 0.0262,
1525
+ "step": 196
1526
+ },
1527
+ {
1528
+ "epoch": 1.8677135027035034,
1529
+ "grad_norm": 0.06787109375,
1530
+ "learning_rate": 6.520716540916709e-05,
1531
+ "loss": 0.0257,
1532
+ "step": 197
1533
+ },
1534
+ {
1535
+ "epoch": 1.877194281905044,
1536
+ "grad_norm": 0.0751953125,
1537
+ "learning_rate": 6.424335292085553e-05,
1538
+ "loss": 0.0265,
1539
+ "step": 198
1540
+ },
1541
+ {
1542
+ "epoch": 1.877194281905044,
1543
+ "eval_loss": 0.037521231919527054,
1544
+ "eval_runtime": 36.0213,
1545
+ "eval_samples_per_second": 19.738,
1546
+ "eval_steps_per_second": 19.738,
1547
+ "step": 198
1548
+ },
1549
+ {
1550
+ "epoch": 1.8866750611065846,
1551
+ "grad_norm": 0.10107421875,
1552
+ "learning_rate": 6.32833340454571e-05,
1553
+ "loss": 0.0269,
1554
+ "step": 199
1555
+ },
1556
+ {
1557
+ "epoch": 1.8961558403081253,
1558
+ "grad_norm": 0.0751953125,
1559
+ "learning_rate": 6.232721063648148e-05,
1560
+ "loss": 0.0279,
1561
+ "step": 200
1562
+ },
1563
+ {
1564
+ "epoch": 1.905636619509666,
1565
+ "grad_norm": 0.0791015625,
1566
+ "learning_rate": 6.137508413414784e-05,
1567
+ "loss": 0.0301,
1568
+ "step": 201
1569
+ },
1570
+ {
1571
+ "epoch": 1.9151173987112067,
1572
+ "grad_norm": 0.0791015625,
1573
+ "learning_rate": 6.0427055554621913e-05,
1574
+ "loss": 0.0289,
1575
+ "step": 202
1576
+ },
1577
+ {
1578
+ "epoch": 1.9245981779127472,
1579
+ "grad_norm": 0.08349609375,
1580
+ "learning_rate": 5.948322547929939e-05,
1581
+ "loss": 0.0239,
1582
+ "step": 203
1583
+ },
1584
+ {
1585
+ "epoch": 1.9340789571142878,
1586
+ "grad_norm": 0.07373046875,
1587
+ "learning_rate": 5.854369404413398e-05,
1588
+ "loss": 0.023,
1589
+ "step": 204
1590
+ },
1591
+ {
1592
+ "epoch": 1.9435597363158283,
1593
+ "grad_norm": 0.080078125,
1594
+ "learning_rate": 5.7608560929013946e-05,
1595
+ "loss": 0.0274,
1596
+ "step": 205
1597
+ },
1598
+ {
1599
+ "epoch": 1.9530405155173691,
1600
+ "grad_norm": 0.08447265625,
1601
+ "learning_rate": 5.667792534718639e-05,
1602
+ "loss": 0.0308,
1603
+ "step": 206
1604
+ },
1605
+ {
1606
+ "epoch": 1.9625212947189097,
1607
+ "grad_norm": 0.0732421875,
1608
+ "learning_rate": 5.5751886034731115e-05,
1609
+ "loss": 0.0253,
1610
+ "step": 207
1611
+ },
1612
+ {
1613
+ "epoch": 1.9720020739204505,
1614
+ "grad_norm": 0.0732421875,
1615
+ "learning_rate": 5.483054124008528e-05,
1616
+ "loss": 0.0261,
1617
+ "step": 208
1618
+ },
1619
+ {
1620
+ "epoch": 1.981482853121991,
1621
+ "grad_norm": 0.07763671875,
1622
+ "learning_rate": 5.391398871361972e-05,
1623
+ "loss": 0.0273,
1624
+ "step": 209
1625
+ },
1626
+ {
1627
+ "epoch": 1.981482853121991,
1628
+ "eval_loss": 0.037543829530477524,
1629
+ "eval_runtime": 36.1289,
1630
+ "eval_samples_per_second": 19.68,
1631
+ "eval_steps_per_second": 19.68,
1632
+ "step": 209
1633
+ },
1634
+ {
1635
+ "epoch": 1.9909636323235316,
1636
+ "grad_norm": 0.07958984375,
1637
+ "learning_rate": 5.300232569726804e-05,
1638
+ "loss": 0.0284,
1639
+ "step": 210
1640
+ },
1641
+ {
1642
+ "epoch": 2.000444411525072,
1643
+ "grad_norm": 0.08544921875,
1644
+ "learning_rate": 5.2095648914209525e-05,
1645
+ "loss": 0.0338,
1646
+ "step": 211
1647
+ },
1648
+ {
1649
+ "epoch": 2.0099251907266127,
1650
+ "grad_norm": 0.06298828125,
1651
+ "learning_rate": 5.119405455860772e-05,
1652
+ "loss": 0.0198,
1653
+ "step": 212
1654
+ },
1655
+ {
1656
+ "epoch": 2.0194059699281537,
1657
+ "grad_norm": 0.05810546875,
1658
+ "learning_rate": 5.029763828540419e-05,
1659
+ "loss": 0.0192,
1660
+ "step": 213
1661
+ },
1662
+ {
1663
+ "epoch": 2.0288867491296942,
1664
+ "grad_norm": 0.059326171875,
1665
+ "learning_rate": 4.940649520017035e-05,
1666
+ "loss": 0.0202,
1667
+ "step": 214
1668
+ },
1669
+ {
1670
+ "epoch": 2.038367528331235,
1671
+ "grad_norm": 0.060546875,
1672
+ "learning_rate": 4.852071984901696e-05,
1673
+ "loss": 0.0199,
1674
+ "step": 215
1675
+ },
1676
+ {
1677
+ "epoch": 2.0478483075327754,
1678
+ "grad_norm": 0.05078125,
1679
+ "learning_rate": 4.7640406208563224e-05,
1680
+ "loss": 0.0169,
1681
+ "step": 216
1682
+ },
1683
+ {
1684
+ "epoch": 2.057329086734316,
1685
+ "grad_norm": 0.058349609375,
1686
+ "learning_rate": 4.676564767596663e-05,
1687
+ "loss": 0.0193,
1688
+ "step": 217
1689
+ },
1690
+ {
1691
+ "epoch": 2.0668098659358565,
1692
+ "grad_norm": 0.05712890625,
1693
+ "learning_rate": 4.5896537059013536e-05,
1694
+ "loss": 0.0175,
1695
+ "step": 218
1696
+ },
1697
+ {
1698
+ "epoch": 2.076290645137397,
1699
+ "grad_norm": 0.056396484375,
1700
+ "learning_rate": 4.503316656627294e-05,
1701
+ "loss": 0.0193,
1702
+ "step": 219
1703
+ },
1704
+ {
1705
+ "epoch": 2.085771424338938,
1706
+ "grad_norm": 0.06298828125,
1707
+ "learning_rate": 4.417562779731355e-05,
1708
+ "loss": 0.0175,
1709
+ "step": 220
1710
+ },
1711
+ {
1712
+ "epoch": 2.085771424338938,
1713
+ "eval_loss": 0.03771064057946205,
1714
+ "eval_runtime": 36.0692,
1715
+ "eval_samples_per_second": 19.712,
1716
+ "eval_steps_per_second": 19.712,
1717
+ "step": 220
1718
+ },
1719
+ {
1720
+ "epoch": 2.0952522035404786,
1721
+ "grad_norm": 0.0693359375,
1722
+ "learning_rate": 4.3324011732985433e-05,
1723
+ "loss": 0.0205,
1724
+ "step": 221
1725
+ },
1726
+ {
1727
+ "epoch": 2.104732982742019,
1728
+ "grad_norm": 0.0693359375,
1729
+ "learning_rate": 4.247840872576739e-05,
1730
+ "loss": 0.0184,
1731
+ "step": 222
1732
+ },
1733
+ {
1734
+ "epoch": 2.1142137619435597,
1735
+ "grad_norm": 0.0634765625,
1736
+ "learning_rate": 4.163890849018114e-05,
1737
+ "loss": 0.0191,
1738
+ "step": 223
1739
+ },
1740
+ {
1741
+ "epoch": 2.1236945411451003,
1742
+ "grad_norm": 0.057373046875,
1743
+ "learning_rate": 4.0805600093272735e-05,
1744
+ "loss": 0.0157,
1745
+ "step": 224
1746
+ },
1747
+ {
1748
+ "epoch": 2.133175320346641,
1749
+ "grad_norm": 0.06640625,
1750
+ "learning_rate": 3.997857194516319e-05,
1751
+ "loss": 0.019,
1752
+ "step": 225
1753
+ },
1754
+ {
1755
+ "epoch": 2.142656099548182,
1756
+ "grad_norm": 0.06494140625,
1757
+ "learning_rate": 3.9157911789668525e-05,
1758
+ "loss": 0.0173,
1759
+ "step": 226
1760
+ },
1761
+ {
1762
+ "epoch": 2.1521368787497224,
1763
+ "grad_norm": 0.064453125,
1764
+ "learning_rate": 3.8343706694990465e-05,
1765
+ "loss": 0.0169,
1766
+ "step": 227
1767
+ },
1768
+ {
1769
+ "epoch": 2.161617657951263,
1770
+ "grad_norm": 0.06689453125,
1771
+ "learning_rate": 3.753604304447915e-05,
1772
+ "loss": 0.0166,
1773
+ "step": 228
1774
+ },
1775
+ {
1776
+ "epoch": 2.1710984371528035,
1777
+ "grad_norm": 0.076171875,
1778
+ "learning_rate": 3.6735006527467965e-05,
1779
+ "loss": 0.0166,
1780
+ "step": 229
1781
+ },
1782
+ {
1783
+ "epoch": 2.180579216354344,
1784
+ "grad_norm": 0.064453125,
1785
+ "learning_rate": 3.594068213018249e-05,
1786
+ "loss": 0.0172,
1787
+ "step": 230
1788
+ },
1789
+ {
1790
+ "epoch": 2.1900599955558846,
1791
+ "grad_norm": 0.06884765625,
1792
+ "learning_rate": 3.515315412672384e-05,
1793
+ "loss": 0.0168,
1794
+ "step": 231
1795
+ },
1796
+ {
1797
+ "epoch": 2.1900599955558846,
1798
+ "eval_loss": 0.03964013606309891,
1799
+ "eval_runtime": 36.2659,
1800
+ "eval_samples_per_second": 19.605,
1801
+ "eval_steps_per_second": 19.605,
1802
+ "step": 231
1803
+ },
1804
+ {
1805
+ "epoch": 2.199540774757425,
1806
+ "grad_norm": 0.0751953125,
1807
+ "learning_rate": 3.437250607012748e-05,
1808
+ "loss": 0.0166,
1809
+ "step": 232
1810
+ },
1811
+ {
1812
+ "epoch": 2.209021553958966,
1813
+ "grad_norm": 0.072265625,
1814
+ "learning_rate": 3.359882078349883e-05,
1815
+ "loss": 0.0181,
1816
+ "step": 233
1817
+ },
1818
+ {
1819
+ "epoch": 2.2185023331605067,
1820
+ "grad_norm": 0.0673828125,
1821
+ "learning_rate": 3.283218035122592e-05,
1822
+ "loss": 0.0179,
1823
+ "step": 234
1824
+ },
1825
+ {
1826
+ "epoch": 2.2279831123620473,
1827
+ "grad_norm": 0.09130859375,
1828
+ "learning_rate": 3.207266611027069e-05,
1829
+ "loss": 0.016,
1830
+ "step": 235
1831
+ },
1832
+ {
1833
+ "epoch": 2.237463891563588,
1834
+ "grad_norm": 0.08447265625,
1835
+ "learning_rate": 3.132035864153958e-05,
1836
+ "loss": 0.0192,
1837
+ "step": 236
1838
+ },
1839
+ {
1840
+ "epoch": 2.2469446707651284,
1841
+ "grad_norm": 0.08154296875,
1842
+ "learning_rate": 3.057533776133421e-05,
1843
+ "loss": 0.0183,
1844
+ "step": 237
1845
+ },
1846
+ {
1847
+ "epoch": 2.2564254499666694,
1848
+ "grad_norm": 0.06640625,
1849
+ "learning_rate": 2.98376825128832e-05,
1850
+ "loss": 0.0146,
1851
+ "step": 238
1852
+ },
1853
+ {
1854
+ "epoch": 2.26590622916821,
1855
+ "grad_norm": 0.07373046875,
1856
+ "learning_rate": 2.910747115795628e-05,
1857
+ "loss": 0.0171,
1858
+ "step": 239
1859
+ },
1860
+ {
1861
+ "epoch": 2.2753870083697505,
1862
+ "grad_norm": 0.072265625,
1863
+ "learning_rate": 2.8384781168560693e-05,
1864
+ "loss": 0.0168,
1865
+ "step": 240
1866
+ },
1867
+ {
1868
+ "epoch": 2.284867787571291,
1869
+ "grad_norm": 0.0859375,
1870
+ "learning_rate": 2.766968921872213e-05,
1871
+ "loss": 0.0166,
1872
+ "step": 241
1873
+ },
1874
+ {
1875
+ "epoch": 2.2943485667728316,
1876
+ "grad_norm": 0.07470703125,
1877
+ "learning_rate": 2.6962271176349852e-05,
1878
+ "loss": 0.0182,
1879
+ "step": 242
1880
+ },
1881
+ {
1882
+ "epoch": 2.2943485667728316,
1883
+ "eval_loss": 0.04028235375881195,
1884
+ "eval_runtime": 36.1866,
1885
+ "eval_samples_per_second": 19.648,
1886
+ "eval_steps_per_second": 19.648,
1887
+ "step": 242
1888
+ },
1889
+ {
1890
+ "epoch": 2.303829345974372,
1891
+ "grad_norm": 0.06640625,
1892
+ "learning_rate": 2.626260209518737e-05,
1893
+ "loss": 0.0159,
1894
+ "step": 243
1895
+ },
1896
+ {
1897
+ "epoch": 2.3133101251759127,
1898
+ "grad_norm": 0.06884765625,
1899
+ "learning_rate": 2.5570756206849832e-05,
1900
+ "loss": 0.0154,
1901
+ "step": 244
1902
+ },
1903
+ {
1904
+ "epoch": 2.3227909043774533,
1905
+ "grad_norm": 0.064453125,
1906
+ "learning_rate": 2.4886806912948035e-05,
1907
+ "loss": 0.0148,
1908
+ "step": 245
1909
+ },
1910
+ {
1911
+ "epoch": 2.3322716835789943,
1912
+ "grad_norm": 0.07080078125,
1913
+ "learning_rate": 2.4210826777301153e-05,
1914
+ "loss": 0.0175,
1915
+ "step": 246
1916
+ },
1917
+ {
1918
+ "epoch": 2.341752462780535,
1919
+ "grad_norm": 0.06494140625,
1920
+ "learning_rate": 2.3542887518238056e-05,
1921
+ "loss": 0.0155,
1922
+ "step": 247
1923
+ },
1924
+ {
1925
+ "epoch": 2.3512332419820754,
1926
+ "grad_norm": 0.078125,
1927
+ "learning_rate": 2.288306000098811e-05,
1928
+ "loss": 0.0166,
1929
+ "step": 248
1930
+ },
1931
+ {
1932
+ "epoch": 2.360714021183616,
1933
+ "grad_norm": 0.083984375,
1934
+ "learning_rate": 2.2231414230162894e-05,
1935
+ "loss": 0.022,
1936
+ "step": 249
1937
+ },
1938
+ {
1939
+ "epoch": 2.3701948003851565,
1940
+ "grad_norm": 0.09033203125,
1941
+ "learning_rate": 2.1588019342328968e-05,
1942
+ "loss": 0.0234,
1943
+ "step": 250
1944
+ },
1945
+ {
1946
+ "epoch": 2.3796755795866975,
1947
+ "grad_norm": 0.07666015625,
1948
+ "learning_rate": 2.0952943598672846e-05,
1949
+ "loss": 0.0176,
1950
+ "step": 251
1951
+ },
1952
+ {
1953
+ "epoch": 2.389156358788238,
1954
+ "grad_norm": 0.06982421875,
1955
+ "learning_rate": 2.0326254377758703e-05,
1956
+ "loss": 0.0189,
1957
+ "step": 252
1958
+ },
1959
+ {
1960
+ "epoch": 2.3986371379897786,
1961
+ "grad_norm": 0.0751953125,
1962
+ "learning_rate": 1.9708018168380037e-05,
1963
+ "loss": 0.0201,
1964
+ "step": 253
1965
+ },
1966
+ {
1967
+ "epoch": 2.3986371379897786,
1968
+ "eval_loss": 0.039680514484643936,
1969
+ "eval_runtime": 36.0607,
1970
+ "eval_samples_per_second": 19.717,
1971
+ "eval_steps_per_second": 19.717,
1972
+ "step": 253
1973
+ },
1974
+ {
1975
+ "epoch": 2.408117917191319,
1976
+ "grad_norm": 0.06298828125,
1977
+ "learning_rate": 1.9098300562505266e-05,
1978
+ "loss": 0.0147,
1979
+ "step": 254
1980
+ },
1981
+ {
1982
+ "epoch": 2.4175986963928597,
1983
+ "grad_norm": 0.0634765625,
1984
+ "learning_rate": 1.8497166248318876e-05,
1985
+ "loss": 0.0172,
1986
+ "step": 255
1987
+ },
1988
+ {
1989
+ "epoch": 2.4270794755944003,
1990
+ "grad_norm": 0.08349609375,
1991
+ "learning_rate": 1.7904679003358283e-05,
1992
+ "loss": 0.0173,
1993
+ "step": 256
1994
+ },
1995
+ {
1996
+ "epoch": 2.436560254795941,
1997
+ "grad_norm": 0.07177734375,
1998
+ "learning_rate": 1.7320901687747292e-05,
1999
+ "loss": 0.0174,
2000
+ "step": 257
2001
+ },
2002
+ {
2003
+ "epoch": 2.446041033997482,
2004
+ "grad_norm": 0.08203125,
2005
+ "learning_rate": 1.674589623752707e-05,
2006
+ "loss": 0.0184,
2007
+ "step": 258
2008
+ },
2009
+ {
2010
+ "epoch": 2.4555218131990224,
2011
+ "grad_norm": 0.0947265625,
2012
+ "learning_rate": 1.617972365808481e-05,
2013
+ "loss": 0.0192,
2014
+ "step": 259
2015
+ },
2016
+ {
2017
+ "epoch": 2.465002592400563,
2018
+ "grad_norm": 0.06005859375,
2019
+ "learning_rate": 1.562244401768144e-05,
2020
+ "loss": 0.0129,
2021
+ "step": 260
2022
+ },
2023
+ {
2024
+ "epoch": 2.4744833716021035,
2025
+ "grad_norm": 0.0791015625,
2026
+ "learning_rate": 1.507411644107879e-05,
2027
+ "loss": 0.0215,
2028
+ "step": 261
2029
+ },
2030
+ {
2031
+ "epoch": 2.483964150803644,
2032
+ "grad_norm": 0.078125,
2033
+ "learning_rate": 1.4534799103266505e-05,
2034
+ "loss": 0.0194,
2035
+ "step": 262
2036
+ },
2037
+ {
2038
+ "epoch": 2.4934449300051846,
2039
+ "grad_norm": 0.07275390625,
2040
+ "learning_rate": 1.4004549223290164e-05,
2041
+ "loss": 0.0168,
2042
+ "step": 263
2043
+ },
2044
+ {
2045
+ "epoch": 2.5029257092067256,
2046
+ "grad_norm": 0.05810546875,
2047
+ "learning_rate": 1.3483423058180421e-05,
2048
+ "loss": 0.0138,
2049
+ "step": 264
2050
+ },
2051
+ {
2052
+ "epoch": 2.5029257092067256,
2053
+ "eval_loss": 0.039309222251176834,
2054
+ "eval_runtime": 36.2397,
2055
+ "eval_samples_per_second": 19.619,
2056
+ "eval_steps_per_second": 19.619,
2057
+ "step": 264
2058
+ },
2059
+ {
2060
+ "epoch": 2.512406488408266,
2061
+ "grad_norm": 0.06787109375,
2062
+ "learning_rate": 1.2971475896984475e-05,
2063
+ "loss": 0.0157,
2064
+ "step": 265
2065
+ }
2066
+ ],
2067
+ "logging_steps": 1,
2068
+ "max_steps": 315,
2069
+ "num_input_tokens_seen": 0,
2070
+ "num_train_epochs": 3,
2071
+ "save_steps": 53,
2072
+ "stateful_callbacks": {
2073
+ "TrainerControl": {
2074
+ "args": {
2075
+ "should_epoch_stop": false,
2076
+ "should_evaluate": false,
2077
+ "should_log": false,
2078
+ "should_save": true,
2079
+ "should_training_stop": false
2080
+ },
2081
+ "attributes": {}
2082
+ }
2083
+ },
2084
+ "total_flos": 4.742595805273129e+17,
2085
+ "train_batch_size": 1,
2086
+ "trial_name": null,
2087
+ "trial_params": null
2088
+ }
checkpoint-265/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c51879fef6458d108abda667041e5749acf5fcdaa68cbc3d11f59cd677f2e93
3
+ size 6072
checkpoint-315/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: NousResearch/Meta-Llama-3-8B-Instruct
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 0.11.1
checkpoint-315/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "up_proj",
28
+ "gate_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }