Hugging Face's logo

sn56a4
/
b9f27a84-be8d-45d2-abb3-773f959abab4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
RoyJoy commited on
Commit
92c1e80
·
verified ·
1 Parent(s): 845c1a2

End of training

Browse files
Files changed (24) hide show
  1. .gitattributes +1 -0
  2. README.md +182 -0
  3. adapter_config.json +34 -0
  4. adapter_model.bin +3 -0
  5. adapter_model.safetensors +3 -0
  6. config.json +37 -0
  7. last-checkpoint/README.md +202 -0
  8. last-checkpoint/adapter_config.json +34 -0
  9. last-checkpoint/adapter_model.safetensors +3 -0
  10. last-checkpoint/optimizer.pt +3 -0
  11. last-checkpoint/rng_state_0.pth +3 -0
  12. last-checkpoint/rng_state_1.pth +3 -0
  13. last-checkpoint/rng_state_2.pth +3 -0
  14. last-checkpoint/rng_state_3.pth +3 -0
  15. last-checkpoint/scheduler.pt +3 -0
  16. last-checkpoint/special_tokens_map.json +23 -0
  17. last-checkpoint/tokenizer.json +3 -0
  18. last-checkpoint/tokenizer_config.json +2064 -0
  19. last-checkpoint/trainer_state.json +2612 -0
  20. last-checkpoint/training_args.bin +3 -0
  21. special_tokens_map.json +23 -0
  22. tokenizer.json +3 -0
  23. tokenizer_config.json +2064 -0
  24. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: unsloth/Hermes-3-Llama-3.1-8B
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: b9f27a84-be8d-45d2-abb3-773f959abab4
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
16
+ <details><summary>See axolotl config</summary>
17
+
18
+ axolotl version: `0.4.1`
19
+ ```yaml
20
+ adapter: lora
21
+ base_model: unsloth/Hermes-3-Llama-3.1-8B
22
+ bf16: auto
23
+ chat_template: llama3
24
+ cosine_min_lr_ratio: 0.1
25
+ data_processes: 16
26
+ dataset_prepared_path: null
27
+ datasets:
28
+ - data_files:
29
+ - 5c3f012d6f350a11_train_data.json
30
+ ds_type: json
31
+ format: custom
32
+ path: /workspace/input_data/5c3f012d6f350a11_train_data.json
33
+ type:
34
+ field_instruction: abstract
35
+ field_output: related_work
36
+ format: '{instruction}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ deepspeed: null
42
+ device_map: '{'''':torch.cuda.current_device()}'
43
+ do_eval: true
44
+ early_stopping_patience: 1
45
+ eval_batch_size: 1
46
+ eval_sample_packing: false
47
+ eval_steps: 25
48
+ evaluation_strategy: steps
49
+ flash_attention: true
50
+ fp16: null
51
+ fsdp: null
52
+ fsdp_config: null
53
+ gradient_accumulation_steps: 64
54
+ gradient_checkpointing: true
55
+ group_by_length: true
56
+ hub_model_id: sn56a4/b9f27a84-be8d-45d2-abb3-773f959abab4
57
+ hub_repo: stevemonite
58
+ hub_strategy: checkpoint
59
+ hub_token: null
60
+ learning_rate: 0.0001
61
+ load_in_4bit: false
62
+ load_in_8bit: false
63
+ local_rank: null
64
+ logging_steps: 1
65
+ lora_alpha: 64
66
+ lora_dropout: 0.05
67
+ lora_fan_in_fan_out: null
68
+ lora_model_dir: null
69
+ lora_r: 32
70
+ lora_target_linear: true
71
+ lora_target_modules:
72
+ - q_proj
73
+ - v_proj
74
+ lr_scheduler: cosine
75
+ max_grad_norm: 1.0
76
+ max_memory:
77
+ 0: 70GiB
78
+ max_steps: 500
79
+ micro_batch_size: 1
80
+ mlflow_experiment_name: /tmp/5c3f012d6f350a11_train_data.json
81
+ model_type: AutoModelForCausalLM
82
+ num_epochs: 4
83
+ optim_args:
84
+ adam_beta1: 0.9
85
+ adam_beta2: 0.95
86
+ adam_epsilon: 1e-5
87
+ optimizer: adamw_torch
88
+ output_dir: miner_id_24
89
+ pad_to_sequence_len: true
90
+ resume_from_checkpoint: null
91
+ s2_attention: null
92
+ sample_packing: false
93
+ save_steps: 50
94
+ save_strategy: steps
95
+ sequence_len: 2048
96
+ strict: false
97
+ tf32: false
98
+ tokenizer_type: AutoTokenizer
99
+ torch_compile: false
100
+ train_on_inputs: false
101
+ trust_remote_code: true
102
+ val_set_size: 50
103
+ wandb_entity: sn56-miner
104
+ wandb_mode: disabled
105
+ wandb_name: b9f27a84-be8d-45d2-abb3-773f959abab4
106
+ wandb_project: god
107
+ wandb_run: 2d93
108
+ wandb_runid: b9f27a84-be8d-45d2-abb3-773f959abab4
109
+ warmup_raio: 0.03
110
+ warmup_ratio: 0.05
111
+ weight_decay: 0.01
112
+ xformers_attention: null
113
+
114
+ ```
115
+
116
+ </details><br>
117
+
118
+ # b9f27a84-be8d-45d2-abb3-773f959abab4
119
+
120
+ This model is a fine-tuned version of [unsloth/Hermes-3-Llama-3.1-8B](https://huggingface.co/unsloth/Hermes-3-Llama-3.1-8B) on the None dataset.
121
+ It achieves the following results on the evaluation set:
122
+ - Loss: 2.3066
123
+
124
+ ## Model description
125
+
126
+ More information needed
127
+
128
+ ## Intended uses & limitations
129
+
130
+ More information needed
131
+
132
+ ## Training and evaluation data
133
+
134
+ More information needed
135
+
136
+ ## Training procedure
137
+
138
+ ### Training hyperparameters
139
+
140
+ The following hyperparameters were used during training:
141
+ - learning_rate: 0.0001
142
+ - train_batch_size: 1
143
+ - eval_batch_size: 1
144
+ - seed: 42
145
+ - distributed_type: multi-GPU
146
+ - num_devices: 4
147
+ - gradient_accumulation_steps: 64
148
+ - total_train_batch_size: 256
149
+ - total_eval_batch_size: 4
150
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
151
+ - lr_scheduler_type: cosine
152
+ - lr_scheduler_warmup_steps: 25
153
+ - training_steps: 500
154
+
155
+ ### Training results
156
+
157
+ | Training Loss | Epoch | Step | Validation Loss |
158
+ |:-------------:|:------:|:----:|:---------------:|
159
+ | 2.6656 | 0.0064 | 1 | 3.0489 |
160
+ | 2.4528 | 0.1589 | 25 | 2.3822 |
161
+ | 2.4471 | 0.3178 | 50 | 2.3415 |
162
+ | 2.3992 | 0.4767 | 75 | 2.3316 |
163
+ | 2.3613 | 0.6356 | 100 | 2.3197 |
164
+ | 2.3707 | 0.7944 | 125 | 2.3157 |
165
+ | 2.3419 | 0.9533 | 150 | 2.3092 |
166
+ | 2.255 | 1.1122 | 175 | 2.3080 |
167
+ | 2.228 | 1.2711 | 200 | 2.3091 |
168
+ | 2.2652 | 1.4300 | 225 | 2.3084 |
169
+ | 2.2084 | 1.5889 | 250 | 2.3041 |
170
+ | 2.2238 | 1.7478 | 275 | 2.3029 |
171
+ | 2.2119 | 1.9067 | 300 | 2.3020 |
172
+ | 2.2045 | 2.0655 | 325 | 2.3016 |
173
+ | 2.1767 | 2.2244 | 350 | 2.3066 |
174
+
175
+
176
+ ### Framework versions
177
+
178
+ - PEFT 0.13.2
179
+ - Transformers 4.46.0
180
+ - Pytorch 2.5.0+cu124
181
+ - Datasets 3.0.1
182
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Hermes-3-Llama-3.1-8B",
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": 64,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "k_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:bbed03358ba11f73feaaa95065a58446ae813377c3d1fc71c8f3d2b2d805cea8
3
+ size 335706186
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6b441e5a407e166d75de29ae94a3955500ad7021ce6dca594b68aff59f6d6ed
3
+ size 335604696
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "unsloth/Hermes-3-Llama-3.1-8B",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 128000,
10
+ "eos_token_id": 128040,
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 32,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 8,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.46.0",
35
+ "use_cache": false,
36
+ "vocab_size": 128256
37
+ }
last-checkpoint/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Hermes-3-Llama-3.1-8B
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 0.13.2
last-checkpoint/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Hermes-3-Llama-3.1-8B",
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": 64,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "gate_proj",
25
+ "v_proj",
26
+ "q_proj",
27
+ "o_proj",
28
+ "k_proj",
29
+ "down_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
last-checkpoint/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30263ee37a2d68a7092f89eb8fa7493fe6f8735c772e021332473d7fcac0680b
3
+ size 335604696
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46b0498e23611388191f2115cb6dceb214463dd39243d7304b3cad927146750
3
+ size 671466706
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6999b9489bb7350f42339a6e403dbb7f9b68ad8f2757bcf005b72ef226794cb
3
+ size 15024
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ce49388e1c9528f986f55439875157d89a4871e8e7acd10dbbd2c4a9c1bc530
3
+ size 15024
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b00fa031576decf3df4a9b5c441241f45eac22271ca0abe7bfa2975f83834a
3
+ size 15024
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b61c20b54b5fd3227b51531ad3983ccdfc8e54598920e059bbf33d95d6d3558
3
+ size 15024
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4112ab6a51bcb64d14b5b501c1d18a2f1bd9a7dc366fede565410f8f2533667f
3
+ size 1064
last-checkpoint/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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
3
+ size 17209403
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<tool_call>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "<tool_response>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<tools>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "128012": {
100
+ "content": "</tools>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "128013": {
108
+ "content": "</tool_call>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<schema>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</schema>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<scratch_pad>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</scratch_pad>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<SCRATCHPAD>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "128020": {
164
+ "content": "</SCRATCHPAD>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "128021": {
172
+ "content": "<REASONING>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "128022": {
180
+ "content": "</REASONING>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "128023": {
188
+ "content": "<INNER_MONOLOGUE>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "128024": {
196
+ "content": "</INNER_MONOLOGUE>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "128025": {
204
+ "content": "<PLAN>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "128026": {
212
+ "content": "</PLAN>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "128027": {
220
+ "content": "<EXECUTION>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "128028": {
228
+ "content": "</EXECUTION>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "128029": {
236
+ "content": "<REFLECTION>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "128030": {
244
+ "content": "</REFLECTION>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "128031": {
252
+ "content": "<THINKING>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "128032": {
260
+ "content": "</THINKING>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "128033": {
268
+ "content": "<SOLUTION>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "128034": {
276
+ "content": "</SOLUTION>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "128035": {
284
+ "content": "<EXPLANATION>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "128036": {
292
+ "content": "</EXPLANATION>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "128037": {
300
+ "content": "<UNIT_TEST>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "128038": {
308
+ "content": "</UNIT_TEST>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "128039": {
316
+ "content": "<|im_start|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "128040": {
324
+ "content": "<|im_end|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<|im_end|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|finetune_right_pad_id|>",
2062
+ "padding_side": "left",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,2612 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.3020389080047607,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-300",
4
+ "epoch": 2.224428997020854,
5
+ "eval_steps": 25,
6
+ "global_step": 350,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.006355511420059583,
13
+ "grad_norm": 1.0325596332550049,
14
+ "learning_rate": 4.000000000000001e-06,
15
+ "loss": 2.6656,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.006355511420059583,
20
+ "eval_loss": 3.048880100250244,
21
+ "eval_runtime": 1.5231,
22
+ "eval_samples_per_second": 32.828,
23
+ "eval_steps_per_second": 8.535,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.012711022840119166,
28
+ "grad_norm": 1.0420786142349243,
29
+ "learning_rate": 8.000000000000001e-06,
30
+ "loss": 2.8138,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.01906653426017875,
35
+ "grad_norm": 1.088529109954834,
36
+ "learning_rate": 1.2e-05,
37
+ "loss": 2.8629,
38
+ "step": 3
39
+ },
40
+ {
41
+ "epoch": 0.02542204568023833,
42
+ "grad_norm": 1.1031228303909302,
43
+ "learning_rate": 1.6000000000000003e-05,
44
+ "loss": 2.8688,
45
+ "step": 4
46
+ },
47
+ {
48
+ "epoch": 0.031777557100297914,
49
+ "grad_norm": 1.1524335145950317,
50
+ "learning_rate": 2e-05,
51
+ "loss": 2.9404,
52
+ "step": 5
53
+ },
54
+ {
55
+ "epoch": 0.0381330685203575,
56
+ "grad_norm": 1.1310076713562012,
57
+ "learning_rate": 2.4e-05,
58
+ "loss": 2.9749,
59
+ "step": 6
60
+ },
61
+ {
62
+ "epoch": 0.04448857994041708,
63
+ "grad_norm": 1.1206061840057373,
64
+ "learning_rate": 2.8000000000000003e-05,
65
+ "loss": 2.9806,
66
+ "step": 7
67
+ },
68
+ {
69
+ "epoch": 0.05084409136047666,
70
+ "grad_norm": 1.0996730327606201,
71
+ "learning_rate": 3.2000000000000005e-05,
72
+ "loss": 2.9687,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.05719960278053625,
77
+ "grad_norm": 1.1184650659561157,
78
+ "learning_rate": 3.6e-05,
79
+ "loss": 2.9386,
80
+ "step": 9
81
+ },
82
+ {
83
+ "epoch": 0.06355511420059583,
84
+ "grad_norm": 1.036566138267517,
85
+ "learning_rate": 4e-05,
86
+ "loss": 2.9295,
87
+ "step": 10
88
+ },
89
+ {
90
+ "epoch": 0.0699106256206554,
91
+ "grad_norm": 0.9670718908309937,
92
+ "learning_rate": 4.4000000000000006e-05,
93
+ "loss": 2.8833,
94
+ "step": 11
95
+ },
96
+ {
97
+ "epoch": 0.076266137040715,
98
+ "grad_norm": 0.881925106048584,
99
+ "learning_rate": 4.8e-05,
100
+ "loss": 2.927,
101
+ "step": 12
102
+ },
103
+ {
104
+ "epoch": 0.08262164846077458,
105
+ "grad_norm": 0.5375174880027771,
106
+ "learning_rate": 5.2000000000000004e-05,
107
+ "loss": 2.5305,
108
+ "step": 13
109
+ },
110
+ {
111
+ "epoch": 0.08897715988083416,
112
+ "grad_norm": 0.5931983590126038,
113
+ "learning_rate": 5.6000000000000006e-05,
114
+ "loss": 2.4271,
115
+ "step": 14
116
+ },
117
+ {
118
+ "epoch": 0.09533267130089375,
119
+ "grad_norm": 0.7447495460510254,
120
+ "learning_rate": 6e-05,
121
+ "loss": 2.5033,
122
+ "step": 15
123
+ },
124
+ {
125
+ "epoch": 0.10168818272095333,
126
+ "grad_norm": 0.7662708759307861,
127
+ "learning_rate": 6.400000000000001e-05,
128
+ "loss": 2.4669,
129
+ "step": 16
130
+ },
131
+ {
132
+ "epoch": 0.1080436941410129,
133
+ "grad_norm": 0.6223545670509338,
134
+ "learning_rate": 6.800000000000001e-05,
135
+ "loss": 2.5253,
136
+ "step": 17
137
+ },
138
+ {
139
+ "epoch": 0.1143992055610725,
140
+ "grad_norm": 0.4566957950592041,
141
+ "learning_rate": 7.2e-05,
142
+ "loss": 2.4488,
143
+ "step": 18
144
+ },
145
+ {
146
+ "epoch": 0.12075471698113208,
147
+ "grad_norm": 0.4528411030769348,
148
+ "learning_rate": 7.6e-05,
149
+ "loss": 2.473,
150
+ "step": 19
151
+ },
152
+ {
153
+ "epoch": 0.12711022840119166,
154
+ "grad_norm": 0.483684778213501,
155
+ "learning_rate": 8e-05,
156
+ "loss": 2.4748,
157
+ "step": 20
158
+ },
159
+ {
160
+ "epoch": 0.13346573982125123,
161
+ "grad_norm": 0.5484008193016052,
162
+ "learning_rate": 8.4e-05,
163
+ "loss": 2.4173,
164
+ "step": 21
165
+ },
166
+ {
167
+ "epoch": 0.1398212512413108,
168
+ "grad_norm": 0.4574620723724365,
169
+ "learning_rate": 8.800000000000001e-05,
170
+ "loss": 2.4398,
171
+ "step": 22
172
+ },
173
+ {
174
+ "epoch": 0.14617676266137042,
175
+ "grad_norm": 0.47648435831069946,
176
+ "learning_rate": 9.200000000000001e-05,
177
+ "loss": 2.4981,
178
+ "step": 23
179
+ },
180
+ {
181
+ "epoch": 0.15253227408143,
182
+ "grad_norm": 0.5476519465446472,
183
+ "learning_rate": 9.6e-05,
184
+ "loss": 2.444,
185
+ "step": 24
186
+ },
187
+ {
188
+ "epoch": 0.15888778550148958,
189
+ "grad_norm": 0.4673982560634613,
190
+ "learning_rate": 0.0001,
191
+ "loss": 2.4528,
192
+ "step": 25
193
+ },
194
+ {
195
+ "epoch": 0.15888778550148958,
196
+ "eval_loss": 2.3822436332702637,
197
+ "eval_runtime": 1.5183,
198
+ "eval_samples_per_second": 32.931,
199
+ "eval_steps_per_second": 8.562,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.16524329692154915,
204
+ "grad_norm": 0.5420854091644287,
205
+ "learning_rate": 9.999901577711012e-05,
206
+ "loss": 2.2626,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.17159880834160873,
211
+ "grad_norm": 0.30429136753082275,
212
+ "learning_rate": 9.999606315149354e-05,
213
+ "loss": 2.2942,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 0.1779543197616683,
218
+ "grad_norm": 0.34320351481437683,
219
+ "learning_rate": 9.999114225230768e-05,
220
+ "loss": 2.2941,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 0.18430983118172792,
225
+ "grad_norm": 0.33083945512771606,
226
+ "learning_rate": 9.998425329480863e-05,
227
+ "loss": 2.2932,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 0.1906653426017875,
232
+ "grad_norm": 0.2973347306251526,
233
+ "learning_rate": 9.997539658034168e-05,
234
+ "loss": 2.3531,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 0.19702085402184707,
239
+ "grad_norm": 0.25613513588905334,
240
+ "learning_rate": 9.996457249632824e-05,
241
+ "loss": 2.3587,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 0.20337636544190665,
246
+ "grad_norm": 0.2822609841823578,
247
+ "learning_rate": 9.995178151624878e-05,
248
+ "loss": 2.3298,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 0.20973187686196623,
253
+ "grad_norm": 0.285084992647171,
254
+ "learning_rate": 9.993702419962222e-05,
255
+ "loss": 2.3383,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 0.2160873882820258,
260
+ "grad_norm": 0.2707081735134125,
261
+ "learning_rate": 9.992030119198141e-05,
262
+ "loss": 2.3304,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 0.2224428997020854,
267
+ "grad_norm": 0.2771173119544983,
268
+ "learning_rate": 9.990161322484486e-05,
269
+ "loss": 2.3881,
270
+ "step": 35
271
+ },
272
+ {
273
+ "epoch": 0.228798411122145,
274
+ "grad_norm": 0.29547515511512756,
275
+ "learning_rate": 9.98809611156848e-05,
276
+ "loss": 2.4241,
277
+ "step": 36
278
+ },
279
+ {
280
+ "epoch": 0.23515392254220457,
281
+ "grad_norm": 0.3037785589694977,
282
+ "learning_rate": 9.985834576789139e-05,
283
+ "loss": 2.4045,
284
+ "step": 37
285
+ },
286
+ {
287
+ "epoch": 0.24150943396226415,
288
+ "grad_norm": 0.28193172812461853,
289
+ "learning_rate": 9.98337681707332e-05,
290
+ "loss": 2.2701,
291
+ "step": 38
292
+ },
293
+ {
294
+ "epoch": 0.24786494538232373,
295
+ "grad_norm": 0.2882024347782135,
296
+ "learning_rate": 9.980722939931397e-05,
297
+ "loss": 2.2449,
298
+ "step": 39
299
+ },
300
+ {
301
+ "epoch": 0.2542204568023833,
302
+ "grad_norm": 0.23482859134674072,
303
+ "learning_rate": 9.977873061452552e-05,
304
+ "loss": 2.2612,
305
+ "step": 40
306
+ },
307
+ {
308
+ "epoch": 0.2605759682224429,
309
+ "grad_norm": 0.23729859292507172,
310
+ "learning_rate": 9.974827306299701e-05,
311
+ "loss": 2.2733,
312
+ "step": 41
313
+ },
314
+ {
315
+ "epoch": 0.26693147964250247,
316
+ "grad_norm": 0.2491757571697235,
317
+ "learning_rate": 9.971585807704043e-05,
318
+ "loss": 2.2879,
319
+ "step": 42
320
+ },
321
+ {
322
+ "epoch": 0.27328699106256205,
323
+ "grad_norm": 0.24617433547973633,
324
+ "learning_rate": 9.968148707459226e-05,
325
+ "loss": 2.3188,
326
+ "step": 43
327
+ },
328
+ {
329
+ "epoch": 0.2796425024826216,
330
+ "grad_norm": 0.2435063272714615,
331
+ "learning_rate": 9.964516155915151e-05,
332
+ "loss": 2.3403,
333
+ "step": 44
334
+ },
335
+ {
336
+ "epoch": 0.28599801390268126,
337
+ "grad_norm": 0.24399644136428833,
338
+ "learning_rate": 9.96068831197139e-05,
339
+ "loss": 2.3412,
340
+ "step": 45
341
+ },
342
+ {
343
+ "epoch": 0.29235352532274084,
344
+ "grad_norm": 0.23476773500442505,
345
+ "learning_rate": 9.956665343070234e-05,
346
+ "loss": 2.3319,
347
+ "step": 46
348
+ },
349
+ {
350
+ "epoch": 0.2987090367428004,
351
+ "grad_norm": 0.22632542252540588,
352
+ "learning_rate": 9.952447425189382e-05,
353
+ "loss": 2.3437,
354
+ "step": 47
355
+ },
356
+ {
357
+ "epoch": 0.30506454816286,
358
+ "grad_norm": 0.2366076111793518,
359
+ "learning_rate": 9.948034742834223e-05,
360
+ "loss": 2.2949,
361
+ "step": 48
362
+ },
363
+ {
364
+ "epoch": 0.3114200595829196,
365
+ "grad_norm": 0.26805731654167175,
366
+ "learning_rate": 9.943427489029776e-05,
367
+ "loss": 2.3785,
368
+ "step": 49
369
+ },
370
+ {
371
+ "epoch": 0.31777557100297915,
372
+ "grad_norm": 0.267456591129303,
373
+ "learning_rate": 9.938625865312251e-05,
374
+ "loss": 2.4471,
375
+ "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.31777557100297915,
379
+ "eval_loss": 2.3415367603302,
380
+ "eval_runtime": 1.5184,
381
+ "eval_samples_per_second": 32.929,
382
+ "eval_steps_per_second": 8.561,
383
+ "step": 50
384
+ },
385
+ {
386
+ "epoch": 0.32413108242303873,
387
+ "grad_norm": 0.3944738507270813,
388
+ "learning_rate": 9.933630081720224e-05,
389
+ "loss": 2.2108,
390
+ "step": 51
391
+ },
392
+ {
393
+ "epoch": 0.3304865938430983,
394
+ "grad_norm": 0.3037647306919098,
395
+ "learning_rate": 9.928440356785453e-05,
396
+ "loss": 2.2115,
397
+ "step": 52
398
+ },
399
+ {
400
+ "epoch": 0.3368421052631579,
401
+ "grad_norm": 0.19321414828300476,
402
+ "learning_rate": 9.923056917523317e-05,
403
+ "loss": 2.2587,
404
+ "step": 53
405
+ },
406
+ {
407
+ "epoch": 0.34319761668321747,
408
+ "grad_norm": 0.21396860480308533,
409
+ "learning_rate": 9.917479999422893e-05,
410
+ "loss": 2.2546,
411
+ "step": 54
412
+ },
413
+ {
414
+ "epoch": 0.34955312810327704,
415
+ "grad_norm": 0.2524327039718628,
416
+ "learning_rate": 9.911709846436641e-05,
417
+ "loss": 2.2853,
418
+ "step": 55
419
+ },
420
+ {
421
+ "epoch": 0.3559086395233366,
422
+ "grad_norm": 0.272514671087265,
423
+ "learning_rate": 9.905746710969752e-05,
424
+ "loss": 2.316,
425
+ "step": 56
426
+ },
427
+ {
428
+ "epoch": 0.3622641509433962,
429
+ "grad_norm": 0.2834374010562897,
430
+ "learning_rate": 9.899590853869082e-05,
431
+ "loss": 2.3255,
432
+ "step": 57
433
+ },
434
+ {
435
+ "epoch": 0.36861966236345584,
436
+ "grad_norm": 0.28034257888793945,
437
+ "learning_rate": 9.893242544411769e-05,
438
+ "loss": 2.2957,
439
+ "step": 58
440
+ },
441
+ {
442
+ "epoch": 0.3749751737835154,
443
+ "grad_norm": 0.2554794251918793,
444
+ "learning_rate": 9.886702060293428e-05,
445
+ "loss": 2.3178,
446
+ "step": 59
447
+ },
448
+ {
449
+ "epoch": 0.381330685203575,
450
+ "grad_norm": 0.2238798439502716,
451
+ "learning_rate": 9.879969687616027e-05,
452
+ "loss": 2.3311,
453
+ "step": 60
454
+ },
455
+ {
456
+ "epoch": 0.38768619662363457,
457
+ "grad_norm": 0.2381383776664734,
458
+ "learning_rate": 9.873045720875356e-05,
459
+ "loss": 2.3277,
460
+ "step": 61
461
+ },
462
+ {
463
+ "epoch": 0.39404170804369415,
464
+ "grad_norm": 0.2427409589290619,
465
+ "learning_rate": 9.86593046294815e-05,
466
+ "loss": 2.3349,
467
+ "step": 62
468
+ },
469
+ {
470
+ "epoch": 0.40039721946375373,
471
+ "grad_norm": 0.358292818069458,
472
+ "learning_rate": 9.858624225078841e-05,
473
+ "loss": 2.225,
474
+ "step": 63
475
+ },
476
+ {
477
+ "epoch": 0.4067527308838133,
478
+ "grad_norm": 0.39267364144325256,
479
+ "learning_rate": 9.851127326865942e-05,
480
+ "loss": 2.2436,
481
+ "step": 64
482
+ },
483
+ {
484
+ "epoch": 0.4131082423038729,
485
+ "grad_norm": 0.3032839000225067,
486
+ "learning_rate": 9.84344009624807e-05,
487
+ "loss": 2.2565,
488
+ "step": 65
489
+ },
490
+ {
491
+ "epoch": 0.41946375372393246,
492
+ "grad_norm": 0.19790630042552948,
493
+ "learning_rate": 9.835562869489592e-05,
494
+ "loss": 2.2335,
495
+ "step": 66
496
+ },
497
+ {
498
+ "epoch": 0.42581926514399204,
499
+ "grad_norm": 0.1997576355934143,
500
+ "learning_rate": 9.827495991165928e-05,
501
+ "loss": 2.3198,
502
+ "step": 67
503
+ },
504
+ {
505
+ "epoch": 0.4321747765640516,
506
+ "grad_norm": 0.2273276150226593,
507
+ "learning_rate": 9.819239814148465e-05,
508
+ "loss": 2.2859,
509
+ "step": 68
510
+ },
511
+ {
512
+ "epoch": 0.4385302879841112,
513
+ "grad_norm": 0.23212000727653503,
514
+ "learning_rate": 9.810794699589136e-05,
515
+ "loss": 2.3063,
516
+ "step": 69
517
+ },
518
+ {
519
+ "epoch": 0.4448857994041708,
520
+ "grad_norm": 0.28264597058296204,
521
+ "learning_rate": 9.80216101690461e-05,
522
+ "loss": 2.3192,
523
+ "step": 70
524
+ },
525
+ {
526
+ "epoch": 0.4512413108242304,
527
+ "grad_norm": 0.2699751853942871,
528
+ "learning_rate": 9.793339143760134e-05,
529
+ "loss": 2.3158,
530
+ "step": 71
531
+ },
532
+ {
533
+ "epoch": 0.45759682224429,
534
+ "grad_norm": 0.27674010396003723,
535
+ "learning_rate": 9.78432946605302e-05,
536
+ "loss": 2.3544,
537
+ "step": 72
538
+ },
539
+ {
540
+ "epoch": 0.46395233366434957,
541
+ "grad_norm": 0.2847268581390381,
542
+ "learning_rate": 9.775132377895759e-05,
543
+ "loss": 2.3427,
544
+ "step": 73
545
+ },
546
+ {
547
+ "epoch": 0.47030784508440915,
548
+ "grad_norm": 0.28473466634750366,
549
+ "learning_rate": 9.765748281598781e-05,
550
+ "loss": 2.413,
551
+ "step": 74
552
+ },
553
+ {
554
+ "epoch": 0.4766633565044687,
555
+ "grad_norm": 0.3029725253582001,
556
+ "learning_rate": 9.756177587652856e-05,
557
+ "loss": 2.3992,
558
+ "step": 75
559
+ },
560
+ {
561
+ "epoch": 0.4766633565044687,
562
+ "eval_loss": 2.33160400390625,
563
+ "eval_runtime": 1.5146,
564
+ "eval_samples_per_second": 33.011,
565
+ "eval_steps_per_second": 8.583,
566
+ "step": 75
567
+ },
568
+ {
569
+ "epoch": 0.4830188679245283,
570
+ "grad_norm": 0.29245060682296753,
571
+ "learning_rate": 9.746420714711145e-05,
572
+ "loss": 2.214,
573
+ "step": 76
574
+ },
575
+ {
576
+ "epoch": 0.4893743793445879,
577
+ "grad_norm": 0.3461180627346039,
578
+ "learning_rate": 9.736478089570876e-05,
579
+ "loss": 2.235,
580
+ "step": 77
581
+ },
582
+ {
583
+ "epoch": 0.49572989076464746,
584
+ "grad_norm": 0.3213370144367218,
585
+ "learning_rate": 9.726350147154684e-05,
586
+ "loss": 2.2504,
587
+ "step": 78
588
+ },
589
+ {
590
+ "epoch": 0.5020854021847071,
591
+ "grad_norm": 0.27867868542671204,
592
+ "learning_rate": 9.716037330491581e-05,
593
+ "loss": 2.2916,
594
+ "step": 79
595
+ },
596
+ {
597
+ "epoch": 0.5084409136047666,
598
+ "grad_norm": 0.22331157326698303,
599
+ "learning_rate": 9.705540090697575e-05,
600
+ "loss": 2.308,
601
+ "step": 80
602
+ },
603
+ {
604
+ "epoch": 0.5147964250248263,
605
+ "grad_norm": 0.20336903631687164,
606
+ "learning_rate": 9.694858886955939e-05,
607
+ "loss": 2.3218,
608
+ "step": 81
609
+ },
610
+ {
611
+ "epoch": 0.5211519364448858,
612
+ "grad_norm": 0.1989986002445221,
613
+ "learning_rate": 9.683994186497132e-05,
614
+ "loss": 2.3078,
615
+ "step": 82
616
+ },
617
+ {
618
+ "epoch": 0.5275074478649454,
619
+ "grad_norm": 0.2182929366827011,
620
+ "learning_rate": 9.672946464578345e-05,
621
+ "loss": 2.2963,
622
+ "step": 83
623
+ },
624
+ {
625
+ "epoch": 0.5338629592850049,
626
+ "grad_norm": 0.2390328347682953,
627
+ "learning_rate": 9.661716204462726e-05,
628
+ "loss": 2.3042,
629
+ "step": 84
630
+ },
631
+ {
632
+ "epoch": 0.5402184707050646,
633
+ "grad_norm": 0.2556857764720917,
634
+ "learning_rate": 9.650303897398232e-05,
635
+ "loss": 2.3292,
636
+ "step": 85
637
+ },
638
+ {
639
+ "epoch": 0.5465739821251241,
640
+ "grad_norm": 0.2651096284389496,
641
+ "learning_rate": 9.638710042596146e-05,
642
+ "loss": 2.3699,
643
+ "step": 86
644
+ },
645
+ {
646
+ "epoch": 0.5529294935451837,
647
+ "grad_norm": 0.3168967068195343,
648
+ "learning_rate": 9.626935147209235e-05,
649
+ "loss": 2.3616,
650
+ "step": 87
651
+ },
652
+ {
653
+ "epoch": 0.5592850049652432,
654
+ "grad_norm": 0.20625124871730804,
655
+ "learning_rate": 9.61497972630957e-05,
656
+ "loss": 2.1843,
657
+ "step": 88
658
+ },
659
+ {
660
+ "epoch": 0.5656405163853029,
661
+ "grad_norm": 0.1992497742176056,
662
+ "learning_rate": 9.602844302865991e-05,
663
+ "loss": 2.2148,
664
+ "step": 89
665
+ },
666
+ {
667
+ "epoch": 0.5719960278053625,
668
+ "grad_norm": 0.1892700493335724,
669
+ "learning_rate": 9.590529407721231e-05,
670
+ "loss": 2.2376,
671
+ "step": 90
672
+ },
673
+ {
674
+ "epoch": 0.578351539225422,
675
+ "grad_norm": 0.20010621845722198,
676
+ "learning_rate": 9.5780355795687e-05,
677
+ "loss": 2.2592,
678
+ "step": 91
679
+ },
680
+ {
681
+ "epoch": 0.5847070506454817,
682
+ "grad_norm": 0.19509659707546234,
683
+ "learning_rate": 9.565363364928918e-05,
684
+ "loss": 2.2988,
685
+ "step": 92
686
+ },
687
+ {
688
+ "epoch": 0.5910625620655412,
689
+ "grad_norm": 0.19188611209392548,
690
+ "learning_rate": 9.552513318125601e-05,
691
+ "loss": 2.2892,
692
+ "step": 93
693
+ },
694
+ {
695
+ "epoch": 0.5974180734856008,
696
+ "grad_norm": 0.19146832823753357,
697
+ "learning_rate": 9.539486001261425e-05,
698
+ "loss": 2.278,
699
+ "step": 94
700
+ },
701
+ {
702
+ "epoch": 0.6037735849056604,
703
+ "grad_norm": 0.19962391257286072,
704
+ "learning_rate": 9.526281984193436e-05,
705
+ "loss": 2.3137,
706
+ "step": 95
707
+ },
708
+ {
709
+ "epoch": 0.61012909632572,
710
+ "grad_norm": 0.1991351693868637,
711
+ "learning_rate": 9.512901844508113e-05,
712
+ "loss": 2.3096,
713
+ "step": 96
714
+ },
715
+ {
716
+ "epoch": 0.6164846077457795,
717
+ "grad_norm": 0.21442659199237823,
718
+ "learning_rate": 9.499346167496111e-05,
719
+ "loss": 2.273,
720
+ "step": 97
721
+ },
722
+ {
723
+ "epoch": 0.6228401191658391,
724
+ "grad_norm": 0.22641701996326447,
725
+ "learning_rate": 9.48561554612666e-05,
726
+ "loss": 2.3529,
727
+ "step": 98
728
+ },
729
+ {
730
+ "epoch": 0.6291956305858987,
731
+ "grad_norm": 0.25172799825668335,
732
+ "learning_rate": 9.471710581021616e-05,
733
+ "loss": 2.3311,
734
+ "step": 99
735
+ },
736
+ {
737
+ "epoch": 0.6355511420059583,
738
+ "grad_norm": 0.3153717815876007,
739
+ "learning_rate": 9.4576318804292e-05,
740
+ "loss": 2.3613,
741
+ "step": 100
742
+ },
743
+ {
744
+ "epoch": 0.6355511420059583,
745
+ "eval_loss": 2.3197498321533203,
746
+ "eval_runtime": 1.5172,
747
+ "eval_samples_per_second": 32.956,
748
+ "eval_steps_per_second": 8.569,
749
+ "step": 100
750
+ },
751
+ {
752
+ "epoch": 0.6419066534260178,
753
+ "grad_norm": 0.20079869031906128,
754
+ "learning_rate": 9.443380060197387e-05,
755
+ "loss": 2.1528,
756
+ "step": 101
757
+ },
758
+ {
759
+ "epoch": 0.6482621648460775,
760
+ "grad_norm": 0.192522794008255,
761
+ "learning_rate": 9.428955743746959e-05,
762
+ "loss": 2.1741,
763
+ "step": 102
764
+ },
765
+ {
766
+ "epoch": 0.6546176762661371,
767
+ "grad_norm": 0.206144317984581,
768
+ "learning_rate": 9.414359562044249e-05,
769
+ "loss": 2.2418,
770
+ "step": 103
771
+ },
772
+ {
773
+ "epoch": 0.6609731876861966,
774
+ "grad_norm": 0.18696987628936768,
775
+ "learning_rate": 9.399592153573528e-05,
776
+ "loss": 2.2845,
777
+ "step": 104
778
+ },
779
+ {
780
+ "epoch": 0.6673286991062563,
781
+ "grad_norm": 0.19477424025535583,
782
+ "learning_rate": 9.384654164309083e-05,
783
+ "loss": 2.2476,
784
+ "step": 105
785
+ },
786
+ {
787
+ "epoch": 0.6736842105263158,
788
+ "grad_norm": 0.190853089094162,
789
+ "learning_rate": 9.369546247686956e-05,
790
+ "loss": 2.2939,
791
+ "step": 106
792
+ },
793
+ {
794
+ "epoch": 0.6800397219463754,
795
+ "grad_norm": 0.19710804522037506,
796
+ "learning_rate": 9.354269064576366e-05,
797
+ "loss": 2.3026,
798
+ "step": 107
799
+ },
800
+ {
801
+ "epoch": 0.6863952333664349,
802
+ "grad_norm": 0.2065049558877945,
803
+ "learning_rate": 9.338823283250788e-05,
804
+ "loss": 2.2893,
805
+ "step": 108
806
+ },
807
+ {
808
+ "epoch": 0.6927507447864946,
809
+ "grad_norm": 0.20753198862075806,
810
+ "learning_rate": 9.323209579358741e-05,
811
+ "loss": 2.2999,
812
+ "step": 109
813
+ },
814
+ {
815
+ "epoch": 0.6991062562065541,
816
+ "grad_norm": 0.22989068925380707,
817
+ "learning_rate": 9.30742863589421e-05,
818
+ "loss": 2.3231,
819
+ "step": 110
820
+ },
821
+ {
822
+ "epoch": 0.7054617676266137,
823
+ "grad_norm": 0.2674986720085144,
824
+ "learning_rate": 9.291481143166785e-05,
825
+ "loss": 2.347,
826
+ "step": 111
827
+ },
828
+ {
829
+ "epoch": 0.7118172790466732,
830
+ "grad_norm": 0.2671983242034912,
831
+ "learning_rate": 9.275367798771466e-05,
832
+ "loss": 2.3922,
833
+ "step": 112
834
+ },
835
+ {
836
+ "epoch": 0.7181727904667329,
837
+ "grad_norm": 0.195315882563591,
838
+ "learning_rate": 9.259089307558131e-05,
839
+ "loss": 2.2213,
840
+ "step": 113
841
+ },
842
+ {
843
+ "epoch": 0.7245283018867924,
844
+ "grad_norm": 0.21104182302951813,
845
+ "learning_rate": 9.242646381600722e-05,
846
+ "loss": 2.1741,
847
+ "step": 114
848
+ },
849
+ {
850
+ "epoch": 0.730883813306852,
851
+ "grad_norm": 0.20763593912124634,
852
+ "learning_rate": 9.226039740166091e-05,
853
+ "loss": 2.2043,
854
+ "step": 115
855
+ },
856
+ {
857
+ "epoch": 0.7372393247269117,
858
+ "grad_norm": 0.19103097915649414,
859
+ "learning_rate": 9.20927010968253e-05,
860
+ "loss": 2.226,
861
+ "step": 116
862
+ },
863
+ {
864
+ "epoch": 0.7435948361469712,
865
+ "grad_norm": 0.18663343787193298,
866
+ "learning_rate": 9.192338223708001e-05,
867
+ "loss": 2.2858,
868
+ "step": 117
869
+ },
870
+ {
871
+ "epoch": 0.7499503475670308,
872
+ "grad_norm": 0.19490988552570343,
873
+ "learning_rate": 9.17524482289805e-05,
874
+ "loss": 2.2627,
875
+ "step": 118
876
+ },
877
+ {
878
+ "epoch": 0.7563058589870904,
879
+ "grad_norm": 0.2018275409936905,
880
+ "learning_rate": 9.157990654973406e-05,
881
+ "loss": 2.2956,
882
+ "step": 119
883
+ },
884
+ {
885
+ "epoch": 0.76266137040715,
886
+ "grad_norm": 0.2031106799840927,
887
+ "learning_rate": 9.140576474687264e-05,
888
+ "loss": 2.2458,
889
+ "step": 120
890
+ },
891
+ {
892
+ "epoch": 0.7690168818272095,
893
+ "grad_norm": 0.23179922997951508,
894
+ "learning_rate": 9.123003043792289e-05,
895
+ "loss": 2.3205,
896
+ "step": 121
897
+ },
898
+ {
899
+ "epoch": 0.7753723932472691,
900
+ "grad_norm": 0.22383373975753784,
901
+ "learning_rate": 9.105271131007274e-05,
902
+ "loss": 2.3469,
903
+ "step": 122
904
+ },
905
+ {
906
+ "epoch": 0.7817279046673287,
907
+ "grad_norm": 0.23412999510765076,
908
+ "learning_rate": 9.087381511983533e-05,
909
+ "loss": 2.3372,
910
+ "step": 123
911
+ },
912
+ {
913
+ "epoch": 0.7880834160873883,
914
+ "grad_norm": 0.2633383870124817,
915
+ "learning_rate": 9.069334969270952e-05,
916
+ "loss": 2.3711,
917
+ "step": 124
918
+ },
919
+ {
920
+ "epoch": 0.7944389275074478,
921
+ "grad_norm": 0.30396324396133423,
922
+ "learning_rate": 9.051132292283771e-05,
923
+ "loss": 2.3707,
924
+ "step": 125
925
+ },
926
+ {
927
+ "epoch": 0.7944389275074478,
928
+ "eval_loss": 2.315741777420044,
929
+ "eval_runtime": 1.5174,
930
+ "eval_samples_per_second": 32.952,
931
+ "eval_steps_per_second": 8.567,
932
+ "step": 125
933
+ },
934
+ {
935
+ "epoch": 0.8007944389275075,
936
+ "grad_norm": 0.22050084173679352,
937
+ "learning_rate": 9.032774277266055e-05,
938
+ "loss": 2.1661,
939
+ "step": 126
940
+ },
941
+ {
942
+ "epoch": 0.807149950347567,
943
+ "grad_norm": 0.21925196051597595,
944
+ "learning_rate": 9.014261727256849e-05,
945
+ "loss": 2.2644,
946
+ "step": 127
947
+ },
948
+ {
949
+ "epoch": 0.8135054617676266,
950
+ "grad_norm": 0.22117425501346588,
951
+ "learning_rate": 8.995595452055063e-05,
952
+ "loss": 2.2411,
953
+ "step": 128
954
+ },
955
+ {
956
+ "epoch": 0.8198609731876862,
957
+ "grad_norm": 0.2100037783384323,
958
+ "learning_rate": 8.976776268184046e-05,
959
+ "loss": 2.2934,
960
+ "step": 129
961
+ },
962
+ {
963
+ "epoch": 0.8262164846077458,
964
+ "grad_norm": 0.19347529113292694,
965
+ "learning_rate": 8.957804998855866e-05,
966
+ "loss": 2.2816,
967
+ "step": 130
968
+ },
969
+ {
970
+ "epoch": 0.8325719960278054,
971
+ "grad_norm": 0.20554985105991364,
972
+ "learning_rate": 8.9386824739353e-05,
973
+ "loss": 2.2956,
974
+ "step": 131
975
+ },
976
+ {
977
+ "epoch": 0.8389275074478649,
978
+ "grad_norm": 0.20611408352851868,
979
+ "learning_rate": 8.91940952990354e-05,
980
+ "loss": 2.2646,
981
+ "step": 132
982
+ },
983
+ {
984
+ "epoch": 0.8452830188679246,
985
+ "grad_norm": 0.21916787326335907,
986
+ "learning_rate": 8.899987009821588e-05,
987
+ "loss": 2.2886,
988
+ "step": 133
989
+ },
990
+ {
991
+ "epoch": 0.8516385302879841,
992
+ "grad_norm": 0.22573725879192352,
993
+ "learning_rate": 8.880415763293398e-05,
994
+ "loss": 2.3545,
995
+ "step": 134
996
+ },
997
+ {
998
+ "epoch": 0.8579940417080437,
999
+ "grad_norm": 0.2310296893119812,
1000
+ "learning_rate": 8.860696646428693e-05,
1001
+ "loss": 2.358,
1002
+ "step": 135
1003
+ },
1004
+ {
1005
+ "epoch": 0.8643495531281032,
1006
+ "grad_norm": 0.2535010874271393,
1007
+ "learning_rate": 8.840830521805525e-05,
1008
+ "loss": 2.3319,
1009
+ "step": 136
1010
+ },
1011
+ {
1012
+ "epoch": 0.8707050645481629,
1013
+ "grad_norm": 0.2632582187652588,
1014
+ "learning_rate": 8.820818258432543e-05,
1015
+ "loss": 2.398,
1016
+ "step": 137
1017
+ },
1018
+ {
1019
+ "epoch": 0.8770605759682224,
1020
+ "grad_norm": 0.2051229327917099,
1021
+ "learning_rate": 8.800660731710981e-05,
1022
+ "loss": 2.1818,
1023
+ "step": 138
1024
+ },
1025
+ {
1026
+ "epoch": 0.883416087388282,
1027
+ "grad_norm": 0.20393678545951843,
1028
+ "learning_rate": 8.780358823396352e-05,
1029
+ "loss": 2.2193,
1030
+ "step": 139
1031
+ },
1032
+ {
1033
+ "epoch": 0.8897715988083416,
1034
+ "grad_norm": 0.20247992873191833,
1035
+ "learning_rate": 8.759913421559902e-05,
1036
+ "loss": 2.2192,
1037
+ "step": 140
1038
+ },
1039
+ {
1040
+ "epoch": 0.8961271102284012,
1041
+ "grad_norm": 0.184554785490036,
1042
+ "learning_rate": 8.739325420549735e-05,
1043
+ "loss": 2.2526,
1044
+ "step": 141
1045
+ },
1046
+ {
1047
+ "epoch": 0.9024826216484608,
1048
+ "grad_norm": 0.182277649641037,
1049
+ "learning_rate": 8.718595720951716e-05,
1050
+ "loss": 2.2645,
1051
+ "step": 142
1052
+ },
1053
+ {
1054
+ "epoch": 0.9088381330685203,
1055
+ "grad_norm": 0.18679510056972504,
1056
+ "learning_rate": 8.697725229550056e-05,
1057
+ "loss": 2.2691,
1058
+ "step": 143
1059
+ },
1060
+ {
1061
+ "epoch": 0.91519364448858,
1062
+ "grad_norm": 0.22123658657073975,
1063
+ "learning_rate": 8.676714859287666e-05,
1064
+ "loss": 2.3247,
1065
+ "step": 144
1066
+ },
1067
+ {
1068
+ "epoch": 0.9215491559086395,
1069
+ "grad_norm": 0.21452046930789948,
1070
+ "learning_rate": 8.655565529226198e-05,
1071
+ "loss": 2.2906,
1072
+ "step": 145
1073
+ },
1074
+ {
1075
+ "epoch": 0.9279046673286991,
1076
+ "grad_norm": 0.20037704706192017,
1077
+ "learning_rate": 8.63427816450587e-05,
1078
+ "loss": 2.3089,
1079
+ "step": 146
1080
+ },
1081
+ {
1082
+ "epoch": 0.9342601787487587,
1083
+ "grad_norm": 0.22000561654567719,
1084
+ "learning_rate": 8.612853696304972e-05,
1085
+ "loss": 2.3329,
1086
+ "step": 147
1087
+ },
1088
+ {
1089
+ "epoch": 0.9406156901688183,
1090
+ "grad_norm": 0.234726682305336,
1091
+ "learning_rate": 8.591293061799151e-05,
1092
+ "loss": 2.3468,
1093
+ "step": 148
1094
+ },
1095
+ {
1096
+ "epoch": 0.9469712015888778,
1097
+ "grad_norm": 0.26201295852661133,
1098
+ "learning_rate": 8.569597204120405e-05,
1099
+ "loss": 2.3253,
1100
+ "step": 149
1101
+ },
1102
+ {
1103
+ "epoch": 0.9533267130089375,
1104
+ "grad_norm": 0.29040974378585815,
1105
+ "learning_rate": 8.547767072315835e-05,
1106
+ "loss": 2.3419,
1107
+ "step": 150
1108
+ },
1109
+ {
1110
+ "epoch": 0.9533267130089375,
1111
+ "eval_loss": 2.3092103004455566,
1112
+ "eval_runtime": 1.5112,
1113
+ "eval_samples_per_second": 33.086,
1114
+ "eval_steps_per_second": 8.602,
1115
+ "step": 150
1116
+ },
1117
+ {
1118
+ "epoch": 0.959682224428997,
1119
+ "grad_norm": 0.2169644832611084,
1120
+ "learning_rate": 8.525803621306125e-05,
1121
+ "loss": 2.1579,
1122
+ "step": 151
1123
+ },
1124
+ {
1125
+ "epoch": 0.9660377358490566,
1126
+ "grad_norm": 0.22146862745285034,
1127
+ "learning_rate": 8.503707811843776e-05,
1128
+ "loss": 2.2482,
1129
+ "step": 152
1130
+ },
1131
+ {
1132
+ "epoch": 0.9723932472691161,
1133
+ "grad_norm": 0.20775218307971954,
1134
+ "learning_rate": 8.481480610471074e-05,
1135
+ "loss": 2.2864,
1136
+ "step": 153
1137
+ },
1138
+ {
1139
+ "epoch": 0.9787487586891758,
1140
+ "grad_norm": 0.19807898998260498,
1141
+ "learning_rate": 8.459122989477812e-05,
1142
+ "loss": 2.2205,
1143
+ "step": 154
1144
+ },
1145
+ {
1146
+ "epoch": 0.9851042701092354,
1147
+ "grad_norm": 0.20046639442443848,
1148
+ "learning_rate": 8.436635926858759e-05,
1149
+ "loss": 2.2656,
1150
+ "step": 155
1151
+ },
1152
+ {
1153
+ "epoch": 0.9914597815292949,
1154
+ "grad_norm": 0.2276119440793991,
1155
+ "learning_rate": 8.414020406270885e-05,
1156
+ "loss": 2.3151,
1157
+ "step": 156
1158
+ },
1159
+ {
1160
+ "epoch": 0.9978152929493546,
1161
+ "grad_norm": 0.27005627751350403,
1162
+ "learning_rate": 8.391277416990325e-05,
1163
+ "loss": 2.4165,
1164
+ "step": 157
1165
+ },
1166
+ {
1167
+ "epoch": 1.0041708043694142,
1168
+ "grad_norm": 0.5210186839103699,
1169
+ "learning_rate": 8.368407953869104e-05,
1170
+ "loss": 3.7234,
1171
+ "step": 158
1172
+ },
1173
+ {
1174
+ "epoch": 1.0105263157894737,
1175
+ "grad_norm": 0.19428348541259766,
1176
+ "learning_rate": 8.345413017291629e-05,
1177
+ "loss": 2.2085,
1178
+ "step": 159
1179
+ },
1180
+ {
1181
+ "epoch": 1.0168818272095332,
1182
+ "grad_norm": 0.1905713677406311,
1183
+ "learning_rate": 8.322293613130917e-05,
1184
+ "loss": 2.1292,
1185
+ "step": 160
1186
+ },
1187
+ {
1188
+ "epoch": 1.0232373386295928,
1189
+ "grad_norm": 0.1900564432144165,
1190
+ "learning_rate": 8.299050752704604e-05,
1191
+ "loss": 2.2072,
1192
+ "step": 161
1193
+ },
1194
+ {
1195
+ "epoch": 1.0295928500496525,
1196
+ "grad_norm": 0.21950459480285645,
1197
+ "learning_rate": 8.2756854527307e-05,
1198
+ "loss": 2.2603,
1199
+ "step": 162
1200
+ },
1201
+ {
1202
+ "epoch": 1.035948361469712,
1203
+ "grad_norm": 0.19662953913211823,
1204
+ "learning_rate": 8.25219873528312e-05,
1205
+ "loss": 2.229,
1206
+ "step": 163
1207
+ },
1208
+ {
1209
+ "epoch": 1.0423038728897716,
1210
+ "grad_norm": 0.18510112166404724,
1211
+ "learning_rate": 8.228591627746971e-05,
1212
+ "loss": 2.2301,
1213
+ "step": 164
1214
+ },
1215
+ {
1216
+ "epoch": 1.048659384309831,
1217
+ "grad_norm": 0.19516927003860474,
1218
+ "learning_rate": 8.204865162773613e-05,
1219
+ "loss": 2.2738,
1220
+ "step": 165
1221
+ },
1222
+ {
1223
+ "epoch": 1.0550148957298908,
1224
+ "grad_norm": 0.21637625992298126,
1225
+ "learning_rate": 8.181020378235487e-05,
1226
+ "loss": 2.2239,
1227
+ "step": 166
1228
+ },
1229
+ {
1230
+ "epoch": 1.0613704071499503,
1231
+ "grad_norm": 0.2477208524942398,
1232
+ "learning_rate": 8.157058317180717e-05,
1233
+ "loss": 2.2268,
1234
+ "step": 167
1235
+ },
1236
+ {
1237
+ "epoch": 1.0677259185700099,
1238
+ "grad_norm": 0.24189040064811707,
1239
+ "learning_rate": 8.132980027787478e-05,
1240
+ "loss": 2.284,
1241
+ "step": 168
1242
+ },
1243
+ {
1244
+ "epoch": 1.0740814299900696,
1245
+ "grad_norm": 0.2541358172893524,
1246
+ "learning_rate": 8.108786563318149e-05,
1247
+ "loss": 2.3687,
1248
+ "step": 169
1249
+ },
1250
+ {
1251
+ "epoch": 1.0804369414101291,
1252
+ "grad_norm": 0.18166010081768036,
1253
+ "learning_rate": 8.084478982073247e-05,
1254
+ "loss": 1.7402,
1255
+ "step": 170
1256
+ },
1257
+ {
1258
+ "epoch": 1.0867924528301887,
1259
+ "grad_norm": 0.266977995634079,
1260
+ "learning_rate": 8.060058347345116e-05,
1261
+ "loss": 2.552,
1262
+ "step": 171
1263
+ },
1264
+ {
1265
+ "epoch": 1.0931479642502482,
1266
+ "grad_norm": 0.23321004211902618,
1267
+ "learning_rate": 8.035525727371436e-05,
1268
+ "loss": 2.2316,
1269
+ "step": 172
1270
+ },
1271
+ {
1272
+ "epoch": 1.099503475670308,
1273
+ "grad_norm": 0.21595069766044617,
1274
+ "learning_rate": 8.010882195288474e-05,
1275
+ "loss": 2.187,
1276
+ "step": 173
1277
+ },
1278
+ {
1279
+ "epoch": 1.1058589870903675,
1280
+ "grad_norm": 0.21202905476093292,
1281
+ "learning_rate": 7.986128829084161e-05,
1282
+ "loss": 2.2375,
1283
+ "step": 174
1284
+ },
1285
+ {
1286
+ "epoch": 1.112214498510427,
1287
+ "grad_norm": 0.19656386971473694,
1288
+ "learning_rate": 7.961266711550922e-05,
1289
+ "loss": 2.255,
1290
+ "step": 175
1291
+ },
1292
+ {
1293
+ "epoch": 1.112214498510427,
1294
+ "eval_loss": 2.307997226715088,
1295
+ "eval_runtime": 1.5241,
1296
+ "eval_samples_per_second": 32.806,
1297
+ "eval_steps_per_second": 8.53,
1298
+ "step": 175
1299
+ },
1300
+ {
1301
+ "epoch": 1.1185700099304865,
1302
+ "grad_norm": 0.19530202448368073,
1303
+ "learning_rate": 7.936296930238321e-05,
1304
+ "loss": 2.2553,
1305
+ "step": 176
1306
+ },
1307
+ {
1308
+ "epoch": 1.1249255213505462,
1309
+ "grad_norm": 0.21238934993743896,
1310
+ "learning_rate": 7.911220577405484e-05,
1311
+ "loss": 2.2186,
1312
+ "step": 177
1313
+ },
1314
+ {
1315
+ "epoch": 1.1312810327706058,
1316
+ "grad_norm": 0.23509657382965088,
1317
+ "learning_rate": 7.886038749973323e-05,
1318
+ "loss": 2.3107,
1319
+ "step": 178
1320
+ },
1321
+ {
1322
+ "epoch": 1.1376365441906653,
1323
+ "grad_norm": 0.24010643362998962,
1324
+ "learning_rate": 7.860752549476542e-05,
1325
+ "loss": 2.1726,
1326
+ "step": 179
1327
+ },
1328
+ {
1329
+ "epoch": 1.1439920556107248,
1330
+ "grad_norm": 0.2709186375141144,
1331
+ "learning_rate": 7.835363082015468e-05,
1332
+ "loss": 2.3172,
1333
+ "step": 180
1334
+ },
1335
+ {
1336
+ "epoch": 1.1503475670307846,
1337
+ "grad_norm": 0.28436481952667236,
1338
+ "learning_rate": 7.809871458207661e-05,
1339
+ "loss": 2.2812,
1340
+ "step": 181
1341
+ },
1342
+ {
1343
+ "epoch": 1.156703078450844,
1344
+ "grad_norm": 0.31739431619644165,
1345
+ "learning_rate": 7.784278793139327e-05,
1346
+ "loss": 2.3839,
1347
+ "step": 182
1348
+ },
1349
+ {
1350
+ "epoch": 1.1630585898709036,
1351
+ "grad_norm": 0.21542128920555115,
1352
+ "learning_rate": 7.758586206316541e-05,
1353
+ "loss": 2.1472,
1354
+ "step": 183
1355
+ },
1356
+ {
1357
+ "epoch": 1.1694141012909633,
1358
+ "grad_norm": 0.22317935526371002,
1359
+ "learning_rate": 7.73279482161629e-05,
1360
+ "loss": 2.1553,
1361
+ "step": 184
1362
+ },
1363
+ {
1364
+ "epoch": 1.1757696127110229,
1365
+ "grad_norm": 0.23224414885044098,
1366
+ "learning_rate": 7.706905767237288e-05,
1367
+ "loss": 2.1696,
1368
+ "step": 185
1369
+ },
1370
+ {
1371
+ "epoch": 1.1821251241310824,
1372
+ "grad_norm": 0.24323226511478424,
1373
+ "learning_rate": 7.680920175650643e-05,
1374
+ "loss": 2.2503,
1375
+ "step": 186
1376
+ },
1377
+ {
1378
+ "epoch": 1.188480635551142,
1379
+ "grad_norm": 0.21809925138950348,
1380
+ "learning_rate": 7.654839183550313e-05,
1381
+ "loss": 2.2149,
1382
+ "step": 187
1383
+ },
1384
+ {
1385
+ "epoch": 1.1948361469712017,
1386
+ "grad_norm": 0.23086406290531158,
1387
+ "learning_rate": 7.628663931803385e-05,
1388
+ "loss": 2.2521,
1389
+ "step": 188
1390
+ },
1391
+ {
1392
+ "epoch": 1.2011916583912612,
1393
+ "grad_norm": 0.2139970064163208,
1394
+ "learning_rate": 7.602395565400164e-05,
1395
+ "loss": 2.1947,
1396
+ "step": 189
1397
+ },
1398
+ {
1399
+ "epoch": 1.2075471698113207,
1400
+ "grad_norm": 0.21761485934257507,
1401
+ "learning_rate": 7.576035233404096e-05,
1402
+ "loss": 2.2688,
1403
+ "step": 190
1404
+ },
1405
+ {
1406
+ "epoch": 1.2139026812313802,
1407
+ "grad_norm": 0.22911959886550903,
1408
+ "learning_rate": 7.549584088901496e-05,
1409
+ "loss": 2.2788,
1410
+ "step": 191
1411
+ },
1412
+ {
1413
+ "epoch": 1.22025819265144,
1414
+ "grad_norm": 0.2622755765914917,
1415
+ "learning_rate": 7.523043288951118e-05,
1416
+ "loss": 2.2542,
1417
+ "step": 192
1418
+ },
1419
+ {
1420
+ "epoch": 1.2266137040714995,
1421
+ "grad_norm": 0.2699742913246155,
1422
+ "learning_rate": 7.496413994533529e-05,
1423
+ "loss": 2.3287,
1424
+ "step": 193
1425
+ },
1426
+ {
1427
+ "epoch": 1.232969215491559,
1428
+ "grad_norm": 0.30408114194869995,
1429
+ "learning_rate": 7.469697370500334e-05,
1430
+ "loss": 2.2232,
1431
+ "step": 194
1432
+ },
1433
+ {
1434
+ "epoch": 1.2393247269116188,
1435
+ "grad_norm": 0.21685215830802917,
1436
+ "learning_rate": 7.442894585523218e-05,
1437
+ "loss": 1.7735,
1438
+ "step": 195
1439
+ },
1440
+ {
1441
+ "epoch": 1.2456802383316783,
1442
+ "grad_norm": 0.24521103501319885,
1443
+ "learning_rate": 7.416006812042828e-05,
1444
+ "loss": 2.5295,
1445
+ "step": 196
1446
+ },
1447
+ {
1448
+ "epoch": 1.2520357497517378,
1449
+ "grad_norm": 0.2069530487060547,
1450
+ "learning_rate": 7.389035226217476e-05,
1451
+ "loss": 2.1908,
1452
+ "step": 197
1453
+ },
1454
+ {
1455
+ "epoch": 1.2583912611717973,
1456
+ "grad_norm": 0.2179119735956192,
1457
+ "learning_rate": 7.361981007871704e-05,
1458
+ "loss": 2.2555,
1459
+ "step": 198
1460
+ },
1461
+ {
1462
+ "epoch": 1.264746772591857,
1463
+ "grad_norm": 0.21959730982780457,
1464
+ "learning_rate": 7.334845340444667e-05,
1465
+ "loss": 2.222,
1466
+ "step": 199
1467
+ },
1468
+ {
1469
+ "epoch": 1.2711022840119166,
1470
+ "grad_norm": 0.20434822142124176,
1471
+ "learning_rate": 7.307629410938363e-05,
1472
+ "loss": 2.228,
1473
+ "step": 200
1474
+ },
1475
+ {
1476
+ "epoch": 1.2711022840119166,
1477
+ "eval_loss": 2.3091487884521484,
1478
+ "eval_runtime": 1.5117,
1479
+ "eval_samples_per_second": 33.075,
1480
+ "eval_steps_per_second": 8.599,
1481
+ "step": 200
1482
+ },
1483
+ {
1484
+ "epoch": 1.2774577954319761,
1485
+ "grad_norm": 0.2185506969690323,
1486
+ "learning_rate": 7.280334409865717e-05,
1487
+ "loss": 2.2782,
1488
+ "step": 201
1489
+ },
1490
+ {
1491
+ "epoch": 1.2838133068520357,
1492
+ "grad_norm": 0.21776600182056427,
1493
+ "learning_rate": 7.252961531198501e-05,
1494
+ "loss": 2.1926,
1495
+ "step": 202
1496
+ },
1497
+ {
1498
+ "epoch": 1.2901688182720954,
1499
+ "grad_norm": 0.24179032444953918,
1500
+ "learning_rate": 7.225511972315104e-05,
1501
+ "loss": 2.3292,
1502
+ "step": 203
1503
+ },
1504
+ {
1505
+ "epoch": 1.296524329692155,
1506
+ "grad_norm": 0.2414858192205429,
1507
+ "learning_rate": 7.197986933948152e-05,
1508
+ "loss": 2.1947,
1509
+ "step": 204
1510
+ },
1511
+ {
1512
+ "epoch": 1.3028798411122144,
1513
+ "grad_norm": 0.2643281817436218,
1514
+ "learning_rate": 7.170387620131993e-05,
1515
+ "loss": 2.2755,
1516
+ "step": 205
1517
+ },
1518
+ {
1519
+ "epoch": 1.3092353525322742,
1520
+ "grad_norm": 0.28699687123298645,
1521
+ "learning_rate": 7.142715238150026e-05,
1522
+ "loss": 2.3962,
1523
+ "step": 206
1524
+ },
1525
+ {
1526
+ "epoch": 1.3155908639523337,
1527
+ "grad_norm": 0.32118549942970276,
1528
+ "learning_rate": 7.114970998481883e-05,
1529
+ "loss": 2.3804,
1530
+ "step": 207
1531
+ },
1532
+ {
1533
+ "epoch": 1.3219463753723932,
1534
+ "grad_norm": 0.22292247414588928,
1535
+ "learning_rate": 7.087156114750487e-05,
1536
+ "loss": 2.0684,
1537
+ "step": 208
1538
+ },
1539
+ {
1540
+ "epoch": 1.3283018867924528,
1541
+ "grad_norm": 0.21520115435123444,
1542
+ "learning_rate": 7.059271803668956e-05,
1543
+ "loss": 2.1806,
1544
+ "step": 209
1545
+ },
1546
+ {
1547
+ "epoch": 1.3346573982125123,
1548
+ "grad_norm": 0.21592098474502563,
1549
+ "learning_rate": 7.031319284987394e-05,
1550
+ "loss": 2.1554,
1551
+ "step": 210
1552
+ },
1553
+ {
1554
+ "epoch": 1.341012909632572,
1555
+ "grad_norm": 0.22017662227153778,
1556
+ "learning_rate": 7.00329978143952e-05,
1557
+ "loss": 2.2556,
1558
+ "step": 211
1559
+ },
1560
+ {
1561
+ "epoch": 1.3473684210526315,
1562
+ "grad_norm": 0.21874964237213135,
1563
+ "learning_rate": 6.975214518689189e-05,
1564
+ "loss": 2.2208,
1565
+ "step": 212
1566
+ },
1567
+ {
1568
+ "epoch": 1.353723932472691,
1569
+ "grad_norm": 0.20557738840579987,
1570
+ "learning_rate": 6.947064725276779e-05,
1571
+ "loss": 2.2034,
1572
+ "step": 213
1573
+ },
1574
+ {
1575
+ "epoch": 1.3600794438927508,
1576
+ "grad_norm": 0.20455682277679443,
1577
+ "learning_rate": 6.918851632565448e-05,
1578
+ "loss": 2.2491,
1579
+ "step": 214
1580
+ },
1581
+ {
1582
+ "epoch": 1.3664349553128103,
1583
+ "grad_norm": 0.24136288464069366,
1584
+ "learning_rate": 6.890576474687263e-05,
1585
+ "loss": 2.319,
1586
+ "step": 215
1587
+ },
1588
+ {
1589
+ "epoch": 1.3727904667328699,
1590
+ "grad_norm": 0.23860681056976318,
1591
+ "learning_rate": 6.862240488489234e-05,
1592
+ "loss": 2.2455,
1593
+ "step": 216
1594
+ },
1595
+ {
1596
+ "epoch": 1.3791459781529296,
1597
+ "grad_norm": 0.25159767270088196,
1598
+ "learning_rate": 6.833844913479192e-05,
1599
+ "loss": 2.2936,
1600
+ "step": 217
1601
+ },
1602
+ {
1603
+ "epoch": 1.3855014895729891,
1604
+ "grad_norm": 0.2641444504261017,
1605
+ "learning_rate": 6.805390991771577e-05,
1606
+ "loss": 2.2236,
1607
+ "step": 218
1608
+ },
1609
+ {
1610
+ "epoch": 1.3918570009930487,
1611
+ "grad_norm": 0.28924816846847534,
1612
+ "learning_rate": 6.776879968033098e-05,
1613
+ "loss": 2.2942,
1614
+ "step": 219
1615
+ },
1616
+ {
1617
+ "epoch": 1.3982125124131082,
1618
+ "grad_norm": 0.2189883291721344,
1619
+ "learning_rate": 6.7483130894283e-05,
1620
+ "loss": 1.8152,
1621
+ "step": 220
1622
+ },
1623
+ {
1624
+ "epoch": 1.4045680238331677,
1625
+ "grad_norm": 0.2362377941608429,
1626
+ "learning_rate": 6.719691605565001e-05,
1627
+ "loss": 2.4699,
1628
+ "step": 221
1629
+ },
1630
+ {
1631
+ "epoch": 1.4109235352532274,
1632
+ "grad_norm": 0.2160421907901764,
1633
+ "learning_rate": 6.691016768439618e-05,
1634
+ "loss": 2.1975,
1635
+ "step": 222
1636
+ },
1637
+ {
1638
+ "epoch": 1.417279046673287,
1639
+ "grad_norm": 0.21473869681358337,
1640
+ "learning_rate": 6.662289832382425e-05,
1641
+ "loss": 2.1945,
1642
+ "step": 223
1643
+ },
1644
+ {
1645
+ "epoch": 1.4236345580933465,
1646
+ "grad_norm": 0.2146051675081253,
1647
+ "learning_rate": 6.633512054002667e-05,
1648
+ "loss": 2.1897,
1649
+ "step": 224
1650
+ },
1651
+ {
1652
+ "epoch": 1.4299900695134062,
1653
+ "grad_norm": 0.21088357269763947,
1654
+ "learning_rate": 6.604684692133597e-05,
1655
+ "loss": 2.2652,
1656
+ "step": 225
1657
+ },
1658
+ {
1659
+ "epoch": 1.4299900695134062,
1660
+ "eval_loss": 2.308363914489746,
1661
+ "eval_runtime": 1.5104,
1662
+ "eval_samples_per_second": 33.103,
1663
+ "eval_steps_per_second": 8.607,
1664
+ "step": 225
1665
+ },
1666
+ {
1667
+ "epoch": 1.4363455809334658,
1668
+ "grad_norm": 0.21634501218795776,
1669
+ "learning_rate": 6.575809007777409e-05,
1670
+ "loss": 2.2218,
1671
+ "step": 226
1672
+ },
1673
+ {
1674
+ "epoch": 1.4427010923535253,
1675
+ "grad_norm": 0.21620678901672363,
1676
+ "learning_rate": 6.546886264050088e-05,
1677
+ "loss": 2.2871,
1678
+ "step": 227
1679
+ },
1680
+ {
1681
+ "epoch": 1.449056603773585,
1682
+ "grad_norm": 0.2234848290681839,
1683
+ "learning_rate": 6.517917726126131e-05,
1684
+ "loss": 2.2693,
1685
+ "step": 228
1686
+ },
1687
+ {
1688
+ "epoch": 1.4554121151936446,
1689
+ "grad_norm": 0.24025674164295197,
1690
+ "learning_rate": 6.488904661183239e-05,
1691
+ "loss": 2.3066,
1692
+ "step": 229
1693
+ },
1694
+ {
1695
+ "epoch": 1.461767626613704,
1696
+ "grad_norm": 0.2580195665359497,
1697
+ "learning_rate": 6.459848338346861e-05,
1698
+ "loss": 2.2348,
1699
+ "step": 230
1700
+ },
1701
+ {
1702
+ "epoch": 1.4681231380337636,
1703
+ "grad_norm": 0.27248427271842957,
1704
+ "learning_rate": 6.430750028634686e-05,
1705
+ "loss": 2.2236,
1706
+ "step": 231
1707
+ },
1708
+ {
1709
+ "epoch": 1.4744786494538231,
1710
+ "grad_norm": 0.32905861735343933,
1711
+ "learning_rate": 6.401611004901046e-05,
1712
+ "loss": 2.3512,
1713
+ "step": 232
1714
+ },
1715
+ {
1716
+ "epoch": 1.4808341608738829,
1717
+ "grad_norm": 0.2446022927761078,
1718
+ "learning_rate": 6.372432541781238e-05,
1719
+ "loss": 2.0837,
1720
+ "step": 233
1721
+ },
1722
+ {
1723
+ "epoch": 1.4871896722939424,
1724
+ "grad_norm": 0.20532265305519104,
1725
+ "learning_rate": 6.343215915635762e-05,
1726
+ "loss": 2.1825,
1727
+ "step": 234
1728
+ },
1729
+ {
1730
+ "epoch": 1.493545183714002,
1731
+ "grad_norm": 0.21579104661941528,
1732
+ "learning_rate": 6.313962404494496e-05,
1733
+ "loss": 2.193,
1734
+ "step": 235
1735
+ },
1736
+ {
1737
+ "epoch": 1.4999006951340617,
1738
+ "grad_norm": 0.22648389637470245,
1739
+ "learning_rate": 6.284673288000783e-05,
1740
+ "loss": 2.1881,
1741
+ "step": 236
1742
+ },
1743
+ {
1744
+ "epoch": 1.5062562065541212,
1745
+ "grad_norm": 0.2369798719882965,
1746
+ "learning_rate": 6.255349847355465e-05,
1747
+ "loss": 2.2334,
1748
+ "step": 237
1749
+ },
1750
+ {
1751
+ "epoch": 1.5126117179741807,
1752
+ "grad_norm": 0.2303883582353592,
1753
+ "learning_rate": 6.22599336526083e-05,
1754
+ "loss": 2.2507,
1755
+ "step": 238
1756
+ },
1757
+ {
1758
+ "epoch": 1.5189672293942404,
1759
+ "grad_norm": 0.21534325182437897,
1760
+ "learning_rate": 6.196605125864507e-05,
1761
+ "loss": 2.208,
1762
+ "step": 239
1763
+ },
1764
+ {
1765
+ "epoch": 1.5253227408142997,
1766
+ "grad_norm": 0.23604141175746918,
1767
+ "learning_rate": 6.167186414703289e-05,
1768
+ "loss": 2.2871,
1769
+ "step": 240
1770
+ },
1771
+ {
1772
+ "epoch": 1.5316782522343595,
1773
+ "grad_norm": 0.2396741509437561,
1774
+ "learning_rate": 6.13773851864691e-05,
1775
+ "loss": 2.2488,
1776
+ "step": 241
1777
+ },
1778
+ {
1779
+ "epoch": 1.538033763654419,
1780
+ "grad_norm": 0.25131046772003174,
1781
+ "learning_rate": 6.108262725841736e-05,
1782
+ "loss": 2.2408,
1783
+ "step": 242
1784
+ },
1785
+ {
1786
+ "epoch": 1.5443892750744785,
1787
+ "grad_norm": 0.26546186208724976,
1788
+ "learning_rate": 6.078760325654438e-05,
1789
+ "loss": 2.2596,
1790
+ "step": 243
1791
+ },
1792
+ {
1793
+ "epoch": 1.5507447864945383,
1794
+ "grad_norm": 0.2935730218887329,
1795
+ "learning_rate": 6.049232608615571e-05,
1796
+ "loss": 2.3499,
1797
+ "step": 244
1798
+ },
1799
+ {
1800
+ "epoch": 1.5571002979145978,
1801
+ "grad_norm": 0.23465891182422638,
1802
+ "learning_rate": 6.019680866363139e-05,
1803
+ "loss": 1.82,
1804
+ "step": 245
1805
+ },
1806
+ {
1807
+ "epoch": 1.5634558093346573,
1808
+ "grad_norm": 0.23507410287857056,
1809
+ "learning_rate": 5.9901063915860765e-05,
1810
+ "loss": 2.5993,
1811
+ "step": 246
1812
+ },
1813
+ {
1814
+ "epoch": 1.569811320754717,
1815
+ "grad_norm": 0.20410220324993134,
1816
+ "learning_rate": 5.9605104779677233e-05,
1817
+ "loss": 2.1952,
1818
+ "step": 247
1819
+ },
1820
+ {
1821
+ "epoch": 1.5761668321747766,
1822
+ "grad_norm": 0.20211568474769592,
1823
+ "learning_rate": 5.930894420129216e-05,
1824
+ "loss": 2.1488,
1825
+ "step": 248
1826
+ },
1827
+ {
1828
+ "epoch": 1.5825223435948361,
1829
+ "grad_norm": 0.22527258098125458,
1830
+ "learning_rate": 5.9012595135728686e-05,
1831
+ "loss": 2.3049,
1832
+ "step": 249
1833
+ },
1834
+ {
1835
+ "epoch": 1.5888778550148959,
1836
+ "grad_norm": 0.20656868815422058,
1837
+ "learning_rate": 5.8716070546254966e-05,
1838
+ "loss": 2.2084,
1839
+ "step": 250
1840
+ },
1841
+ {
1842
+ "epoch": 1.5888778550148959,
1843
+ "eval_loss": 2.304069995880127,
1844
+ "eval_runtime": 1.5096,
1845
+ "eval_samples_per_second": 33.121,
1846
+ "eval_steps_per_second": 8.611,
1847
+ "step": 250
1848
+ },
1849
+ {
1850
+ "epoch": 1.5952333664349552,
1851
+ "grad_norm": 0.222466841340065,
1852
+ "learning_rate": 5.841938340381714e-05,
1853
+ "loss": 2.2831,
1854
+ "step": 251
1855
+ },
1856
+ {
1857
+ "epoch": 1.601588877855015,
1858
+ "grad_norm": 0.23157593607902527,
1859
+ "learning_rate": 5.812254668647199e-05,
1860
+ "loss": 2.2102,
1861
+ "step": 252
1862
+ },
1863
+ {
1864
+ "epoch": 1.6079443892750744,
1865
+ "grad_norm": 0.23068071901798248,
1866
+ "learning_rate": 5.782557337881911e-05,
1867
+ "loss": 2.2799,
1868
+ "step": 253
1869
+ },
1870
+ {
1871
+ "epoch": 1.614299900695134,
1872
+ "grad_norm": 0.24991615116596222,
1873
+ "learning_rate": 5.7528476471433044e-05,
1874
+ "loss": 2.2399,
1875
+ "step": 254
1876
+ },
1877
+ {
1878
+ "epoch": 1.6206554121151937,
1879
+ "grad_norm": 0.2582293152809143,
1880
+ "learning_rate": 5.7231268960295e-05,
1881
+ "loss": 2.2302,
1882
+ "step": 255
1883
+ },
1884
+ {
1885
+ "epoch": 1.6270109235352532,
1886
+ "grad_norm": 0.2798979580402374,
1887
+ "learning_rate": 5.6933963846224335e-05,
1888
+ "loss": 2.3088,
1889
+ "step": 256
1890
+ },
1891
+ {
1892
+ "epoch": 1.6333664349553128,
1893
+ "grad_norm": 0.31460028886795044,
1894
+ "learning_rate": 5.663657413430985e-05,
1895
+ "loss": 2.378,
1896
+ "step": 257
1897
+ },
1898
+ {
1899
+ "epoch": 1.6397219463753725,
1900
+ "grad_norm": 0.2301398515701294,
1901
+ "learning_rate": 5.633911283334097e-05,
1902
+ "loss": 2.1036,
1903
+ "step": 258
1904
+ },
1905
+ {
1906
+ "epoch": 1.646077457795432,
1907
+ "grad_norm": 0.20988218486309052,
1908
+ "learning_rate": 5.604159295523863e-05,
1909
+ "loss": 2.1369,
1910
+ "step": 259
1911
+ },
1912
+ {
1913
+ "epoch": 1.6524329692154915,
1914
+ "grad_norm": 0.22619880735874176,
1915
+ "learning_rate": 5.574402751448614e-05,
1916
+ "loss": 2.1594,
1917
+ "step": 260
1918
+ },
1919
+ {
1920
+ "epoch": 1.6587884806355513,
1921
+ "grad_norm": 0.22871357202529907,
1922
+ "learning_rate": 5.544642952755984e-05,
1923
+ "loss": 2.2471,
1924
+ "step": 261
1925
+ },
1926
+ {
1927
+ "epoch": 1.6651439920556106,
1928
+ "grad_norm": 0.21389460563659668,
1929
+ "learning_rate": 5.5148812012359785e-05,
1930
+ "loss": 2.157,
1931
+ "step": 262
1932
+ },
1933
+ {
1934
+ "epoch": 1.6714995034756703,
1935
+ "grad_norm": 0.21570387482643127,
1936
+ "learning_rate": 5.485118798764022e-05,
1937
+ "loss": 2.2141,
1938
+ "step": 263
1939
+ },
1940
+ {
1941
+ "epoch": 1.6778550148957299,
1942
+ "grad_norm": 0.21957939863204956,
1943
+ "learning_rate": 5.4553570472440165e-05,
1944
+ "loss": 2.2172,
1945
+ "step": 264
1946
+ },
1947
+ {
1948
+ "epoch": 1.6842105263157894,
1949
+ "grad_norm": 0.22865276038646698,
1950
+ "learning_rate": 5.425597248551387e-05,
1951
+ "loss": 2.3174,
1952
+ "step": 265
1953
+ },
1954
+ {
1955
+ "epoch": 1.6905660377358491,
1956
+ "grad_norm": 0.22632096707820892,
1957
+ "learning_rate": 5.395840704476138e-05,
1958
+ "loss": 2.2178,
1959
+ "step": 266
1960
+ },
1961
+ {
1962
+ "epoch": 1.6969215491559086,
1963
+ "grad_norm": 0.25706589221954346,
1964
+ "learning_rate": 5.366088716665905e-05,
1965
+ "loss": 2.27,
1966
+ "step": 267
1967
+ },
1968
+ {
1969
+ "epoch": 1.7032770605759682,
1970
+ "grad_norm": 0.2791062593460083,
1971
+ "learning_rate": 5.336342586569016e-05,
1972
+ "loss": 2.2799,
1973
+ "step": 268
1974
+ },
1975
+ {
1976
+ "epoch": 1.709632571996028,
1977
+ "grad_norm": 0.2988054156303406,
1978
+ "learning_rate": 5.3066036153775675e-05,
1979
+ "loss": 2.266,
1980
+ "step": 269
1981
+ },
1982
+ {
1983
+ "epoch": 1.7159880834160874,
1984
+ "grad_norm": 0.22925472259521484,
1985
+ "learning_rate": 5.2768731039705e-05,
1986
+ "loss": 1.7885,
1987
+ "step": 270
1988
+ },
1989
+ {
1990
+ "epoch": 1.722343594836147,
1991
+ "grad_norm": 0.23760093748569489,
1992
+ "learning_rate": 5.247152352856696e-05,
1993
+ "loss": 2.5497,
1994
+ "step": 271
1995
+ },
1996
+ {
1997
+ "epoch": 1.7286991062562067,
1998
+ "grad_norm": 0.2082970291376114,
1999
+ "learning_rate": 5.2174426621180906e-05,
2000
+ "loss": 2.1978,
2001
+ "step": 272
2002
+ },
2003
+ {
2004
+ "epoch": 1.735054617676266,
2005
+ "grad_norm": 0.20604585111141205,
2006
+ "learning_rate": 5.187745331352802e-05,
2007
+ "loss": 2.1954,
2008
+ "step": 273
2009
+ },
2010
+ {
2011
+ "epoch": 1.7414101290963258,
2012
+ "grad_norm": 0.216554656624794,
2013
+ "learning_rate": 5.158061659618286e-05,
2014
+ "loss": 2.2281,
2015
+ "step": 274
2016
+ },
2017
+ {
2018
+ "epoch": 1.7477656405163853,
2019
+ "grad_norm": 0.21528418362140656,
2020
+ "learning_rate": 5.128392945374505e-05,
2021
+ "loss": 2.2238,
2022
+ "step": 275
2023
+ },
2024
+ {
2025
+ "epoch": 1.7477656405163853,
2026
+ "eval_loss": 2.3029215335845947,
2027
+ "eval_runtime": 1.5101,
2028
+ "eval_samples_per_second": 33.111,
2029
+ "eval_steps_per_second": 8.609,
2030
+ "step": 275
2031
+ },
2032
+ {
2033
+ "epoch": 1.7541211519364448,
2034
+ "grad_norm": 0.21457256376743317,
2035
+ "learning_rate": 5.098740486427134e-05,
2036
+ "loss": 2.2227,
2037
+ "step": 276
2038
+ },
2039
+ {
2040
+ "epoch": 1.7604766633565045,
2041
+ "grad_norm": 0.23223957419395447,
2042
+ "learning_rate": 5.0691055798707844e-05,
2043
+ "loss": 2.2478,
2044
+ "step": 277
2045
+ },
2046
+ {
2047
+ "epoch": 1.766832174776564,
2048
+ "grad_norm": 0.24318185448646545,
2049
+ "learning_rate": 5.039489522032278e-05,
2050
+ "loss": 2.2334,
2051
+ "step": 278
2052
+ },
2053
+ {
2054
+ "epoch": 1.7731876861966236,
2055
+ "grad_norm": 0.2434845119714737,
2056
+ "learning_rate": 5.009893608413924e-05,
2057
+ "loss": 2.1982,
2058
+ "step": 279
2059
+ },
2060
+ {
2061
+ "epoch": 1.7795431976166833,
2062
+ "grad_norm": 0.2671870291233063,
2063
+ "learning_rate": 4.980319133636863e-05,
2064
+ "loss": 2.2872,
2065
+ "step": 280
2066
+ },
2067
+ {
2068
+ "epoch": 1.7858987090367426,
2069
+ "grad_norm": 0.28545892238616943,
2070
+ "learning_rate": 4.95076739138443e-05,
2071
+ "loss": 2.2756,
2072
+ "step": 281
2073
+ },
2074
+ {
2075
+ "epoch": 1.7922542204568024,
2076
+ "grad_norm": 0.320546418428421,
2077
+ "learning_rate": 4.9212396743455637e-05,
2078
+ "loss": 2.3082,
2079
+ "step": 282
2080
+ },
2081
+ {
2082
+ "epoch": 1.7986097318768621,
2083
+ "grad_norm": 0.23770391941070557,
2084
+ "learning_rate": 4.8917372741582655e-05,
2085
+ "loss": 2.1408,
2086
+ "step": 283
2087
+ },
2088
+ {
2089
+ "epoch": 1.8049652432969214,
2090
+ "grad_norm": 0.22296488285064697,
2091
+ "learning_rate": 4.8622614813530906e-05,
2092
+ "loss": 2.1225,
2093
+ "step": 284
2094
+ },
2095
+ {
2096
+ "epoch": 1.8113207547169812,
2097
+ "grad_norm": 0.22379352152347565,
2098
+ "learning_rate": 4.83281358529671e-05,
2099
+ "loss": 2.1747,
2100
+ "step": 285
2101
+ },
2102
+ {
2103
+ "epoch": 1.8176762661370407,
2104
+ "grad_norm": 0.23434078693389893,
2105
+ "learning_rate": 4.803394874135494e-05,
2106
+ "loss": 2.2316,
2107
+ "step": 286
2108
+ },
2109
+ {
2110
+ "epoch": 1.8240317775571002,
2111
+ "grad_norm": 0.22429004311561584,
2112
+ "learning_rate": 4.774006634739171e-05,
2113
+ "loss": 2.2137,
2114
+ "step": 287
2115
+ },
2116
+ {
2117
+ "epoch": 1.83038728897716,
2118
+ "grad_norm": 0.2382650375366211,
2119
+ "learning_rate": 4.7446501526445366e-05,
2120
+ "loss": 2.2743,
2121
+ "step": 288
2122
+ },
2123
+ {
2124
+ "epoch": 1.8367428003972195,
2125
+ "grad_norm": 0.22307072579860687,
2126
+ "learning_rate": 4.715326711999218e-05,
2127
+ "loss": 2.1545,
2128
+ "step": 289
2129
+ },
2130
+ {
2131
+ "epoch": 1.843098311817279,
2132
+ "grad_norm": 0.22870178520679474,
2133
+ "learning_rate": 4.686037595505507e-05,
2134
+ "loss": 2.258,
2135
+ "step": 290
2136
+ },
2137
+ {
2138
+ "epoch": 1.8494538232373388,
2139
+ "grad_norm": 0.23796506226062775,
2140
+ "learning_rate": 4.6567840843642384e-05,
2141
+ "loss": 2.2455,
2142
+ "step": 291
2143
+ },
2144
+ {
2145
+ "epoch": 1.855809334657398,
2146
+ "grad_norm": 0.3638233244419098,
2147
+ "learning_rate": 4.6275674582187636e-05,
2148
+ "loss": 2.2754,
2149
+ "step": 292
2150
+ },
2151
+ {
2152
+ "epoch": 1.8621648460774578,
2153
+ "grad_norm": 0.28538650274276733,
2154
+ "learning_rate": 4.5983889950989554e-05,
2155
+ "loss": 2.2267,
2156
+ "step": 293
2157
+ },
2158
+ {
2159
+ "epoch": 1.8685203574975173,
2160
+ "grad_norm": 0.31076282262802124,
2161
+ "learning_rate": 4.5692499713653157e-05,
2162
+ "loss": 2.3608,
2163
+ "step": 294
2164
+ },
2165
+ {
2166
+ "epoch": 1.8748758689175768,
2167
+ "grad_norm": 0.2438335418701172,
2168
+ "learning_rate": 4.54015166165314e-05,
2169
+ "loss": 1.7719,
2170
+ "step": 295
2171
+ },
2172
+ {
2173
+ "epoch": 1.8812313803376366,
2174
+ "grad_norm": 0.25157031416893005,
2175
+ "learning_rate": 4.511095338816761e-05,
2176
+ "loss": 2.5203,
2177
+ "step": 296
2178
+ },
2179
+ {
2180
+ "epoch": 1.8875868917576961,
2181
+ "grad_norm": 0.20811647176742554,
2182
+ "learning_rate": 4.48208227387387e-05,
2183
+ "loss": 2.1719,
2184
+ "step": 297
2185
+ },
2186
+ {
2187
+ "epoch": 1.8939424031777556,
2188
+ "grad_norm": 0.2120012789964676,
2189
+ "learning_rate": 4.453113735949914e-05,
2190
+ "loss": 2.1853,
2191
+ "step": 298
2192
+ },
2193
+ {
2194
+ "epoch": 1.9002979145978154,
2195
+ "grad_norm": 0.21405063569545746,
2196
+ "learning_rate": 4.42419099222259e-05,
2197
+ "loss": 2.1882,
2198
+ "step": 299
2199
+ },
2200
+ {
2201
+ "epoch": 1.906653426017875,
2202
+ "grad_norm": 0.22690372169017792,
2203
+ "learning_rate": 4.395315307866405e-05,
2204
+ "loss": 2.2119,
2205
+ "step": 300
2206
+ },
2207
+ {
2208
+ "epoch": 1.906653426017875,
2209
+ "eval_loss": 2.3020389080047607,
2210
+ "eval_runtime": 1.51,
2211
+ "eval_samples_per_second": 33.113,
2212
+ "eval_steps_per_second": 8.609,
2213
+ "step": 300
2214
+ },
2215
+ {
2216
+ "epoch": 1.9130089374379344,
2217
+ "grad_norm": 0.23434974253177643,
2218
+ "learning_rate": 4.366487945997335e-05,
2219
+ "loss": 2.1907,
2220
+ "step": 301
2221
+ },
2222
+ {
2223
+ "epoch": 1.9193644488579942,
2224
+ "grad_norm": 0.22699026763439178,
2225
+ "learning_rate": 4.337710167617577e-05,
2226
+ "loss": 2.2486,
2227
+ "step": 302
2228
+ },
2229
+ {
2230
+ "epoch": 1.9257199602780535,
2231
+ "grad_norm": 0.24884426593780518,
2232
+ "learning_rate": 4.308983231560384e-05,
2233
+ "loss": 2.2289,
2234
+ "step": 303
2235
+ },
2236
+ {
2237
+ "epoch": 1.9320754716981132,
2238
+ "grad_norm": 0.24829219281673431,
2239
+ "learning_rate": 4.2803083944350016e-05,
2240
+ "loss": 2.2107,
2241
+ "step": 304
2242
+ },
2243
+ {
2244
+ "epoch": 1.9384309831181727,
2245
+ "grad_norm": 0.2585359513759613,
2246
+ "learning_rate": 4.2516869105717004e-05,
2247
+ "loss": 2.2945,
2248
+ "step": 305
2249
+ },
2250
+ {
2251
+ "epoch": 1.9447864945382323,
2252
+ "grad_norm": 0.28458529710769653,
2253
+ "learning_rate": 4.223120031966903e-05,
2254
+ "loss": 2.2366,
2255
+ "step": 306
2256
+ },
2257
+ {
2258
+ "epoch": 1.951142005958292,
2259
+ "grad_norm": 0.3298734426498413,
2260
+ "learning_rate": 4.1946090082284264e-05,
2261
+ "loss": 2.3884,
2262
+ "step": 307
2263
+ },
2264
+ {
2265
+ "epoch": 1.9574975173783515,
2266
+ "grad_norm": 0.22929073870182037,
2267
+ "learning_rate": 4.166155086520809e-05,
2268
+ "loss": 2.1712,
2269
+ "step": 308
2270
+ },
2271
+ {
2272
+ "epoch": 1.963853028798411,
2273
+ "grad_norm": 0.20995154976844788,
2274
+ "learning_rate": 4.137759511510766e-05,
2275
+ "loss": 2.1756,
2276
+ "step": 309
2277
+ },
2278
+ {
2279
+ "epoch": 1.9702085402184708,
2280
+ "grad_norm": 0.22254884243011475,
2281
+ "learning_rate": 4.109423525312738e-05,
2282
+ "loss": 2.2643,
2283
+ "step": 310
2284
+ },
2285
+ {
2286
+ "epoch": 1.9765640516385303,
2287
+ "grad_norm": 0.23102299869060516,
2288
+ "learning_rate": 4.081148367434554e-05,
2289
+ "loss": 2.2153,
2290
+ "step": 311
2291
+ },
2292
+ {
2293
+ "epoch": 1.9829195630585899,
2294
+ "grad_norm": 0.25142958760261536,
2295
+ "learning_rate": 4.052935274723222e-05,
2296
+ "loss": 2.1985,
2297
+ "step": 312
2298
+ },
2299
+ {
2300
+ "epoch": 1.9892750744786496,
2301
+ "grad_norm": 0.24793897569179535,
2302
+ "learning_rate": 4.02478548131081e-05,
2303
+ "loss": 2.256,
2304
+ "step": 313
2305
+ },
2306
+ {
2307
+ "epoch": 1.995630585898709,
2308
+ "grad_norm": 0.28536108136177063,
2309
+ "learning_rate": 3.9967002185604805e-05,
2310
+ "loss": 2.3481,
2311
+ "step": 314
2312
+ },
2313
+ {
2314
+ "epoch": 2.0019860973187686,
2315
+ "grad_norm": 0.5548765063285828,
2316
+ "learning_rate": 3.968680715012606e-05,
2317
+ "loss": 3.6251,
2318
+ "step": 315
2319
+ },
2320
+ {
2321
+ "epoch": 2.0083416087388284,
2322
+ "grad_norm": 0.22422701120376587,
2323
+ "learning_rate": 3.940728196331045e-05,
2324
+ "loss": 2.0935,
2325
+ "step": 316
2326
+ },
2327
+ {
2328
+ "epoch": 2.0146971201588877,
2329
+ "grad_norm": 0.20903456211090088,
2330
+ "learning_rate": 3.912843885249515e-05,
2331
+ "loss": 2.1515,
2332
+ "step": 317
2333
+ },
2334
+ {
2335
+ "epoch": 2.0210526315789474,
2336
+ "grad_norm": 0.20581288635730743,
2337
+ "learning_rate": 3.885029001518119e-05,
2338
+ "loss": 2.1726,
2339
+ "step": 318
2340
+ },
2341
+ {
2342
+ "epoch": 2.0274081429990067,
2343
+ "grad_norm": 0.22312361001968384,
2344
+ "learning_rate": 3.857284761849975e-05,
2345
+ "loss": 2.1979,
2346
+ "step": 319
2347
+ },
2348
+ {
2349
+ "epoch": 2.0337636544190665,
2350
+ "grad_norm": 0.22348229587078094,
2351
+ "learning_rate": 3.829612379868006e-05,
2352
+ "loss": 2.2117,
2353
+ "step": 320
2354
+ },
2355
+ {
2356
+ "epoch": 2.0401191658391262,
2357
+ "grad_norm": 0.22266767919063568,
2358
+ "learning_rate": 3.8020130660518495e-05,
2359
+ "loss": 2.2157,
2360
+ "step": 321
2361
+ },
2362
+ {
2363
+ "epoch": 2.0464746772591855,
2364
+ "grad_norm": 0.23664413392543793,
2365
+ "learning_rate": 3.774488027684898e-05,
2366
+ "loss": 2.2099,
2367
+ "step": 322
2368
+ },
2369
+ {
2370
+ "epoch": 2.0528301886792453,
2371
+ "grad_norm": 0.24889320135116577,
2372
+ "learning_rate": 3.7470384688015e-05,
2373
+ "loss": 2.1944,
2374
+ "step": 323
2375
+ },
2376
+ {
2377
+ "epoch": 2.059185700099305,
2378
+ "grad_norm": 0.2663976848125458,
2379
+ "learning_rate": 3.7196655901342836e-05,
2380
+ "loss": 2.1792,
2381
+ "step": 324
2382
+ },
2383
+ {
2384
+ "epoch": 2.0655412115193643,
2385
+ "grad_norm": 0.2890424132347107,
2386
+ "learning_rate": 3.692370589061639e-05,
2387
+ "loss": 2.2045,
2388
+ "step": 325
2389
+ },
2390
+ {
2391
+ "epoch": 2.0655412115193643,
2392
+ "eval_loss": 2.3015811443328857,
2393
+ "eval_runtime": 1.5096,
2394
+ "eval_samples_per_second": 33.122,
2395
+ "eval_steps_per_second": 8.612,
2396
+ "step": 325
2397
+ },
2398
+ {
2399
+ "epoch": 2.071896722939424,
2400
+ "grad_norm": 0.3092862665653229,
2401
+ "learning_rate": 3.665154659555336e-05,
2402
+ "loss": 2.2105,
2403
+ "step": 326
2404
+ },
2405
+ {
2406
+ "epoch": 2.078252234359484,
2407
+ "grad_norm": 0.2822588086128235,
2408
+ "learning_rate": 3.638018992128296e-05,
2409
+ "loss": 1.8203,
2410
+ "step": 327
2411
+ },
2412
+ {
2413
+ "epoch": 2.084607745779543,
2414
+ "grad_norm": 0.2667306363582611,
2415
+ "learning_rate": 3.6109647737825246e-05,
2416
+ "loss": 2.5053,
2417
+ "step": 328
2418
+ },
2419
+ {
2420
+ "epoch": 2.090963257199603,
2421
+ "grad_norm": 0.2170848250389099,
2422
+ "learning_rate": 3.583993187957173e-05,
2423
+ "loss": 2.1155,
2424
+ "step": 329
2425
+ },
2426
+ {
2427
+ "epoch": 2.097318768619662,
2428
+ "grad_norm": 0.23939752578735352,
2429
+ "learning_rate": 3.557105414476782e-05,
2430
+ "loss": 2.1199,
2431
+ "step": 330
2432
+ },
2433
+ {
2434
+ "epoch": 2.103674280039722,
2435
+ "grad_norm": 0.24040144681930542,
2436
+ "learning_rate": 3.530302629499667e-05,
2437
+ "loss": 2.2042,
2438
+ "step": 331
2439
+ },
2440
+ {
2441
+ "epoch": 2.1100297914597816,
2442
+ "grad_norm": 0.23685196042060852,
2443
+ "learning_rate": 3.503586005466474e-05,
2444
+ "loss": 2.0769,
2445
+ "step": 332
2446
+ },
2447
+ {
2448
+ "epoch": 2.116385302879841,
2449
+ "grad_norm": 0.23992370069026947,
2450
+ "learning_rate": 3.476956711048885e-05,
2451
+ "loss": 2.1787,
2452
+ "step": 333
2453
+ },
2454
+ {
2455
+ "epoch": 2.1227408142999007,
2456
+ "grad_norm": 0.25517672300338745,
2457
+ "learning_rate": 3.4504159110985035e-05,
2458
+ "loss": 2.2335,
2459
+ "step": 334
2460
+ },
2461
+ {
2462
+ "epoch": 2.1290963257199604,
2463
+ "grad_norm": 0.2546270787715912,
2464
+ "learning_rate": 3.423964766595906e-05,
2465
+ "loss": 2.1222,
2466
+ "step": 335
2467
+ },
2468
+ {
2469
+ "epoch": 2.1354518371400197,
2470
+ "grad_norm": 0.2679215371608734,
2471
+ "learning_rate": 3.3976044345998365e-05,
2472
+ "loss": 2.1973,
2473
+ "step": 336
2474
+ },
2475
+ {
2476
+ "epoch": 2.1418073485600795,
2477
+ "grad_norm": 0.2851313650608063,
2478
+ "learning_rate": 3.371336068196617e-05,
2479
+ "loss": 2.2163,
2480
+ "step": 337
2481
+ },
2482
+ {
2483
+ "epoch": 2.1481628599801392,
2484
+ "grad_norm": 0.31128042936325073,
2485
+ "learning_rate": 3.345160816449687e-05,
2486
+ "loss": 2.1715,
2487
+ "step": 338
2488
+ },
2489
+ {
2490
+ "epoch": 2.1545183714001985,
2491
+ "grad_norm": 0.3457167148590088,
2492
+ "learning_rate": 3.3190798243493595e-05,
2493
+ "loss": 2.2396,
2494
+ "step": 339
2495
+ },
2496
+ {
2497
+ "epoch": 2.1608738828202583,
2498
+ "grad_norm": 0.32169675827026367,
2499
+ "learning_rate": 3.293094232762715e-05,
2500
+ "loss": 2.1081,
2501
+ "step": 340
2502
+ },
2503
+ {
2504
+ "epoch": 2.1672293942403176,
2505
+ "grad_norm": 0.24396829307079315,
2506
+ "learning_rate": 3.26720517838371e-05,
2507
+ "loss": 2.0669,
2508
+ "step": 341
2509
+ },
2510
+ {
2511
+ "epoch": 2.1735849056603773,
2512
+ "grad_norm": 0.25499778985977173,
2513
+ "learning_rate": 3.241413793683458e-05,
2514
+ "loss": 2.1445,
2515
+ "step": 342
2516
+ },
2517
+ {
2518
+ "epoch": 2.179940417080437,
2519
+ "grad_norm": 0.25378331542015076,
2520
+ "learning_rate": 3.215721206860673e-05,
2521
+ "loss": 2.1485,
2522
+ "step": 343
2523
+ },
2524
+ {
2525
+ "epoch": 2.1862959285004964,
2526
+ "grad_norm": 0.2579626441001892,
2527
+ "learning_rate": 3.19012854179234e-05,
2528
+ "loss": 2.1483,
2529
+ "step": 344
2530
+ },
2531
+ {
2532
+ "epoch": 2.192651439920556,
2533
+ "grad_norm": 0.2530902326107025,
2534
+ "learning_rate": 3.164636917984534e-05,
2535
+ "loss": 2.135,
2536
+ "step": 345
2537
+ },
2538
+ {
2539
+ "epoch": 2.199006951340616,
2540
+ "grad_norm": 0.26239219307899475,
2541
+ "learning_rate": 3.1392474505234604e-05,
2542
+ "loss": 2.169,
2543
+ "step": 346
2544
+ },
2545
+ {
2546
+ "epoch": 2.205362462760675,
2547
+ "grad_norm": 0.275020033121109,
2548
+ "learning_rate": 3.11396125002668e-05,
2549
+ "loss": 2.2371,
2550
+ "step": 347
2551
+ },
2552
+ {
2553
+ "epoch": 2.211717974180735,
2554
+ "grad_norm": 0.27179548144340515,
2555
+ "learning_rate": 3.088779422594514e-05,
2556
+ "loss": 2.1947,
2557
+ "step": 348
2558
+ },
2559
+ {
2560
+ "epoch": 2.2180734856007946,
2561
+ "grad_norm": 0.2944357097148895,
2562
+ "learning_rate": 3.063703069761679e-05,
2563
+ "loss": 2.2554,
2564
+ "step": 349
2565
+ },
2566
+ {
2567
+ "epoch": 2.224428997020854,
2568
+ "grad_norm": 0.31469622254371643,
2569
+ "learning_rate": 3.0387332884490805e-05,
2570
+ "loss": 2.1767,
2571
+ "step": 350
2572
+ },
2573
+ {
2574
+ "epoch": 2.224428997020854,
2575
+ "eval_loss": 2.3065717220306396,
2576
+ "eval_runtime": 1.5093,
2577
+ "eval_samples_per_second": 33.127,
2578
+ "eval_steps_per_second": 8.613,
2579
+ "step": 350
2580
+ }
2581
+ ],
2582
+ "logging_steps": 1,
2583
+ "max_steps": 500,
2584
+ "num_input_tokens_seen": 0,
2585
+ "num_train_epochs": 4,
2586
+ "save_steps": 50,
2587
+ "stateful_callbacks": {
2588
+ "EarlyStoppingCallback": {
2589
+ "args": {
2590
+ "early_stopping_patience": 1,
2591
+ "early_stopping_threshold": 0.0
2592
+ },
2593
+ "attributes": {
2594
+ "early_stopping_patience_counter": 1
2595
+ }
2596
+ },
2597
+ "TrainerControl": {
2598
+ "args": {
2599
+ "should_epoch_stop": false,
2600
+ "should_evaluate": false,
2601
+ "should_log": false,
2602
+ "should_save": true,
2603
+ "should_training_stop": true
2604
+ },
2605
+ "attributes": {}
2606
+ }
2607
+ },
2608
+ "total_flos": 8.35531706424361e+18,
2609
+ "train_batch_size": 1,
2610
+ "trial_name": null,
2611
+ "trial_params": null
2612
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2f90cad5aa92fe97f4e71cd083a70326f8f3f6ae96f5305620011633d1b6c6
3
+ size 6840
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b5e679cb69af62e14c3b98d346177bd4137d882a44f87dec9efec982b01a05
3
+ size 17209403
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<tool_call>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "128003": {
28
+ "content": "<tool_response>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
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": "<|eom_id|>",
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": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<tools>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "128012": {
100
+ "content": "</tools>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "128013": {
108
+ "content": "</tool_call>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "128014": {
116
+ "content": "</tool_response>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "128015": {
124
+ "content": "<schema>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "128016": {
132
+ "content": "</schema>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "128017": {
140
+ "content": "<scratch_pad>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "128018": {
148
+ "content": "</scratch_pad>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "128019": {
156
+ "content": "<SCRATCHPAD>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "128020": {
164
+ "content": "</SCRATCHPAD>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "128021": {
172
+ "content": "<REASONING>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "128022": {
180
+ "content": "</REASONING>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "128023": {
188
+ "content": "<INNER_MONOLOGUE>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "128024": {
196
+ "content": "</INNER_MONOLOGUE>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "128025": {
204
+ "content": "<PLAN>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "128026": {
212
+ "content": "</PLAN>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "128027": {
220
+ "content": "<EXECUTION>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "128028": {
228
+ "content": "</EXECUTION>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "128029": {
236
+ "content": "<REFLECTION>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "128030": {
244
+ "content": "</REFLECTION>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "128031": {
252
+ "content": "<THINKING>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "128032": {
260
+ "content": "</THINKING>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "128033": {
268
+ "content": "<SOLUTION>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "128034": {
276
+ "content": "</SOLUTION>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "128035": {
284
+ "content": "<EXPLANATION>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "128036": {
292
+ "content": "</EXPLANATION>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "128037": {
300
+ "content": "<UNIT_TEST>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "128038": {
308
+ "content": "</UNIT_TEST>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "128039": {
316
+ "content": "<|im_start|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "128040": {
324
+ "content": "<|im_end|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "<|im_end|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|finetune_right_pad_id|>",
2062
+ "padding_side": "left",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed2f90cad5aa92fe97f4e71cd083a70326f8f3f6ae96f5305620011633d1b6c6
3
+ size 6840