Hugging Face's logo

shuoxing
/
Llama3-8b-Review-lora-lr-1e-5-a-256-alpha-512

PEFT
Safetensors
llama
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
shuoxing commited on
Commit
3010acf
·
verified ·
1 Parent(s): 71d7e28

Upload folder using huggingface_hub

Browse files
Files changed (32) hide show
  1. .gitattributes +2 -0
  2. README.md +157 -6
  3. adapter_config.json +37 -0
  4. adapter_model.safetensors +3 -0
  5. checkpoint-491/README.md +202 -0
  6. checkpoint-491/adapter_config.json +37 -0
  7. checkpoint-491/adapter_model.safetensors +3 -0
  8. checkpoint-491/global_step491/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  9. checkpoint-491/global_step491/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  10. checkpoint-491/global_step491/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  11. checkpoint-491/global_step491/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  12. checkpoint-491/global_step491/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  13. checkpoint-491/global_step491/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  14. checkpoint-491/global_step491/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  15. checkpoint-491/global_step491/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  16. checkpoint-491/latest +1 -0
  17. checkpoint-491/rng_state_0.pth +3 -0
  18. checkpoint-491/rng_state_1.pth +3 -0
  19. checkpoint-491/rng_state_2.pth +3 -0
  20. checkpoint-491/rng_state_3.pth +3 -0
  21. checkpoint-491/scheduler.pt +3 -0
  22. checkpoint-491/special_tokens_map.json +23 -0
  23. checkpoint-491/tokenizer.json +3 -0
  24. checkpoint-491/tokenizer_config.json +2064 -0
  25. checkpoint-491/trainer_state.json +3478 -0
  26. checkpoint-491/training_args.bin +3 -0
  27. checkpoint-491/zero_to_fp32.py +760 -0
  28. config.json +52 -0
  29. special_tokens_map.json +23 -0
  30. tokenizer.json +3 -0
  31. tokenizer_config.json +2064 -0
  32. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
+ checkpoint-491/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,7 +1,158 @@
1
  ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- base_model:
6
- - meta-llama/Meta-Llama-3-8B
7
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - data/training_data.json
9
+ model-index:
10
+ - name: output/llama_1e-5_r_256_alpha_512
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ [<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)
18
+ <details><summary>See axolotl config</summary>
19
+
20
+ axolotl version: `0.7.0`
21
+ ```yaml
22
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
23
+ # optionally might have model_type or tokenizer_type
24
+ model_type: LlamaForCausalLM
25
+ tokenizer_type: AutoTokenizer
26
+ # Automatically upload checkpoint and final model to HF
27
+ # hub_model_id: username/custom_model_name
28
+
29
+ load_in_8bit: true
30
+ load_in_4bit: false
31
+ strict: false
32
+
33
+ chat_template: llama3
34
+ datasets:
35
+ - path: data/training_data.json
36
+ type: chat_template
37
+ field_messages: messages
38
+ message_property_mappings:
39
+ role: role
40
+ content: content
41
+ roles:
42
+ user:
43
+ - user
44
+ assistant:
45
+ - assistant
46
+
47
+ dataset_prepared_path:
48
+ val_set_size: 0.1
49
+ output_dir: ./output/llama_1e-5_r_256_alpha_512
50
+
51
+ sequence_len: 8000
52
+ sample_packing: false
53
+ pad_to_sequence_len: true
54
+
55
+ adapter: lora
56
+ lora_model_dir:
57
+ lora_r: 256
58
+ lora_alpha: 512
59
+ lora_dropout: 0.05
60
+ lora_target_linear: true
61
+ lora_fan_in_fan_out:
62
+
63
+ wandb_project: llama-review
64
+ wandb_entity:
65
+ wandb_watch:
66
+ wandb_name: llama_1e-5_r_256_alpha_512
67
+ wandb_log_model:
68
+
69
+ gradient_accumulation_steps: 4
70
+ micro_batch_size: 1
71
+ num_epochs: 1
72
+ optimizer: adamw_bnb_8bit
73
+ lr_scheduler: cosine
74
+ learning_rate: 1e-5
75
+
76
+ train_on_inputs: false
77
+ group_by_length: false
78
+ bf16: auto
79
+ fp16:
80
+ tf32: false
81
+
82
+ gradient_checkpointing: true
83
+ early_stopping_patience:
84
+ resume_from_checkpoint:
85
+ local_rank:
86
+ logging_steps: 1
87
+ xformers_attention:
88
+ flash_attention: true
89
+ s2_attention:
90
+
91
+ warmup_steps: 100
92
+ evals_per_epoch:
93
+ eval_table_size:
94
+ eval_max_new_tokens:
95
+ saves_per_epoch: 1
96
+ debug:
97
+ deepspeed: deepspeed_3.json
98
+ weight_decay: 0.0
99
+ fsdp:
100
+ fsdp_config:
101
+ special_tokens:
102
+ pad_token: <|end_of_text|>
103
+
104
+ ```
105
+
106
+ </details><br>
107
+
108
+ # output/llama_1e-5_r_256_alpha_512
109
+
110
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the data/training_data.json dataset.
111
+ It achieves the following results on the evaluation set:
112
+ - Loss: 13.8053
113
+
114
+ ## Model description
115
+
116
+ More information needed
117
+
118
+ ## Intended uses & limitations
119
+
120
+ More information needed
121
+
122
+ ## Training and evaluation data
123
+
124
+ More information needed
125
+
126
+ ## Training procedure
127
+
128
+ ### Training hyperparameters
129
+
130
+ The following hyperparameters were used during training:
131
+ - learning_rate: 1e-05
132
+ - train_batch_size: 1
133
+ - eval_batch_size: 1
134
+ - seed: 42
135
+ - distributed_type: multi-GPU
136
+ - num_devices: 4
137
+ - gradient_accumulation_steps: 4
138
+ - total_train_batch_size: 16
139
+ - total_eval_batch_size: 4
140
+ - optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
141
+ - lr_scheduler_type: cosine
142
+ - lr_scheduler_warmup_steps: 100
143
+ - num_epochs: 1.0
144
+
145
+ ### Training results
146
+
147
+ | Training Loss | Epoch | Step | Validation Loss |
148
+ |:-------------:|:------:|:----:|:---------------:|
149
+ | 13.8163 | 0.9995 | 491 | 13.8053 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - PEFT 0.14.0
155
+ - Transformers 4.48.3
156
+ - Pytorch 2.6.0+cu124
157
+ - Datasets 3.2.0
158
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": null,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 512,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 256,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "v_proj",
28
+ "o_proj",
29
+ "gate_proj",
30
+ "down_proj",
31
+ "up_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e4a4ec2b0971c39eee5aefa4023f0a39415a001fdce7158d7058c4452ca6c4
3
+ size 1342239008
checkpoint-491/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoint-491/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": null,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 512,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 256,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "v_proj",
28
+ "o_proj",
29
+ "gate_proj",
30
+ "down_proj",
31
+ "up_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoint-491/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e4a4ec2b0971c39eee5aefa4023f0a39415a001fdce7158d7058c4452ca6c4
3
+ size 1342239008
checkpoint-491/global_step491/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838696e1c9f4369fd227ccb19dfcdcda58ded7e59f93f943f77681d97849d413
3
+ size 1012627360
checkpoint-491/global_step491/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2a2a537f6e14bd5f6c460c293030a5abb6702f2f6f9b59425b95a89ab88d31
3
+ size 1012627360
checkpoint-491/global_step491/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1687e8ab7a70f43ed7afa228ad51b41997e091c49286a00818c21f00ab6759f0
3
+ size 1012627360
checkpoint-491/global_step491/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf48474ce9906cb46219e2c08bad0f3c37b46d9b469c83345540f4dcf0e2a8c
3
+ size 1012627360
checkpoint-491/global_step491/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62d2f60cb5300c62d5f629df2324254799605c8f3945455627f1093aa7cf6fd2
3
+ size 6119790
checkpoint-491/global_step491/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1d5bda0135479df8318b87636249defcbb2d07aa5140dd98e2851416ec3e2b6
3
+ size 6119790
checkpoint-491/global_step491/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02f4b5faeedf6336b8b490ea916d0945e4cb4b75bb74f542930da2cf444b00d
3
+ size 6119790
checkpoint-491/global_step491/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a030424c932d0136d66233e47122c8af4eeb2abace3d77f416711ef8bf10f89
3
+ size 6119790
checkpoint-491/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step491
checkpoint-491/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a6fef189b15ca3f1ebf14635bb03852125fc10bf32260de955d18d347d0a9c0
3
+ size 15024
checkpoint-491/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564e4287eb22aa941f8239acc2b9a4fb7d77b36bc105293d89dbd7b397482ffe
3
+ size 15024
checkpoint-491/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2d185d469fc3102faab4490a7375512db38defdf8ea6b01fdef565da4fdca5b
3
+ size 15024
checkpoint-491/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f699b65059c270be1cf5edb0bf271be5949f92f77a5c3a639293bf3a71a78b6
3
+ size 15024
checkpoint-491/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:815509d90dc3b1e0d52bda5233be5b08196947ab5995bf61b86826da5feda809
3
+ size 1064
checkpoint-491/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": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-491/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-491/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": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
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": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
checkpoint-491/trainer_state.json ADDED
@@ -0,0 +1,3478 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9994910941475827,
5
+ "eval_steps": 500,
6
+ "global_step": 491,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.002035623409669211,
13
+ "grad_norm": 2244783.3021161165,
14
+ "learning_rate": 1.0000000000000001e-07,
15
+ "loss": 13.8236,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.004071246819338422,
20
+ "grad_norm": 4218192.586319844,
21
+ "learning_rate": 2.0000000000000002e-07,
22
+ "loss": 13.7798,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.0061068702290076335,
27
+ "grad_norm": 4594205.112133389,
28
+ "learning_rate": 3.0000000000000004e-07,
29
+ "loss": 13.844,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.008142493638676845,
34
+ "grad_norm": 11263009.553503217,
35
+ "learning_rate": 4.0000000000000003e-07,
36
+ "loss": 13.8135,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.010178117048346057,
41
+ "grad_norm": 8938655.40470094,
42
+ "learning_rate": 5.000000000000001e-07,
43
+ "loss": 13.8361,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.012213740458015267,
48
+ "grad_norm": 3666969.2787727225,
49
+ "learning_rate": 6.000000000000001e-07,
50
+ "loss": 13.7754,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.014249363867684479,
55
+ "grad_norm": 2213140.2581639104,
56
+ "learning_rate": 7.000000000000001e-07,
57
+ "loss": 13.816,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.01628498727735369,
62
+ "grad_norm": 5204945.168357011,
63
+ "learning_rate": 8.000000000000001e-07,
64
+ "loss": 13.7919,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.0183206106870229,
69
+ "grad_norm": 3161273.4979725075,
70
+ "learning_rate": 9.000000000000001e-07,
71
+ "loss": 13.7921,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.020356234096692113,
76
+ "grad_norm": 4721972.526161844,
77
+ "learning_rate": 1.0000000000000002e-06,
78
+ "loss": 13.8129,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.022391857506361322,
83
+ "grad_norm": 1993836.4706857507,
84
+ "learning_rate": 1.1e-06,
85
+ "loss": 13.7899,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.024427480916030534,
90
+ "grad_norm": 2841663.624406631,
91
+ "learning_rate": 1.2000000000000002e-06,
92
+ "loss": 13.8222,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.026463104325699746,
97
+ "grad_norm": 1851625.2694659713,
98
+ "learning_rate": 1.3e-06,
99
+ "loss": 13.8051,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.028498727735368958,
104
+ "grad_norm": 1799567.0732118108,
105
+ "learning_rate": 1.4000000000000001e-06,
106
+ "loss": 13.8232,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.030534351145038167,
111
+ "grad_norm": 1739244.434987474,
112
+ "learning_rate": 1.5e-06,
113
+ "loss": 13.787,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.03256997455470738,
118
+ "grad_norm": 2049274.0550949178,
119
+ "learning_rate": 1.6000000000000001e-06,
120
+ "loss": 13.8272,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.03460559796437659,
125
+ "grad_norm": 2196819.6130670137,
126
+ "learning_rate": 1.7000000000000002e-06,
127
+ "loss": 13.7819,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.0366412213740458,
132
+ "grad_norm": 3122206.233837503,
133
+ "learning_rate": 1.8000000000000001e-06,
134
+ "loss": 13.7931,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.03867684478371501,
139
+ "grad_norm": 6250105.385689335,
140
+ "learning_rate": 1.9000000000000002e-06,
141
+ "loss": 13.8169,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.04071246819338423,
146
+ "grad_norm": 3333302.4953560205,
147
+ "learning_rate": 2.0000000000000003e-06,
148
+ "loss": 13.7969,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.042748091603053436,
153
+ "grad_norm": 1842864.15838755,
154
+ "learning_rate": 2.1000000000000002e-06,
155
+ "loss": 13.7789,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.044783715012722644,
160
+ "grad_norm": 2814803.976988681,
161
+ "learning_rate": 2.2e-06,
162
+ "loss": 13.8063,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.04681933842239186,
167
+ "grad_norm": 5480609.064869341,
168
+ "learning_rate": 2.3000000000000004e-06,
169
+ "loss": 13.8059,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.04885496183206107,
174
+ "grad_norm": 2330308.564996049,
175
+ "learning_rate": 2.4000000000000003e-06,
176
+ "loss": 13.7774,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.05089058524173028,
181
+ "grad_norm": 1954680.474250264,
182
+ "learning_rate": 2.5e-06,
183
+ "loss": 13.8188,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.05292620865139949,
188
+ "grad_norm": 2348178.4882796686,
189
+ "learning_rate": 2.6e-06,
190
+ "loss": 13.7916,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.0549618320610687,
195
+ "grad_norm": 2063424.030791769,
196
+ "learning_rate": 2.7000000000000004e-06,
197
+ "loss": 13.8352,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.056997455470737916,
202
+ "grad_norm": 3096470.2787967124,
203
+ "learning_rate": 2.8000000000000003e-06,
204
+ "loss": 13.814,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.059033078880407125,
209
+ "grad_norm": 2313554.624060415,
210
+ "learning_rate": 2.9e-06,
211
+ "loss": 13.8149,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.061068702290076333,
216
+ "grad_norm": 2759287.606120093,
217
+ "learning_rate": 3e-06,
218
+ "loss": 13.7901,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.06310432569974554,
223
+ "grad_norm": 20688012.381375346,
224
+ "learning_rate": 3.1000000000000004e-06,
225
+ "loss": 13.8016,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.06513994910941476,
230
+ "grad_norm": 2818955.21640328,
231
+ "learning_rate": 3.2000000000000003e-06,
232
+ "loss": 13.8174,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.06717557251908397,
237
+ "grad_norm": 3642298.4739112426,
238
+ "learning_rate": 3.3000000000000006e-06,
239
+ "loss": 13.8439,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.06921119592875317,
244
+ "grad_norm": 4530146.859043687,
245
+ "learning_rate": 3.4000000000000005e-06,
246
+ "loss": 13.798,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.07124681933842239,
251
+ "grad_norm": 3901948.6988777495,
252
+ "learning_rate": 3.5e-06,
253
+ "loss": 13.7871,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.0732824427480916,
258
+ "grad_norm": 2763745.5952281994,
259
+ "learning_rate": 3.6000000000000003e-06,
260
+ "loss": 13.7899,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.07531806615776081,
265
+ "grad_norm": 6149669.662012621,
266
+ "learning_rate": 3.7e-06,
267
+ "loss": 13.7854,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.07735368956743002,
272
+ "grad_norm": 2493897.7698470936,
273
+ "learning_rate": 3.8000000000000005e-06,
274
+ "loss": 13.7955,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.07938931297709924,
279
+ "grad_norm": 1961343.832258401,
280
+ "learning_rate": 3.900000000000001e-06,
281
+ "loss": 13.8098,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.08142493638676845,
286
+ "grad_norm": 2547368.4155277675,
287
+ "learning_rate": 4.000000000000001e-06,
288
+ "loss": 13.8144,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.08346055979643766,
293
+ "grad_norm": 12326034.534851212,
294
+ "learning_rate": 4.1e-06,
295
+ "loss": 13.7863,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.08549618320610687,
300
+ "grad_norm": 3960181.1514259093,
301
+ "learning_rate": 4.2000000000000004e-06,
302
+ "loss": 13.766,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.08753180661577609,
307
+ "grad_norm": 10011098.88152794,
308
+ "learning_rate": 4.3e-06,
309
+ "loss": 13.8034,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.08956743002544529,
314
+ "grad_norm": 3789423.3303024317,
315
+ "learning_rate": 4.4e-06,
316
+ "loss": 13.791,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.0916030534351145,
321
+ "grad_norm": 3039428.004186018,
322
+ "learning_rate": 4.5e-06,
323
+ "loss": 13.7903,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.09363867684478372,
328
+ "grad_norm": 3356582.7961585973,
329
+ "learning_rate": 4.600000000000001e-06,
330
+ "loss": 13.8235,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.09567430025445292,
335
+ "grad_norm": 2820493.914527673,
336
+ "learning_rate": 4.7e-06,
337
+ "loss": 13.8022,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.09770992366412214,
342
+ "grad_norm": 3791222.908966115,
343
+ "learning_rate": 4.800000000000001e-06,
344
+ "loss": 13.7717,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.09974554707379135,
349
+ "grad_norm": 3283270.2287080307,
350
+ "learning_rate": 4.9000000000000005e-06,
351
+ "loss": 13.787,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.10178117048346055,
356
+ "grad_norm": 2485970.4909266913,
357
+ "learning_rate": 5e-06,
358
+ "loss": 13.7976,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.10381679389312977,
363
+ "grad_norm": 4547104.520705372,
364
+ "learning_rate": 5.1e-06,
365
+ "loss": 13.7639,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.10585241730279898,
370
+ "grad_norm": 2824615.9607255333,
371
+ "learning_rate": 5.2e-06,
372
+ "loss": 13.7782,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.1078880407124682,
377
+ "grad_norm": 2095536.7289427207,
378
+ "learning_rate": 5.300000000000001e-06,
379
+ "loss": 13.8148,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.1099236641221374,
384
+ "grad_norm": 2351584.5173169677,
385
+ "learning_rate": 5.400000000000001e-06,
386
+ "loss": 13.7998,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.11195928753180662,
391
+ "grad_norm": 3228695.507820654,
392
+ "learning_rate": 5.500000000000001e-06,
393
+ "loss": 13.8394,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.11399491094147583,
398
+ "grad_norm": 9313699.37550104,
399
+ "learning_rate": 5.600000000000001e-06,
400
+ "loss": 13.7991,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.11603053435114503,
405
+ "grad_norm": 3293386.5704521113,
406
+ "learning_rate": 5.7e-06,
407
+ "loss": 13.7839,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.11806615776081425,
412
+ "grad_norm": 3718314.8927475032,
413
+ "learning_rate": 5.8e-06,
414
+ "loss": 13.811,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.12010178117048347,
419
+ "grad_norm": 3124256.4145811866,
420
+ "learning_rate": 5.9e-06,
421
+ "loss": 13.7796,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.12213740458015267,
426
+ "grad_norm": 3177179.019257336,
427
+ "learning_rate": 6e-06,
428
+ "loss": 13.7927,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.12417302798982188,
433
+ "grad_norm": 3023297.2648282214,
434
+ "learning_rate": 6.1e-06,
435
+ "loss": 13.7867,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.12620865139949108,
440
+ "grad_norm": 3214697.401730724,
441
+ "learning_rate": 6.200000000000001e-06,
442
+ "loss": 13.7771,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.1282442748091603,
447
+ "grad_norm": 5100755.95841697,
448
+ "learning_rate": 6.300000000000001e-06,
449
+ "loss": 13.8624,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.13027989821882952,
454
+ "grad_norm": 2723163.1725419424,
455
+ "learning_rate": 6.4000000000000006e-06,
456
+ "loss": 13.8343,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.13231552162849872,
461
+ "grad_norm": 3190220.582667358,
462
+ "learning_rate": 6.5000000000000004e-06,
463
+ "loss": 13.8278,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.13435114503816795,
468
+ "grad_norm": 4004364.9481327008,
469
+ "learning_rate": 6.600000000000001e-06,
470
+ "loss": 13.8181,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.13638676844783715,
475
+ "grad_norm": 3042780.596978967,
476
+ "learning_rate": 6.700000000000001e-06,
477
+ "loss": 13.8136,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.13842239185750635,
482
+ "grad_norm": 3848690.0005479343,
483
+ "learning_rate": 6.800000000000001e-06,
484
+ "loss": 13.8067,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.14045801526717558,
489
+ "grad_norm": 3081170.591628097,
490
+ "learning_rate": 6.9e-06,
491
+ "loss": 13.802,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.14249363867684478,
496
+ "grad_norm": 3465407.339307021,
497
+ "learning_rate": 7e-06,
498
+ "loss": 13.7681,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.14452926208651398,
503
+ "grad_norm": 2647645.8680279553,
504
+ "learning_rate": 7.100000000000001e-06,
505
+ "loss": 13.8244,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.1465648854961832,
510
+ "grad_norm": 2676701.9454676,
511
+ "learning_rate": 7.2000000000000005e-06,
512
+ "loss": 13.8011,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.1486005089058524,
517
+ "grad_norm": 2103570.9894912024,
518
+ "learning_rate": 7.3e-06,
519
+ "loss": 13.7988,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.15063613231552161,
524
+ "grad_norm": 2809043.7511407104,
525
+ "learning_rate": 7.4e-06,
526
+ "loss": 13.8103,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.15267175572519084,
531
+ "grad_norm": 4000235.7083044164,
532
+ "learning_rate": 7.500000000000001e-06,
533
+ "loss": 13.8168,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.15470737913486005,
538
+ "grad_norm": 8459155.529969739,
539
+ "learning_rate": 7.600000000000001e-06,
540
+ "loss": 13.774,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.15674300254452928,
545
+ "grad_norm": 16399233.534973303,
546
+ "learning_rate": 7.7e-06,
547
+ "loss": 13.8219,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.15877862595419848,
552
+ "grad_norm": 2696806.469277922,
553
+ "learning_rate": 7.800000000000002e-06,
554
+ "loss": 13.7919,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.16081424936386768,
559
+ "grad_norm": 6832348.586697958,
560
+ "learning_rate": 7.9e-06,
561
+ "loss": 13.8085,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.1628498727735369,
566
+ "grad_norm": 2802377.0728139468,
567
+ "learning_rate": 8.000000000000001e-06,
568
+ "loss": 13.7758,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.1648854961832061,
573
+ "grad_norm": 3693570.1419803873,
574
+ "learning_rate": 8.1e-06,
575
+ "loss": 13.8108,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.1669211195928753,
580
+ "grad_norm": 1899967.9199083971,
581
+ "learning_rate": 8.2e-06,
582
+ "loss": 13.7788,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.16895674300254454,
587
+ "grad_norm": 2632120.314827873,
588
+ "learning_rate": 8.3e-06,
589
+ "loss": 13.7979,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.17099236641221374,
594
+ "grad_norm": 2240799.146098359,
595
+ "learning_rate": 8.400000000000001e-06,
596
+ "loss": 13.7656,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.17302798982188294,
601
+ "grad_norm": 2881127.214705138,
602
+ "learning_rate": 8.5e-06,
603
+ "loss": 13.8209,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.17506361323155217,
608
+ "grad_norm": 4313944.882142538,
609
+ "learning_rate": 8.6e-06,
610
+ "loss": 13.8141,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.17709923664122137,
615
+ "grad_norm": 4205463.004393998,
616
+ "learning_rate": 8.700000000000001e-06,
617
+ "loss": 13.7967,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.17913486005089058,
622
+ "grad_norm": 2478941.649437644,
623
+ "learning_rate": 8.8e-06,
624
+ "loss": 13.7916,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.1811704834605598,
629
+ "grad_norm": 3528590.3048747736,
630
+ "learning_rate": 8.900000000000001e-06,
631
+ "loss": 13.7464,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.183206106870229,
636
+ "grad_norm": 2318484.135702536,
637
+ "learning_rate": 9e-06,
638
+ "loss": 13.8293,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.1852417302798982,
643
+ "grad_norm": 2158526.8137466703,
644
+ "learning_rate": 9.100000000000001e-06,
645
+ "loss": 13.7882,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.18727735368956744,
650
+ "grad_norm": 3658620.230343455,
651
+ "learning_rate": 9.200000000000002e-06,
652
+ "loss": 13.7981,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.18931297709923664,
657
+ "grad_norm": 2456882.2321177353,
658
+ "learning_rate": 9.3e-06,
659
+ "loss": 13.8297,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.19134860050890584,
664
+ "grad_norm": 2990599.371813722,
665
+ "learning_rate": 9.4e-06,
666
+ "loss": 13.7921,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.19338422391857507,
671
+ "grad_norm": 5560006.043017588,
672
+ "learning_rate": 9.5e-06,
673
+ "loss": 13.8165,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.19541984732824427,
678
+ "grad_norm": 1762528.334237519,
679
+ "learning_rate": 9.600000000000001e-06,
680
+ "loss": 13.794,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.19745547073791347,
685
+ "grad_norm": 2238736.0246347915,
686
+ "learning_rate": 9.7e-06,
687
+ "loss": 13.8312,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.1994910941475827,
692
+ "grad_norm": 1991545.6391396692,
693
+ "learning_rate": 9.800000000000001e-06,
694
+ "loss": 13.7997,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.2015267175572519,
699
+ "grad_norm": 2812661.8889751355,
700
+ "learning_rate": 9.9e-06,
701
+ "loss": 13.7873,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.2035623409669211,
706
+ "grad_norm": 2569208.410955407,
707
+ "learning_rate": 1e-05,
708
+ "loss": 13.8016,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.20559796437659034,
713
+ "grad_norm": 5078922.075783424,
714
+ "learning_rate": 9.999838607294157e-06,
715
+ "loss": 13.8041,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.20763358778625954,
720
+ "grad_norm": 2652997.6261025066,
721
+ "learning_rate": 9.999354439595668e-06,
722
+ "loss": 13.7995,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.20966921119592874,
727
+ "grad_norm": 7720533.0329790395,
728
+ "learning_rate": 9.998547528160987e-06,
729
+ "loss": 13.7946,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.21170483460559797,
734
+ "grad_norm": 4996759.547611104,
735
+ "learning_rate": 9.997417925081963e-06,
736
+ "loss": 13.8414,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.21374045801526717,
741
+ "grad_norm": 2594583.6722655715,
742
+ "learning_rate": 9.995965703282472e-06,
743
+ "loss": 13.8074,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.2157760814249364,
748
+ "grad_norm": 2448594.3176417607,
749
+ "learning_rate": 9.99419095651372e-06,
750
+ "loss": 13.7975,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.2178117048346056,
755
+ "grad_norm": 2714056.8451403086,
756
+ "learning_rate": 9.992093799348182e-06,
757
+ "loss": 13.8033,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.2198473282442748,
762
+ "grad_norm": 2961036.7491148347,
763
+ "learning_rate": 9.9896743671722e-06,
764
+ "loss": 13.8288,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.22188295165394403,
769
+ "grad_norm": 4655525.14394145,
770
+ "learning_rate": 9.986932816177258e-06,
771
+ "loss": 13.809,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.22391857506361323,
776
+ "grad_norm": 4477853.58417314,
777
+ "learning_rate": 9.98386932334989e-06,
778
+ "loss": 13.7901,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.22595419847328244,
783
+ "grad_norm": 7786381.525914281,
784
+ "learning_rate": 9.980484086460258e-06,
785
+ "loss": 13.7985,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.22798982188295167,
790
+ "grad_norm": 2476772.377738302,
791
+ "learning_rate": 9.976777324049374e-06,
792
+ "loss": 13.8245,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.23002544529262087,
797
+ "grad_norm": 2424723.3375852606,
798
+ "learning_rate": 9.972749275415005e-06,
799
+ "loss": 13.8106,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.23206106870229007,
804
+ "grad_norm": 3908900.533498587,
805
+ "learning_rate": 9.96840020059622e-06,
806
+ "loss": 13.8147,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.2340966921119593,
811
+ "grad_norm": 6536739.236436032,
812
+ "learning_rate": 9.963730380356599e-06,
813
+ "loss": 13.7825,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.2361323155216285,
818
+ "grad_norm": 2895977.217837065,
819
+ "learning_rate": 9.958740116166113e-06,
820
+ "loss": 13.8305,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.2381679389312977,
825
+ "grad_norm": 3560241.3442100273,
826
+ "learning_rate": 9.953429730181653e-06,
827
+ "loss": 13.8031,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.24020356234096693,
832
+ "grad_norm": 1955074.0369023099,
833
+ "learning_rate": 9.947799565226253e-06,
834
+ "loss": 13.8003,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.24223918575063613,
839
+ "grad_norm": 3497318.257096594,
840
+ "learning_rate": 9.94184998476693e-06,
841
+ "loss": 13.8214,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.24427480916030533,
846
+ "grad_norm": 3346632.116332331,
847
+ "learning_rate": 9.93558137289124e-06,
848
+ "loss": 13.7768,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.24631043256997456,
853
+ "grad_norm": 2439047.5049070125,
854
+ "learning_rate": 9.928994134282477e-06,
855
+ "loss": 13.8308,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.24834605597964376,
860
+ "grad_norm": 2664458.243837202,
861
+ "learning_rate": 9.922088694193546e-06,
862
+ "loss": 13.8132,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.250381679389313,
867
+ "grad_norm": 2619630.1649600505,
868
+ "learning_rate": 9.91486549841951e-06,
869
+ "loss": 13.8046,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.25241730279898217,
874
+ "grad_norm": 6268665.590956273,
875
+ "learning_rate": 9.907325013268816e-06,
876
+ "loss": 13.8003,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.2544529262086514,
881
+ "grad_norm": 3719517.4601419703,
882
+ "learning_rate": 9.899467725533181e-06,
883
+ "loss": 13.8048,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.2564885496183206,
888
+ "grad_norm": 3607937.2215440352,
889
+ "learning_rate": 9.89129414245618e-06,
890
+ "loss": 13.7788,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.2585241730279898,
895
+ "grad_norm": 4184303.763179342,
896
+ "learning_rate": 9.882804791700488e-06,
897
+ "loss": 13.7775,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.26055979643765903,
902
+ "grad_norm": 1838438.1959072966,
903
+ "learning_rate": 9.87400022131382e-06,
904
+ "loss": 13.8457,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.26259541984732826,
909
+ "grad_norm": 2268135.323406917,
910
+ "learning_rate": 9.864880999693551e-06,
911
+ "loss": 13.7905,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.26463104325699743,
916
+ "grad_norm": 6234862.720815243,
917
+ "learning_rate": 9.855447715550024e-06,
918
+ "loss": 13.8322,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.26666666666666666,
923
+ "grad_norm": 2161673.2272078265,
924
+ "learning_rate": 9.845700977868536e-06,
925
+ "loss": 13.7802,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.2687022900763359,
930
+ "grad_norm": 2040946.090751483,
931
+ "learning_rate": 9.835641415870038e-06,
932
+ "loss": 13.8012,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.27073791348600507,
937
+ "grad_norm": 1690704.8881864555,
938
+ "learning_rate": 9.825269678970502e-06,
939
+ "loss": 13.8144,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.2727735368956743,
944
+ "grad_norm": 3302151.7787588844,
945
+ "learning_rate": 9.814586436738998e-06,
946
+ "loss": 13.7961,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.2748091603053435,
951
+ "grad_norm": 2678767.7092372375,
952
+ "learning_rate": 9.803592378854476e-06,
953
+ "loss": 13.7924,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.2768447837150127,
958
+ "grad_norm": 1882847.5546937664,
959
+ "learning_rate": 9.792288215061237e-06,
960
+ "loss": 13.7571,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.27888040712468193,
965
+ "grad_norm": 2535286.1758342357,
966
+ "learning_rate": 9.780674675123113e-06,
967
+ "loss": 13.8159,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.28091603053435116,
972
+ "grad_norm": 2564638.3112862715,
973
+ "learning_rate": 9.768752508776358e-06,
974
+ "loss": 13.8283,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.28295165394402033,
979
+ "grad_norm": 4141816.881587341,
980
+ "learning_rate": 9.756522485681247e-06,
981
+ "loss": 13.8205,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.28498727735368956,
986
+ "grad_norm": 2736144.4377185158,
987
+ "learning_rate": 9.743985395372387e-06,
988
+ "loss": 13.8191,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.2870229007633588,
993
+ "grad_norm": 2915473.6501582544,
994
+ "learning_rate": 9.73114204720775e-06,
995
+ "loss": 13.7825,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.28905852417302796,
1000
+ "grad_norm": 4206163.240001201,
1001
+ "learning_rate": 9.717993270316421e-06,
1002
+ "loss": 13.8325,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.2910941475826972,
1007
+ "grad_norm": 5230479.261609765,
1008
+ "learning_rate": 9.704539913545073e-06,
1009
+ "loss": 13.8205,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.2931297709923664,
1014
+ "grad_norm": 1844426.584030888,
1015
+ "learning_rate": 9.690782845403164e-06,
1016
+ "loss": 13.7856,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.2951653944020356,
1021
+ "grad_norm": 2494575.837554648,
1022
+ "learning_rate": 9.676722954006878e-06,
1023
+ "loss": 13.7562,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.2972010178117048,
1028
+ "grad_norm": 4691983.503821501,
1029
+ "learning_rate": 9.66236114702178e-06,
1030
+ "loss": 13.8174,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.29923664122137406,
1035
+ "grad_norm": 11448273.842583835,
1036
+ "learning_rate": 9.647698351604227e-06,
1037
+ "loss": 13.811,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.30127226463104323,
1042
+ "grad_norm": 2421950.649919781,
1043
+ "learning_rate": 9.632735514341508e-06,
1044
+ "loss": 13.798,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.30330788804071246,
1049
+ "grad_norm": 3423539.343520856,
1050
+ "learning_rate": 9.617473601190743e-06,
1051
+ "loss": 13.7918,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.3053435114503817,
1056
+ "grad_norm": 3264738.7097397717,
1057
+ "learning_rate": 9.601913597416513e-06,
1058
+ "loss": 13.8008,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.3073791348600509,
1063
+ "grad_norm": 1943889.953196763,
1064
+ "learning_rate": 9.586056507527266e-06,
1065
+ "loss": 13.7854,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.3094147582697201,
1070
+ "grad_norm": 3137121.9149822216,
1071
+ "learning_rate": 9.569903355210457e-06,
1072
+ "loss": 13.8321,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.3114503816793893,
1077
+ "grad_norm": 2080163.2784456573,
1078
+ "learning_rate": 9.55345518326647e-06,
1079
+ "loss": 13.7755,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.31348600508905855,
1084
+ "grad_norm": 1730160.4186251867,
1085
+ "learning_rate": 9.5367130535413e-06,
1086
+ "loss": 13.8155,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.3155216284987277,
1091
+ "grad_norm": 4116918.3545234683,
1092
+ "learning_rate": 9.519678046857987e-06,
1093
+ "loss": 13.8182,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.31755725190839695,
1098
+ "grad_norm": 3736775.455979484,
1099
+ "learning_rate": 9.502351262946865e-06,
1100
+ "loss": 13.8155,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.3195928753180662,
1105
+ "grad_norm": 4078409.8308530655,
1106
+ "learning_rate": 9.48473382037455e-06,
1107
+ "loss": 13.8245,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.32162849872773536,
1112
+ "grad_norm": 102844859.60289915,
1113
+ "learning_rate": 9.466826856471728e-06,
1114
+ "loss": 13.7664,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.3236641221374046,
1119
+ "grad_norm": 2697351.488139713,
1120
+ "learning_rate": 9.448631527259749e-06,
1121
+ "loss": 13.824,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.3256997455470738,
1126
+ "grad_norm": 2650130.4884775463,
1127
+ "learning_rate": 9.430149007375974e-06,
1128
+ "loss": 13.82,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.327735368956743,
1133
+ "grad_norm": 2848577.7461152556,
1134
+ "learning_rate": 9.411380489997962e-06,
1135
+ "loss": 13.7988,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.3297709923664122,
1140
+ "grad_norm": 2491523.6147146528,
1141
+ "learning_rate": 9.392327186766434e-06,
1142
+ "loss": 13.7801,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.33180661577608145,
1147
+ "grad_norm": 2225342.8572617928,
1148
+ "learning_rate": 9.372990327707057e-06,
1149
+ "loss": 13.8134,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.3338422391857506,
1154
+ "grad_norm": 3593367.5642024544,
1155
+ "learning_rate": 9.353371161151032e-06,
1156
+ "loss": 13.7934,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.33587786259541985,
1161
+ "grad_norm": 3596895.2611031746,
1162
+ "learning_rate": 9.333470953654513e-06,
1163
+ "loss": 13.8181,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.3379134860050891,
1168
+ "grad_norm": 1983403.4312289366,
1169
+ "learning_rate": 9.31329098991683e-06,
1170
+ "loss": 13.8016,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.33994910941475825,
1175
+ "grad_norm": 2840359.066969552,
1176
+ "learning_rate": 9.292832572697566e-06,
1177
+ "loss": 13.7929,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.3419847328244275,
1182
+ "grad_norm": 2440280.3409614386,
1183
+ "learning_rate": 9.272097022732444e-06,
1184
+ "loss": 13.7855,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.3440203562340967,
1189
+ "grad_norm": 3564583.9519162746,
1190
+ "learning_rate": 9.251085678648072e-06,
1191
+ "loss": 13.7962,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.3460559796437659,
1196
+ "grad_norm": 3017839.1906693154,
1197
+ "learning_rate": 9.22979989687552e-06,
1198
+ "loss": 13.7882,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.3480916030534351,
1203
+ "grad_norm": 1926367.5770608934,
1204
+ "learning_rate": 9.208241051562753e-06,
1205
+ "loss": 13.829,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.35012722646310435,
1210
+ "grad_norm": 2347553.991884138,
1211
+ "learning_rate": 9.186410534485924e-06,
1212
+ "loss": 13.7865,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.3521628498727735,
1217
+ "grad_norm": 3954302.4427076643,
1218
+ "learning_rate": 9.164309754959523e-06,
1219
+ "loss": 13.8042,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.35419847328244275,
1224
+ "grad_norm": 3440382.5762445726,
1225
+ "learning_rate": 9.14194013974539e-06,
1226
+ "loss": 13.8065,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.356234096692112,
1231
+ "grad_norm": 3100692.355061626,
1232
+ "learning_rate": 9.11930313296062e-06,
1233
+ "loss": 13.8002,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.35826972010178115,
1238
+ "grad_norm": 3335035.757879338,
1239
+ "learning_rate": 9.096400195984322e-06,
1240
+ "loss": 13.8002,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.3603053435114504,
1245
+ "grad_norm": 2934238.222131686,
1246
+ "learning_rate": 9.073232807363283e-06,
1247
+ "loss": 13.7968,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.3623409669211196,
1252
+ "grad_norm": 3863277.6264942884,
1253
+ "learning_rate": 9.049802462716521e-06,
1254
+ "loss": 13.8059,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.3643765903307888,
1259
+ "grad_norm": 1979824.2277182264,
1260
+ "learning_rate": 9.026110674638722e-06,
1261
+ "loss": 13.7686,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.366412213740458,
1266
+ "grad_norm": 3941584.712432807,
1267
+ "learning_rate": 9.002158972602599e-06,
1268
+ "loss": 13.7605,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.36844783715012724,
1273
+ "grad_norm": 2814992.789501057,
1274
+ "learning_rate": 8.977948902860154e-06,
1275
+ "loss": 13.8302,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.3704834605597964,
1280
+ "grad_norm": 2652186.9612782886,
1281
+ "learning_rate": 8.953482028342853e-06,
1282
+ "loss": 13.7782,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.37251908396946565,
1287
+ "grad_norm": 3385003.9687919975,
1288
+ "learning_rate": 8.92875992856073e-06,
1289
+ "loss": 13.8049,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.3745547073791349,
1294
+ "grad_norm": 5173853.448674343,
1295
+ "learning_rate": 8.903784199500412e-06,
1296
+ "loss": 13.7785,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.37659033078880405,
1301
+ "grad_norm": 4211561.315304709,
1302
+ "learning_rate": 8.8785564535221e-06,
1303
+ "loss": 13.8245,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.3786259541984733,
1308
+ "grad_norm": 2082428.2757180594,
1309
+ "learning_rate": 8.853078319255466e-06,
1310
+ "loss": 13.8218,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.3806615776081425,
1315
+ "grad_norm": 2180497.2165646055,
1316
+ "learning_rate": 8.827351441494525e-06,
1317
+ "loss": 13.7686,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.3826972010178117,
1322
+ "grad_norm": 2403683.8496971005,
1323
+ "learning_rate": 8.80137748109144e-06,
1324
+ "loss": 13.8504,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.3847328244274809,
1329
+ "grad_norm": 2088585.2805628132,
1330
+ "learning_rate": 8.77515811484931e-06,
1331
+ "loss": 13.8108,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.38676844783715014,
1336
+ "grad_norm": 2694457.991947191,
1337
+ "learning_rate": 8.748695035413925e-06,
1338
+ "loss": 13.8309,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.3888040712468193,
1343
+ "grad_norm": 3397579.358486345,
1344
+ "learning_rate": 8.72198995116448e-06,
1345
+ "loss": 13.7726,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.39083969465648855,
1350
+ "grad_norm": 1991789.4895514157,
1351
+ "learning_rate": 8.695044586103297e-06,
1352
+ "loss": 13.7618,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.3928753180661578,
1357
+ "grad_norm": 5556327.041255268,
1358
+ "learning_rate": 8.667860679744529e-06,
1359
+ "loss": 13.7844,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.39491094147582695,
1364
+ "grad_norm": 2177637.385711558,
1365
+ "learning_rate": 8.640439987001855e-06,
1366
+ "loss": 13.7805,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.3969465648854962,
1371
+ "grad_norm": 5370184.851617085,
1372
+ "learning_rate": 8.612784278075195e-06,
1373
+ "loss": 13.7892,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.3989821882951654,
1378
+ "grad_norm": 2473463.532725396,
1379
+ "learning_rate": 8.58489533833643e-06,
1380
+ "loss": 13.7826,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.4010178117048346,
1385
+ "grad_norm": 3439577.606571749,
1386
+ "learning_rate": 8.556774968214134e-06,
1387
+ "loss": 13.8133,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.4030534351145038,
1392
+ "grad_norm": 2463771.55347351,
1393
+ "learning_rate": 8.52842498307736e-06,
1394
+ "loss": 13.8139,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 0.40508905852417304,
1399
+ "grad_norm": 2610726.9405806856,
1400
+ "learning_rate": 8.499847213118431e-06,
1401
+ "loss": 13.7792,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 0.4071246819338422,
1406
+ "grad_norm": 5126921.560500939,
1407
+ "learning_rate": 8.471043503234796e-06,
1408
+ "loss": 13.7862,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 0.40916030534351144,
1413
+ "grad_norm": 2337790.258284094,
1414
+ "learning_rate": 8.442015712909926e-06,
1415
+ "loss": 13.8018,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 0.4111959287531807,
1420
+ "grad_norm": 2269326.88734255,
1421
+ "learning_rate": 8.412765716093273e-06,
1422
+ "loss": 13.8081,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 0.41323155216284985,
1427
+ "grad_norm": 2482439.54650581,
1428
+ "learning_rate": 8.383295401079284e-06,
1429
+ "loss": 13.8155,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 0.4152671755725191,
1434
+ "grad_norm": 2331248.12998744,
1435
+ "learning_rate": 8.353606670385514e-06,
1436
+ "loss": 13.7731,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 0.4173027989821883,
1441
+ "grad_norm": 2419939.8754564477,
1442
+ "learning_rate": 8.3237014406298e-06,
1443
+ "loss": 13.8313,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 0.4193384223918575,
1448
+ "grad_norm": 2294086.8182832007,
1449
+ "learning_rate": 8.293581642406517e-06,
1450
+ "loss": 13.836,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 0.4213740458015267,
1455
+ "grad_norm": 3514387.9792135926,
1456
+ "learning_rate": 8.263249220161957e-06,
1457
+ "loss": 13.8349,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 0.42340966921119594,
1462
+ "grad_norm": 2691961.5452496265,
1463
+ "learning_rate": 8.232706132068806e-06,
1464
+ "loss": 13.8321,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 0.42544529262086517,
1469
+ "grad_norm": 2645633.6227109493,
1470
+ "learning_rate": 8.201954349899712e-06,
1471
+ "loss": 13.8001,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 0.42748091603053434,
1476
+ "grad_norm": 3335230.860278415,
1477
+ "learning_rate": 8.17099585890001e-06,
1478
+ "loss": 13.8217,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 0.42951653944020357,
1483
+ "grad_norm": 2566670.9506267244,
1484
+ "learning_rate": 8.139832657659557e-06,
1485
+ "loss": 13.7714,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 0.4315521628498728,
1490
+ "grad_norm": 2370635.7525829547,
1491
+ "learning_rate": 8.108466757983695e-06,
1492
+ "loss": 13.7885,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 0.433587786259542,
1497
+ "grad_norm": 4441547.469959615,
1498
+ "learning_rate": 8.076900184763394e-06,
1499
+ "loss": 13.7823,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 0.4356234096692112,
1504
+ "grad_norm": 24430772.164419036,
1505
+ "learning_rate": 8.04513497584452e-06,
1506
+ "loss": 13.846,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.43765903307888043,
1511
+ "grad_norm": 1935048.054024762,
1512
+ "learning_rate": 8.013173181896283e-06,
1513
+ "loss": 13.7878,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 0.4396946564885496,
1518
+ "grad_norm": 1873118.933736968,
1519
+ "learning_rate": 7.981016866278843e-06,
1520
+ "loss": 13.7934,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 0.44173027989821884,
1525
+ "grad_norm": 2169804.42270086,
1526
+ "learning_rate": 7.94866810491012e-06,
1527
+ "loss": 13.7965,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 0.44376590330788807,
1532
+ "grad_norm": 3286778.9186343704,
1533
+ "learning_rate": 7.916128986131761e-06,
1534
+ "loss": 13.8332,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 0.44580152671755724,
1539
+ "grad_norm": 2593694.969662653,
1540
+ "learning_rate": 7.883401610574338e-06,
1541
+ "loss": 13.7957,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 0.44783715012722647,
1546
+ "grad_norm": 4975950.65536953,
1547
+ "learning_rate": 7.850488091021726e-06,
1548
+ "loss": 13.8212,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 0.4498727735368957,
1553
+ "grad_norm": 2795061.731221561,
1554
+ "learning_rate": 7.817390552274721e-06,
1555
+ "loss": 13.7835,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 0.45190839694656487,
1560
+ "grad_norm": 2386068.803973628,
1561
+ "learning_rate": 7.784111131013858e-06,
1562
+ "loss": 13.8274,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 0.4539440203562341,
1567
+ "grad_norm": 4657398.876885557,
1568
+ "learning_rate": 7.750651975661471e-06,
1569
+ "loss": 13.7771,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 0.45597964376590333,
1574
+ "grad_norm": 3655891.188475978,
1575
+ "learning_rate": 7.717015246243012e-06,
1576
+ "loss": 13.8151,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 0.4580152671755725,
1581
+ "grad_norm": 3667526.462351342,
1582
+ "learning_rate": 7.683203114247587e-06,
1583
+ "loss": 13.7915,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 0.46005089058524173,
1588
+ "grad_norm": 3809298.1813372867,
1589
+ "learning_rate": 7.649217762487786e-06,
1590
+ "loss": 13.8205,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 0.46208651399491096,
1595
+ "grad_norm": 3288055.728671065,
1596
+ "learning_rate": 7.615061384958764e-06,
1597
+ "loss": 13.8062,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 0.46412213740458014,
1602
+ "grad_norm": 5662460.544065125,
1603
+ "learning_rate": 7.580736186696593e-06,
1604
+ "loss": 13.8049,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 0.46615776081424937,
1609
+ "grad_norm": 4421743.27796514,
1610
+ "learning_rate": 7.546244383635929e-06,
1611
+ "loss": 13.7686,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 0.4681933842239186,
1616
+ "grad_norm": 2313331.4271743125,
1617
+ "learning_rate": 7.5115882024669375e-06,
1618
+ "loss": 13.8003,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 0.47022900763358777,
1623
+ "grad_norm": 6343328.905525712,
1624
+ "learning_rate": 7.476769880491561e-06,
1625
+ "loss": 13.7806,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 0.472264631043257,
1630
+ "grad_norm": 2640558.638662984,
1631
+ "learning_rate": 7.44179166547908e-06,
1632
+ "loss": 13.7999,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 0.47430025445292623,
1637
+ "grad_norm": 4310404.449472289,
1638
+ "learning_rate": 7.406655815520998e-06,
1639
+ "loss": 13.8118,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 0.4763358778625954,
1644
+ "grad_norm": 4518592.431753858,
1645
+ "learning_rate": 7.371364598885276e-06,
1646
+ "loss": 13.7864,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 0.47837150127226463,
1651
+ "grad_norm": 2098819.871080459,
1652
+ "learning_rate": 7.335920293869891e-06,
1653
+ "loss": 13.8016,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 0.48040712468193386,
1658
+ "grad_norm": 2463516.9812008953,
1659
+ "learning_rate": 7.300325188655762e-06,
1660
+ "loss": 13.7913,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 0.48244274809160304,
1665
+ "grad_norm": 3102860.0228757737,
1666
+ "learning_rate": 7.264581581159024e-06,
1667
+ "loss": 13.7706,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 0.48447837150127226,
1672
+ "grad_norm": 1914868.4483156833,
1673
+ "learning_rate": 7.2286917788826926e-06,
1674
+ "loss": 13.8093,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 0.4865139949109415,
1679
+ "grad_norm": 2539581.4122914425,
1680
+ "learning_rate": 7.192658098767686e-06,
1681
+ "loss": 13.7854,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 0.48854961832061067,
1686
+ "grad_norm": 3707976.67600207,
1687
+ "learning_rate": 7.1564828670432595e-06,
1688
+ "loss": 13.8176,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 0.4905852417302799,
1693
+ "grad_norm": 3593935.7875790736,
1694
+ "learning_rate": 7.120168419076825e-06,
1695
+ "loss": 13.767,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 0.4926208651399491,
1700
+ "grad_norm": 19371415.336839173,
1701
+ "learning_rate": 7.083717099223192e-06,
1702
+ "loss": 13.7774,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 0.4946564885496183,
1707
+ "grad_norm": 2053853.5565662459,
1708
+ "learning_rate": 7.047131260673214e-06,
1709
+ "loss": 13.8225,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 0.49669211195928753,
1714
+ "grad_norm": 4077586.3030170733,
1715
+ "learning_rate": 7.010413265301888e-06,
1716
+ "loss": 13.7911,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 0.49872773536895676,
1721
+ "grad_norm": 2640760.978026206,
1722
+ "learning_rate": 6.97356548351586e-06,
1723
+ "loss": 13.8096,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 0.500763358778626,
1728
+ "grad_norm": 3012267.667522946,
1729
+ "learning_rate": 6.936590294100414e-06,
1730
+ "loss": 13.7508,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 0.5027989821882952,
1735
+ "grad_norm": 2736053.147326933,
1736
+ "learning_rate": 6.899490084065897e-06,
1737
+ "loss": 13.8161,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 0.5048346055979643,
1742
+ "grad_norm": 3879858.467910511,
1743
+ "learning_rate": 6.862267248493624e-06,
1744
+ "loss": 13.8145,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 0.5068702290076336,
1749
+ "grad_norm": 2410669.072572543,
1750
+ "learning_rate": 6.824924190381257e-06,
1751
+ "loss": 13.7883,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 0.5089058524173028,
1756
+ "grad_norm": 2792170.4070734098,
1757
+ "learning_rate": 6.7874633204876705e-06,
1758
+ "loss": 13.83,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 0.510941475826972,
1763
+ "grad_norm": 3054954.4878360187,
1764
+ "learning_rate": 6.7498870571773275e-06,
1765
+ "loss": 13.8138,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 0.5129770992366413,
1770
+ "grad_norm": 13118018.692801312,
1771
+ "learning_rate": 6.712197826264154e-06,
1772
+ "loss": 13.7877,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 0.5150127226463105,
1777
+ "grad_norm": 2274862.944795723,
1778
+ "learning_rate": 6.674398060854931e-06,
1779
+ "loss": 13.788,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 0.5170483460559796,
1784
+ "grad_norm": 6493219.085795618,
1785
+ "learning_rate": 6.636490201192229e-06,
1786
+ "loss": 13.8056,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 0.5190839694656488,
1791
+ "grad_norm": 2210871.447412882,
1792
+ "learning_rate": 6.5984766944968636e-06,
1793
+ "loss": 13.7964,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 0.5211195928753181,
1798
+ "grad_norm": 2535457.1929967045,
1799
+ "learning_rate": 6.560359994809916e-06,
1800
+ "loss": 13.8025,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 0.5231552162849873,
1805
+ "grad_norm": 3487433.3872100264,
1806
+ "learning_rate": 6.522142562834307e-06,
1807
+ "loss": 13.7752,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 0.5251908396946565,
1812
+ "grad_norm": 2350043.7437156746,
1813
+ "learning_rate": 6.483826865775941e-06,
1814
+ "loss": 13.7891,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 0.5272264631043257,
1819
+ "grad_norm": 3776676.8394483137,
1820
+ "learning_rate": 6.445415377184427e-06,
1821
+ "loss": 13.8172,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 0.5292620865139949,
1826
+ "grad_norm": 3888987.2901650295,
1827
+ "learning_rate": 6.4069105767933944e-06,
1828
+ "loss": 13.7623,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 0.5312977099236641,
1833
+ "grad_norm": 3340457.7579122144,
1834
+ "learning_rate": 6.368314950360416e-06,
1835
+ "loss": 13.8065,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 0.5333333333333333,
1840
+ "grad_norm": 5982292.313514162,
1841
+ "learning_rate": 6.3296309895065215e-06,
1842
+ "loss": 13.7812,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 0.5353689567430026,
1847
+ "grad_norm": 3219916.0058936477,
1848
+ "learning_rate": 6.290861191555359e-06,
1849
+ "loss": 13.745,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 0.5374045801526718,
1854
+ "grad_norm": 11720301.310935492,
1855
+ "learning_rate": 6.252008059371968e-06,
1856
+ "loss": 13.8253,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 0.539440203562341,
1861
+ "grad_norm": 3118271.2300748057,
1862
+ "learning_rate": 6.213074101201202e-06,
1863
+ "loss": 13.7763,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 0.5414758269720101,
1868
+ "grad_norm": 1697945.554145853,
1869
+ "learning_rate": 6.174061830505801e-06,
1870
+ "loss": 13.7883,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 0.5435114503816794,
1875
+ "grad_norm": 2857758.0379691618,
1876
+ "learning_rate": 6.1349737658041385e-06,
1877
+ "loss": 13.7939,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 0.5455470737913486,
1882
+ "grad_norm": 1961975.7441584785,
1883
+ "learning_rate": 6.095812430507627e-06,
1884
+ "loss": 13.7989,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 0.5475826972010178,
1889
+ "grad_norm": 4193880.83293653,
1890
+ "learning_rate": 6.056580352757813e-06,
1891
+ "loss": 13.8241,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 0.549618320610687,
1896
+ "grad_norm": 3312744.2202664735,
1897
+ "learning_rate": 6.0172800652631706e-06,
1898
+ "loss": 13.7733,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 0.5516539440203563,
1903
+ "grad_norm": 7858171.4628072195,
1904
+ "learning_rate": 5.977914105135594e-06,
1905
+ "loss": 13.8072,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 0.5536895674300254,
1910
+ "grad_norm": 3941663.415453141,
1911
+ "learning_rate": 5.938485013726612e-06,
1912
+ "loss": 13.8103,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 0.5557251908396946,
1917
+ "grad_norm": 3610433.10118229,
1918
+ "learning_rate": 5.898995336463326e-06,
1919
+ "loss": 13.807,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 0.5577608142493639,
1924
+ "grad_norm": 4164601.1328435126,
1925
+ "learning_rate": 5.859447622684084e-06,
1926
+ "loss": 13.815,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 0.5597964376590331,
1931
+ "grad_norm": 2548966.8285937863,
1932
+ "learning_rate": 5.819844425473899e-06,
1933
+ "loss": 13.7778,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 0.5618320610687023,
1938
+ "grad_norm": 4078882.101176789,
1939
+ "learning_rate": 5.780188301499636e-06,
1940
+ "loss": 13.8193,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 0.5638676844783715,
1945
+ "grad_norm": 2517308.8894206337,
1946
+ "learning_rate": 5.740481810844952e-06,
1947
+ "loss": 13.8063,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 0.5659033078880407,
1952
+ "grad_norm": 2769966.422515691,
1953
+ "learning_rate": 5.700727516845038e-06,
1954
+ "loss": 13.8094,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 0.5679389312977099,
1959
+ "grad_norm": 3505593.62357941,
1960
+ "learning_rate": 5.660927985921122e-06,
1961
+ "loss": 13.8098,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 0.5699745547073791,
1966
+ "grad_norm": 2349437.1104983217,
1967
+ "learning_rate": 5.621085787414799e-06,
1968
+ "loss": 13.799,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 0.5720101781170484,
1973
+ "grad_norm": 3132576.359530331,
1974
+ "learning_rate": 5.581203493422161e-06,
1975
+ "loss": 13.7891,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 0.5740458015267176,
1980
+ "grad_norm": 4404000.913374095,
1981
+ "learning_rate": 5.541283678627742e-06,
1982
+ "loss": 13.7851,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 0.5760814249363868,
1987
+ "grad_norm": 3276477.3200832414,
1988
+ "learning_rate": 5.501328920138314e-06,
1989
+ "loss": 13.8194,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 0.5781170483460559,
1994
+ "grad_norm": 3546838.8556743674,
1995
+ "learning_rate": 5.46134179731651e-06,
1996
+ "loss": 13.8107,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 0.5801526717557252,
2001
+ "grad_norm": 2115264.4674158324,
2002
+ "learning_rate": 5.421324891614312e-06,
2003
+ "loss": 13.7984,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 0.5821882951653944,
2008
+ "grad_norm": 2235578.204459906,
2009
+ "learning_rate": 5.3812807864063946e-06,
2010
+ "loss": 13.8009,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 0.5842239185750636,
2015
+ "grad_norm": 4052228.371342962,
2016
+ "learning_rate": 5.341212066823356e-06,
2017
+ "loss": 13.7885,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 0.5862595419847328,
2022
+ "grad_norm": 2755225.8421591343,
2023
+ "learning_rate": 5.3011213195848245e-06,
2024
+ "loss": 13.7845,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 0.5882951653944021,
2029
+ "grad_norm": 3206915.4484688323,
2030
+ "learning_rate": 5.26101113283247e-06,
2031
+ "loss": 13.8352,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 0.5903307888040712,
2036
+ "grad_norm": 8291421.864476618,
2037
+ "learning_rate": 5.220884095962924e-06,
2038
+ "loss": 13.7882,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 0.5923664122137404,
2043
+ "grad_norm": 4520092.054349328,
2044
+ "learning_rate": 5.1807427994606065e-06,
2045
+ "loss": 13.7911,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 0.5944020356234097,
2050
+ "grad_norm": 1988928.2728027685,
2051
+ "learning_rate": 5.140589834730503e-06,
2052
+ "loss": 13.8379,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 0.5964376590330789,
2057
+ "grad_norm": 4465132.927934143,
2058
+ "learning_rate": 5.100427793930862e-06,
2059
+ "loss": 13.7948,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 0.5984732824427481,
2064
+ "grad_norm": 2286780.168218436,
2065
+ "learning_rate": 5.06025926980586e-06,
2066
+ "loss": 13.8048,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 0.6005089058524173,
2071
+ "grad_norm": 2724184.449634601,
2072
+ "learning_rate": 5.0200868555182155e-06,
2073
+ "loss": 13.7999,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 0.6025445292620865,
2078
+ "grad_norm": 2576691.827404387,
2079
+ "learning_rate": 4.979913144481785e-06,
2080
+ "loss": 13.8064,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 0.6045801526717557,
2085
+ "grad_norm": 2744547.316751667,
2086
+ "learning_rate": 4.939740730194141e-06,
2087
+ "loss": 13.7882,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 0.6066157760814249,
2092
+ "grad_norm": 2335607.7276287796,
2093
+ "learning_rate": 4.899572206069138e-06,
2094
+ "loss": 13.8027,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 0.6086513994910941,
2099
+ "grad_norm": 2599599.7384826983,
2100
+ "learning_rate": 4.8594101652694996e-06,
2101
+ "loss": 13.8156,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 0.6106870229007634,
2106
+ "grad_norm": 3536926.667490122,
2107
+ "learning_rate": 4.819257200539394e-06,
2108
+ "loss": 13.7784,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 0.6127226463104326,
2113
+ "grad_norm": 3302834.606287667,
2114
+ "learning_rate": 4.779115904037079e-06,
2115
+ "loss": 13.8263,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 0.6147582697201018,
2120
+ "grad_norm": 3042014.762667294,
2121
+ "learning_rate": 4.738988867167531e-06,
2122
+ "loss": 13.7901,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 0.616793893129771,
2127
+ "grad_norm": 2828614.249275787,
2128
+ "learning_rate": 4.698878680415176e-06,
2129
+ "loss": 13.8186,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 0.6188295165394402,
2134
+ "grad_norm": 3470485.7180142673,
2135
+ "learning_rate": 4.6587879331766465e-06,
2136
+ "loss": 13.8252,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 0.6208651399491094,
2141
+ "grad_norm": 2142989.454887267,
2142
+ "learning_rate": 4.618719213593605e-06,
2143
+ "loss": 13.8266,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 0.6229007633587786,
2148
+ "grad_norm": 3599418.075481026,
2149
+ "learning_rate": 4.5786751083856895e-06,
2150
+ "loss": 13.7994,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 0.6249363867684479,
2155
+ "grad_norm": 2468894.215654323,
2156
+ "learning_rate": 4.53865820268349e-06,
2157
+ "loss": 13.7975,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 0.6269720101781171,
2162
+ "grad_norm": 3514891.7530831015,
2163
+ "learning_rate": 4.498671079861686e-06,
2164
+ "loss": 13.8089,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 0.6290076335877862,
2169
+ "grad_norm": 2860617.0108131613,
2170
+ "learning_rate": 4.4587163213722595e-06,
2171
+ "loss": 13.8118,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 0.6310432569974554,
2176
+ "grad_norm": 3631959.0225475803,
2177
+ "learning_rate": 4.41879650657784e-06,
2178
+ "loss": 13.7789,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 0.6330788804071247,
2183
+ "grad_norm": 16505260.927290315,
2184
+ "learning_rate": 4.3789142125852015e-06,
2185
+ "loss": 13.7988,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 0.6351145038167939,
2190
+ "grad_norm": 2464199.3044430655,
2191
+ "learning_rate": 4.339072014078879e-06,
2192
+ "loss": 13.8382,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 0.6371501272264631,
2197
+ "grad_norm": 2003547.7230704648,
2198
+ "learning_rate": 4.299272483154963e-06,
2199
+ "loss": 13.8229,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 0.6391857506361324,
2204
+ "grad_norm": 2815342.948838401,
2205
+ "learning_rate": 4.259518189155049e-06,
2206
+ "loss": 13.8061,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 0.6412213740458015,
2211
+ "grad_norm": 3015740.318214435,
2212
+ "learning_rate": 4.219811698500365e-06,
2213
+ "loss": 13.8036,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 0.6432569974554707,
2218
+ "grad_norm": 3876924.4779627738,
2219
+ "learning_rate": 4.1801555745261025e-06,
2220
+ "loss": 13.7914,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 0.6452926208651399,
2225
+ "grad_norm": 3172609.6206479096,
2226
+ "learning_rate": 4.140552377315918e-06,
2227
+ "loss": 13.8449,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 0.6473282442748092,
2232
+ "grad_norm": 4902114.509930776,
2233
+ "learning_rate": 4.101004663536675e-06,
2234
+ "loss": 13.7976,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 0.6493638676844784,
2239
+ "grad_norm": 2691295.2268303274,
2240
+ "learning_rate": 4.061514986273391e-06,
2241
+ "loss": 13.8136,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 0.6513994910941476,
2246
+ "grad_norm": 3460007.077345259,
2247
+ "learning_rate": 4.022085894864408e-06,
2248
+ "loss": 13.7403,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 0.6534351145038167,
2253
+ "grad_norm": 2367194.347019021,
2254
+ "learning_rate": 3.982719934736832e-06,
2255
+ "loss": 13.7971,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 0.655470737913486,
2260
+ "grad_norm": 15501881.45680894,
2261
+ "learning_rate": 3.943419647242189e-06,
2262
+ "loss": 13.8015,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 0.6575063613231552,
2267
+ "grad_norm": 2840321.3616006514,
2268
+ "learning_rate": 3.904187569492373e-06,
2269
+ "loss": 13.8104,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 0.6595419847328244,
2274
+ "grad_norm": 2030054.0765901625,
2275
+ "learning_rate": 3.865026234195863e-06,
2276
+ "loss": 13.7948,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 0.6615776081424937,
2281
+ "grad_norm": 2852479.1215876606,
2282
+ "learning_rate": 3.8259381694942e-06,
2283
+ "loss": 13.7901,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 0.6636132315521629,
2288
+ "grad_norm": 3456741.004275556,
2289
+ "learning_rate": 3.786925898798801e-06,
2290
+ "loss": 13.7857,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 0.665648854961832,
2295
+ "grad_norm": 2066561.8194525177,
2296
+ "learning_rate": 3.7479919406280334e-06,
2297
+ "loss": 13.8063,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 0.6676844783715012,
2302
+ "grad_norm": 3433587.7234547967,
2303
+ "learning_rate": 3.709138808444641e-06,
2304
+ "loss": 13.8119,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 0.6697201017811705,
2309
+ "grad_norm": 3578864.1748913922,
2310
+ "learning_rate": 3.6703690104934806e-06,
2311
+ "loss": 13.7908,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 0.6717557251908397,
2316
+ "grad_norm": 4610701.366359627,
2317
+ "learning_rate": 3.6316850496395863e-06,
2318
+ "loss": 13.7847,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 0.6737913486005089,
2323
+ "grad_norm": 2286947.6993929525,
2324
+ "learning_rate": 3.5930894232066072e-06,
2325
+ "loss": 13.8097,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 0.6758269720101782,
2330
+ "grad_norm": 2505249.1545348107,
2331
+ "learning_rate": 3.5545846228155743e-06,
2332
+ "loss": 13.7801,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 0.6778625954198473,
2337
+ "grad_norm": 5630898.8033584,
2338
+ "learning_rate": 3.516173134224059e-06,
2339
+ "loss": 13.8135,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 0.6798982188295165,
2344
+ "grad_norm": 5219141.786739386,
2345
+ "learning_rate": 3.477857437165694e-06,
2346
+ "loss": 13.8255,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 0.6819338422391857,
2351
+ "grad_norm": 2124438.8087317753,
2352
+ "learning_rate": 3.4396400051900846e-06,
2353
+ "loss": 13.7879,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 0.683969465648855,
2358
+ "grad_norm": 2105149.4046267755,
2359
+ "learning_rate": 3.401523305503139e-06,
2360
+ "loss": 13.808,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 0.6860050890585242,
2365
+ "grad_norm": 2809609.693441461,
2366
+ "learning_rate": 3.3635097988077724e-06,
2367
+ "loss": 13.8112,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 0.6880407124681934,
2372
+ "grad_norm": 2457213.1931723696,
2373
+ "learning_rate": 3.3256019391450696e-06,
2374
+ "loss": 13.8489,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 0.6900763358778625,
2379
+ "grad_norm": 12558459.530425403,
2380
+ "learning_rate": 3.287802173735848e-06,
2381
+ "loss": 13.8277,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 0.6921119592875318,
2386
+ "grad_norm": 6967431.723878883,
2387
+ "learning_rate": 3.250112942822673e-06,
2388
+ "loss": 13.8185,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 0.694147582697201,
2393
+ "grad_norm": 3411907.5422053095,
2394
+ "learning_rate": 3.212536679512332e-06,
2395
+ "loss": 13.787,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 0.6961832061068702,
2400
+ "grad_norm": 2429502.145664427,
2401
+ "learning_rate": 3.1750758096187446e-06,
2402
+ "loss": 13.8105,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 0.6982188295165395,
2407
+ "grad_norm": 2327547.2445986923,
2408
+ "learning_rate": 3.137732751506376e-06,
2409
+ "loss": 13.7772,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 0.7002544529262087,
2414
+ "grad_norm": 3569398.8894632743,
2415
+ "learning_rate": 3.1005099159341044e-06,
2416
+ "loss": 13.7938,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 0.7022900763358778,
2421
+ "grad_norm": 3211149.457873932,
2422
+ "learning_rate": 3.0634097058995877e-06,
2423
+ "loss": 13.7915,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 0.704325699745547,
2428
+ "grad_norm": 3830655.2384712566,
2429
+ "learning_rate": 3.0264345164841426e-06,
2430
+ "loss": 13.8191,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 0.7063613231552163,
2435
+ "grad_norm": 3823712.125917996,
2436
+ "learning_rate": 2.989586734698113e-06,
2437
+ "loss": 13.8023,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 0.7083969465648855,
2442
+ "grad_norm": 32196514.721627507,
2443
+ "learning_rate": 2.9528687393267865e-06,
2444
+ "loss": 13.7764,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 0.7104325699745547,
2449
+ "grad_norm": 1882821.5554029653,
2450
+ "learning_rate": 2.9162829007768103e-06,
2451
+ "loss": 13.8351,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 0.712468193384224,
2456
+ "grad_norm": 3350119.682457626,
2457
+ "learning_rate": 2.879831580923176e-06,
2458
+ "loss": 13.7957,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 0.7145038167938931,
2463
+ "grad_norm": 3937737.379258324,
2464
+ "learning_rate": 2.843517132956742e-06,
2465
+ "loss": 13.8002,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 0.7165394402035623,
2470
+ "grad_norm": 3146762.068649268,
2471
+ "learning_rate": 2.8073419012323154e-06,
2472
+ "loss": 13.7632,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 0.7185750636132315,
2477
+ "grad_norm": 2767069.333419986,
2478
+ "learning_rate": 2.771308221117309e-06,
2479
+ "loss": 13.7933,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 0.7206106870229008,
2484
+ "grad_norm": 4373321.192999916,
2485
+ "learning_rate": 2.7354184188409773e-06,
2486
+ "loss": 13.798,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 0.72264631043257,
2491
+ "grad_norm": 3450348.839131381,
2492
+ "learning_rate": 2.6996748113442397e-06,
2493
+ "loss": 13.8177,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 0.7246819338422392,
2498
+ "grad_norm": 5591120.72637471,
2499
+ "learning_rate": 2.66407970613011e-06,
2500
+ "loss": 13.7984,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 0.7267175572519083,
2505
+ "grad_norm": 1703861.5304970315,
2506
+ "learning_rate": 2.6286354011147252e-06,
2507
+ "loss": 13.8147,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 0.7287531806615776,
2512
+ "grad_norm": 3465138.9565325286,
2513
+ "learning_rate": 2.593344184479003e-06,
2514
+ "loss": 13.8088,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 0.7307888040712468,
2519
+ "grad_norm": 4545416.100109938,
2520
+ "learning_rate": 2.5582083345209217e-06,
2521
+ "loss": 13.8249,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 0.732824427480916,
2526
+ "grad_norm": 3516332.5584949586,
2527
+ "learning_rate": 2.5232301195084395e-06,
2528
+ "loss": 13.8055,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 0.7348600508905853,
2533
+ "grad_norm": 2312331.751163826,
2534
+ "learning_rate": 2.488411797533064e-06,
2535
+ "loss": 13.8223,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 0.7368956743002545,
2540
+ "grad_norm": 2685597.665166646,
2541
+ "learning_rate": 2.4537556163640726e-06,
2542
+ "loss": 13.8293,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 0.7389312977099237,
2547
+ "grad_norm": 2522967.966999191,
2548
+ "learning_rate": 2.4192638133034074e-06,
2549
+ "loss": 13.7902,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 0.7409669211195928,
2554
+ "grad_norm": 2195261.840643841,
2555
+ "learning_rate": 2.384938615041238e-06,
2556
+ "loss": 13.782,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 0.7430025445292621,
2561
+ "grad_norm": 6598560.135727499,
2562
+ "learning_rate": 2.350782237512215e-06,
2563
+ "loss": 13.8163,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 0.7450381679389313,
2568
+ "grad_norm": 2786370.46056762,
2569
+ "learning_rate": 2.316796885752415e-06,
2570
+ "loss": 13.7821,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 0.7470737913486005,
2575
+ "grad_norm": 2943271.811966078,
2576
+ "learning_rate": 2.2829847537569904e-06,
2577
+ "loss": 13.7909,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 0.7491094147582698,
2582
+ "grad_norm": 2462160.442139116,
2583
+ "learning_rate": 2.2493480243385298e-06,
2584
+ "loss": 13.814,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 0.751145038167939,
2589
+ "grad_norm": 2225343.862719593,
2590
+ "learning_rate": 2.2158888689861434e-06,
2591
+ "loss": 13.8084,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 0.7531806615776081,
2596
+ "grad_norm": 2960178.644234803,
2597
+ "learning_rate": 2.182609447725279e-06,
2598
+ "loss": 13.8266,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 0.7552162849872773,
2603
+ "grad_norm": 2914387.1052595368,
2604
+ "learning_rate": 2.149511908978275e-06,
2605
+ "loss": 13.8007,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 0.7572519083969466,
2610
+ "grad_norm": 3028649.837352563,
2611
+ "learning_rate": 2.1165983894256647e-06,
2612
+ "loss": 13.7907,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 0.7592875318066158,
2617
+ "grad_norm": 2648884.5001803297,
2618
+ "learning_rate": 2.0838710138682412e-06,
2619
+ "loss": 13.8052,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 0.761323155216285,
2624
+ "grad_norm": 3498649.6090777554,
2625
+ "learning_rate": 2.051331895089882e-06,
2626
+ "loss": 13.8098,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 0.7633587786259542,
2631
+ "grad_norm": 23098352.355775494,
2632
+ "learning_rate": 2.0189831337211573e-06,
2633
+ "loss": 13.8393,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 0.7653944020356234,
2638
+ "grad_norm": 2461084.0552417845,
2639
+ "learning_rate": 1.9868268181037186e-06,
2640
+ "loss": 13.7867,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 0.7674300254452926,
2645
+ "grad_norm": 3735300.3296117457,
2646
+ "learning_rate": 1.9548650241554812e-06,
2647
+ "loss": 13.804,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 0.7694656488549618,
2652
+ "grad_norm": 3008756.34059785,
2653
+ "learning_rate": 1.923099815236608e-06,
2654
+ "loss": 13.7861,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 0.771501272264631,
2659
+ "grad_norm": 7710036.601809266,
2660
+ "learning_rate": 1.8915332420163074e-06,
2661
+ "loss": 13.7991,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 0.7735368956743003,
2666
+ "grad_norm": 3540790.6907704584,
2667
+ "learning_rate": 1.8601673423404449e-06,
2668
+ "loss": 13.7907,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 0.7755725190839695,
2673
+ "grad_norm": 2333150.5964701963,
2674
+ "learning_rate": 1.8290041410999893e-06,
2675
+ "loss": 13.8226,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 0.7776081424936386,
2680
+ "grad_norm": 3965290.2964736833,
2681
+ "learning_rate": 1.798045650100289e-06,
2682
+ "loss": 13.7884,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 0.7796437659033079,
2687
+ "grad_norm": 2968777.429909849,
2688
+ "learning_rate": 1.7672938679311957e-06,
2689
+ "loss": 13.7859,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 0.7816793893129771,
2694
+ "grad_norm": 5317126.450461407,
2695
+ "learning_rate": 1.736750779838044e-06,
2696
+ "loss": 13.8526,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 0.7837150127226463,
2701
+ "grad_norm": 3055487.063269149,
2702
+ "learning_rate": 1.7064183575934856e-06,
2703
+ "loss": 13.8009,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 0.7857506361323155,
2708
+ "grad_norm": 16905669.825724535,
2709
+ "learning_rate": 1.676298559370202e-06,
2710
+ "loss": 13.7807,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 0.7877862595419848,
2715
+ "grad_norm": 5137867.698262086,
2716
+ "learning_rate": 1.6463933296144863e-06,
2717
+ "loss": 13.8198,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 0.7898218829516539,
2722
+ "grad_norm": 3398913.1351794973,
2723
+ "learning_rate": 1.6167045989207185e-06,
2724
+ "loss": 13.7712,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 0.7918575063613231,
2729
+ "grad_norm": 3925212.2891858686,
2730
+ "learning_rate": 1.5872342839067305e-06,
2731
+ "loss": 13.807,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 0.7938931297709924,
2736
+ "grad_norm": 2924712.3948877575,
2737
+ "learning_rate": 1.5579842870900746e-06,
2738
+ "loss": 13.8241,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 0.7959287531806616,
2743
+ "grad_norm": 5390343.102311131,
2744
+ "learning_rate": 1.5289564967652033e-06,
2745
+ "loss": 13.8485,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 0.7979643765903308,
2750
+ "grad_norm": 3074687.848582143,
2751
+ "learning_rate": 1.5001527868815702e-06,
2752
+ "loss": 13.8125,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 0.8,
2757
+ "grad_norm": 3184498.416088956,
2758
+ "learning_rate": 1.4715750169226417e-06,
2759
+ "loss": 13.766,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 0.8020356234096692,
2764
+ "grad_norm": 2441964.563817395,
2765
+ "learning_rate": 1.4432250317858675e-06,
2766
+ "loss": 13.7805,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 0.8040712468193384,
2771
+ "grad_norm": 2091387.9994893048,
2772
+ "learning_rate": 1.4151046616635727e-06,
2773
+ "loss": 13.7952,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 0.8061068702290076,
2778
+ "grad_norm": 3508560.4814663967,
2779
+ "learning_rate": 1.3872157219248045e-06,
2780
+ "loss": 13.7889,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 0.8081424936386769,
2785
+ "grad_norm": 3962771.0203186534,
2786
+ "learning_rate": 1.3595600129981469e-06,
2787
+ "loss": 13.7979,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 0.8101781170483461,
2792
+ "grad_norm": 2731620.334807845,
2793
+ "learning_rate": 1.3321393202554739e-06,
2794
+ "loss": 13.7976,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 0.8122137404580153,
2799
+ "grad_norm": 3197496.0139092538,
2800
+ "learning_rate": 1.3049554138967052e-06,
2801
+ "loss": 13.7901,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 0.8142493638676844,
2806
+ "grad_norm": 7014943.992062835,
2807
+ "learning_rate": 1.278010048835523e-06,
2808
+ "loss": 13.7998,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 0.8162849872773537,
2813
+ "grad_norm": 3316247.1212317836,
2814
+ "learning_rate": 1.2513049645860759e-06,
2815
+ "loss": 13.765,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 0.8183206106870229,
2820
+ "grad_norm": 2783094.2613453907,
2821
+ "learning_rate": 1.224841885150691e-06,
2822
+ "loss": 13.8445,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 0.8203562340966921,
2827
+ "grad_norm": 3355566.32780499,
2828
+ "learning_rate": 1.1986225189085627e-06,
2829
+ "loss": 13.8081,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 0.8223918575063613,
2834
+ "grad_norm": 2212096.023617605,
2835
+ "learning_rate": 1.172648558505477e-06,
2836
+ "loss": 13.7965,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 0.8244274809160306,
2841
+ "grad_norm": 1744005.9134531072,
2842
+ "learning_rate": 1.1469216807445348e-06,
2843
+ "loss": 13.827,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 0.8264631043256997,
2848
+ "grad_norm": 5478757.4739052905,
2849
+ "learning_rate": 1.1214435464779006e-06,
2850
+ "loss": 13.8068,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 0.8284987277353689,
2855
+ "grad_norm": 10845370.007264948,
2856
+ "learning_rate": 1.0962158004995893e-06,
2857
+ "loss": 13.8192,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 0.8305343511450382,
2862
+ "grad_norm": 6268218.580873969,
2863
+ "learning_rate": 1.0712400714392723e-06,
2864
+ "loss": 13.7939,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 0.8325699745547074,
2869
+ "grad_norm": 4049672.137206165,
2870
+ "learning_rate": 1.0465179716571467e-06,
2871
+ "loss": 13.7897,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 0.8346055979643766,
2876
+ "grad_norm": 5672727.971393141,
2877
+ "learning_rate": 1.0220510971398473e-06,
2878
+ "loss": 13.8234,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 0.8366412213740458,
2883
+ "grad_norm": 2826950.9583422337,
2884
+ "learning_rate": 9.978410273974015e-07,
2885
+ "loss": 13.7928,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 0.838676844783715,
2890
+ "grad_norm": 2758814.4659312656,
2891
+ "learning_rate": 9.738893253612808e-07,
2892
+ "loss": 13.802,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 0.8407124681933842,
2897
+ "grad_norm": 2475383.7033035085,
2898
+ "learning_rate": 9.50197537283481e-07,
2899
+ "loss": 13.7978,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 0.8427480916030534,
2904
+ "grad_norm": 3247115.9631803534,
2905
+ "learning_rate": 9.267671926367166e-07,
2906
+ "loss": 13.826,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 0.8447837150127226,
2911
+ "grad_norm": 2633292.367379474,
2912
+ "learning_rate": 9.035998040156801e-07,
2913
+ "loss": 13.7931,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 0.8468193384223919,
2918
+ "grad_norm": 2515821.989602333,
2919
+ "learning_rate": 8.806968670393801e-07,
2920
+ "loss": 13.7718,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 0.8488549618320611,
2925
+ "grad_norm": 2652660.850368756,
2926
+ "learning_rate": 8.580598602546109e-07,
2927
+ "loss": 13.8055,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 0.8508905852417303,
2932
+ "grad_norm": 2999838.4744108086,
2933
+ "learning_rate": 8.356902450404792e-07,
2934
+ "loss": 13.817,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 0.8529262086513995,
2939
+ "grad_norm": 2359848.6979157086,
2940
+ "learning_rate": 8.135894655140758e-07,
2941
+ "loss": 13.79,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 0.8549618320610687,
2946
+ "grad_norm": 3156996.0591459703,
2947
+ "learning_rate": 7.91758948437249e-07,
2948
+ "loss": 13.7984,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 0.8569974554707379,
2953
+ "grad_norm": 3762598.8987431657,
2954
+ "learning_rate": 7.702001031244816e-07,
2955
+ "loss": 13.8018,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 0.8590330788804071,
2960
+ "grad_norm": 1976772.2357703648,
2961
+ "learning_rate": 7.489143213519301e-07,
2962
+ "loss": 13.8201,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 0.8610687022900764,
2967
+ "grad_norm": 2785725.350606155,
2968
+ "learning_rate": 7.279029772675572e-07,
2969
+ "loss": 13.7565,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 0.8631043256997456,
2974
+ "grad_norm": 2620438.7904132027,
2975
+ "learning_rate": 7.071674273024353e-07,
2976
+ "loss": 13.793,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 0.8651399491094147,
2981
+ "grad_norm": 2646276.309564974,
2982
+ "learning_rate": 6.86709010083172e-07,
2983
+ "loss": 13.8229,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 0.867175572519084,
2988
+ "grad_norm": 2628696.346363584,
2989
+ "learning_rate": 6.665290463454882e-07,
2990
+ "loss": 13.7809,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 0.8692111959287532,
2995
+ "grad_norm": 3600670.0350286104,
2996
+ "learning_rate": 6.466288388489689e-07,
2997
+ "loss": 13.8044,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 0.8712468193384224,
3002
+ "grad_norm": 2947142.074939093,
3003
+ "learning_rate": 6.270096722929442e-07,
3004
+ "loss": 13.8006,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 0.8732824427480916,
3009
+ "grad_norm": 2029930.0771920187,
3010
+ "learning_rate": 6.076728132335669e-07,
3011
+ "loss": 13.796,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 0.8753180661577609,
3016
+ "grad_norm": 2143832.4235748462,
3017
+ "learning_rate": 5.886195100020408e-07,
3018
+ "loss": 13.7854,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 0.87735368956743,
3023
+ "grad_norm": 13943126.109787703,
3024
+ "learning_rate": 5.698509926240275e-07,
3025
+ "loss": 13.7955,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 0.8793893129770992,
3030
+ "grad_norm": 3462678.627784003,
3031
+ "learning_rate": 5.513684727402529e-07,
3032
+ "loss": 13.8238,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 0.8814249363867684,
3037
+ "grad_norm": 2958565.3339085556,
3038
+ "learning_rate": 5.331731435282705e-07,
3039
+ "loss": 13.8227,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 0.8834605597964377,
3044
+ "grad_norm": 2315016.094193514,
3045
+ "learning_rate": 5.152661796254505e-07,
3046
+ "loss": 13.7815,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 0.8854961832061069,
3051
+ "grad_norm": 3124561.491445178,
3052
+ "learning_rate": 4.976487370531352e-07,
3053
+ "loss": 13.7972,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 0.8875318066157761,
3058
+ "grad_norm": 2569217.587769061,
3059
+ "learning_rate": 4.803219531420128e-07,
3060
+ "loss": 13.7759,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 0.8895674300254452,
3065
+ "grad_norm": 5211670.405327593,
3066
+ "learning_rate": 4.6328694645870254e-07,
3067
+ "loss": 13.7982,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 0.8916030534351145,
3072
+ "grad_norm": 2303871.1225886643,
3073
+ "learning_rate": 4.46544816733529e-07,
3074
+ "loss": 13.7919,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 0.8936386768447837,
3079
+ "grad_norm": 3417955.106120249,
3080
+ "learning_rate": 4.3009664478954384e-07,
3081
+ "loss": 13.8388,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 0.8956743002544529,
3086
+ "grad_norm": 3491337.261636375,
3087
+ "learning_rate": 4.139434924727359e-07,
3088
+ "loss": 13.7903,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 0.8977099236641222,
3093
+ "grad_norm": 2598696.463432398,
3094
+ "learning_rate": 3.9808640258348686e-07,
3095
+ "loss": 13.7935,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 0.8997455470737914,
3100
+ "grad_norm": 2406731.2012268724,
3101
+ "learning_rate": 3.825263988092587e-07,
3102
+ "loss": 13.8001,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 0.9017811704834605,
3107
+ "grad_norm": 1850343.550069675,
3108
+ "learning_rate": 3.672644856584928e-07,
3109
+ "loss": 13.8345,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 0.9038167938931297,
3114
+ "grad_norm": 2877460.3830578206,
3115
+ "learning_rate": 3.523016483957742e-07,
3116
+ "loss": 13.8395,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 0.905852417302799,
3121
+ "grad_norm": 3386724.5492421445,
3122
+ "learning_rate": 3.3763885297822153e-07,
3123
+ "loss": 13.8028,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 0.9078880407124682,
3128
+ "grad_norm": 2849485.569450586,
3129
+ "learning_rate": 3.2327704599312283e-07,
3130
+ "loss": 13.8038,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 0.9099236641221374,
3135
+ "grad_norm": 3175459.533705238,
3136
+ "learning_rate": 3.0921715459683753e-07,
3137
+ "loss": 13.8303,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 0.9119592875318067,
3142
+ "grad_norm": 22724636.64948581,
3143
+ "learning_rate": 2.95460086454929e-07,
3144
+ "loss": 13.772,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 0.9139949109414758,
3149
+ "grad_norm": 2467166.6966894856,
3150
+ "learning_rate": 2.820067296835799e-07,
3151
+ "loss": 13.7719,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 0.916030534351145,
3156
+ "grad_norm": 3412055.676564019,
3157
+ "learning_rate": 2.688579527922514e-07,
3158
+ "loss": 13.7956,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 0.9180661577608142,
3163
+ "grad_norm": 2620791.7542605917,
3164
+ "learning_rate": 2.560146046276135e-07,
3165
+ "loss": 13.7717,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 0.9201017811704835,
3170
+ "grad_norm": 2077929.3418459287,
3171
+ "learning_rate": 2.4347751431875453e-07,
3172
+ "loss": 13.7763,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 0.9221374045801527,
3177
+ "grad_norm": 2370550.2619939703,
3178
+ "learning_rate": 2.3124749122364286e-07,
3179
+ "loss": 13.7964,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 0.9241730279898219,
3184
+ "grad_norm": 5750923.606982284,
3185
+ "learning_rate": 2.1932532487688784e-07,
3186
+ "loss": 13.791,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 0.926208651399491,
3191
+ "grad_norm": 3460175.4976370293,
3192
+ "learning_rate": 2.0771178493876387e-07,
3193
+ "loss": 13.79,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 0.9282442748091603,
3198
+ "grad_norm": 5901311.706134819,
3199
+ "learning_rate": 1.964076211455246e-07,
3200
+ "loss": 13.7797,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 0.9302798982188295,
3205
+ "grad_norm": 5105079.708966371,
3206
+ "learning_rate": 1.8541356326100436e-07,
3207
+ "loss": 13.7849,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 0.9323155216284987,
3212
+ "grad_norm": 4198563.584774799,
3213
+ "learning_rate": 1.7473032102949983e-07,
3214
+ "loss": 13.8415,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 0.934351145038168,
3219
+ "grad_norm": 3844225.7229981595,
3220
+ "learning_rate": 1.6435858412996275e-07,
3221
+ "loss": 13.766,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 0.9363867684478372,
3226
+ "grad_norm": 3854801.945640343,
3227
+ "learning_rate": 1.542990221314644e-07,
3228
+ "loss": 13.7996,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 0.9384223918575063,
3233
+ "grad_norm": 4666453.104767151,
3234
+ "learning_rate": 1.445522844499775e-07,
3235
+ "loss": 13.8,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 0.9404580152671755,
3240
+ "grad_norm": 5472437.376052735,
3241
+ "learning_rate": 1.3511900030644954e-07,
3242
+ "loss": 13.7599,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 0.9424936386768448,
3247
+ "grad_norm": 4682435.578567764,
3248
+ "learning_rate": 1.2599977868618052e-07,
3249
+ "loss": 13.7934,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 0.944529262086514,
3254
+ "grad_norm": 9272421.276272465,
3255
+ "learning_rate": 1.1719520829951203e-07,
3256
+ "loss": 13.8146,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 0.9465648854961832,
3261
+ "grad_norm": 4195416.415355079,
3262
+ "learning_rate": 1.087058575438199e-07,
3263
+ "loss": 13.8253,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 0.9486005089058525,
3268
+ "grad_norm": 3012392.88106662,
3269
+ "learning_rate": 1.0053227446681912e-07,
3270
+ "loss": 13.8254,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 0.9506361323155216,
3275
+ "grad_norm": 4716265.36093074,
3276
+ "learning_rate": 9.267498673118547e-08,
3277
+ "loss": 13.8287,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 0.9526717557251908,
3282
+ "grad_norm": 3046833.346747879,
3283
+ "learning_rate": 8.513450158049109e-08,
3284
+ "loss": 13.7954,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 0.95470737913486,
3289
+ "grad_norm": 3919156.6955382572,
3290
+ "learning_rate": 7.791130580645623e-08,
3291
+ "loss": 13.7727,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 0.9567430025445293,
3296
+ "grad_norm": 2642703.3691420523,
3297
+ "learning_rate": 7.100586571752444e-08,
3298
+ "loss": 13.8211,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 0.9587786259541985,
3303
+ "grad_norm": 2860021.0276084486,
3304
+ "learning_rate": 6.441862710876102e-08,
3305
+ "loss": 13.7861,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 0.9608142493638677,
3310
+ "grad_norm": 2389117.180384712,
3311
+ "learning_rate": 5.815001523307162e-08,
3312
+ "loss": 13.7998,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 0.9628498727735368,
3317
+ "grad_norm": 4343380.201960487,
3318
+ "learning_rate": 5.220043477374759e-08,
3319
+ "loss": 13.7891,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 0.9648854961832061,
3324
+ "grad_norm": 5212705.489252775,
3325
+ "learning_rate": 4.657026981834623e-08,
3326
+ "loss": 13.8108,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 0.9669211195928753,
3331
+ "grad_norm": 2520458.4461040264,
3332
+ "learning_rate": 4.125988383388957e-08,
3333
+ "loss": 13.8067,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 0.9689567430025445,
3338
+ "grad_norm": 4182021.7452560714,
3339
+ "learning_rate": 3.626961964340203e-08,
3340
+ "loss": 13.7897,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 0.9709923664122138,
3345
+ "grad_norm": 10159149.969018588,
3346
+ "learning_rate": 3.159979940378088e-08,
3347
+ "loss": 13.8046,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 0.973027989821883,
3352
+ "grad_norm": 2510949.593741673,
3353
+ "learning_rate": 2.725072458499567e-08,
3354
+ "loss": 13.8275,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 0.9750636132315522,
3359
+ "grad_norm": 2900958.891211133,
3360
+ "learning_rate": 2.3222675950627106e-08,
3361
+ "loss": 13.7972,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 0.9770992366412213,
3366
+ "grad_norm": 3768468.1026937226,
3367
+ "learning_rate": 1.9515913539743247e-08,
3368
+ "loss": 13.8208,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 0.9791348600508906,
3373
+ "grad_norm": 2563277.62892743,
3374
+ "learning_rate": 1.613067665010959e-08,
3375
+ "loss": 13.8265,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 0.9811704834605598,
3380
+ "grad_norm": 23583570.860715404,
3381
+ "learning_rate": 1.3067183822742525e-08,
3382
+ "loss": 13.8262,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 0.983206106870229,
3387
+ "grad_norm": 8371515.456262343,
3388
+ "learning_rate": 1.0325632827801745e-08,
3389
+ "loss": 13.8356,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 0.9852417302798983,
3394
+ "grad_norm": 4260314.378446997,
3395
+ "learning_rate": 7.906200651819907e-09,
3396
+ "loss": 13.8054,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 0.9872773536895675,
3401
+ "grad_norm": 2235986.274852917,
3402
+ "learning_rate": 5.809043486279531e-09,
3403
+ "loss": 13.7764,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 0.9893129770992366,
3408
+ "grad_norm": 2261687.826321509,
3409
+ "learning_rate": 4.034296717527752e-09,
3410
+ "loss": 13.8129,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 0.9913486005089058,
3415
+ "grad_norm": 5923746.692619356,
3416
+ "learning_rate": 2.5820749180388573e-09,
3417
+ "loss": 13.843,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 0.9933842239185751,
3422
+ "grad_norm": 2729193.3221547497,
3423
+ "learning_rate": 1.4524718390140913e-09,
3424
+ "loss": 13.8395,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 0.9954198473282443,
3429
+ "grad_norm": 2703798.169864237,
3430
+ "learning_rate": 6.455604043331676e-10,
3431
+ "loss": 13.8165,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 0.9974554707379135,
3436
+ "grad_norm": 3350867.6861675973,
3437
+ "learning_rate": 1.6139270584358823e-10,
3438
+ "loss": 13.8103,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 0.9994910941475827,
3443
+ "grad_norm": 1851326.2112600075,
3444
+ "learning_rate": 0.0,
3445
+ "loss": 13.8163,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 0.9994910941475827,
3450
+ "eval_loss": 13.805337905883789,
3451
+ "eval_runtime": 382.78,
3452
+ "eval_samples_per_second": 2.283,
3453
+ "eval_steps_per_second": 0.572,
3454
+ "step": 491
3455
+ }
3456
+ ],
3457
+ "logging_steps": 1,
3458
+ "max_steps": 491,
3459
+ "num_input_tokens_seen": 0,
3460
+ "num_train_epochs": 1,
3461
+ "save_steps": 500,
3462
+ "stateful_callbacks": {
3463
+ "TrainerControl": {
3464
+ "args": {
3465
+ "should_epoch_stop": false,
3466
+ "should_evaluate": false,
3467
+ "should_log": false,
3468
+ "should_save": true,
3469
+ "should_training_stop": true
3470
+ },
3471
+ "attributes": {}
3472
+ }
3473
+ },
3474
+ "total_flos": 100344791040000.0,
3475
+ "train_batch_size": 1,
3476
+ "trial_name": null,
3477
+ "trial_params": null
3478
+ }
checkpoint-491/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34619531acd21ae7ece795f3fa13daabb37932bc224fa97cf4379fb8741b7f0b
3
+ size 9144
checkpoint-491/zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info(f"Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info(f"Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 128000,
10
+ "eos_token_id": 128009,
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
+ "quantization_config": {
24
+ "_load_in_4bit": false,
25
+ "_load_in_8bit": true,
26
+ "bnb_4bit_compute_dtype": "float32",
27
+ "bnb_4bit_quant_storage": "uint8",
28
+ "bnb_4bit_quant_type": "fp4",
29
+ "bnb_4bit_use_double_quant": false,
30
+ "llm_int8_enable_fp32_cpu_offload": false,
31
+ "llm_int8_has_fp16_weight": false,
32
+ "llm_int8_skip_modules": null,
33
+ "llm_int8_threshold": 6.0,
34
+ "load_in_4bit": false,
35
+ "load_in_8bit": true,
36
+ "quant_method": "bitsandbytes"
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": {
40
+ "factor": 8.0,
41
+ "high_freq_factor": 4.0,
42
+ "low_freq_factor": 1.0,
43
+ "original_max_position_embeddings": 8192,
44
+ "rope_type": "llama3"
45
+ },
46
+ "rope_theta": 500000.0,
47
+ "tie_word_embeddings": false,
48
+ "torch_dtype": "bfloat16",
49
+ "transformers_version": "4.48.3",
50
+ "use_cache": false,
51
+ "vocab_size": 128256
52
+ }
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": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
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": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
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": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|end_of_text|>",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34619531acd21ae7ece795f3fa13daabb37932bc224fa97cf4379fb8741b7f0b
3
+ size 9144