Hugging Face's logo

nicoboss
/
Llama-3.2-1B-Instruct-Uncensored-Lora

PEFT
Safetensors
llama
Generated from Trainer
Model card Files Community
1
nicoboss commited on
Commit
b1554b2
•
1 Parent(s): b78e390

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +5 -0
  2. README.md +162 -0
  3. adapter_config.json +34 -0
  4. adapter_model.safetensors +3 -0
  5. checkpoint-117/README.md +202 -0
  6. checkpoint-117/adapter_config.json +34 -0
  7. checkpoint-117/adapter_model.safetensors +3 -0
  8. checkpoint-117/optimizer.pt +3 -0
  9. checkpoint-117/rng_state.pth +3 -0
  10. checkpoint-117/scheduler.pt +3 -0
  11. checkpoint-117/special_tokens_map.json +23 -0
  12. checkpoint-117/tokenizer.json +3 -0
  13. checkpoint-117/tokenizer_config.json +2063 -0
  14. checkpoint-117/trainer_state.json +852 -0
  15. checkpoint-117/training_args.bin +3 -0
  16. checkpoint-234/README.md +202 -0
  17. checkpoint-234/adapter_config.json +34 -0
  18. checkpoint-234/adapter_model.safetensors +3 -0
  19. checkpoint-234/optimizer.pt +3 -0
  20. checkpoint-234/rng_state.pth +3 -0
  21. checkpoint-234/scheduler.pt +3 -0
  22. checkpoint-234/special_tokens_map.json +23 -0
  23. checkpoint-234/tokenizer.json +3 -0
  24. checkpoint-234/tokenizer_config.json +2063 -0
  25. checkpoint-234/trainer_state.json +1671 -0
  26. checkpoint-234/training_args.bin +3 -0
  27. checkpoint-351/README.md +202 -0
  28. checkpoint-351/adapter_config.json +34 -0
  29. checkpoint-351/adapter_model.safetensors +3 -0
  30. checkpoint-351/optimizer.pt +3 -0
  31. checkpoint-351/rng_state.pth +3 -0
  32. checkpoint-351/scheduler.pt +3 -0
  33. checkpoint-351/special_tokens_map.json +23 -0
  34. checkpoint-351/tokenizer.json +3 -0
  35. checkpoint-351/tokenizer_config.json +2063 -0
  36. checkpoint-351/trainer_state.json +2490 -0
  37. checkpoint-351/training_args.bin +3 -0
  38. checkpoint-468/README.md +202 -0
  39. checkpoint-468/adapter_config.json +34 -0
  40. checkpoint-468/adapter_model.safetensors +3 -0
  41. checkpoint-468/optimizer.pt +3 -0
  42. checkpoint-468/rng_state.pth +3 -0
  43. checkpoint-468/scheduler.pt +3 -0
  44. checkpoint-468/special_tokens_map.json +23 -0
  45. checkpoint-468/tokenizer.json +3 -0
  46. checkpoint-468/tokenizer_config.json +2063 -0
  47. checkpoint-468/trainer_state.json +3309 -0
  48. checkpoint-468/training_args.bin +3 -0
  49. config.json +36 -0
  50. special_tokens_map.json +23 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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-117/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-234/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-351/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoint-468/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.2-1B-Instruct
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: Llama-3.2-1B-Instruct-Uncensored
8
+ results: []
9
+ license: llama3.2
10
+ datasets:
11
+ - Guilherme34/uncensor
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: `0.4.1`
21
+ ```yaml
22
+ base_model: /root/Llama-3.2-1B-Instruct
23
+ model_type: LlamaForCausalLM
24
+ tokenizer_type: AutoTokenizer
25
+
26
+ load_in_8bit: false
27
+ load_in_4bit: false
28
+ strict: false
29
+
30
+ chat_template: llama3
31
+ datasets:
32
+ - path: fozziethebeat/alpaca_messages_2k_test
33
+ type: chat_template
34
+ chat_template: llama3
35
+ field_messages: messages
36
+ message_field_role: role
37
+ message_field_content: content
38
+ roles:
39
+ user:
40
+ - user
41
+ assistant:
42
+ - assistant
43
+
44
+ datasets:
45
+ - path: Guilherme34/uncensor
46
+ type: chat_template
47
+ chat_template: llama3
48
+ field_messages: messages
49
+ message_field_role: role
50
+ message_field_content: content
51
+ roles:
52
+ system:
53
+ - system
54
+ user:
55
+ - user
56
+ assistant:
57
+ - assistant
58
+ dataset_prepared_path: last_run_prepared
59
+ val_set_size: 0.0
60
+ output_dir: ./outputs/out/Llama-3.2-1B-Instruct-Uncensored
61
+ save_safetensors: true
62
+
63
+ sequence_len: 4096
64
+ sample_packing: false
65
+ pad_to_sequence_len: true
66
+
67
+ adapter: lora
68
+ lora_model_dir:
69
+ lora_r: 32
70
+ lora_alpha: 16
71
+ lora_dropout: 0.05
72
+ lora_target_linear: true
73
+ lora_fan_in_fan_out:
74
+
75
+ wandb_project:
76
+ wandb_entity:
77
+ wandb_watch:
78
+ wandb_name:
79
+ wandb_log_model:
80
+
81
+ gradient_accumulation_steps: 4
82
+ micro_batch_size: 2
83
+ num_epochs: 4
84
+ optimizer: adamw_bnb_8bit
85
+ lr_scheduler: cosine
86
+ learning_rate: 0.0002
87
+
88
+ train_on_inputs: false
89
+ group_by_length: false
90
+ bf16: auto
91
+ fp16:
92
+ tf32: false
93
+
94
+ gradient_checkpointing: true
95
+ early_stopping_patience:
96
+ resume_from_checkpoint:
97
+ local_rank:
98
+ logging_steps: 1
99
+ xformers_attention:
100
+ flash_attention: true
101
+ s2_attention:
102
+
103
+ warmup_steps: 10
104
+ evals_per_epoch: 4
105
+ eval_table_size:
106
+ eval_max_new_tokens: 128
107
+ saves_per_epoch: 1
108
+ debug:
109
+ deepspeed:
110
+ weight_decay: 0.0
111
+ fsdp:
112
+ fsdp_config:
113
+ special_tokens:
114
+ pad_token: <|end_of_text|>
115
+
116
+ ```
117
+
118
+ </details><br>
119
+
120
+ # outputs/out/Llama-3.2-1B-Instruct-Uncensored
121
+
122
+ This model was trained from scratch on the None dataset.
123
+
124
+ ## Model description
125
+
126
+ More information needed
127
+
128
+ ## Intended uses & limitations
129
+
130
+ More information needed
131
+
132
+ ## Training and evaluation data
133
+
134
+ More information needed
135
+
136
+ ## Training procedure
137
+
138
+ ### Training hyperparameters
139
+
140
+ The following hyperparameters were used during training:
141
+ - learning_rate: 0.0002
142
+ - train_batch_size: 2
143
+ - eval_batch_size: 2
144
+ - seed: 42
145
+ - gradient_accumulation_steps: 4
146
+ - total_train_batch_size: 8
147
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
148
+ - lr_scheduler_type: cosine
149
+ - lr_scheduler_warmup_steps: 10
150
+ - num_epochs: 4
151
+
152
+ ### Training results
153
+
154
+
155
+
156
+ ### Framework versions
157
+
158
+ - PEFT 0.13.0
159
+ - Transformers 4.45.1
160
+ - Pytorch 2.3.1+cu121
161
+ - Datasets 2.21.0
162
+ - Tokenizers 0.20.0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a427c367308079b9fa9ff81abeaf446296f64c969a7543028cdfc5dba18304
3
+ size 90207248
checkpoint-117/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /root/Llama-3.2-1B-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 0.13.0
checkpoint-117/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-117/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5f9cb9a17dd4ae85848b60566c0c5afb2f1718c6cdec87672eab2fb033e41d
3
+ size 90207248
checkpoint-117/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0a84a8c016f3ff0a8991a68a02ca3493a2257ac46fa86487358ad49df019b71
3
+ size 46057082
checkpoint-117/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c38f5fa0ef62a8b438fd1222e398986c3115e57b41b0ecb51fbfcca6d26032
3
+ size 14244
checkpoint-117/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e6bb887f60ead14806ab781b36a2d2c6f0961c257f4780e647407683f4efc61
3
+ size 1064
checkpoint-117/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-117/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-117/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-117/trainer_state.json ADDED
@@ -0,0 +1,852 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 117,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008547008547008548,
13
+ "grad_norm": 0.6336084008216858,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.2928,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017094017094017096,
20
+ "grad_norm": 0.6126894950866699,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.1179,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02564102564102564,
27
+ "grad_norm": 0.6590365171432495,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.2546,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03418803418803419,
34
+ "grad_norm": 0.3842516839504242,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.402,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.042735042735042736,
41
+ "grad_norm": 0.7100726962089539,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.1523,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05128205128205128,
48
+ "grad_norm": 0.4285312592983246,
49
+ "learning_rate": 0.00012,
50
+ "loss": 1.4567,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.05982905982905983,
55
+ "grad_norm": 0.5057687163352966,
56
+ "learning_rate": 0.00014,
57
+ "loss": 1.2153,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.06837606837606838,
62
+ "grad_norm": 0.3327566683292389,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.1503,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07692307692307693,
69
+ "grad_norm": 0.29217734932899475,
70
+ "learning_rate": 0.00018,
71
+ "loss": 0.9723,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08547008547008547,
76
+ "grad_norm": 0.5076949000358582,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.5848,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.09401709401709402,
83
+ "grad_norm": 0.40562769770622253,
84
+ "learning_rate": 0.0001999976474595967,
85
+ "loss": 1.3397,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10256410256410256,
90
+ "grad_norm": 0.33129796385765076,
91
+ "learning_rate": 0.00019999058994907564,
92
+ "loss": 1.0107,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1111111111111111,
97
+ "grad_norm": 0.39453431963920593,
98
+ "learning_rate": 0.00019997882780049847,
99
+ "loss": 1.1293,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.11965811965811966,
104
+ "grad_norm": 0.3235519826412201,
105
+ "learning_rate": 0.0001999623615672837,
106
+ "loss": 1.259,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1282051282051282,
111
+ "grad_norm": 0.2598688006401062,
112
+ "learning_rate": 0.00019994119202418098,
113
+ "loss": 1.2164,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.13675213675213677,
118
+ "grad_norm": 0.2793278992176056,
119
+ "learning_rate": 0.00019991532016723439,
120
+ "loss": 1.0104,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.1452991452991453,
125
+ "grad_norm": 0.24649402499198914,
126
+ "learning_rate": 0.00019988474721373568,
127
+ "loss": 1.2559,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.15384615384615385,
132
+ "grad_norm": 0.23192395269870758,
133
+ "learning_rate": 0.00019984947460216707,
134
+ "loss": 0.8831,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.1623931623931624,
139
+ "grad_norm": 0.2821623384952545,
140
+ "learning_rate": 0.00019980950399213344,
141
+ "loss": 0.9643,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.17094017094017094,
146
+ "grad_norm": 0.2398855984210968,
147
+ "learning_rate": 0.00019976483726428422,
148
+ "loss": 0.9148,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.1794871794871795,
153
+ "grad_norm": 0.2592308819293976,
154
+ "learning_rate": 0.0001997154765202251,
155
+ "loss": 0.8939,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.18803418803418803,
160
+ "grad_norm": 0.25392013788223267,
161
+ "learning_rate": 0.00019966142408241901,
162
+ "loss": 0.9752,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.19658119658119658,
167
+ "grad_norm": 0.2928493022918701,
168
+ "learning_rate": 0.00019960268249407675,
169
+ "loss": 1.0981,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.20512820512820512,
174
+ "grad_norm": 0.2692890763282776,
175
+ "learning_rate": 0.00019953925451903756,
176
+ "loss": 0.9699,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.21367521367521367,
181
+ "grad_norm": 0.23414169251918793,
182
+ "learning_rate": 0.0001994711431416389,
183
+ "loss": 1.3802,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.2222222222222222,
188
+ "grad_norm": 0.32594603300094604,
189
+ "learning_rate": 0.00019939835156657616,
190
+ "loss": 1.3705,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.23076923076923078,
195
+ "grad_norm": 0.27903756499290466,
196
+ "learning_rate": 0.00019932088321875172,
197
+ "loss": 0.9765,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.23931623931623933,
202
+ "grad_norm": 0.27631697058677673,
203
+ "learning_rate": 0.00019923874174311394,
204
+ "loss": 0.7924,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.24786324786324787,
209
+ "grad_norm": 0.28414595127105713,
210
+ "learning_rate": 0.0001991519310044857,
211
+ "loss": 1.2446,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.2564102564102564,
216
+ "grad_norm": 0.280527800321579,
217
+ "learning_rate": 0.00019906045508738228,
218
+ "loss": 1.1986,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.26495726495726496,
223
+ "grad_norm": 0.25973978638648987,
224
+ "learning_rate": 0.0001989643182958196,
225
+ "loss": 0.9276,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.27350427350427353,
230
+ "grad_norm": 0.2691807448863983,
231
+ "learning_rate": 0.00019886352515311134,
232
+ "loss": 0.9007,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.28205128205128205,
237
+ "grad_norm": 0.260856032371521,
238
+ "learning_rate": 0.0001987580804016563,
239
+ "loss": 1.1973,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.2905982905982906,
244
+ "grad_norm": 0.28188374638557434,
245
+ "learning_rate": 0.00019864798900271532,
246
+ "loss": 1.1079,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.29914529914529914,
251
+ "grad_norm": 0.25889885425567627,
252
+ "learning_rate": 0.0001985332561361776,
253
+ "loss": 0.8755,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.3076923076923077,
258
+ "grad_norm": 0.2496309131383896,
259
+ "learning_rate": 0.00019841388720031727,
260
+ "loss": 0.8361,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3162393162393162,
265
+ "grad_norm": 0.276593416929245,
266
+ "learning_rate": 0.00019828988781153917,
267
+ "loss": 0.9342,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3247863247863248,
272
+ "grad_norm": 0.24598534405231476,
273
+ "learning_rate": 0.00019816126380411476,
274
+ "loss": 0.9002,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3333333333333333,
279
+ "grad_norm": 0.25998443365097046,
280
+ "learning_rate": 0.00019802802122990758,
281
+ "loss": 1.0115,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.3418803418803419,
286
+ "grad_norm": 0.2910752594470978,
287
+ "learning_rate": 0.00019789016635808837,
288
+ "loss": 1.1122,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.3504273504273504,
293
+ "grad_norm": 0.23144645988941193,
294
+ "learning_rate": 0.00019774770567484022,
295
+ "loss": 1.0541,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.358974358974359,
300
+ "grad_norm": 0.23637208342552185,
301
+ "learning_rate": 0.00019760064588305345,
302
+ "loss": 0.9,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.36752136752136755,
307
+ "grad_norm": 0.24016380310058594,
308
+ "learning_rate": 0.00019744899390201006,
309
+ "loss": 0.9473,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.37606837606837606,
314
+ "grad_norm": 0.23975665867328644,
315
+ "learning_rate": 0.0001972927568670583,
316
+ "loss": 1.361,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.38461538461538464,
321
+ "grad_norm": 0.2693803310394287,
322
+ "learning_rate": 0.00019713194212927696,
323
+ "loss": 1.1029,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.39316239316239315,
328
+ "grad_norm": 0.2764308452606201,
329
+ "learning_rate": 0.00019696655725512933,
330
+ "loss": 0.9312,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4017094017094017,
335
+ "grad_norm": 0.25453776121139526,
336
+ "learning_rate": 0.00019679661002610743,
337
+ "loss": 0.9677,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.41025641025641024,
342
+ "grad_norm": 0.26758676767349243,
343
+ "learning_rate": 0.00019662210843836574,
344
+ "loss": 0.9591,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.4188034188034188,
349
+ "grad_norm": 0.27530986070632935,
350
+ "learning_rate": 0.0001964430607023449,
351
+ "loss": 0.9504,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.42735042735042733,
356
+ "grad_norm": 0.2969217896461487,
357
+ "learning_rate": 0.00019625947524238563,
358
+ "loss": 1.11,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.4358974358974359,
363
+ "grad_norm": 0.26885175704956055,
364
+ "learning_rate": 0.00019607136069633212,
365
+ "loss": 0.8923,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.4444444444444444,
370
+ "grad_norm": 0.255889892578125,
371
+ "learning_rate": 0.0001958787259151258,
372
+ "loss": 0.9118,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.452991452991453,
377
+ "grad_norm": 0.2702856659889221,
378
+ "learning_rate": 0.00019568157996238884,
379
+ "loss": 0.9143,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.46153846153846156,
384
+ "grad_norm": 0.2267722338438034,
385
+ "learning_rate": 0.0001954799321139975,
386
+ "loss": 1.1196,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.4700854700854701,
391
+ "grad_norm": 0.23851439356803894,
392
+ "learning_rate": 0.00019527379185764612,
393
+ "loss": 0.8702,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.47863247863247865,
398
+ "grad_norm": 0.30145585536956787,
399
+ "learning_rate": 0.00019506316889240027,
400
+ "loss": 1.4398,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.48717948717948717,
405
+ "grad_norm": 0.2665199339389801,
406
+ "learning_rate": 0.00019484807312824067,
407
+ "loss": 0.8006,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.49572649572649574,
412
+ "grad_norm": 0.3289227783679962,
413
+ "learning_rate": 0.0001946285146855968,
414
+ "loss": 0.9466,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5042735042735043,
419
+ "grad_norm": 0.2549362778663635,
420
+ "learning_rate": 0.0001944045038948709,
421
+ "loss": 0.8871,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5128205128205128,
426
+ "grad_norm": 0.289874792098999,
427
+ "learning_rate": 0.00019417605129595157,
428
+ "loss": 0.8717,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5213675213675214,
433
+ "grad_norm": 0.32114192843437195,
434
+ "learning_rate": 0.0001939431676377183,
435
+ "loss": 0.9448,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5299145299145299,
440
+ "grad_norm": 0.2595084309577942,
441
+ "learning_rate": 0.0001937058638775353,
442
+ "loss": 0.8295,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5384615384615384,
447
+ "grad_norm": 0.22089529037475586,
448
+ "learning_rate": 0.00019346415118073632,
449
+ "loss": 1.2068,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5470085470085471,
454
+ "grad_norm": 0.3057108223438263,
455
+ "learning_rate": 0.00019321804092009906,
456
+ "loss": 0.9483,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5555555555555556,
461
+ "grad_norm": 0.2628245949745178,
462
+ "learning_rate": 0.00019296754467531014,
463
+ "loss": 0.928,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.5641025641025641,
468
+ "grad_norm": 0.31952518224716187,
469
+ "learning_rate": 0.00019271267423242024,
470
+ "loss": 0.9064,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.5726495726495726,
475
+ "grad_norm": 0.2862078845500946,
476
+ "learning_rate": 0.00019245344158328972,
477
+ "loss": 1.0335,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.5811965811965812,
482
+ "grad_norm": 0.27666571736335754,
483
+ "learning_rate": 0.0001921898589250242,
484
+ "loss": 0.8877,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.5897435897435898,
489
+ "grad_norm": 0.24311263859272003,
490
+ "learning_rate": 0.0001919219386594007,
491
+ "loss": 0.8868,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.5982905982905983,
496
+ "grad_norm": 0.2716294825077057,
497
+ "learning_rate": 0.00019164969339228422,
498
+ "loss": 0.9431,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6068376068376068,
503
+ "grad_norm": 0.3183337152004242,
504
+ "learning_rate": 0.00019137313593303463,
505
+ "loss": 1.0538,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6153846153846154,
510
+ "grad_norm": 0.2670356333255768,
511
+ "learning_rate": 0.00019109227929390378,
512
+ "loss": 1.3404,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6239316239316239,
517
+ "grad_norm": 0.26112431287765503,
518
+ "learning_rate": 0.00019080713668942356,
519
+ "loss": 0.8849,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.6324786324786325,
524
+ "grad_norm": 0.3271474838256836,
525
+ "learning_rate": 0.00019051772153578389,
526
+ "loss": 1.0236,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6410256410256411,
531
+ "grad_norm": 0.32266974449157715,
532
+ "learning_rate": 0.00019022404745020163,
533
+ "loss": 0.8979,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6495726495726496,
538
+ "grad_norm": 0.2465939223766327,
539
+ "learning_rate": 0.00018992612825027976,
540
+ "loss": 0.891,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.6581196581196581,
545
+ "grad_norm": 0.31744077801704407,
546
+ "learning_rate": 0.0001896239779533575,
547
+ "loss": 1.0727,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.6666666666666666,
552
+ "grad_norm": 0.2582801878452301,
553
+ "learning_rate": 0.00018931761077585035,
554
+ "loss": 0.9047,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.6752136752136753,
559
+ "grad_norm": 0.25554949045181274,
560
+ "learning_rate": 0.00018900704113258165,
561
+ "loss": 0.8029,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.6837606837606838,
566
+ "grad_norm": 0.2558218836784363,
567
+ "learning_rate": 0.00018869228363610404,
568
+ "loss": 0.8504,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.6923076923076923,
573
+ "grad_norm": 0.3036883771419525,
574
+ "learning_rate": 0.00018837335309601213,
575
+ "loss": 0.9286,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.7008547008547008,
580
+ "grad_norm": 0.24368591606616974,
581
+ "learning_rate": 0.00018805026451824546,
582
+ "loss": 1.4037,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7094017094017094,
587
+ "grad_norm": 0.22905252873897552,
588
+ "learning_rate": 0.00018772303310438275,
589
+ "loss": 1.2179,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.717948717948718,
594
+ "grad_norm": 0.3644798696041107,
595
+ "learning_rate": 0.00018739167425092644,
596
+ "loss": 1.3658,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7264957264957265,
601
+ "grad_norm": 0.25496625900268555,
602
+ "learning_rate": 0.00018705620354857833,
603
+ "loss": 0.7991,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7350427350427351,
608
+ "grad_norm": 0.2917548418045044,
609
+ "learning_rate": 0.00018671663678150607,
610
+ "loss": 0.7979,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7435897435897436,
615
+ "grad_norm": 0.2509627342224121,
616
+ "learning_rate": 0.0001863729899266004,
617
+ "loss": 0.8439,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.7521367521367521,
622
+ "grad_norm": 0.26703646779060364,
623
+ "learning_rate": 0.0001860252791527236,
624
+ "loss": 1.1359,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.7606837606837606,
629
+ "grad_norm": 0.2911994159221649,
630
+ "learning_rate": 0.00018567352081994852,
631
+ "loss": 1.378,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.7692307692307693,
636
+ "grad_norm": 0.24897685647010803,
637
+ "learning_rate": 0.00018531773147878895,
638
+ "loss": 1.1141,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.7777777777777778,
643
+ "grad_norm": 0.28840702772140503,
644
+ "learning_rate": 0.0001849579278694209,
645
+ "loss": 0.9043,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.7863247863247863,
650
+ "grad_norm": 0.2617591619491577,
651
+ "learning_rate": 0.00018459412692089494,
652
+ "loss": 0.7995,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.7948717948717948,
657
+ "grad_norm": 0.2502082586288452,
658
+ "learning_rate": 0.0001842263457503397,
659
+ "loss": 0.789,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8034188034188035,
664
+ "grad_norm": 0.30928075313568115,
665
+ "learning_rate": 0.00018385460166215638,
666
+ "loss": 0.9983,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.811965811965812,
671
+ "grad_norm": 0.33725544810295105,
672
+ "learning_rate": 0.00018347891214720477,
673
+ "loss": 0.955,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8205128205128205,
678
+ "grad_norm": 0.24872225522994995,
679
+ "learning_rate": 0.00018309929488198012,
680
+ "loss": 1.1854,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8290598290598291,
685
+ "grad_norm": 0.2822365462779999,
686
+ "learning_rate": 0.00018271576772778154,
687
+ "loss": 0.8358,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8376068376068376,
692
+ "grad_norm": 0.2920995056629181,
693
+ "learning_rate": 0.00018232834872987147,
694
+ "loss": 1.3358,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.8461538461538461,
699
+ "grad_norm": 0.303602397441864,
700
+ "learning_rate": 0.00018193705611662696,
701
+ "loss": 0.9797,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.8547008547008547,
706
+ "grad_norm": 0.3406928479671478,
707
+ "learning_rate": 0.0001815419082986815,
708
+ "loss": 0.9816,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.8632478632478633,
713
+ "grad_norm": 0.22692528367042542,
714
+ "learning_rate": 0.00018114292386805936,
715
+ "loss": 1.221,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.8717948717948718,
720
+ "grad_norm": 0.22570784389972687,
721
+ "learning_rate": 0.00018074012159730032,
722
+ "loss": 1.1856,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.8803418803418803,
727
+ "grad_norm": 0.2517668306827545,
728
+ "learning_rate": 0.00018033352043857675,
729
+ "loss": 1.1498,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.8888888888888888,
734
+ "grad_norm": 0.27244430780410767,
735
+ "learning_rate": 0.00017992313952280172,
736
+ "loss": 1.1015,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.8974358974358975,
741
+ "grad_norm": 0.3242965638637543,
742
+ "learning_rate": 0.00017950899815872892,
743
+ "loss": 1.2942,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.905982905982906,
748
+ "grad_norm": 0.32707729935646057,
749
+ "learning_rate": 0.00017909111583204422,
750
+ "loss": 1.2383,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9145299145299145,
755
+ "grad_norm": 0.37845203280448914,
756
+ "learning_rate": 0.0001786695122044487,
757
+ "loss": 0.9584,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9230769230769231,
762
+ "grad_norm": 0.26341512799263,
763
+ "learning_rate": 0.0001782442071127338,
764
+ "loss": 1.1443,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.9316239316239316,
769
+ "grad_norm": 0.3688293397426605,
770
+ "learning_rate": 0.0001778152205678477,
771
+ "loss": 1.5414,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.9401709401709402,
776
+ "grad_norm": 0.3266530930995941,
777
+ "learning_rate": 0.00017738257275395404,
778
+ "loss": 1.0778,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.9487179487179487,
783
+ "grad_norm": 0.4219954311847687,
784
+ "learning_rate": 0.00017694628402748202,
785
+ "loss": 1.1903,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.9572649572649573,
790
+ "grad_norm": 0.28938961029052734,
791
+ "learning_rate": 0.0001765063749161688,
792
+ "loss": 0.8998,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.9658119658119658,
797
+ "grad_norm": 0.3432457745075226,
798
+ "learning_rate": 0.00017606286611809353,
799
+ "loss": 0.9684,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.9743589743589743,
804
+ "grad_norm": 0.26857873797416687,
805
+ "learning_rate": 0.00017561577850070355,
806
+ "loss": 1.0045,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.9829059829059829,
811
+ "grad_norm": 0.24974624812602997,
812
+ "learning_rate": 0.00017516513309983253,
813
+ "loss": 0.7979,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.9914529914529915,
818
+ "grad_norm": 0.343883752822876,
819
+ "learning_rate": 0.00017471095111871074,
820
+ "loss": 1.0162,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.0,
825
+ "grad_norm": 0.29970595240592957,
826
+ "learning_rate": 0.0001742532539269674,
827
+ "loss": 0.8354,
828
+ "step": 117
829
+ }
830
+ ],
831
+ "logging_steps": 1,
832
+ "max_steps": 468,
833
+ "num_input_tokens_seen": 0,
834
+ "num_train_epochs": 4,
835
+ "save_steps": 117,
836
+ "stateful_callbacks": {
837
+ "TrainerControl": {
838
+ "args": {
839
+ "should_epoch_stop": false,
840
+ "should_evaluate": false,
841
+ "should_log": false,
842
+ "should_save": true,
843
+ "should_training_stop": false
844
+ },
845
+ "attributes": {}
846
+ }
847
+ },
848
+ "total_flos": 2.287953380376576e+16,
849
+ "train_batch_size": 2,
850
+ "trial_name": null,
851
+ "trial_params": null
852
+ }
checkpoint-117/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c808f6ec67547ffc25e425768bac91068256414f8730443120d2ab7c48580d
3
+ size 6200
checkpoint-234/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /root/Llama-3.2-1B-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 0.13.0
checkpoint-234/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-234/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d8793d41d73d30021302f3e94e2a1d96164cb7903a898291309e7f263bccdab
3
+ size 90207248
checkpoint-234/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1caeb2513058c9010f4bcaa9ea90b6ba8972367a608010ddcb1571df77d754ef
3
+ size 46057082
checkpoint-234/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b5fa8d3f7d4cfcfd1e171173fed7fc09f61fd555735bebdc905f416b886b35
3
+ size 14244
checkpoint-234/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:997057b731bc65f59ea4d3bb39f1828f4d4670db8a01f052c60d232d4e8dfea7
3
+ size 1064
checkpoint-234/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-234/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-234/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-234/trainer_state.json ADDED
@@ -0,0 +1,1671 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 234,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008547008547008548,
13
+ "grad_norm": 0.6336084008216858,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.2928,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017094017094017096,
20
+ "grad_norm": 0.6126894950866699,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.1179,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02564102564102564,
27
+ "grad_norm": 0.6590365171432495,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.2546,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03418803418803419,
34
+ "grad_norm": 0.3842516839504242,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.402,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.042735042735042736,
41
+ "grad_norm": 0.7100726962089539,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.1523,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05128205128205128,
48
+ "grad_norm": 0.4285312592983246,
49
+ "learning_rate": 0.00012,
50
+ "loss": 1.4567,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.05982905982905983,
55
+ "grad_norm": 0.5057687163352966,
56
+ "learning_rate": 0.00014,
57
+ "loss": 1.2153,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.06837606837606838,
62
+ "grad_norm": 0.3327566683292389,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.1503,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07692307692307693,
69
+ "grad_norm": 0.29217734932899475,
70
+ "learning_rate": 0.00018,
71
+ "loss": 0.9723,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08547008547008547,
76
+ "grad_norm": 0.5076949000358582,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.5848,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.09401709401709402,
83
+ "grad_norm": 0.40562769770622253,
84
+ "learning_rate": 0.0001999976474595967,
85
+ "loss": 1.3397,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10256410256410256,
90
+ "grad_norm": 0.33129796385765076,
91
+ "learning_rate": 0.00019999058994907564,
92
+ "loss": 1.0107,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1111111111111111,
97
+ "grad_norm": 0.39453431963920593,
98
+ "learning_rate": 0.00019997882780049847,
99
+ "loss": 1.1293,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.11965811965811966,
104
+ "grad_norm": 0.3235519826412201,
105
+ "learning_rate": 0.0001999623615672837,
106
+ "loss": 1.259,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1282051282051282,
111
+ "grad_norm": 0.2598688006401062,
112
+ "learning_rate": 0.00019994119202418098,
113
+ "loss": 1.2164,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.13675213675213677,
118
+ "grad_norm": 0.2793278992176056,
119
+ "learning_rate": 0.00019991532016723439,
120
+ "loss": 1.0104,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.1452991452991453,
125
+ "grad_norm": 0.24649402499198914,
126
+ "learning_rate": 0.00019988474721373568,
127
+ "loss": 1.2559,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.15384615384615385,
132
+ "grad_norm": 0.23192395269870758,
133
+ "learning_rate": 0.00019984947460216707,
134
+ "loss": 0.8831,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.1623931623931624,
139
+ "grad_norm": 0.2821623384952545,
140
+ "learning_rate": 0.00019980950399213344,
141
+ "loss": 0.9643,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.17094017094017094,
146
+ "grad_norm": 0.2398855984210968,
147
+ "learning_rate": 0.00019976483726428422,
148
+ "loss": 0.9148,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.1794871794871795,
153
+ "grad_norm": 0.2592308819293976,
154
+ "learning_rate": 0.0001997154765202251,
155
+ "loss": 0.8939,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.18803418803418803,
160
+ "grad_norm": 0.25392013788223267,
161
+ "learning_rate": 0.00019966142408241901,
162
+ "loss": 0.9752,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.19658119658119658,
167
+ "grad_norm": 0.2928493022918701,
168
+ "learning_rate": 0.00019960268249407675,
169
+ "loss": 1.0981,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.20512820512820512,
174
+ "grad_norm": 0.2692890763282776,
175
+ "learning_rate": 0.00019953925451903756,
176
+ "loss": 0.9699,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.21367521367521367,
181
+ "grad_norm": 0.23414169251918793,
182
+ "learning_rate": 0.0001994711431416389,
183
+ "loss": 1.3802,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.2222222222222222,
188
+ "grad_norm": 0.32594603300094604,
189
+ "learning_rate": 0.00019939835156657616,
190
+ "loss": 1.3705,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.23076923076923078,
195
+ "grad_norm": 0.27903756499290466,
196
+ "learning_rate": 0.00019932088321875172,
197
+ "loss": 0.9765,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.23931623931623933,
202
+ "grad_norm": 0.27631697058677673,
203
+ "learning_rate": 0.00019923874174311394,
204
+ "loss": 0.7924,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.24786324786324787,
209
+ "grad_norm": 0.28414595127105713,
210
+ "learning_rate": 0.0001991519310044857,
211
+ "loss": 1.2446,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.2564102564102564,
216
+ "grad_norm": 0.280527800321579,
217
+ "learning_rate": 0.00019906045508738228,
218
+ "loss": 1.1986,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.26495726495726496,
223
+ "grad_norm": 0.25973978638648987,
224
+ "learning_rate": 0.0001989643182958196,
225
+ "loss": 0.9276,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.27350427350427353,
230
+ "grad_norm": 0.2691807448863983,
231
+ "learning_rate": 0.00019886352515311134,
232
+ "loss": 0.9007,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.28205128205128205,
237
+ "grad_norm": 0.260856032371521,
238
+ "learning_rate": 0.0001987580804016563,
239
+ "loss": 1.1973,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.2905982905982906,
244
+ "grad_norm": 0.28188374638557434,
245
+ "learning_rate": 0.00019864798900271532,
246
+ "loss": 1.1079,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.29914529914529914,
251
+ "grad_norm": 0.25889885425567627,
252
+ "learning_rate": 0.0001985332561361776,
253
+ "loss": 0.8755,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.3076923076923077,
258
+ "grad_norm": 0.2496309131383896,
259
+ "learning_rate": 0.00019841388720031727,
260
+ "loss": 0.8361,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3162393162393162,
265
+ "grad_norm": 0.276593416929245,
266
+ "learning_rate": 0.00019828988781153917,
267
+ "loss": 0.9342,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3247863247863248,
272
+ "grad_norm": 0.24598534405231476,
273
+ "learning_rate": 0.00019816126380411476,
274
+ "loss": 0.9002,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3333333333333333,
279
+ "grad_norm": 0.25998443365097046,
280
+ "learning_rate": 0.00019802802122990758,
281
+ "loss": 1.0115,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.3418803418803419,
286
+ "grad_norm": 0.2910752594470978,
287
+ "learning_rate": 0.00019789016635808837,
288
+ "loss": 1.1122,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.3504273504273504,
293
+ "grad_norm": 0.23144645988941193,
294
+ "learning_rate": 0.00019774770567484022,
295
+ "loss": 1.0541,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.358974358974359,
300
+ "grad_norm": 0.23637208342552185,
301
+ "learning_rate": 0.00019760064588305345,
302
+ "loss": 0.9,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.36752136752136755,
307
+ "grad_norm": 0.24016380310058594,
308
+ "learning_rate": 0.00019744899390201006,
309
+ "loss": 0.9473,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.37606837606837606,
314
+ "grad_norm": 0.23975665867328644,
315
+ "learning_rate": 0.0001972927568670583,
316
+ "loss": 1.361,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.38461538461538464,
321
+ "grad_norm": 0.2693803310394287,
322
+ "learning_rate": 0.00019713194212927696,
323
+ "loss": 1.1029,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.39316239316239315,
328
+ "grad_norm": 0.2764308452606201,
329
+ "learning_rate": 0.00019696655725512933,
330
+ "loss": 0.9312,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4017094017094017,
335
+ "grad_norm": 0.25453776121139526,
336
+ "learning_rate": 0.00019679661002610743,
337
+ "loss": 0.9677,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.41025641025641024,
342
+ "grad_norm": 0.26758676767349243,
343
+ "learning_rate": 0.00019662210843836574,
344
+ "loss": 0.9591,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.4188034188034188,
349
+ "grad_norm": 0.27530986070632935,
350
+ "learning_rate": 0.0001964430607023449,
351
+ "loss": 0.9504,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.42735042735042733,
356
+ "grad_norm": 0.2969217896461487,
357
+ "learning_rate": 0.00019625947524238563,
358
+ "loss": 1.11,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.4358974358974359,
363
+ "grad_norm": 0.26885175704956055,
364
+ "learning_rate": 0.00019607136069633212,
365
+ "loss": 0.8923,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.4444444444444444,
370
+ "grad_norm": 0.255889892578125,
371
+ "learning_rate": 0.0001958787259151258,
372
+ "loss": 0.9118,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.452991452991453,
377
+ "grad_norm": 0.2702856659889221,
378
+ "learning_rate": 0.00019568157996238884,
379
+ "loss": 0.9143,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.46153846153846156,
384
+ "grad_norm": 0.2267722338438034,
385
+ "learning_rate": 0.0001954799321139975,
386
+ "loss": 1.1196,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.4700854700854701,
391
+ "grad_norm": 0.23851439356803894,
392
+ "learning_rate": 0.00019527379185764612,
393
+ "loss": 0.8702,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.47863247863247865,
398
+ "grad_norm": 0.30145585536956787,
399
+ "learning_rate": 0.00019506316889240027,
400
+ "loss": 1.4398,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.48717948717948717,
405
+ "grad_norm": 0.2665199339389801,
406
+ "learning_rate": 0.00019484807312824067,
407
+ "loss": 0.8006,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.49572649572649574,
412
+ "grad_norm": 0.3289227783679962,
413
+ "learning_rate": 0.0001946285146855968,
414
+ "loss": 0.9466,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5042735042735043,
419
+ "grad_norm": 0.2549362778663635,
420
+ "learning_rate": 0.0001944045038948709,
421
+ "loss": 0.8871,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5128205128205128,
426
+ "grad_norm": 0.289874792098999,
427
+ "learning_rate": 0.00019417605129595157,
428
+ "loss": 0.8717,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5213675213675214,
433
+ "grad_norm": 0.32114192843437195,
434
+ "learning_rate": 0.0001939431676377183,
435
+ "loss": 0.9448,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5299145299145299,
440
+ "grad_norm": 0.2595084309577942,
441
+ "learning_rate": 0.0001937058638775353,
442
+ "loss": 0.8295,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5384615384615384,
447
+ "grad_norm": 0.22089529037475586,
448
+ "learning_rate": 0.00019346415118073632,
449
+ "loss": 1.2068,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5470085470085471,
454
+ "grad_norm": 0.3057108223438263,
455
+ "learning_rate": 0.00019321804092009906,
456
+ "loss": 0.9483,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5555555555555556,
461
+ "grad_norm": 0.2628245949745178,
462
+ "learning_rate": 0.00019296754467531014,
463
+ "loss": 0.928,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.5641025641025641,
468
+ "grad_norm": 0.31952518224716187,
469
+ "learning_rate": 0.00019271267423242024,
470
+ "loss": 0.9064,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.5726495726495726,
475
+ "grad_norm": 0.2862078845500946,
476
+ "learning_rate": 0.00019245344158328972,
477
+ "loss": 1.0335,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.5811965811965812,
482
+ "grad_norm": 0.27666571736335754,
483
+ "learning_rate": 0.0001921898589250242,
484
+ "loss": 0.8877,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.5897435897435898,
489
+ "grad_norm": 0.24311263859272003,
490
+ "learning_rate": 0.0001919219386594007,
491
+ "loss": 0.8868,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.5982905982905983,
496
+ "grad_norm": 0.2716294825077057,
497
+ "learning_rate": 0.00019164969339228422,
498
+ "loss": 0.9431,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6068376068376068,
503
+ "grad_norm": 0.3183337152004242,
504
+ "learning_rate": 0.00019137313593303463,
505
+ "loss": 1.0538,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6153846153846154,
510
+ "grad_norm": 0.2670356333255768,
511
+ "learning_rate": 0.00019109227929390378,
512
+ "loss": 1.3404,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6239316239316239,
517
+ "grad_norm": 0.26112431287765503,
518
+ "learning_rate": 0.00019080713668942356,
519
+ "loss": 0.8849,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.6324786324786325,
524
+ "grad_norm": 0.3271474838256836,
525
+ "learning_rate": 0.00019051772153578389,
526
+ "loss": 1.0236,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6410256410256411,
531
+ "grad_norm": 0.32266974449157715,
532
+ "learning_rate": 0.00019022404745020163,
533
+ "loss": 0.8979,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6495726495726496,
538
+ "grad_norm": 0.2465939223766327,
539
+ "learning_rate": 0.00018992612825027976,
540
+ "loss": 0.891,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.6581196581196581,
545
+ "grad_norm": 0.31744077801704407,
546
+ "learning_rate": 0.0001896239779533575,
547
+ "loss": 1.0727,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.6666666666666666,
552
+ "grad_norm": 0.2582801878452301,
553
+ "learning_rate": 0.00018931761077585035,
554
+ "loss": 0.9047,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.6752136752136753,
559
+ "grad_norm": 0.25554949045181274,
560
+ "learning_rate": 0.00018900704113258165,
561
+ "loss": 0.8029,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.6837606837606838,
566
+ "grad_norm": 0.2558218836784363,
567
+ "learning_rate": 0.00018869228363610404,
568
+ "loss": 0.8504,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.6923076923076923,
573
+ "grad_norm": 0.3036883771419525,
574
+ "learning_rate": 0.00018837335309601213,
575
+ "loss": 0.9286,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.7008547008547008,
580
+ "grad_norm": 0.24368591606616974,
581
+ "learning_rate": 0.00018805026451824546,
582
+ "loss": 1.4037,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7094017094017094,
587
+ "grad_norm": 0.22905252873897552,
588
+ "learning_rate": 0.00018772303310438275,
589
+ "loss": 1.2179,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.717948717948718,
594
+ "grad_norm": 0.3644798696041107,
595
+ "learning_rate": 0.00018739167425092644,
596
+ "loss": 1.3658,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7264957264957265,
601
+ "grad_norm": 0.25496625900268555,
602
+ "learning_rate": 0.00018705620354857833,
603
+ "loss": 0.7991,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7350427350427351,
608
+ "grad_norm": 0.2917548418045044,
609
+ "learning_rate": 0.00018671663678150607,
610
+ "loss": 0.7979,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7435897435897436,
615
+ "grad_norm": 0.2509627342224121,
616
+ "learning_rate": 0.0001863729899266004,
617
+ "loss": 0.8439,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.7521367521367521,
622
+ "grad_norm": 0.26703646779060364,
623
+ "learning_rate": 0.0001860252791527236,
624
+ "loss": 1.1359,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.7606837606837606,
629
+ "grad_norm": 0.2911994159221649,
630
+ "learning_rate": 0.00018567352081994852,
631
+ "loss": 1.378,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.7692307692307693,
636
+ "grad_norm": 0.24897685647010803,
637
+ "learning_rate": 0.00018531773147878895,
638
+ "loss": 1.1141,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.7777777777777778,
643
+ "grad_norm": 0.28840702772140503,
644
+ "learning_rate": 0.0001849579278694209,
645
+ "loss": 0.9043,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.7863247863247863,
650
+ "grad_norm": 0.2617591619491577,
651
+ "learning_rate": 0.00018459412692089494,
652
+ "loss": 0.7995,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.7948717948717948,
657
+ "grad_norm": 0.2502082586288452,
658
+ "learning_rate": 0.0001842263457503397,
659
+ "loss": 0.789,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8034188034188035,
664
+ "grad_norm": 0.30928075313568115,
665
+ "learning_rate": 0.00018385460166215638,
666
+ "loss": 0.9983,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.811965811965812,
671
+ "grad_norm": 0.33725544810295105,
672
+ "learning_rate": 0.00018347891214720477,
673
+ "loss": 0.955,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8205128205128205,
678
+ "grad_norm": 0.24872225522994995,
679
+ "learning_rate": 0.00018309929488198012,
680
+ "loss": 1.1854,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8290598290598291,
685
+ "grad_norm": 0.2822365462779999,
686
+ "learning_rate": 0.00018271576772778154,
687
+ "loss": 0.8358,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8376068376068376,
692
+ "grad_norm": 0.2920995056629181,
693
+ "learning_rate": 0.00018232834872987147,
694
+ "loss": 1.3358,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.8461538461538461,
699
+ "grad_norm": 0.303602397441864,
700
+ "learning_rate": 0.00018193705611662696,
701
+ "loss": 0.9797,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.8547008547008547,
706
+ "grad_norm": 0.3406928479671478,
707
+ "learning_rate": 0.0001815419082986815,
708
+ "loss": 0.9816,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.8632478632478633,
713
+ "grad_norm": 0.22692528367042542,
714
+ "learning_rate": 0.00018114292386805936,
715
+ "loss": 1.221,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.8717948717948718,
720
+ "grad_norm": 0.22570784389972687,
721
+ "learning_rate": 0.00018074012159730032,
722
+ "loss": 1.1856,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.8803418803418803,
727
+ "grad_norm": 0.2517668306827545,
728
+ "learning_rate": 0.00018033352043857675,
729
+ "loss": 1.1498,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.8888888888888888,
734
+ "grad_norm": 0.27244430780410767,
735
+ "learning_rate": 0.00017992313952280172,
736
+ "loss": 1.1015,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.8974358974358975,
741
+ "grad_norm": 0.3242965638637543,
742
+ "learning_rate": 0.00017950899815872892,
743
+ "loss": 1.2942,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.905982905982906,
748
+ "grad_norm": 0.32707729935646057,
749
+ "learning_rate": 0.00017909111583204422,
750
+ "loss": 1.2383,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9145299145299145,
755
+ "grad_norm": 0.37845203280448914,
756
+ "learning_rate": 0.0001786695122044487,
757
+ "loss": 0.9584,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9230769230769231,
762
+ "grad_norm": 0.26341512799263,
763
+ "learning_rate": 0.0001782442071127338,
764
+ "loss": 1.1443,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.9316239316239316,
769
+ "grad_norm": 0.3688293397426605,
770
+ "learning_rate": 0.0001778152205678477,
771
+ "loss": 1.5414,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.9401709401709402,
776
+ "grad_norm": 0.3266530930995941,
777
+ "learning_rate": 0.00017738257275395404,
778
+ "loss": 1.0778,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.9487179487179487,
783
+ "grad_norm": 0.4219954311847687,
784
+ "learning_rate": 0.00017694628402748202,
785
+ "loss": 1.1903,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.9572649572649573,
790
+ "grad_norm": 0.28938961029052734,
791
+ "learning_rate": 0.0001765063749161688,
792
+ "loss": 0.8998,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.9658119658119658,
797
+ "grad_norm": 0.3432457745075226,
798
+ "learning_rate": 0.00017606286611809353,
799
+ "loss": 0.9684,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.9743589743589743,
804
+ "grad_norm": 0.26857873797416687,
805
+ "learning_rate": 0.00017561577850070355,
806
+ "loss": 1.0045,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.9829059829059829,
811
+ "grad_norm": 0.24974624812602997,
812
+ "learning_rate": 0.00017516513309983253,
813
+ "loss": 0.7979,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.9914529914529915,
818
+ "grad_norm": 0.343883752822876,
819
+ "learning_rate": 0.00017471095111871074,
820
+ "loss": 1.0162,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.0,
825
+ "grad_norm": 0.29970595240592957,
826
+ "learning_rate": 0.0001742532539269674,
827
+ "loss": 0.8354,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.0085470085470085,
832
+ "grad_norm": 0.2625507414340973,
833
+ "learning_rate": 0.00017379206305962526,
834
+ "loss": 0.7908,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.017094017094017,
839
+ "grad_norm": 0.2953716814517975,
840
+ "learning_rate": 0.00017332740021608722,
841
+ "loss": 0.8421,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.0256410256410255,
846
+ "grad_norm": 0.4784148931503296,
847
+ "learning_rate": 0.00017285928725911562,
848
+ "loss": 1.2155,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.0341880341880343,
853
+ "grad_norm": 0.5949030518531799,
854
+ "learning_rate": 0.00017238774621380337,
855
+ "loss": 1.2108,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.0427350427350428,
860
+ "grad_norm": 0.41158854961395264,
861
+ "learning_rate": 0.00017191279926653761,
862
+ "loss": 1.5972,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.0512820512820513,
867
+ "grad_norm": 0.31010663509368896,
868
+ "learning_rate": 0.00017143446876395602,
869
+ "loss": 1.1852,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.0598290598290598,
874
+ "grad_norm": 0.300396203994751,
875
+ "learning_rate": 0.00017095277721189528,
876
+ "loss": 1.1387,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.0683760683760684,
881
+ "grad_norm": 0.570995032787323,
882
+ "learning_rate": 0.00017046774727433222,
883
+ "loss": 1.0398,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.0769230769230769,
888
+ "grad_norm": 0.3038155734539032,
889
+ "learning_rate": 0.00016997940177231722,
890
+ "loss": 0.7614,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.0854700854700854,
895
+ "grad_norm": 0.27748215198516846,
896
+ "learning_rate": 0.00016948776368290084,
897
+ "loss": 1.0286,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.0940170940170941,
902
+ "grad_norm": 0.3376232981681824,
903
+ "learning_rate": 0.00016899285613805246,
904
+ "loss": 0.7464,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.1025641025641026,
909
+ "grad_norm": 0.33782312273979187,
910
+ "learning_rate": 0.00016849470242357196,
911
+ "loss": 0.7747,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.1111111111111112,
916
+ "grad_norm": 0.30509698390960693,
917
+ "learning_rate": 0.00016799332597799413,
918
+ "loss": 0.8188,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.1196581196581197,
923
+ "grad_norm": 0.2920445203781128,
924
+ "learning_rate": 0.00016748875039148593,
925
+ "loss": 1.0563,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.1282051282051282,
930
+ "grad_norm": 0.30515843629837036,
931
+ "learning_rate": 0.0001669809994047364,
932
+ "loss": 1.0849,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.1367521367521367,
937
+ "grad_norm": 0.35152626037597656,
938
+ "learning_rate": 0.0001664700969078398,
939
+ "loss": 0.9146,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.1452991452991452,
944
+ "grad_norm": 0.318646103143692,
945
+ "learning_rate": 0.00016595606693917142,
946
+ "loss": 1.1709,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.1538461538461537,
951
+ "grad_norm": 0.2702546715736389,
952
+ "learning_rate": 0.00016543893368425666,
953
+ "loss": 0.7313,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.1623931623931625,
958
+ "grad_norm": 0.3528870940208435,
959
+ "learning_rate": 0.00016491872147463306,
960
+ "loss": 0.8208,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.170940170940171,
965
+ "grad_norm": 0.28231188654899597,
966
+ "learning_rate": 0.00016439545478670543,
967
+ "loss": 1.7001,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.1794871794871795,
972
+ "grad_norm": 0.3122393488883972,
973
+ "learning_rate": 0.00016386915824059427,
974
+ "loss": 0.7343,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.188034188034188,
979
+ "grad_norm": 0.2875630855560303,
980
+ "learning_rate": 0.00016333985659897735,
981
+ "loss": 0.7207,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.1965811965811965,
986
+ "grad_norm": 0.38364624977111816,
987
+ "learning_rate": 0.00016280757476592466,
988
+ "loss": 0.779,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.205128205128205,
993
+ "grad_norm": 0.30091550946235657,
994
+ "learning_rate": 0.0001622723377857265,
995
+ "loss": 0.7685,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.2136752136752136,
1000
+ "grad_norm": 0.28651681542396545,
1001
+ "learning_rate": 0.00016173417084171536,
1002
+ "loss": 1.1618,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.2222222222222223,
1007
+ "grad_norm": 0.3049664795398712,
1008
+ "learning_rate": 0.00016119309925508078,
1009
+ "loss": 0.7262,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.2307692307692308,
1014
+ "grad_norm": 0.38781028985977173,
1015
+ "learning_rate": 0.0001606491484836782,
1016
+ "loss": 0.8057,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.2393162393162394,
1021
+ "grad_norm": 0.3604777455329895,
1022
+ "learning_rate": 0.00016010234412083086,
1023
+ "loss": 0.8435,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.2478632478632479,
1028
+ "grad_norm": 0.3753257691860199,
1029
+ "learning_rate": 0.00015955271189412598,
1030
+ "loss": 0.8945,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.2564102564102564,
1035
+ "grad_norm": 0.35498958826065063,
1036
+ "learning_rate": 0.00015900027766420393,
1037
+ "loss": 0.7545,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.264957264957265,
1042
+ "grad_norm": 0.337697833776474,
1043
+ "learning_rate": 0.00015844506742354164,
1044
+ "loss": 0.8178,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.2735042735042734,
1049
+ "grad_norm": 0.34326887130737305,
1050
+ "learning_rate": 0.00015788710729522953,
1051
+ "loss": 0.9658,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.282051282051282,
1056
+ "grad_norm": 0.3605210483074188,
1057
+ "learning_rate": 0.00015732642353174259,
1058
+ "loss": 1.1598,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.2905982905982907,
1063
+ "grad_norm": 0.2907405197620392,
1064
+ "learning_rate": 0.0001567630425137049,
1065
+ "loss": 0.6474,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.2991452991452992,
1070
+ "grad_norm": 0.36666378378868103,
1071
+ "learning_rate": 0.00015619699074864864,
1072
+ "loss": 0.772,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.3076923076923077,
1077
+ "grad_norm": 0.42435774207115173,
1078
+ "learning_rate": 0.00015562829486976673,
1079
+ "loss": 0.8633,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.3162393162393162,
1084
+ "grad_norm": 0.34810835123062134,
1085
+ "learning_rate": 0.00015505698163465986,
1086
+ "loss": 0.982,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.3247863247863247,
1091
+ "grad_norm": 0.38605523109436035,
1092
+ "learning_rate": 0.00015448307792407734,
1093
+ "loss": 0.7854,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.3333333333333333,
1098
+ "grad_norm": 0.3216642439365387,
1099
+ "learning_rate": 0.00015390661074065256,
1100
+ "loss": 0.7786,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.341880341880342,
1105
+ "grad_norm": 0.3482376039028168,
1106
+ "learning_rate": 0.00015332760720763232,
1107
+ "loss": 1.1516,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.3504273504273505,
1112
+ "grad_norm": 0.4383181035518646,
1113
+ "learning_rate": 0.00015274609456760073,
1114
+ "loss": 0.8356,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.358974358974359,
1119
+ "grad_norm": 0.415587842464447,
1120
+ "learning_rate": 0.00015216210018119733,
1121
+ "loss": 1.0019,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.3675213675213675,
1126
+ "grad_norm": 0.36597633361816406,
1127
+ "learning_rate": 0.00015157565152583002,
1128
+ "loss": 0.7382,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.376068376068376,
1133
+ "grad_norm": 0.36167895793914795,
1134
+ "learning_rate": 0.0001509867761943818,
1135
+ "loss": 0.9089,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.3846153846153846,
1140
+ "grad_norm": 0.35900619626045227,
1141
+ "learning_rate": 0.00015039550189391298,
1142
+ "loss": 0.7338,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.393162393162393,
1147
+ "grad_norm": 0.3245941996574402,
1148
+ "learning_rate": 0.0001498018564443571,
1149
+ "loss": 1.0774,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.4017094017094016,
1154
+ "grad_norm": 0.3721596896648407,
1155
+ "learning_rate": 0.0001492058677772123,
1156
+ "loss": 0.9292,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.4102564102564101,
1161
+ "grad_norm": 0.37743324041366577,
1162
+ "learning_rate": 0.000148607563934227,
1163
+ "loss": 0.812,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.4188034188034189,
1168
+ "grad_norm": 0.30644622445106506,
1169
+ "learning_rate": 0.00014800697306608044,
1170
+ "loss": 0.6427,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.4273504273504274,
1175
+ "grad_norm": 0.39433762431144714,
1176
+ "learning_rate": 0.00014740412343105828,
1177
+ "loss": 0.9262,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.435897435897436,
1182
+ "grad_norm": 0.34150931239128113,
1183
+ "learning_rate": 0.00014679904339372302,
1184
+ "loss": 0.7721,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.4444444444444444,
1189
+ "grad_norm": 0.3927769064903259,
1190
+ "learning_rate": 0.00014619176142357935,
1191
+ "loss": 0.7861,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.452991452991453,
1196
+ "grad_norm": 0.3742867410182953,
1197
+ "learning_rate": 0.0001455823060937347,
1198
+ "loss": 0.8983,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.4615384615384617,
1203
+ "grad_norm": 0.3988594114780426,
1204
+ "learning_rate": 0.00014497070607955476,
1205
+ "loss": 0.7946,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.4700854700854702,
1210
+ "grad_norm": 0.3588651418685913,
1211
+ "learning_rate": 0.00014435699015731448,
1212
+ "loss": 0.7881,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.4786324786324787,
1217
+ "grad_norm": 0.3405568599700928,
1218
+ "learning_rate": 0.00014374118720284388,
1219
+ "loss": 0.8645,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.4871794871794872,
1224
+ "grad_norm": 0.2791353762149811,
1225
+ "learning_rate": 0.00014312332619016965,
1226
+ "loss": 0.9498,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.4957264957264957,
1231
+ "grad_norm": 0.3834662139415741,
1232
+ "learning_rate": 0.0001425034361901516,
1233
+ "loss": 0.8281,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.5042735042735043,
1238
+ "grad_norm": 0.40144065022468567,
1239
+ "learning_rate": 0.00014188154636911524,
1240
+ "loss": 1.4235,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.5128205128205128,
1245
+ "grad_norm": 0.4115220606327057,
1246
+ "learning_rate": 0.0001412576859874791,
1247
+ "loss": 0.7451,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.5213675213675213,
1252
+ "grad_norm": 0.3392897844314575,
1253
+ "learning_rate": 0.00014063188439837832,
1254
+ "loss": 0.7047,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.5299145299145298,
1259
+ "grad_norm": 0.3308214545249939,
1260
+ "learning_rate": 0.0001400041710462833,
1261
+ "loss": 0.7011,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.5384615384615383,
1266
+ "grad_norm": 0.3544357419013977,
1267
+ "learning_rate": 0.0001393745754656146,
1268
+ "loss": 0.7985,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.547008547008547,
1273
+ "grad_norm": 0.3125544488430023,
1274
+ "learning_rate": 0.00013874312727935292,
1275
+ "loss": 0.7115,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.5555555555555556,
1280
+ "grad_norm": 0.31898999214172363,
1281
+ "learning_rate": 0.00013810985619764572,
1282
+ "loss": 1.1459,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.564102564102564,
1287
+ "grad_norm": 0.3448270857334137,
1288
+ "learning_rate": 0.00013747479201640914,
1289
+ "loss": 0.6875,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.5726495726495726,
1294
+ "grad_norm": 0.4556581676006317,
1295
+ "learning_rate": 0.00013683796461592604,
1296
+ "loss": 0.8871,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.5811965811965814,
1301
+ "grad_norm": 0.3367992341518402,
1302
+ "learning_rate": 0.00013619940395944027,
1303
+ "loss": 0.7687,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.5897435897435899,
1308
+ "grad_norm": 0.35872966051101685,
1309
+ "learning_rate": 0.00013555914009174663,
1310
+ "loss": 0.8261,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.5982905982905984,
1315
+ "grad_norm": 0.3715200424194336,
1316
+ "learning_rate": 0.00013491720313777756,
1317
+ "loss": 1.3308,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.606837606837607,
1322
+ "grad_norm": 0.3741316497325897,
1323
+ "learning_rate": 0.00013427362330118543,
1324
+ "loss": 0.7169,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.6153846153846154,
1329
+ "grad_norm": 0.3634923994541168,
1330
+ "learning_rate": 0.0001336284308629216,
1331
+ "loss": 0.9805,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.623931623931624,
1336
+ "grad_norm": 0.3144815266132355,
1337
+ "learning_rate": 0.00013298165617981172,
1338
+ "loss": 1.0045,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.6324786324786325,
1343
+ "grad_norm": 0.4095522463321686,
1344
+ "learning_rate": 0.00013233332968312715,
1345
+ "loss": 1.1136,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.641025641025641,
1350
+ "grad_norm": 0.35933032631874084,
1351
+ "learning_rate": 0.0001316834818771535,
1352
+ "loss": 0.8102,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.6495726495726495,
1357
+ "grad_norm": 0.4028998911380768,
1358
+ "learning_rate": 0.00013103214333775521,
1359
+ "loss": 0.843,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.658119658119658,
1364
+ "grad_norm": 0.401076078414917,
1365
+ "learning_rate": 0.00013037934471093682,
1366
+ "loss": 0.6997,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.6666666666666665,
1371
+ "grad_norm": 0.36478322744369507,
1372
+ "learning_rate": 0.00012972511671140125,
1373
+ "loss": 0.7362,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.6752136752136753,
1378
+ "grad_norm": 0.3325231969356537,
1379
+ "learning_rate": 0.00012906949012110456,
1380
+ "loss": 0.9889,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.6837606837606838,
1385
+ "grad_norm": 0.3909556567668915,
1386
+ "learning_rate": 0.00012841249578780757,
1387
+ "loss": 0.8985,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.6923076923076923,
1392
+ "grad_norm": 0.31815868616104126,
1393
+ "learning_rate": 0.00012775416462362457,
1394
+ "loss": 0.8205,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.7008547008547008,
1399
+ "grad_norm": 0.3717130124568939,
1400
+ "learning_rate": 0.00012709452760356884,
1401
+ "loss": 1.2108,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.7094017094017095,
1406
+ "grad_norm": 0.3459589183330536,
1407
+ "learning_rate": 0.00012643361576409516,
1408
+ "loss": 0.8245,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.717948717948718,
1413
+ "grad_norm": 0.3962521255016327,
1414
+ "learning_rate": 0.00012577146020163968,
1415
+ "loss": 0.8364,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.7264957264957266,
1420
+ "grad_norm": 0.41842907667160034,
1421
+ "learning_rate": 0.00012510809207115666,
1422
+ "loss": 0.7526,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.735042735042735,
1427
+ "grad_norm": 0.3551943302154541,
1428
+ "learning_rate": 0.00012444354258465268,
1429
+ "loss": 0.7563,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.7435897435897436,
1434
+ "grad_norm": 0.3701689541339874,
1435
+ "learning_rate": 0.00012377784300971807,
1436
+ "loss": 1.0242,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.7521367521367521,
1441
+ "grad_norm": 0.34136760234832764,
1442
+ "learning_rate": 0.0001231110246680558,
1443
+ "loss": 1.1623,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.7606837606837606,
1448
+ "grad_norm": 0.45741143822669983,
1449
+ "learning_rate": 0.00012244311893400763,
1450
+ "loss": 0.912,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.7692307692307692,
1455
+ "grad_norm": 0.44242578744888306,
1456
+ "learning_rate": 0.00012177415723307808,
1457
+ "loss": 0.7916,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.7777777777777777,
1462
+ "grad_norm": 0.3459125757217407,
1463
+ "learning_rate": 0.00012110417104045575,
1464
+ "loss": 0.6614,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.7863247863247862,
1469
+ "grad_norm": 0.3435271382331848,
1470
+ "learning_rate": 0.00012043319187953241,
1471
+ "loss": 0.8433,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.7948717948717947,
1476
+ "grad_norm": 0.404305636882782,
1477
+ "learning_rate": 0.00011976125132041974,
1478
+ "loss": 0.8646,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.8034188034188035,
1483
+ "grad_norm": 0.5799421668052673,
1484
+ "learning_rate": 0.00011908838097846404,
1485
+ "loss": 1.3677,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.811965811965812,
1490
+ "grad_norm": 0.370825856924057,
1491
+ "learning_rate": 0.00011841461251275867,
1492
+ "loss": 1.0736,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.8205128205128205,
1497
+ "grad_norm": 0.43012121319770813,
1498
+ "learning_rate": 0.00011773997762465429,
1499
+ "loss": 0.8208,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.8290598290598292,
1504
+ "grad_norm": 0.33933213353157043,
1505
+ "learning_rate": 0.0001170645080562676,
1506
+ "loss": 0.7598,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.8376068376068377,
1511
+ "grad_norm": 0.35830000042915344,
1512
+ "learning_rate": 0.00011638823558898762,
1513
+ "loss": 0.7402,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.8461538461538463,
1518
+ "grad_norm": 0.37512725591659546,
1519
+ "learning_rate": 0.00011571119204198037,
1520
+ "loss": 0.7306,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.8547008547008548,
1525
+ "grad_norm": 0.35193270444869995,
1526
+ "learning_rate": 0.00011503340927069189,
1527
+ "loss": 0.8577,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.8632478632478633,
1532
+ "grad_norm": 0.3259103000164032,
1533
+ "learning_rate": 0.00011435491916534919,
1534
+ "loss": 0.7147,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.8717948717948718,
1539
+ "grad_norm": 0.3664517402648926,
1540
+ "learning_rate": 0.00011367575364946006,
1541
+ "loss": 0.7411,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.8803418803418803,
1546
+ "grad_norm": 0.428186297416687,
1547
+ "learning_rate": 0.00011299594467831078,
1548
+ "loss": 0.7532,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.8888888888888888,
1553
+ "grad_norm": 0.4050661623477936,
1554
+ "learning_rate": 0.00011231552423746283,
1555
+ "loss": 0.7799,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.8974358974358974,
1560
+ "grad_norm": 0.3434165120124817,
1561
+ "learning_rate": 0.00011163452434124773,
1562
+ "loss": 0.7433,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.9059829059829059,
1567
+ "grad_norm": 0.4107282757759094,
1568
+ "learning_rate": 0.00011095297703126093,
1569
+ "loss": 0.7374,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.9145299145299144,
1574
+ "grad_norm": 0.4014933109283447,
1575
+ "learning_rate": 0.00011027091437485404,
1576
+ "loss": 0.9252,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.9230769230769231,
1581
+ "grad_norm": 0.3325748145580292,
1582
+ "learning_rate": 0.00010958836846362621,
1583
+ "loss": 0.9575,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.9316239316239316,
1588
+ "grad_norm": 0.3845024108886719,
1589
+ "learning_rate": 0.00010890537141191417,
1590
+ "loss": 0.7212,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.9401709401709402,
1595
+ "grad_norm": 0.3581906855106354,
1596
+ "learning_rate": 0.00010822195535528106,
1597
+ "loss": 1.015,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.9487179487179487,
1602
+ "grad_norm": 0.38040146231651306,
1603
+ "learning_rate": 0.00010753815244900458,
1604
+ "loss": 0.6995,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.9572649572649574,
1609
+ "grad_norm": 0.4363343119621277,
1610
+ "learning_rate": 0.00010685399486656406,
1611
+ "loss": 0.7875,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.965811965811966,
1616
+ "grad_norm": 0.374661386013031,
1617
+ "learning_rate": 0.00010616951479812658,
1618
+ "loss": 0.7548,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.9743589743589745,
1623
+ "grad_norm": 0.37670278549194336,
1624
+ "learning_rate": 0.00010548474444903247,
1625
+ "loss": 0.6929,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.982905982905983,
1630
+ "grad_norm": 0.3678586483001709,
1631
+ "learning_rate": 0.00010479971603828,
1632
+ "loss": 0.6928,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.9914529914529915,
1637
+ "grad_norm": 0.33861783146858215,
1638
+ "learning_rate": 0.00010411446179700943,
1639
+ "loss": 0.7386,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 2.0,
1644
+ "grad_norm": 0.8249924182891846,
1645
+ "learning_rate": 0.00010342901396698659,
1646
+ "loss": 1.1202,
1647
+ "step": 234
1648
+ }
1649
+ ],
1650
+ "logging_steps": 1,
1651
+ "max_steps": 468,
1652
+ "num_input_tokens_seen": 0,
1653
+ "num_train_epochs": 4,
1654
+ "save_steps": 117,
1655
+ "stateful_callbacks": {
1656
+ "TrainerControl": {
1657
+ "args": {
1658
+ "should_epoch_stop": false,
1659
+ "should_evaluate": false,
1660
+ "should_log": false,
1661
+ "should_save": true,
1662
+ "should_training_stop": false
1663
+ },
1664
+ "attributes": {}
1665
+ }
1666
+ },
1667
+ "total_flos": 4.575906760753152e+16,
1668
+ "train_batch_size": 2,
1669
+ "trial_name": null,
1670
+ "trial_params": null
1671
+ }
checkpoint-234/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c808f6ec67547ffc25e425768bac91068256414f8730443120d2ab7c48580d
3
+ size 6200
checkpoint-351/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /root/Llama-3.2-1B-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 0.13.0
checkpoint-351/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-351/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77b859d3bf9bd9ff4ea6083493db600ac3b941f6c6a65738facb1fceed390ff3
3
+ size 90207248
checkpoint-351/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d627d328a96cbcbc922d2c97163423f36d187b31f7321a25612a53c25508d6
3
+ size 46057338
checkpoint-351/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dddceeee0c17513e1c791653ce29078f7ad3814cb2725531ab776ee65c552a2
3
+ size 14244
checkpoint-351/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:454dfa8bbb56ee568c79ad1c952ebecb5c624e8574cf9b37d1ca345031d56714
3
+ size 1064
checkpoint-351/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-351/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-351/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-351/trainer_state.json ADDED
@@ -0,0 +1,2490 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 351,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008547008547008548,
13
+ "grad_norm": 0.6336084008216858,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.2928,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017094017094017096,
20
+ "grad_norm": 0.6126894950866699,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.1179,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02564102564102564,
27
+ "grad_norm": 0.6590365171432495,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.2546,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03418803418803419,
34
+ "grad_norm": 0.3842516839504242,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.402,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.042735042735042736,
41
+ "grad_norm": 0.7100726962089539,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.1523,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05128205128205128,
48
+ "grad_norm": 0.4285312592983246,
49
+ "learning_rate": 0.00012,
50
+ "loss": 1.4567,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.05982905982905983,
55
+ "grad_norm": 0.5057687163352966,
56
+ "learning_rate": 0.00014,
57
+ "loss": 1.2153,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.06837606837606838,
62
+ "grad_norm": 0.3327566683292389,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.1503,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07692307692307693,
69
+ "grad_norm": 0.29217734932899475,
70
+ "learning_rate": 0.00018,
71
+ "loss": 0.9723,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08547008547008547,
76
+ "grad_norm": 0.5076949000358582,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.5848,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.09401709401709402,
83
+ "grad_norm": 0.40562769770622253,
84
+ "learning_rate": 0.0001999976474595967,
85
+ "loss": 1.3397,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10256410256410256,
90
+ "grad_norm": 0.33129796385765076,
91
+ "learning_rate": 0.00019999058994907564,
92
+ "loss": 1.0107,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1111111111111111,
97
+ "grad_norm": 0.39453431963920593,
98
+ "learning_rate": 0.00019997882780049847,
99
+ "loss": 1.1293,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.11965811965811966,
104
+ "grad_norm": 0.3235519826412201,
105
+ "learning_rate": 0.0001999623615672837,
106
+ "loss": 1.259,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1282051282051282,
111
+ "grad_norm": 0.2598688006401062,
112
+ "learning_rate": 0.00019994119202418098,
113
+ "loss": 1.2164,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.13675213675213677,
118
+ "grad_norm": 0.2793278992176056,
119
+ "learning_rate": 0.00019991532016723439,
120
+ "loss": 1.0104,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.1452991452991453,
125
+ "grad_norm": 0.24649402499198914,
126
+ "learning_rate": 0.00019988474721373568,
127
+ "loss": 1.2559,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.15384615384615385,
132
+ "grad_norm": 0.23192395269870758,
133
+ "learning_rate": 0.00019984947460216707,
134
+ "loss": 0.8831,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.1623931623931624,
139
+ "grad_norm": 0.2821623384952545,
140
+ "learning_rate": 0.00019980950399213344,
141
+ "loss": 0.9643,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.17094017094017094,
146
+ "grad_norm": 0.2398855984210968,
147
+ "learning_rate": 0.00019976483726428422,
148
+ "loss": 0.9148,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.1794871794871795,
153
+ "grad_norm": 0.2592308819293976,
154
+ "learning_rate": 0.0001997154765202251,
155
+ "loss": 0.8939,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.18803418803418803,
160
+ "grad_norm": 0.25392013788223267,
161
+ "learning_rate": 0.00019966142408241901,
162
+ "loss": 0.9752,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.19658119658119658,
167
+ "grad_norm": 0.2928493022918701,
168
+ "learning_rate": 0.00019960268249407675,
169
+ "loss": 1.0981,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.20512820512820512,
174
+ "grad_norm": 0.2692890763282776,
175
+ "learning_rate": 0.00019953925451903756,
176
+ "loss": 0.9699,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.21367521367521367,
181
+ "grad_norm": 0.23414169251918793,
182
+ "learning_rate": 0.0001994711431416389,
183
+ "loss": 1.3802,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.2222222222222222,
188
+ "grad_norm": 0.32594603300094604,
189
+ "learning_rate": 0.00019939835156657616,
190
+ "loss": 1.3705,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.23076923076923078,
195
+ "grad_norm": 0.27903756499290466,
196
+ "learning_rate": 0.00019932088321875172,
197
+ "loss": 0.9765,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.23931623931623933,
202
+ "grad_norm": 0.27631697058677673,
203
+ "learning_rate": 0.00019923874174311394,
204
+ "loss": 0.7924,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.24786324786324787,
209
+ "grad_norm": 0.28414595127105713,
210
+ "learning_rate": 0.0001991519310044857,
211
+ "loss": 1.2446,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.2564102564102564,
216
+ "grad_norm": 0.280527800321579,
217
+ "learning_rate": 0.00019906045508738228,
218
+ "loss": 1.1986,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.26495726495726496,
223
+ "grad_norm": 0.25973978638648987,
224
+ "learning_rate": 0.0001989643182958196,
225
+ "loss": 0.9276,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.27350427350427353,
230
+ "grad_norm": 0.2691807448863983,
231
+ "learning_rate": 0.00019886352515311134,
232
+ "loss": 0.9007,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.28205128205128205,
237
+ "grad_norm": 0.260856032371521,
238
+ "learning_rate": 0.0001987580804016563,
239
+ "loss": 1.1973,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.2905982905982906,
244
+ "grad_norm": 0.28188374638557434,
245
+ "learning_rate": 0.00019864798900271532,
246
+ "loss": 1.1079,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.29914529914529914,
251
+ "grad_norm": 0.25889885425567627,
252
+ "learning_rate": 0.0001985332561361776,
253
+ "loss": 0.8755,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.3076923076923077,
258
+ "grad_norm": 0.2496309131383896,
259
+ "learning_rate": 0.00019841388720031727,
260
+ "loss": 0.8361,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3162393162393162,
265
+ "grad_norm": 0.276593416929245,
266
+ "learning_rate": 0.00019828988781153917,
267
+ "loss": 0.9342,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3247863247863248,
272
+ "grad_norm": 0.24598534405231476,
273
+ "learning_rate": 0.00019816126380411476,
274
+ "loss": 0.9002,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3333333333333333,
279
+ "grad_norm": 0.25998443365097046,
280
+ "learning_rate": 0.00019802802122990758,
281
+ "loss": 1.0115,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.3418803418803419,
286
+ "grad_norm": 0.2910752594470978,
287
+ "learning_rate": 0.00019789016635808837,
288
+ "loss": 1.1122,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.3504273504273504,
293
+ "grad_norm": 0.23144645988941193,
294
+ "learning_rate": 0.00019774770567484022,
295
+ "loss": 1.0541,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.358974358974359,
300
+ "grad_norm": 0.23637208342552185,
301
+ "learning_rate": 0.00019760064588305345,
302
+ "loss": 0.9,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.36752136752136755,
307
+ "grad_norm": 0.24016380310058594,
308
+ "learning_rate": 0.00019744899390201006,
309
+ "loss": 0.9473,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.37606837606837606,
314
+ "grad_norm": 0.23975665867328644,
315
+ "learning_rate": 0.0001972927568670583,
316
+ "loss": 1.361,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.38461538461538464,
321
+ "grad_norm": 0.2693803310394287,
322
+ "learning_rate": 0.00019713194212927696,
323
+ "loss": 1.1029,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.39316239316239315,
328
+ "grad_norm": 0.2764308452606201,
329
+ "learning_rate": 0.00019696655725512933,
330
+ "loss": 0.9312,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4017094017094017,
335
+ "grad_norm": 0.25453776121139526,
336
+ "learning_rate": 0.00019679661002610743,
337
+ "loss": 0.9677,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.41025641025641024,
342
+ "grad_norm": 0.26758676767349243,
343
+ "learning_rate": 0.00019662210843836574,
344
+ "loss": 0.9591,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.4188034188034188,
349
+ "grad_norm": 0.27530986070632935,
350
+ "learning_rate": 0.0001964430607023449,
351
+ "loss": 0.9504,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.42735042735042733,
356
+ "grad_norm": 0.2969217896461487,
357
+ "learning_rate": 0.00019625947524238563,
358
+ "loss": 1.11,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.4358974358974359,
363
+ "grad_norm": 0.26885175704956055,
364
+ "learning_rate": 0.00019607136069633212,
365
+ "loss": 0.8923,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.4444444444444444,
370
+ "grad_norm": 0.255889892578125,
371
+ "learning_rate": 0.0001958787259151258,
372
+ "loss": 0.9118,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.452991452991453,
377
+ "grad_norm": 0.2702856659889221,
378
+ "learning_rate": 0.00019568157996238884,
379
+ "loss": 0.9143,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.46153846153846156,
384
+ "grad_norm": 0.2267722338438034,
385
+ "learning_rate": 0.0001954799321139975,
386
+ "loss": 1.1196,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.4700854700854701,
391
+ "grad_norm": 0.23851439356803894,
392
+ "learning_rate": 0.00019527379185764612,
393
+ "loss": 0.8702,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.47863247863247865,
398
+ "grad_norm": 0.30145585536956787,
399
+ "learning_rate": 0.00019506316889240027,
400
+ "loss": 1.4398,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.48717948717948717,
405
+ "grad_norm": 0.2665199339389801,
406
+ "learning_rate": 0.00019484807312824067,
407
+ "loss": 0.8006,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.49572649572649574,
412
+ "grad_norm": 0.3289227783679962,
413
+ "learning_rate": 0.0001946285146855968,
414
+ "loss": 0.9466,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5042735042735043,
419
+ "grad_norm": 0.2549362778663635,
420
+ "learning_rate": 0.0001944045038948709,
421
+ "loss": 0.8871,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5128205128205128,
426
+ "grad_norm": 0.289874792098999,
427
+ "learning_rate": 0.00019417605129595157,
428
+ "loss": 0.8717,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5213675213675214,
433
+ "grad_norm": 0.32114192843437195,
434
+ "learning_rate": 0.0001939431676377183,
435
+ "loss": 0.9448,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5299145299145299,
440
+ "grad_norm": 0.2595084309577942,
441
+ "learning_rate": 0.0001937058638775353,
442
+ "loss": 0.8295,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5384615384615384,
447
+ "grad_norm": 0.22089529037475586,
448
+ "learning_rate": 0.00019346415118073632,
449
+ "loss": 1.2068,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5470085470085471,
454
+ "grad_norm": 0.3057108223438263,
455
+ "learning_rate": 0.00019321804092009906,
456
+ "loss": 0.9483,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5555555555555556,
461
+ "grad_norm": 0.2628245949745178,
462
+ "learning_rate": 0.00019296754467531014,
463
+ "loss": 0.928,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.5641025641025641,
468
+ "grad_norm": 0.31952518224716187,
469
+ "learning_rate": 0.00019271267423242024,
470
+ "loss": 0.9064,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.5726495726495726,
475
+ "grad_norm": 0.2862078845500946,
476
+ "learning_rate": 0.00019245344158328972,
477
+ "loss": 1.0335,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.5811965811965812,
482
+ "grad_norm": 0.27666571736335754,
483
+ "learning_rate": 0.0001921898589250242,
484
+ "loss": 0.8877,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.5897435897435898,
489
+ "grad_norm": 0.24311263859272003,
490
+ "learning_rate": 0.0001919219386594007,
491
+ "loss": 0.8868,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.5982905982905983,
496
+ "grad_norm": 0.2716294825077057,
497
+ "learning_rate": 0.00019164969339228422,
498
+ "loss": 0.9431,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6068376068376068,
503
+ "grad_norm": 0.3183337152004242,
504
+ "learning_rate": 0.00019137313593303463,
505
+ "loss": 1.0538,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6153846153846154,
510
+ "grad_norm": 0.2670356333255768,
511
+ "learning_rate": 0.00019109227929390378,
512
+ "loss": 1.3404,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6239316239316239,
517
+ "grad_norm": 0.26112431287765503,
518
+ "learning_rate": 0.00019080713668942356,
519
+ "loss": 0.8849,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.6324786324786325,
524
+ "grad_norm": 0.3271474838256836,
525
+ "learning_rate": 0.00019051772153578389,
526
+ "loss": 1.0236,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6410256410256411,
531
+ "grad_norm": 0.32266974449157715,
532
+ "learning_rate": 0.00019022404745020163,
533
+ "loss": 0.8979,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6495726495726496,
538
+ "grad_norm": 0.2465939223766327,
539
+ "learning_rate": 0.00018992612825027976,
540
+ "loss": 0.891,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.6581196581196581,
545
+ "grad_norm": 0.31744077801704407,
546
+ "learning_rate": 0.0001896239779533575,
547
+ "loss": 1.0727,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.6666666666666666,
552
+ "grad_norm": 0.2582801878452301,
553
+ "learning_rate": 0.00018931761077585035,
554
+ "loss": 0.9047,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.6752136752136753,
559
+ "grad_norm": 0.25554949045181274,
560
+ "learning_rate": 0.00018900704113258165,
561
+ "loss": 0.8029,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.6837606837606838,
566
+ "grad_norm": 0.2558218836784363,
567
+ "learning_rate": 0.00018869228363610404,
568
+ "loss": 0.8504,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.6923076923076923,
573
+ "grad_norm": 0.3036883771419525,
574
+ "learning_rate": 0.00018837335309601213,
575
+ "loss": 0.9286,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.7008547008547008,
580
+ "grad_norm": 0.24368591606616974,
581
+ "learning_rate": 0.00018805026451824546,
582
+ "loss": 1.4037,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7094017094017094,
587
+ "grad_norm": 0.22905252873897552,
588
+ "learning_rate": 0.00018772303310438275,
589
+ "loss": 1.2179,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.717948717948718,
594
+ "grad_norm": 0.3644798696041107,
595
+ "learning_rate": 0.00018739167425092644,
596
+ "loss": 1.3658,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7264957264957265,
601
+ "grad_norm": 0.25496625900268555,
602
+ "learning_rate": 0.00018705620354857833,
603
+ "loss": 0.7991,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7350427350427351,
608
+ "grad_norm": 0.2917548418045044,
609
+ "learning_rate": 0.00018671663678150607,
610
+ "loss": 0.7979,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7435897435897436,
615
+ "grad_norm": 0.2509627342224121,
616
+ "learning_rate": 0.0001863729899266004,
617
+ "loss": 0.8439,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.7521367521367521,
622
+ "grad_norm": 0.26703646779060364,
623
+ "learning_rate": 0.0001860252791527236,
624
+ "loss": 1.1359,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.7606837606837606,
629
+ "grad_norm": 0.2911994159221649,
630
+ "learning_rate": 0.00018567352081994852,
631
+ "loss": 1.378,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.7692307692307693,
636
+ "grad_norm": 0.24897685647010803,
637
+ "learning_rate": 0.00018531773147878895,
638
+ "loss": 1.1141,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.7777777777777778,
643
+ "grad_norm": 0.28840702772140503,
644
+ "learning_rate": 0.0001849579278694209,
645
+ "loss": 0.9043,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.7863247863247863,
650
+ "grad_norm": 0.2617591619491577,
651
+ "learning_rate": 0.00018459412692089494,
652
+ "loss": 0.7995,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.7948717948717948,
657
+ "grad_norm": 0.2502082586288452,
658
+ "learning_rate": 0.0001842263457503397,
659
+ "loss": 0.789,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8034188034188035,
664
+ "grad_norm": 0.30928075313568115,
665
+ "learning_rate": 0.00018385460166215638,
666
+ "loss": 0.9983,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.811965811965812,
671
+ "grad_norm": 0.33725544810295105,
672
+ "learning_rate": 0.00018347891214720477,
673
+ "loss": 0.955,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8205128205128205,
678
+ "grad_norm": 0.24872225522994995,
679
+ "learning_rate": 0.00018309929488198012,
680
+ "loss": 1.1854,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8290598290598291,
685
+ "grad_norm": 0.2822365462779999,
686
+ "learning_rate": 0.00018271576772778154,
687
+ "loss": 0.8358,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8376068376068376,
692
+ "grad_norm": 0.2920995056629181,
693
+ "learning_rate": 0.00018232834872987147,
694
+ "loss": 1.3358,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.8461538461538461,
699
+ "grad_norm": 0.303602397441864,
700
+ "learning_rate": 0.00018193705611662696,
701
+ "loss": 0.9797,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.8547008547008547,
706
+ "grad_norm": 0.3406928479671478,
707
+ "learning_rate": 0.0001815419082986815,
708
+ "loss": 0.9816,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.8632478632478633,
713
+ "grad_norm": 0.22692528367042542,
714
+ "learning_rate": 0.00018114292386805936,
715
+ "loss": 1.221,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.8717948717948718,
720
+ "grad_norm": 0.22570784389972687,
721
+ "learning_rate": 0.00018074012159730032,
722
+ "loss": 1.1856,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.8803418803418803,
727
+ "grad_norm": 0.2517668306827545,
728
+ "learning_rate": 0.00018033352043857675,
729
+ "loss": 1.1498,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.8888888888888888,
734
+ "grad_norm": 0.27244430780410767,
735
+ "learning_rate": 0.00017992313952280172,
736
+ "loss": 1.1015,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.8974358974358975,
741
+ "grad_norm": 0.3242965638637543,
742
+ "learning_rate": 0.00017950899815872892,
743
+ "loss": 1.2942,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.905982905982906,
748
+ "grad_norm": 0.32707729935646057,
749
+ "learning_rate": 0.00017909111583204422,
750
+ "loss": 1.2383,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9145299145299145,
755
+ "grad_norm": 0.37845203280448914,
756
+ "learning_rate": 0.0001786695122044487,
757
+ "loss": 0.9584,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9230769230769231,
762
+ "grad_norm": 0.26341512799263,
763
+ "learning_rate": 0.0001782442071127338,
764
+ "loss": 1.1443,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.9316239316239316,
769
+ "grad_norm": 0.3688293397426605,
770
+ "learning_rate": 0.0001778152205678477,
771
+ "loss": 1.5414,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.9401709401709402,
776
+ "grad_norm": 0.3266530930995941,
777
+ "learning_rate": 0.00017738257275395404,
778
+ "loss": 1.0778,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.9487179487179487,
783
+ "grad_norm": 0.4219954311847687,
784
+ "learning_rate": 0.00017694628402748202,
785
+ "loss": 1.1903,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.9572649572649573,
790
+ "grad_norm": 0.28938961029052734,
791
+ "learning_rate": 0.0001765063749161688,
792
+ "loss": 0.8998,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.9658119658119658,
797
+ "grad_norm": 0.3432457745075226,
798
+ "learning_rate": 0.00017606286611809353,
799
+ "loss": 0.9684,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.9743589743589743,
804
+ "grad_norm": 0.26857873797416687,
805
+ "learning_rate": 0.00017561577850070355,
806
+ "loss": 1.0045,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.9829059829059829,
811
+ "grad_norm": 0.24974624812602997,
812
+ "learning_rate": 0.00017516513309983253,
813
+ "loss": 0.7979,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.9914529914529915,
818
+ "grad_norm": 0.343883752822876,
819
+ "learning_rate": 0.00017471095111871074,
820
+ "loss": 1.0162,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.0,
825
+ "grad_norm": 0.29970595240592957,
826
+ "learning_rate": 0.0001742532539269674,
827
+ "loss": 0.8354,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.0085470085470085,
832
+ "grad_norm": 0.2625507414340973,
833
+ "learning_rate": 0.00017379206305962526,
834
+ "loss": 0.7908,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.017094017094017,
839
+ "grad_norm": 0.2953716814517975,
840
+ "learning_rate": 0.00017332740021608722,
841
+ "loss": 0.8421,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.0256410256410255,
846
+ "grad_norm": 0.4784148931503296,
847
+ "learning_rate": 0.00017285928725911562,
848
+ "loss": 1.2155,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.0341880341880343,
853
+ "grad_norm": 0.5949030518531799,
854
+ "learning_rate": 0.00017238774621380337,
855
+ "loss": 1.2108,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.0427350427350428,
860
+ "grad_norm": 0.41158854961395264,
861
+ "learning_rate": 0.00017191279926653761,
862
+ "loss": 1.5972,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.0512820512820513,
867
+ "grad_norm": 0.31010663509368896,
868
+ "learning_rate": 0.00017143446876395602,
869
+ "loss": 1.1852,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.0598290598290598,
874
+ "grad_norm": 0.300396203994751,
875
+ "learning_rate": 0.00017095277721189528,
876
+ "loss": 1.1387,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.0683760683760684,
881
+ "grad_norm": 0.570995032787323,
882
+ "learning_rate": 0.00017046774727433222,
883
+ "loss": 1.0398,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.0769230769230769,
888
+ "grad_norm": 0.3038155734539032,
889
+ "learning_rate": 0.00016997940177231722,
890
+ "loss": 0.7614,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.0854700854700854,
895
+ "grad_norm": 0.27748215198516846,
896
+ "learning_rate": 0.00016948776368290084,
897
+ "loss": 1.0286,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.0940170940170941,
902
+ "grad_norm": 0.3376232981681824,
903
+ "learning_rate": 0.00016899285613805246,
904
+ "loss": 0.7464,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.1025641025641026,
909
+ "grad_norm": 0.33782312273979187,
910
+ "learning_rate": 0.00016849470242357196,
911
+ "loss": 0.7747,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.1111111111111112,
916
+ "grad_norm": 0.30509698390960693,
917
+ "learning_rate": 0.00016799332597799413,
918
+ "loss": 0.8188,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.1196581196581197,
923
+ "grad_norm": 0.2920445203781128,
924
+ "learning_rate": 0.00016748875039148593,
925
+ "loss": 1.0563,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.1282051282051282,
930
+ "grad_norm": 0.30515843629837036,
931
+ "learning_rate": 0.0001669809994047364,
932
+ "loss": 1.0849,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.1367521367521367,
937
+ "grad_norm": 0.35152626037597656,
938
+ "learning_rate": 0.0001664700969078398,
939
+ "loss": 0.9146,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.1452991452991452,
944
+ "grad_norm": 0.318646103143692,
945
+ "learning_rate": 0.00016595606693917142,
946
+ "loss": 1.1709,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.1538461538461537,
951
+ "grad_norm": 0.2702546715736389,
952
+ "learning_rate": 0.00016543893368425666,
953
+ "loss": 0.7313,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.1623931623931625,
958
+ "grad_norm": 0.3528870940208435,
959
+ "learning_rate": 0.00016491872147463306,
960
+ "loss": 0.8208,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.170940170940171,
965
+ "grad_norm": 0.28231188654899597,
966
+ "learning_rate": 0.00016439545478670543,
967
+ "loss": 1.7001,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.1794871794871795,
972
+ "grad_norm": 0.3122393488883972,
973
+ "learning_rate": 0.00016386915824059427,
974
+ "loss": 0.7343,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.188034188034188,
979
+ "grad_norm": 0.2875630855560303,
980
+ "learning_rate": 0.00016333985659897735,
981
+ "loss": 0.7207,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.1965811965811965,
986
+ "grad_norm": 0.38364624977111816,
987
+ "learning_rate": 0.00016280757476592466,
988
+ "loss": 0.779,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.205128205128205,
993
+ "grad_norm": 0.30091550946235657,
994
+ "learning_rate": 0.0001622723377857265,
995
+ "loss": 0.7685,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.2136752136752136,
1000
+ "grad_norm": 0.28651681542396545,
1001
+ "learning_rate": 0.00016173417084171536,
1002
+ "loss": 1.1618,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.2222222222222223,
1007
+ "grad_norm": 0.3049664795398712,
1008
+ "learning_rate": 0.00016119309925508078,
1009
+ "loss": 0.7262,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.2307692307692308,
1014
+ "grad_norm": 0.38781028985977173,
1015
+ "learning_rate": 0.0001606491484836782,
1016
+ "loss": 0.8057,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.2393162393162394,
1021
+ "grad_norm": 0.3604777455329895,
1022
+ "learning_rate": 0.00016010234412083086,
1023
+ "loss": 0.8435,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.2478632478632479,
1028
+ "grad_norm": 0.3753257691860199,
1029
+ "learning_rate": 0.00015955271189412598,
1030
+ "loss": 0.8945,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.2564102564102564,
1035
+ "grad_norm": 0.35498958826065063,
1036
+ "learning_rate": 0.00015900027766420393,
1037
+ "loss": 0.7545,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.264957264957265,
1042
+ "grad_norm": 0.337697833776474,
1043
+ "learning_rate": 0.00015844506742354164,
1044
+ "loss": 0.8178,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.2735042735042734,
1049
+ "grad_norm": 0.34326887130737305,
1050
+ "learning_rate": 0.00015788710729522953,
1051
+ "loss": 0.9658,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.282051282051282,
1056
+ "grad_norm": 0.3605210483074188,
1057
+ "learning_rate": 0.00015732642353174259,
1058
+ "loss": 1.1598,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.2905982905982907,
1063
+ "grad_norm": 0.2907405197620392,
1064
+ "learning_rate": 0.0001567630425137049,
1065
+ "loss": 0.6474,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.2991452991452992,
1070
+ "grad_norm": 0.36666378378868103,
1071
+ "learning_rate": 0.00015619699074864864,
1072
+ "loss": 0.772,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.3076923076923077,
1077
+ "grad_norm": 0.42435774207115173,
1078
+ "learning_rate": 0.00015562829486976673,
1079
+ "loss": 0.8633,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.3162393162393162,
1084
+ "grad_norm": 0.34810835123062134,
1085
+ "learning_rate": 0.00015505698163465986,
1086
+ "loss": 0.982,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.3247863247863247,
1091
+ "grad_norm": 0.38605523109436035,
1092
+ "learning_rate": 0.00015448307792407734,
1093
+ "loss": 0.7854,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.3333333333333333,
1098
+ "grad_norm": 0.3216642439365387,
1099
+ "learning_rate": 0.00015390661074065256,
1100
+ "loss": 0.7786,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.341880341880342,
1105
+ "grad_norm": 0.3482376039028168,
1106
+ "learning_rate": 0.00015332760720763232,
1107
+ "loss": 1.1516,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.3504273504273505,
1112
+ "grad_norm": 0.4383181035518646,
1113
+ "learning_rate": 0.00015274609456760073,
1114
+ "loss": 0.8356,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.358974358974359,
1119
+ "grad_norm": 0.415587842464447,
1120
+ "learning_rate": 0.00015216210018119733,
1121
+ "loss": 1.0019,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.3675213675213675,
1126
+ "grad_norm": 0.36597633361816406,
1127
+ "learning_rate": 0.00015157565152583002,
1128
+ "loss": 0.7382,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.376068376068376,
1133
+ "grad_norm": 0.36167895793914795,
1134
+ "learning_rate": 0.0001509867761943818,
1135
+ "loss": 0.9089,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.3846153846153846,
1140
+ "grad_norm": 0.35900619626045227,
1141
+ "learning_rate": 0.00015039550189391298,
1142
+ "loss": 0.7338,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.393162393162393,
1147
+ "grad_norm": 0.3245941996574402,
1148
+ "learning_rate": 0.0001498018564443571,
1149
+ "loss": 1.0774,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.4017094017094016,
1154
+ "grad_norm": 0.3721596896648407,
1155
+ "learning_rate": 0.0001492058677772123,
1156
+ "loss": 0.9292,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.4102564102564101,
1161
+ "grad_norm": 0.37743324041366577,
1162
+ "learning_rate": 0.000148607563934227,
1163
+ "loss": 0.812,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.4188034188034189,
1168
+ "grad_norm": 0.30644622445106506,
1169
+ "learning_rate": 0.00014800697306608044,
1170
+ "loss": 0.6427,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.4273504273504274,
1175
+ "grad_norm": 0.39433762431144714,
1176
+ "learning_rate": 0.00014740412343105828,
1177
+ "loss": 0.9262,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.435897435897436,
1182
+ "grad_norm": 0.34150931239128113,
1183
+ "learning_rate": 0.00014679904339372302,
1184
+ "loss": 0.7721,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.4444444444444444,
1189
+ "grad_norm": 0.3927769064903259,
1190
+ "learning_rate": 0.00014619176142357935,
1191
+ "loss": 0.7861,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.452991452991453,
1196
+ "grad_norm": 0.3742867410182953,
1197
+ "learning_rate": 0.0001455823060937347,
1198
+ "loss": 0.8983,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.4615384615384617,
1203
+ "grad_norm": 0.3988594114780426,
1204
+ "learning_rate": 0.00014497070607955476,
1205
+ "loss": 0.7946,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.4700854700854702,
1210
+ "grad_norm": 0.3588651418685913,
1211
+ "learning_rate": 0.00014435699015731448,
1212
+ "loss": 0.7881,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.4786324786324787,
1217
+ "grad_norm": 0.3405568599700928,
1218
+ "learning_rate": 0.00014374118720284388,
1219
+ "loss": 0.8645,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.4871794871794872,
1224
+ "grad_norm": 0.2791353762149811,
1225
+ "learning_rate": 0.00014312332619016965,
1226
+ "loss": 0.9498,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.4957264957264957,
1231
+ "grad_norm": 0.3834662139415741,
1232
+ "learning_rate": 0.0001425034361901516,
1233
+ "loss": 0.8281,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.5042735042735043,
1238
+ "grad_norm": 0.40144065022468567,
1239
+ "learning_rate": 0.00014188154636911524,
1240
+ "loss": 1.4235,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.5128205128205128,
1245
+ "grad_norm": 0.4115220606327057,
1246
+ "learning_rate": 0.0001412576859874791,
1247
+ "loss": 0.7451,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.5213675213675213,
1252
+ "grad_norm": 0.3392897844314575,
1253
+ "learning_rate": 0.00014063188439837832,
1254
+ "loss": 0.7047,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.5299145299145298,
1259
+ "grad_norm": 0.3308214545249939,
1260
+ "learning_rate": 0.0001400041710462833,
1261
+ "loss": 0.7011,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.5384615384615383,
1266
+ "grad_norm": 0.3544357419013977,
1267
+ "learning_rate": 0.0001393745754656146,
1268
+ "loss": 0.7985,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.547008547008547,
1273
+ "grad_norm": 0.3125544488430023,
1274
+ "learning_rate": 0.00013874312727935292,
1275
+ "loss": 0.7115,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.5555555555555556,
1280
+ "grad_norm": 0.31898999214172363,
1281
+ "learning_rate": 0.00013810985619764572,
1282
+ "loss": 1.1459,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.564102564102564,
1287
+ "grad_norm": 0.3448270857334137,
1288
+ "learning_rate": 0.00013747479201640914,
1289
+ "loss": 0.6875,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.5726495726495726,
1294
+ "grad_norm": 0.4556581676006317,
1295
+ "learning_rate": 0.00013683796461592604,
1296
+ "loss": 0.8871,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.5811965811965814,
1301
+ "grad_norm": 0.3367992341518402,
1302
+ "learning_rate": 0.00013619940395944027,
1303
+ "loss": 0.7687,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.5897435897435899,
1308
+ "grad_norm": 0.35872966051101685,
1309
+ "learning_rate": 0.00013555914009174663,
1310
+ "loss": 0.8261,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.5982905982905984,
1315
+ "grad_norm": 0.3715200424194336,
1316
+ "learning_rate": 0.00013491720313777756,
1317
+ "loss": 1.3308,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.606837606837607,
1322
+ "grad_norm": 0.3741316497325897,
1323
+ "learning_rate": 0.00013427362330118543,
1324
+ "loss": 0.7169,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.6153846153846154,
1329
+ "grad_norm": 0.3634923994541168,
1330
+ "learning_rate": 0.0001336284308629216,
1331
+ "loss": 0.9805,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.623931623931624,
1336
+ "grad_norm": 0.3144815266132355,
1337
+ "learning_rate": 0.00013298165617981172,
1338
+ "loss": 1.0045,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.6324786324786325,
1343
+ "grad_norm": 0.4095522463321686,
1344
+ "learning_rate": 0.00013233332968312715,
1345
+ "loss": 1.1136,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.641025641025641,
1350
+ "grad_norm": 0.35933032631874084,
1351
+ "learning_rate": 0.0001316834818771535,
1352
+ "loss": 0.8102,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.6495726495726495,
1357
+ "grad_norm": 0.4028998911380768,
1358
+ "learning_rate": 0.00013103214333775521,
1359
+ "loss": 0.843,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.658119658119658,
1364
+ "grad_norm": 0.401076078414917,
1365
+ "learning_rate": 0.00013037934471093682,
1366
+ "loss": 0.6997,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.6666666666666665,
1371
+ "grad_norm": 0.36478322744369507,
1372
+ "learning_rate": 0.00012972511671140125,
1373
+ "loss": 0.7362,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.6752136752136753,
1378
+ "grad_norm": 0.3325231969356537,
1379
+ "learning_rate": 0.00012906949012110456,
1380
+ "loss": 0.9889,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.6837606837606838,
1385
+ "grad_norm": 0.3909556567668915,
1386
+ "learning_rate": 0.00012841249578780757,
1387
+ "loss": 0.8985,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.6923076923076923,
1392
+ "grad_norm": 0.31815868616104126,
1393
+ "learning_rate": 0.00012775416462362457,
1394
+ "loss": 0.8205,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.7008547008547008,
1399
+ "grad_norm": 0.3717130124568939,
1400
+ "learning_rate": 0.00012709452760356884,
1401
+ "loss": 1.2108,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.7094017094017095,
1406
+ "grad_norm": 0.3459589183330536,
1407
+ "learning_rate": 0.00012643361576409516,
1408
+ "loss": 0.8245,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.717948717948718,
1413
+ "grad_norm": 0.3962521255016327,
1414
+ "learning_rate": 0.00012577146020163968,
1415
+ "loss": 0.8364,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.7264957264957266,
1420
+ "grad_norm": 0.41842907667160034,
1421
+ "learning_rate": 0.00012510809207115666,
1422
+ "loss": 0.7526,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.735042735042735,
1427
+ "grad_norm": 0.3551943302154541,
1428
+ "learning_rate": 0.00012444354258465268,
1429
+ "loss": 0.7563,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.7435897435897436,
1434
+ "grad_norm": 0.3701689541339874,
1435
+ "learning_rate": 0.00012377784300971807,
1436
+ "loss": 1.0242,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.7521367521367521,
1441
+ "grad_norm": 0.34136760234832764,
1442
+ "learning_rate": 0.0001231110246680558,
1443
+ "loss": 1.1623,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.7606837606837606,
1448
+ "grad_norm": 0.45741143822669983,
1449
+ "learning_rate": 0.00012244311893400763,
1450
+ "loss": 0.912,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.7692307692307692,
1455
+ "grad_norm": 0.44242578744888306,
1456
+ "learning_rate": 0.00012177415723307808,
1457
+ "loss": 0.7916,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.7777777777777777,
1462
+ "grad_norm": 0.3459125757217407,
1463
+ "learning_rate": 0.00012110417104045575,
1464
+ "loss": 0.6614,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.7863247863247862,
1469
+ "grad_norm": 0.3435271382331848,
1470
+ "learning_rate": 0.00012043319187953241,
1471
+ "loss": 0.8433,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.7948717948717947,
1476
+ "grad_norm": 0.404305636882782,
1477
+ "learning_rate": 0.00011976125132041974,
1478
+ "loss": 0.8646,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.8034188034188035,
1483
+ "grad_norm": 0.5799421668052673,
1484
+ "learning_rate": 0.00011908838097846404,
1485
+ "loss": 1.3677,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.811965811965812,
1490
+ "grad_norm": 0.370825856924057,
1491
+ "learning_rate": 0.00011841461251275867,
1492
+ "loss": 1.0736,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.8205128205128205,
1497
+ "grad_norm": 0.43012121319770813,
1498
+ "learning_rate": 0.00011773997762465429,
1499
+ "loss": 0.8208,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.8290598290598292,
1504
+ "grad_norm": 0.33933213353157043,
1505
+ "learning_rate": 0.0001170645080562676,
1506
+ "loss": 0.7598,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.8376068376068377,
1511
+ "grad_norm": 0.35830000042915344,
1512
+ "learning_rate": 0.00011638823558898762,
1513
+ "loss": 0.7402,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.8461538461538463,
1518
+ "grad_norm": 0.37512725591659546,
1519
+ "learning_rate": 0.00011571119204198037,
1520
+ "loss": 0.7306,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.8547008547008548,
1525
+ "grad_norm": 0.35193270444869995,
1526
+ "learning_rate": 0.00011503340927069189,
1527
+ "loss": 0.8577,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.8632478632478633,
1532
+ "grad_norm": 0.3259103000164032,
1533
+ "learning_rate": 0.00011435491916534919,
1534
+ "loss": 0.7147,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.8717948717948718,
1539
+ "grad_norm": 0.3664517402648926,
1540
+ "learning_rate": 0.00011367575364946006,
1541
+ "loss": 0.7411,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.8803418803418803,
1546
+ "grad_norm": 0.428186297416687,
1547
+ "learning_rate": 0.00011299594467831078,
1548
+ "loss": 0.7532,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.8888888888888888,
1553
+ "grad_norm": 0.4050661623477936,
1554
+ "learning_rate": 0.00011231552423746283,
1555
+ "loss": 0.7799,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.8974358974358974,
1560
+ "grad_norm": 0.3434165120124817,
1561
+ "learning_rate": 0.00011163452434124773,
1562
+ "loss": 0.7433,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.9059829059829059,
1567
+ "grad_norm": 0.4107282757759094,
1568
+ "learning_rate": 0.00011095297703126093,
1569
+ "loss": 0.7374,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.9145299145299144,
1574
+ "grad_norm": 0.4014933109283447,
1575
+ "learning_rate": 0.00011027091437485404,
1576
+ "loss": 0.9252,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.9230769230769231,
1581
+ "grad_norm": 0.3325748145580292,
1582
+ "learning_rate": 0.00010958836846362621,
1583
+ "loss": 0.9575,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.9316239316239316,
1588
+ "grad_norm": 0.3845024108886719,
1589
+ "learning_rate": 0.00010890537141191417,
1590
+ "loss": 0.7212,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.9401709401709402,
1595
+ "grad_norm": 0.3581906855106354,
1596
+ "learning_rate": 0.00010822195535528106,
1597
+ "loss": 1.015,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.9487179487179487,
1602
+ "grad_norm": 0.38040146231651306,
1603
+ "learning_rate": 0.00010753815244900458,
1604
+ "loss": 0.6995,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.9572649572649574,
1609
+ "grad_norm": 0.4363343119621277,
1610
+ "learning_rate": 0.00010685399486656406,
1611
+ "loss": 0.7875,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.965811965811966,
1616
+ "grad_norm": 0.374661386013031,
1617
+ "learning_rate": 0.00010616951479812658,
1618
+ "loss": 0.7548,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.9743589743589745,
1623
+ "grad_norm": 0.37670278549194336,
1624
+ "learning_rate": 0.00010548474444903247,
1625
+ "loss": 0.6929,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.982905982905983,
1630
+ "grad_norm": 0.3678586483001709,
1631
+ "learning_rate": 0.00010479971603828,
1632
+ "loss": 0.6928,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.9914529914529915,
1637
+ "grad_norm": 0.33861783146858215,
1638
+ "learning_rate": 0.00010411446179700943,
1639
+ "loss": 0.7386,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 2.0,
1644
+ "grad_norm": 0.8249924182891846,
1645
+ "learning_rate": 0.00010342901396698659,
1646
+ "loss": 1.1202,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 2.0085470085470085,
1651
+ "grad_norm": 0.3209660053253174,
1652
+ "learning_rate": 0.00010274340479908568,
1653
+ "loss": 0.5614,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 2.017094017094017,
1658
+ "grad_norm": 0.35706081986427307,
1659
+ "learning_rate": 0.00010205766655177215,
1660
+ "loss": 0.6367,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 2.0256410256410255,
1665
+ "grad_norm": 0.3861965537071228,
1666
+ "learning_rate": 0.00010137183148958463,
1667
+ "loss": 0.7618,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 2.034188034188034,
1672
+ "grad_norm": 0.3865705728530884,
1673
+ "learning_rate": 0.00010068593188161697,
1674
+ "loss": 0.6082,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 2.0427350427350426,
1679
+ "grad_norm": 0.4773464798927307,
1680
+ "learning_rate": 0.0001,
1681
+ "loss": 0.7599,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 2.051282051282051,
1686
+ "grad_norm": 0.40682271122932434,
1687
+ "learning_rate": 9.931406811838308e-05,
1688
+ "loss": 0.5965,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 2.0598290598290596,
1693
+ "grad_norm": 0.44999873638153076,
1694
+ "learning_rate": 9.862816851041541e-05,
1695
+ "loss": 0.6273,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 2.0683760683760686,
1700
+ "grad_norm": 0.3938470184803009,
1701
+ "learning_rate": 9.79423334482279e-05,
1702
+ "loss": 0.7883,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 2.076923076923077,
1707
+ "grad_norm": 0.40996649861335754,
1708
+ "learning_rate": 9.725659520091433e-05,
1709
+ "loss": 0.6598,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 2.0854700854700856,
1714
+ "grad_norm": 0.41541314125061035,
1715
+ "learning_rate": 9.657098603301346e-05,
1716
+ "loss": 0.7229,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 2.094017094017094,
1721
+ "grad_norm": 0.353305846452713,
1722
+ "learning_rate": 9.588553820299056e-05,
1723
+ "loss": 0.5847,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 2.1025641025641026,
1728
+ "grad_norm": 0.4282464385032654,
1729
+ "learning_rate": 9.520028396172003e-05,
1730
+ "loss": 0.8587,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 2.111111111111111,
1735
+ "grad_norm": 0.41154712438583374,
1736
+ "learning_rate": 9.451525555096753e-05,
1737
+ "loss": 0.636,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 2.1196581196581197,
1742
+ "grad_norm": 0.40562766790390015,
1743
+ "learning_rate": 9.383048520187344e-05,
1744
+ "loss": 0.6537,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 2.128205128205128,
1749
+ "grad_norm": 0.39767637848854065,
1750
+ "learning_rate": 9.314600513343595e-05,
1751
+ "loss": 0.5577,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 2.1367521367521367,
1756
+ "grad_norm": 0.40367597341537476,
1757
+ "learning_rate": 9.246184755099545e-05,
1758
+ "loss": 1.046,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 2.1452991452991452,
1763
+ "grad_norm": 0.36436665058135986,
1764
+ "learning_rate": 9.177804464471898e-05,
1765
+ "loss": 0.969,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 2.1538461538461537,
1770
+ "grad_norm": 0.44953399896621704,
1771
+ "learning_rate": 9.109462858808586e-05,
1772
+ "loss": 1.1065,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 2.1623931623931623,
1777
+ "grad_norm": 0.4293656051158905,
1778
+ "learning_rate": 9.041163153637381e-05,
1779
+ "loss": 0.6931,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 2.1709401709401708,
1784
+ "grad_norm": 0.6912404298782349,
1785
+ "learning_rate": 8.972908562514598e-05,
1786
+ "loss": 0.8489,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 2.1794871794871793,
1791
+ "grad_norm": 0.5662364363670349,
1792
+ "learning_rate": 8.904702296873912e-05,
1793
+ "loss": 0.7001,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 2.1880341880341883,
1798
+ "grad_norm": 0.43007197976112366,
1799
+ "learning_rate": 8.836547565875227e-05,
1800
+ "loss": 0.6258,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 2.1965811965811968,
1805
+ "grad_norm": 0.4075295925140381,
1806
+ "learning_rate": 8.76844757625372e-05,
1807
+ "loss": 1.0233,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 2.2051282051282053,
1812
+ "grad_norm": 0.4470670521259308,
1813
+ "learning_rate": 8.70040553216892e-05,
1814
+ "loss": 0.5802,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 2.213675213675214,
1819
+ "grad_norm": 0.5310265421867371,
1820
+ "learning_rate": 8.632424635053997e-05,
1821
+ "loss": 0.8648,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 2.2222222222222223,
1826
+ "grad_norm": 0.3991585373878479,
1827
+ "learning_rate": 8.564508083465079e-05,
1828
+ "loss": 0.6131,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 2.230769230769231,
1833
+ "grad_norm": 0.4161868989467621,
1834
+ "learning_rate": 8.496659072930813e-05,
1835
+ "loss": 0.6663,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 2.2393162393162394,
1840
+ "grad_norm": 0.3924509882926941,
1841
+ "learning_rate": 8.428880795801965e-05,
1842
+ "loss": 0.5843,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 2.247863247863248,
1847
+ "grad_norm": 0.4469972550868988,
1848
+ "learning_rate": 8.36117644110124e-05,
1849
+ "loss": 0.9308,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 2.2564102564102564,
1854
+ "grad_norm": 0.43694007396698,
1855
+ "learning_rate": 8.293549194373243e-05,
1856
+ "loss": 0.5301,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 2.264957264957265,
1861
+ "grad_norm": 0.36313438415527344,
1862
+ "learning_rate": 8.226002237534572e-05,
1863
+ "loss": 0.6025,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 2.2735042735042734,
1868
+ "grad_norm": 0.5126502513885498,
1869
+ "learning_rate": 8.158538748724139e-05,
1870
+ "loss": 1.0082,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 2.282051282051282,
1875
+ "grad_norm": 0.7607345581054688,
1876
+ "learning_rate": 8.091161902153595e-05,
1877
+ "loss": 0.8165,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 2.2905982905982905,
1882
+ "grad_norm": 0.40674644708633423,
1883
+ "learning_rate": 8.023874867958027e-05,
1884
+ "loss": 0.9011,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 2.299145299145299,
1889
+ "grad_norm": 0.4444192051887512,
1890
+ "learning_rate": 7.95668081204676e-05,
1891
+ "loss": 0.9077,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 2.3076923076923075,
1896
+ "grad_norm": 0.47018325328826904,
1897
+ "learning_rate": 7.889582895954427e-05,
1898
+ "loss": 0.6565,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 2.316239316239316,
1903
+ "grad_norm": 0.45229724049568176,
1904
+ "learning_rate": 7.822584276692191e-05,
1905
+ "loss": 0.5789,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 2.324786324786325,
1910
+ "grad_norm": 0.4436100125312805,
1911
+ "learning_rate": 7.755688106599241e-05,
1912
+ "loss": 0.5985,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 2.3333333333333335,
1917
+ "grad_norm": 0.43845564126968384,
1918
+ "learning_rate": 7.688897533194424e-05,
1919
+ "loss": 0.7054,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 2.341880341880342,
1924
+ "grad_norm": 0.5257022976875305,
1925
+ "learning_rate": 7.622215699028196e-05,
1926
+ "loss": 0.6775,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 2.3504273504273505,
1931
+ "grad_norm": 0.38463449478149414,
1932
+ "learning_rate": 7.555645741534736e-05,
1933
+ "loss": 0.5418,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 2.358974358974359,
1938
+ "grad_norm": 0.4846791625022888,
1939
+ "learning_rate": 7.489190792884338e-05,
1940
+ "loss": 1.1746,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 2.3675213675213675,
1945
+ "grad_norm": 0.599614143371582,
1946
+ "learning_rate": 7.422853979836034e-05,
1947
+ "loss": 0.9562,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 2.376068376068376,
1952
+ "grad_norm": 0.44910863041877747,
1953
+ "learning_rate": 7.356638423590485e-05,
1954
+ "loss": 0.6637,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 2.3846153846153846,
1959
+ "grad_norm": 0.41623038053512573,
1960
+ "learning_rate": 7.290547239643117e-05,
1961
+ "loss": 0.6137,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 2.393162393162393,
1966
+ "grad_norm": 0.41245952248573303,
1967
+ "learning_rate": 7.224583537637544e-05,
1968
+ "loss": 0.701,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 2.4017094017094016,
1973
+ "grad_norm": 0.437512069940567,
1974
+ "learning_rate": 7.158750421219244e-05,
1975
+ "loss": 1.0071,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 2.41025641025641,
1980
+ "grad_norm": 0.47157779335975647,
1981
+ "learning_rate": 7.093050987889547e-05,
1982
+ "loss": 0.6301,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 2.4188034188034186,
1987
+ "grad_norm": 0.4809150695800781,
1988
+ "learning_rate": 7.027488328859876e-05,
1989
+ "loss": 0.6223,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 2.427350427350427,
1994
+ "grad_norm": 0.4056383967399597,
1995
+ "learning_rate": 6.96206552890632e-05,
1996
+ "loss": 0.7179,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 2.435897435897436,
2001
+ "grad_norm": 0.4516913890838623,
2002
+ "learning_rate": 6.896785666224481e-05,
2003
+ "loss": 0.6584,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 2.4444444444444446,
2008
+ "grad_norm": 0.5465108752250671,
2009
+ "learning_rate": 6.831651812284652e-05,
2010
+ "loss": 0.6704,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 2.452991452991453,
2015
+ "grad_norm": 0.4418526589870453,
2016
+ "learning_rate": 6.766667031687286e-05,
2017
+ "loss": 0.6599,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 2.4615384615384617,
2022
+ "grad_norm": 0.5614168047904968,
2023
+ "learning_rate": 6.701834382018832e-05,
2024
+ "loss": 0.682,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 2.47008547008547,
2029
+ "grad_norm": 0.4477944076061249,
2030
+ "learning_rate": 6.637156913707839e-05,
2031
+ "loss": 0.5673,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 2.4786324786324787,
2036
+ "grad_norm": 0.4335084855556488,
2037
+ "learning_rate": 6.572637669881458e-05,
2038
+ "loss": 0.649,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 2.4871794871794872,
2043
+ "grad_norm": 0.5068711638450623,
2044
+ "learning_rate": 6.508279686222243e-05,
2045
+ "loss": 0.9612,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 2.4957264957264957,
2050
+ "grad_norm": 0.45187613368034363,
2051
+ "learning_rate": 6.444085990825338e-05,
2052
+ "loss": 0.7145,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 2.5042735042735043,
2057
+ "grad_norm": 0.43183228373527527,
2058
+ "learning_rate": 6.380059604055974e-05,
2059
+ "loss": 0.6139,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 2.5128205128205128,
2064
+ "grad_norm": 0.5947943329811096,
2065
+ "learning_rate": 6.316203538407397e-05,
2066
+ "loss": 0.7478,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 2.5213675213675213,
2071
+ "grad_norm": 0.4441166818141937,
2072
+ "learning_rate": 6.252520798359092e-05,
2073
+ "loss": 0.5858,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 2.52991452991453,
2078
+ "grad_norm": 0.4649028778076172,
2079
+ "learning_rate": 6.18901438023543e-05,
2080
+ "loss": 0.611,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 2.5384615384615383,
2085
+ "grad_norm": 0.4889965355396271,
2086
+ "learning_rate": 6.125687272064713e-05,
2087
+ "loss": 0.6749,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 2.547008547008547,
2092
+ "grad_norm": 0.3767229914665222,
2093
+ "learning_rate": 6.0625424534385425e-05,
2094
+ "loss": 0.8812,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 2.5555555555555554,
2099
+ "grad_norm": 0.5386160016059875,
2100
+ "learning_rate": 5.9995828953716695e-05,
2101
+ "loss": 0.6275,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 2.564102564102564,
2106
+ "grad_norm": 0.49474480748176575,
2107
+ "learning_rate": 5.936811560162169e-05,
2108
+ "loss": 0.7034,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 2.5726495726495724,
2113
+ "grad_norm": 0.45355015993118286,
2114
+ "learning_rate": 5.87423140125209e-05,
2115
+ "loss": 0.5933,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 2.5811965811965814,
2120
+ "grad_norm": 0.4447164833545685,
2121
+ "learning_rate": 5.811845363088477e-05,
2122
+ "loss": 0.5839,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 2.58974358974359,
2127
+ "grad_norm": 0.48180091381073,
2128
+ "learning_rate": 5.749656380984844e-05,
2129
+ "loss": 0.6213,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 2.5982905982905984,
2134
+ "grad_norm": 0.46600985527038574,
2135
+ "learning_rate": 5.687667380983037e-05,
2136
+ "loss": 0.5586,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 2.606837606837607,
2141
+ "grad_norm": 0.4069865345954895,
2142
+ "learning_rate": 5.625881279715615e-05,
2143
+ "loss": 0.5236,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 2.6153846153846154,
2148
+ "grad_norm": 0.427859365940094,
2149
+ "learning_rate": 5.5643009842685554e-05,
2150
+ "loss": 1.0195,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 2.623931623931624,
2155
+ "grad_norm": 0.4362795948982239,
2156
+ "learning_rate": 5.502929392044528e-05,
2157
+ "loss": 0.6477,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 2.6324786324786325,
2162
+ "grad_norm": 0.4781452417373657,
2163
+ "learning_rate": 5.4417693906265365e-05,
2164
+ "loss": 0.5336,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 2.641025641025641,
2169
+ "grad_norm": 0.4984622895717621,
2170
+ "learning_rate": 5.380823857642069e-05,
2171
+ "loss": 0.6726,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 2.6495726495726495,
2176
+ "grad_norm": 0.6048721075057983,
2177
+ "learning_rate": 5.3200956606277006e-05,
2178
+ "loss": 0.9416,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 2.658119658119658,
2183
+ "grad_norm": 0.42853838205337524,
2184
+ "learning_rate": 5.259587656894174e-05,
2185
+ "loss": 0.559,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 2.6666666666666665,
2190
+ "grad_norm": 0.5723150968551636,
2191
+ "learning_rate": 5.199302693391959e-05,
2192
+ "loss": 0.7749,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 2.6752136752136755,
2197
+ "grad_norm": 0.5739536285400391,
2198
+ "learning_rate": 5.139243606577302e-05,
2199
+ "loss": 0.7624,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 2.683760683760684,
2204
+ "grad_norm": 0.597714364528656,
2205
+ "learning_rate": 5.0794132222787707e-05,
2206
+ "loss": 0.6945,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 2.6923076923076925,
2211
+ "grad_norm": 0.47430750727653503,
2212
+ "learning_rate": 5.019814355564292e-05,
2213
+ "loss": 0.6807,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 2.700854700854701,
2218
+ "grad_norm": 0.4511941969394684,
2219
+ "learning_rate": 4.960449810608705e-05,
2220
+ "loss": 0.793,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 2.7094017094017095,
2225
+ "grad_norm": 0.4567405879497528,
2226
+ "learning_rate": 4.90132238056182e-05,
2227
+ "loss": 0.6009,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 2.717948717948718,
2232
+ "grad_norm": 0.4015594720840454,
2233
+ "learning_rate": 4.8424348474170014e-05,
2234
+ "loss": 1.0635,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 2.7264957264957266,
2239
+ "grad_norm": 0.502829372882843,
2240
+ "learning_rate": 4.783789981880267e-05,
2241
+ "loss": 0.6601,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 2.735042735042735,
2246
+ "grad_norm": 0.4572563171386719,
2247
+ "learning_rate": 4.725390543239929e-05,
2248
+ "loss": 0.6075,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 2.7435897435897436,
2253
+ "grad_norm": 0.4478137791156769,
2254
+ "learning_rate": 4.667239279236768e-05,
2255
+ "loss": 0.7446,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 2.752136752136752,
2260
+ "grad_norm": 0.533441424369812,
2261
+ "learning_rate": 4.609338925934743e-05,
2262
+ "loss": 0.5933,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 2.7606837606837606,
2267
+ "grad_norm": 0.4419093132019043,
2268
+ "learning_rate": 4.551692207592265e-05,
2269
+ "loss": 0.9199,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 2.769230769230769,
2274
+ "grad_norm": 0.4668772220611572,
2275
+ "learning_rate": 4.494301836534016e-05,
2276
+ "loss": 0.6787,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 2.7777777777777777,
2281
+ "grad_norm": 0.560838520526886,
2282
+ "learning_rate": 4.4371705130233275e-05,
2283
+ "loss": 0.6768,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 2.786324786324786,
2288
+ "grad_norm": 0.47518014907836914,
2289
+ "learning_rate": 4.380300925135138e-05,
2290
+ "loss": 0.6669,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 2.7948717948717947,
2295
+ "grad_norm": 0.43352407217025757,
2296
+ "learning_rate": 4.3236957486295115e-05,
2297
+ "loss": 1.0962,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 2.8034188034188032,
2302
+ "grad_norm": 0.39011329412460327,
2303
+ "learning_rate": 4.267357646825746e-05,
2304
+ "loss": 1.311,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 2.8119658119658117,
2309
+ "grad_norm": 0.4802456200122833,
2310
+ "learning_rate": 4.211289270477047e-05,
2311
+ "loss": 0.5656,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 2.8205128205128203,
2316
+ "grad_norm": 0.4346143305301666,
2317
+ "learning_rate": 4.1554932576458415e-05,
2318
+ "loss": 0.621,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 2.8290598290598292,
2323
+ "grad_norm": 0.546248733997345,
2324
+ "learning_rate": 4.0999722335796075e-05,
2325
+ "loss": 1.156,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 2.8376068376068377,
2330
+ "grad_norm": 0.49097940325737,
2331
+ "learning_rate": 4.044728810587406e-05,
2332
+ "loss": 0.6616,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 2.8461538461538463,
2337
+ "grad_norm": 0.4826516807079315,
2338
+ "learning_rate": 3.989765587916914e-05,
2339
+ "loss": 0.5668,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 2.8547008547008548,
2344
+ "grad_norm": 0.49177631735801697,
2345
+ "learning_rate": 3.935085151632185e-05,
2346
+ "loss": 0.8622,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 2.8632478632478633,
2351
+ "grad_norm": 0.4546498954296112,
2352
+ "learning_rate": 3.8806900744919205e-05,
2353
+ "loss": 0.4802,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 2.871794871794872,
2358
+ "grad_norm": 0.5135761499404907,
2359
+ "learning_rate": 3.826582915828468e-05,
2360
+ "loss": 0.7947,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 2.8803418803418803,
2365
+ "grad_norm": 0.5024504065513611,
2366
+ "learning_rate": 3.7727662214273495e-05,
2367
+ "loss": 0.6771,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 2.888888888888889,
2372
+ "grad_norm": 0.4174403250217438,
2373
+ "learning_rate": 3.719242523407539e-05,
2374
+ "loss": 0.5623,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 2.8974358974358974,
2379
+ "grad_norm": 0.4062444865703583,
2380
+ "learning_rate": 3.666014340102268e-05,
2381
+ "loss": 0.8662,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 2.905982905982906,
2386
+ "grad_norm": 0.435547411441803,
2387
+ "learning_rate": 3.613084175940578e-05,
2388
+ "loss": 0.9646,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 2.9145299145299144,
2393
+ "grad_norm": 0.420063853263855,
2394
+ "learning_rate": 3.5604545213294616e-05,
2395
+ "loss": 1.0064,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 2.9230769230769234,
2400
+ "grad_norm": 0.41142135858535767,
2401
+ "learning_rate": 3.508127852536698e-05,
2402
+ "loss": 0.913,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 2.931623931623932,
2407
+ "grad_norm": 0.5464742183685303,
2408
+ "learning_rate": 3.456106631574336e-05,
2409
+ "loss": 0.7721,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 2.9401709401709404,
2414
+ "grad_norm": 0.4335322678089142,
2415
+ "learning_rate": 3.4043933060828605e-05,
2416
+ "loss": 0.6868,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 2.948717948717949,
2421
+ "grad_norm": 0.43466970324516296,
2422
+ "learning_rate": 3.352990309216022e-05,
2423
+ "loss": 0.9365,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 2.9572649572649574,
2428
+ "grad_norm": 0.6501834988594055,
2429
+ "learning_rate": 3.3019000595263574e-05,
2430
+ "loss": 0.7254,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 2.965811965811966,
2435
+ "grad_norm": 0.4817217290401459,
2436
+ "learning_rate": 3.251124960851408e-05,
2437
+ "loss": 0.5734,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 2.9743589743589745,
2442
+ "grad_norm": 0.5768493413925171,
2443
+ "learning_rate": 3.200667402200586e-05,
2444
+ "loss": 0.725,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 2.982905982905983,
2449
+ "grad_norm": 0.5193359851837158,
2450
+ "learning_rate": 3.1505297576428075e-05,
2451
+ "loss": 0.6118,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 2.9914529914529915,
2456
+ "grad_norm": 0.4567442834377289,
2457
+ "learning_rate": 3.100714386194757e-05,
2458
+ "loss": 0.644,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 3.0,
2463
+ "grad_norm": 0.5161424279212952,
2464
+ "learning_rate": 3.0512236317099175e-05,
2465
+ "loss": 0.5467,
2466
+ "step": 351
2467
+ }
2468
+ ],
2469
+ "logging_steps": 1,
2470
+ "max_steps": 468,
2471
+ "num_input_tokens_seen": 0,
2472
+ "num_train_epochs": 4,
2473
+ "save_steps": 117,
2474
+ "stateful_callbacks": {
2475
+ "TrainerControl": {
2476
+ "args": {
2477
+ "should_epoch_stop": false,
2478
+ "should_evaluate": false,
2479
+ "should_log": false,
2480
+ "should_save": true,
2481
+ "should_training_stop": false
2482
+ },
2483
+ "attributes": {}
2484
+ }
2485
+ },
2486
+ "total_flos": 6.863860141129728e+16,
2487
+ "train_batch_size": 2,
2488
+ "trial_name": null,
2489
+ "trial_params": null
2490
+ }
checkpoint-351/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c808f6ec67547ffc25e425768bac91068256414f8730443120d2ab7c48580d
3
+ size 6200
checkpoint-468/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /root/Llama-3.2-1B-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 0.13.0
checkpoint-468/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/root/Llama-3.2-1B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "v_proj",
25
+ "o_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "up_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-468/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a427c367308079b9fa9ff81abeaf446296f64c969a7543028cdfc5dba18304
3
+ size 90207248
checkpoint-468/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30f89df6b71dc629976a7f2148634d8c7c98c1ac9b7bd40b7630e2af8becd69d
3
+ size 46057338
checkpoint-468/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b08c25fff3b1d22d82c741eadbe633993c881a7e4c8dcd4fb1d1ed6649e8039
3
+ size 14244
checkpoint-468/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d9d5bc4bd8cbd6ad2f885036e809b26ec312eff058ed18571dab24711118e2c
3
+ size 1064
checkpoint-468/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-468/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
checkpoint-468/tokenizer_config.json ADDED
@@ -0,0 +1,2063 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|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
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "tokenizer_class": "PreTrainedTokenizerFast"
2063
+ }
checkpoint-468/trainer_state.json ADDED
@@ -0,0 +1,3309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 468,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008547008547008548,
13
+ "grad_norm": 0.6336084008216858,
14
+ "learning_rate": 2e-05,
15
+ "loss": 1.2928,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.017094017094017096,
20
+ "grad_norm": 0.6126894950866699,
21
+ "learning_rate": 4e-05,
22
+ "loss": 1.1179,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.02564102564102564,
27
+ "grad_norm": 0.6590365171432495,
28
+ "learning_rate": 6e-05,
29
+ "loss": 1.2546,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.03418803418803419,
34
+ "grad_norm": 0.3842516839504242,
35
+ "learning_rate": 8e-05,
36
+ "loss": 1.402,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.042735042735042736,
41
+ "grad_norm": 0.7100726962089539,
42
+ "learning_rate": 0.0001,
43
+ "loss": 1.1523,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05128205128205128,
48
+ "grad_norm": 0.4285312592983246,
49
+ "learning_rate": 0.00012,
50
+ "loss": 1.4567,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.05982905982905983,
55
+ "grad_norm": 0.5057687163352966,
56
+ "learning_rate": 0.00014,
57
+ "loss": 1.2153,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.06837606837606838,
62
+ "grad_norm": 0.3327566683292389,
63
+ "learning_rate": 0.00016,
64
+ "loss": 1.1503,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.07692307692307693,
69
+ "grad_norm": 0.29217734932899475,
70
+ "learning_rate": 0.00018,
71
+ "loss": 0.9723,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.08547008547008547,
76
+ "grad_norm": 0.5076949000358582,
77
+ "learning_rate": 0.0002,
78
+ "loss": 1.5848,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.09401709401709402,
83
+ "grad_norm": 0.40562769770622253,
84
+ "learning_rate": 0.0001999976474595967,
85
+ "loss": 1.3397,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.10256410256410256,
90
+ "grad_norm": 0.33129796385765076,
91
+ "learning_rate": 0.00019999058994907564,
92
+ "loss": 1.0107,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.1111111111111111,
97
+ "grad_norm": 0.39453431963920593,
98
+ "learning_rate": 0.00019997882780049847,
99
+ "loss": 1.1293,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.11965811965811966,
104
+ "grad_norm": 0.3235519826412201,
105
+ "learning_rate": 0.0001999623615672837,
106
+ "loss": 1.259,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.1282051282051282,
111
+ "grad_norm": 0.2598688006401062,
112
+ "learning_rate": 0.00019994119202418098,
113
+ "loss": 1.2164,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.13675213675213677,
118
+ "grad_norm": 0.2793278992176056,
119
+ "learning_rate": 0.00019991532016723439,
120
+ "loss": 1.0104,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.1452991452991453,
125
+ "grad_norm": 0.24649402499198914,
126
+ "learning_rate": 0.00019988474721373568,
127
+ "loss": 1.2559,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.15384615384615385,
132
+ "grad_norm": 0.23192395269870758,
133
+ "learning_rate": 0.00019984947460216707,
134
+ "loss": 0.8831,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.1623931623931624,
139
+ "grad_norm": 0.2821623384952545,
140
+ "learning_rate": 0.00019980950399213344,
141
+ "loss": 0.9643,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.17094017094017094,
146
+ "grad_norm": 0.2398855984210968,
147
+ "learning_rate": 0.00019976483726428422,
148
+ "loss": 0.9148,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.1794871794871795,
153
+ "grad_norm": 0.2592308819293976,
154
+ "learning_rate": 0.0001997154765202251,
155
+ "loss": 0.8939,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.18803418803418803,
160
+ "grad_norm": 0.25392013788223267,
161
+ "learning_rate": 0.00019966142408241901,
162
+ "loss": 0.9752,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.19658119658119658,
167
+ "grad_norm": 0.2928493022918701,
168
+ "learning_rate": 0.00019960268249407675,
169
+ "loss": 1.0981,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.20512820512820512,
174
+ "grad_norm": 0.2692890763282776,
175
+ "learning_rate": 0.00019953925451903756,
176
+ "loss": 0.9699,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.21367521367521367,
181
+ "grad_norm": 0.23414169251918793,
182
+ "learning_rate": 0.0001994711431416389,
183
+ "loss": 1.3802,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.2222222222222222,
188
+ "grad_norm": 0.32594603300094604,
189
+ "learning_rate": 0.00019939835156657616,
190
+ "loss": 1.3705,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.23076923076923078,
195
+ "grad_norm": 0.27903756499290466,
196
+ "learning_rate": 0.00019932088321875172,
197
+ "loss": 0.9765,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.23931623931623933,
202
+ "grad_norm": 0.27631697058677673,
203
+ "learning_rate": 0.00019923874174311394,
204
+ "loss": 0.7924,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.24786324786324787,
209
+ "grad_norm": 0.28414595127105713,
210
+ "learning_rate": 0.0001991519310044857,
211
+ "loss": 1.2446,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.2564102564102564,
216
+ "grad_norm": 0.280527800321579,
217
+ "learning_rate": 0.00019906045508738228,
218
+ "loss": 1.1986,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.26495726495726496,
223
+ "grad_norm": 0.25973978638648987,
224
+ "learning_rate": 0.0001989643182958196,
225
+ "loss": 0.9276,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.27350427350427353,
230
+ "grad_norm": 0.2691807448863983,
231
+ "learning_rate": 0.00019886352515311134,
232
+ "loss": 0.9007,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.28205128205128205,
237
+ "grad_norm": 0.260856032371521,
238
+ "learning_rate": 0.0001987580804016563,
239
+ "loss": 1.1973,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.2905982905982906,
244
+ "grad_norm": 0.28188374638557434,
245
+ "learning_rate": 0.00019864798900271532,
246
+ "loss": 1.1079,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.29914529914529914,
251
+ "grad_norm": 0.25889885425567627,
252
+ "learning_rate": 0.0001985332561361776,
253
+ "loss": 0.8755,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.3076923076923077,
258
+ "grad_norm": 0.2496309131383896,
259
+ "learning_rate": 0.00019841388720031727,
260
+ "loss": 0.8361,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.3162393162393162,
265
+ "grad_norm": 0.276593416929245,
266
+ "learning_rate": 0.00019828988781153917,
267
+ "loss": 0.9342,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.3247863247863248,
272
+ "grad_norm": 0.24598534405231476,
273
+ "learning_rate": 0.00019816126380411476,
274
+ "loss": 0.9002,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3333333333333333,
279
+ "grad_norm": 0.25998443365097046,
280
+ "learning_rate": 0.00019802802122990758,
281
+ "loss": 1.0115,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.3418803418803419,
286
+ "grad_norm": 0.2910752594470978,
287
+ "learning_rate": 0.00019789016635808837,
288
+ "loss": 1.1122,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.3504273504273504,
293
+ "grad_norm": 0.23144645988941193,
294
+ "learning_rate": 0.00019774770567484022,
295
+ "loss": 1.0541,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.358974358974359,
300
+ "grad_norm": 0.23637208342552185,
301
+ "learning_rate": 0.00019760064588305345,
302
+ "loss": 0.9,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.36752136752136755,
307
+ "grad_norm": 0.24016380310058594,
308
+ "learning_rate": 0.00019744899390201006,
309
+ "loss": 0.9473,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.37606837606837606,
314
+ "grad_norm": 0.23975665867328644,
315
+ "learning_rate": 0.0001972927568670583,
316
+ "loss": 1.361,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.38461538461538464,
321
+ "grad_norm": 0.2693803310394287,
322
+ "learning_rate": 0.00019713194212927696,
323
+ "loss": 1.1029,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.39316239316239315,
328
+ "grad_norm": 0.2764308452606201,
329
+ "learning_rate": 0.00019696655725512933,
330
+ "loss": 0.9312,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.4017094017094017,
335
+ "grad_norm": 0.25453776121139526,
336
+ "learning_rate": 0.00019679661002610743,
337
+ "loss": 0.9677,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.41025641025641024,
342
+ "grad_norm": 0.26758676767349243,
343
+ "learning_rate": 0.00019662210843836574,
344
+ "loss": 0.9591,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.4188034188034188,
349
+ "grad_norm": 0.27530986070632935,
350
+ "learning_rate": 0.0001964430607023449,
351
+ "loss": 0.9504,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.42735042735042733,
356
+ "grad_norm": 0.2969217896461487,
357
+ "learning_rate": 0.00019625947524238563,
358
+ "loss": 1.11,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.4358974358974359,
363
+ "grad_norm": 0.26885175704956055,
364
+ "learning_rate": 0.00019607136069633212,
365
+ "loss": 0.8923,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.4444444444444444,
370
+ "grad_norm": 0.255889892578125,
371
+ "learning_rate": 0.0001958787259151258,
372
+ "loss": 0.9118,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.452991452991453,
377
+ "grad_norm": 0.2702856659889221,
378
+ "learning_rate": 0.00019568157996238884,
379
+ "loss": 0.9143,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.46153846153846156,
384
+ "grad_norm": 0.2267722338438034,
385
+ "learning_rate": 0.0001954799321139975,
386
+ "loss": 1.1196,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.4700854700854701,
391
+ "grad_norm": 0.23851439356803894,
392
+ "learning_rate": 0.00019527379185764612,
393
+ "loss": 0.8702,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.47863247863247865,
398
+ "grad_norm": 0.30145585536956787,
399
+ "learning_rate": 0.00019506316889240027,
400
+ "loss": 1.4398,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.48717948717948717,
405
+ "grad_norm": 0.2665199339389801,
406
+ "learning_rate": 0.00019484807312824067,
407
+ "loss": 0.8006,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.49572649572649574,
412
+ "grad_norm": 0.3289227783679962,
413
+ "learning_rate": 0.0001946285146855968,
414
+ "loss": 0.9466,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.5042735042735043,
419
+ "grad_norm": 0.2549362778663635,
420
+ "learning_rate": 0.0001944045038948709,
421
+ "loss": 0.8871,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5128205128205128,
426
+ "grad_norm": 0.289874792098999,
427
+ "learning_rate": 0.00019417605129595157,
428
+ "loss": 0.8717,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5213675213675214,
433
+ "grad_norm": 0.32114192843437195,
434
+ "learning_rate": 0.0001939431676377183,
435
+ "loss": 0.9448,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5299145299145299,
440
+ "grad_norm": 0.2595084309577942,
441
+ "learning_rate": 0.0001937058638775353,
442
+ "loss": 0.8295,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5384615384615384,
447
+ "grad_norm": 0.22089529037475586,
448
+ "learning_rate": 0.00019346415118073632,
449
+ "loss": 1.2068,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5470085470085471,
454
+ "grad_norm": 0.3057108223438263,
455
+ "learning_rate": 0.00019321804092009906,
456
+ "loss": 0.9483,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5555555555555556,
461
+ "grad_norm": 0.2628245949745178,
462
+ "learning_rate": 0.00019296754467531014,
463
+ "loss": 0.928,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.5641025641025641,
468
+ "grad_norm": 0.31952518224716187,
469
+ "learning_rate": 0.00019271267423242024,
470
+ "loss": 0.9064,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.5726495726495726,
475
+ "grad_norm": 0.2862078845500946,
476
+ "learning_rate": 0.00019245344158328972,
477
+ "loss": 1.0335,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.5811965811965812,
482
+ "grad_norm": 0.27666571736335754,
483
+ "learning_rate": 0.0001921898589250242,
484
+ "loss": 0.8877,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.5897435897435898,
489
+ "grad_norm": 0.24311263859272003,
490
+ "learning_rate": 0.0001919219386594007,
491
+ "loss": 0.8868,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.5982905982905983,
496
+ "grad_norm": 0.2716294825077057,
497
+ "learning_rate": 0.00019164969339228422,
498
+ "loss": 0.9431,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6068376068376068,
503
+ "grad_norm": 0.3183337152004242,
504
+ "learning_rate": 0.00019137313593303463,
505
+ "loss": 1.0538,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6153846153846154,
510
+ "grad_norm": 0.2670356333255768,
511
+ "learning_rate": 0.00019109227929390378,
512
+ "loss": 1.3404,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.6239316239316239,
517
+ "grad_norm": 0.26112431287765503,
518
+ "learning_rate": 0.00019080713668942356,
519
+ "loss": 0.8849,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.6324786324786325,
524
+ "grad_norm": 0.3271474838256836,
525
+ "learning_rate": 0.00019051772153578389,
526
+ "loss": 1.0236,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6410256410256411,
531
+ "grad_norm": 0.32266974449157715,
532
+ "learning_rate": 0.00019022404745020163,
533
+ "loss": 0.8979,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6495726495726496,
538
+ "grad_norm": 0.2465939223766327,
539
+ "learning_rate": 0.00018992612825027976,
540
+ "loss": 0.891,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.6581196581196581,
545
+ "grad_norm": 0.31744077801704407,
546
+ "learning_rate": 0.0001896239779533575,
547
+ "loss": 1.0727,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.6666666666666666,
552
+ "grad_norm": 0.2582801878452301,
553
+ "learning_rate": 0.00018931761077585035,
554
+ "loss": 0.9047,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.6752136752136753,
559
+ "grad_norm": 0.25554949045181274,
560
+ "learning_rate": 0.00018900704113258165,
561
+ "loss": 0.8029,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.6837606837606838,
566
+ "grad_norm": 0.2558218836784363,
567
+ "learning_rate": 0.00018869228363610404,
568
+ "loss": 0.8504,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.6923076923076923,
573
+ "grad_norm": 0.3036883771419525,
574
+ "learning_rate": 0.00018837335309601213,
575
+ "loss": 0.9286,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.7008547008547008,
580
+ "grad_norm": 0.24368591606616974,
581
+ "learning_rate": 0.00018805026451824546,
582
+ "loss": 1.4037,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7094017094017094,
587
+ "grad_norm": 0.22905252873897552,
588
+ "learning_rate": 0.00018772303310438275,
589
+ "loss": 1.2179,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.717948717948718,
594
+ "grad_norm": 0.3644798696041107,
595
+ "learning_rate": 0.00018739167425092644,
596
+ "loss": 1.3658,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7264957264957265,
601
+ "grad_norm": 0.25496625900268555,
602
+ "learning_rate": 0.00018705620354857833,
603
+ "loss": 0.7991,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7350427350427351,
608
+ "grad_norm": 0.2917548418045044,
609
+ "learning_rate": 0.00018671663678150607,
610
+ "loss": 0.7979,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.7435897435897436,
615
+ "grad_norm": 0.2509627342224121,
616
+ "learning_rate": 0.0001863729899266004,
617
+ "loss": 0.8439,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.7521367521367521,
622
+ "grad_norm": 0.26703646779060364,
623
+ "learning_rate": 0.0001860252791527236,
624
+ "loss": 1.1359,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.7606837606837606,
629
+ "grad_norm": 0.2911994159221649,
630
+ "learning_rate": 0.00018567352081994852,
631
+ "loss": 1.378,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.7692307692307693,
636
+ "grad_norm": 0.24897685647010803,
637
+ "learning_rate": 0.00018531773147878895,
638
+ "loss": 1.1141,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.7777777777777778,
643
+ "grad_norm": 0.28840702772140503,
644
+ "learning_rate": 0.0001849579278694209,
645
+ "loss": 0.9043,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.7863247863247863,
650
+ "grad_norm": 0.2617591619491577,
651
+ "learning_rate": 0.00018459412692089494,
652
+ "loss": 0.7995,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.7948717948717948,
657
+ "grad_norm": 0.2502082586288452,
658
+ "learning_rate": 0.0001842263457503397,
659
+ "loss": 0.789,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.8034188034188035,
664
+ "grad_norm": 0.30928075313568115,
665
+ "learning_rate": 0.00018385460166215638,
666
+ "loss": 0.9983,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.811965811965812,
671
+ "grad_norm": 0.33725544810295105,
672
+ "learning_rate": 0.00018347891214720477,
673
+ "loss": 0.955,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8205128205128205,
678
+ "grad_norm": 0.24872225522994995,
679
+ "learning_rate": 0.00018309929488198012,
680
+ "loss": 1.1854,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8290598290598291,
685
+ "grad_norm": 0.2822365462779999,
686
+ "learning_rate": 0.00018271576772778154,
687
+ "loss": 0.8358,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.8376068376068376,
692
+ "grad_norm": 0.2920995056629181,
693
+ "learning_rate": 0.00018232834872987147,
694
+ "loss": 1.3358,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.8461538461538461,
699
+ "grad_norm": 0.303602397441864,
700
+ "learning_rate": 0.00018193705611662696,
701
+ "loss": 0.9797,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.8547008547008547,
706
+ "grad_norm": 0.3406928479671478,
707
+ "learning_rate": 0.0001815419082986815,
708
+ "loss": 0.9816,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.8632478632478633,
713
+ "grad_norm": 0.22692528367042542,
714
+ "learning_rate": 0.00018114292386805936,
715
+ "loss": 1.221,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.8717948717948718,
720
+ "grad_norm": 0.22570784389972687,
721
+ "learning_rate": 0.00018074012159730032,
722
+ "loss": 1.1856,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.8803418803418803,
727
+ "grad_norm": 0.2517668306827545,
728
+ "learning_rate": 0.00018033352043857675,
729
+ "loss": 1.1498,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.8888888888888888,
734
+ "grad_norm": 0.27244430780410767,
735
+ "learning_rate": 0.00017992313952280172,
736
+ "loss": 1.1015,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.8974358974358975,
741
+ "grad_norm": 0.3242965638637543,
742
+ "learning_rate": 0.00017950899815872892,
743
+ "loss": 1.2942,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.905982905982906,
748
+ "grad_norm": 0.32707729935646057,
749
+ "learning_rate": 0.00017909111583204422,
750
+ "loss": 1.2383,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9145299145299145,
755
+ "grad_norm": 0.37845203280448914,
756
+ "learning_rate": 0.0001786695122044487,
757
+ "loss": 0.9584,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.9230769230769231,
762
+ "grad_norm": 0.26341512799263,
763
+ "learning_rate": 0.0001782442071127338,
764
+ "loss": 1.1443,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.9316239316239316,
769
+ "grad_norm": 0.3688293397426605,
770
+ "learning_rate": 0.0001778152205678477,
771
+ "loss": 1.5414,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.9401709401709402,
776
+ "grad_norm": 0.3266530930995941,
777
+ "learning_rate": 0.00017738257275395404,
778
+ "loss": 1.0778,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.9487179487179487,
783
+ "grad_norm": 0.4219954311847687,
784
+ "learning_rate": 0.00017694628402748202,
785
+ "loss": 1.1903,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.9572649572649573,
790
+ "grad_norm": 0.28938961029052734,
791
+ "learning_rate": 0.0001765063749161688,
792
+ "loss": 0.8998,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.9658119658119658,
797
+ "grad_norm": 0.3432457745075226,
798
+ "learning_rate": 0.00017606286611809353,
799
+ "loss": 0.9684,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.9743589743589743,
804
+ "grad_norm": 0.26857873797416687,
805
+ "learning_rate": 0.00017561577850070355,
806
+ "loss": 1.0045,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.9829059829059829,
811
+ "grad_norm": 0.24974624812602997,
812
+ "learning_rate": 0.00017516513309983253,
813
+ "loss": 0.7979,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.9914529914529915,
818
+ "grad_norm": 0.343883752822876,
819
+ "learning_rate": 0.00017471095111871074,
820
+ "loss": 1.0162,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 1.0,
825
+ "grad_norm": 0.29970595240592957,
826
+ "learning_rate": 0.0001742532539269674,
827
+ "loss": 0.8354,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 1.0085470085470085,
832
+ "grad_norm": 0.2625507414340973,
833
+ "learning_rate": 0.00017379206305962526,
834
+ "loss": 0.7908,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 1.017094017094017,
839
+ "grad_norm": 0.2953716814517975,
840
+ "learning_rate": 0.00017332740021608722,
841
+ "loss": 0.8421,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 1.0256410256410255,
846
+ "grad_norm": 0.4784148931503296,
847
+ "learning_rate": 0.00017285928725911562,
848
+ "loss": 1.2155,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 1.0341880341880343,
853
+ "grad_norm": 0.5949030518531799,
854
+ "learning_rate": 0.00017238774621380337,
855
+ "loss": 1.2108,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 1.0427350427350428,
860
+ "grad_norm": 0.41158854961395264,
861
+ "learning_rate": 0.00017191279926653761,
862
+ "loss": 1.5972,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 1.0512820512820513,
867
+ "grad_norm": 0.31010663509368896,
868
+ "learning_rate": 0.00017143446876395602,
869
+ "loss": 1.1852,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 1.0598290598290598,
874
+ "grad_norm": 0.300396203994751,
875
+ "learning_rate": 0.00017095277721189528,
876
+ "loss": 1.1387,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 1.0683760683760684,
881
+ "grad_norm": 0.570995032787323,
882
+ "learning_rate": 0.00017046774727433222,
883
+ "loss": 1.0398,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 1.0769230769230769,
888
+ "grad_norm": 0.3038155734539032,
889
+ "learning_rate": 0.00016997940177231722,
890
+ "loss": 0.7614,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 1.0854700854700854,
895
+ "grad_norm": 0.27748215198516846,
896
+ "learning_rate": 0.00016948776368290084,
897
+ "loss": 1.0286,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 1.0940170940170941,
902
+ "grad_norm": 0.3376232981681824,
903
+ "learning_rate": 0.00016899285613805246,
904
+ "loss": 0.7464,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 1.1025641025641026,
909
+ "grad_norm": 0.33782312273979187,
910
+ "learning_rate": 0.00016849470242357196,
911
+ "loss": 0.7747,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 1.1111111111111112,
916
+ "grad_norm": 0.30509698390960693,
917
+ "learning_rate": 0.00016799332597799413,
918
+ "loss": 0.8188,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 1.1196581196581197,
923
+ "grad_norm": 0.2920445203781128,
924
+ "learning_rate": 0.00016748875039148593,
925
+ "loss": 1.0563,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 1.1282051282051282,
930
+ "grad_norm": 0.30515843629837036,
931
+ "learning_rate": 0.0001669809994047364,
932
+ "loss": 1.0849,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 1.1367521367521367,
937
+ "grad_norm": 0.35152626037597656,
938
+ "learning_rate": 0.0001664700969078398,
939
+ "loss": 0.9146,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 1.1452991452991452,
944
+ "grad_norm": 0.318646103143692,
945
+ "learning_rate": 0.00016595606693917142,
946
+ "loss": 1.1709,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 1.1538461538461537,
951
+ "grad_norm": 0.2702546715736389,
952
+ "learning_rate": 0.00016543893368425666,
953
+ "loss": 0.7313,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 1.1623931623931625,
958
+ "grad_norm": 0.3528870940208435,
959
+ "learning_rate": 0.00016491872147463306,
960
+ "loss": 0.8208,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 1.170940170940171,
965
+ "grad_norm": 0.28231188654899597,
966
+ "learning_rate": 0.00016439545478670543,
967
+ "loss": 1.7001,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 1.1794871794871795,
972
+ "grad_norm": 0.3122393488883972,
973
+ "learning_rate": 0.00016386915824059427,
974
+ "loss": 0.7343,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 1.188034188034188,
979
+ "grad_norm": 0.2875630855560303,
980
+ "learning_rate": 0.00016333985659897735,
981
+ "loss": 0.7207,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 1.1965811965811965,
986
+ "grad_norm": 0.38364624977111816,
987
+ "learning_rate": 0.00016280757476592466,
988
+ "loss": 0.779,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 1.205128205128205,
993
+ "grad_norm": 0.30091550946235657,
994
+ "learning_rate": 0.0001622723377857265,
995
+ "loss": 0.7685,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 1.2136752136752136,
1000
+ "grad_norm": 0.28651681542396545,
1001
+ "learning_rate": 0.00016173417084171536,
1002
+ "loss": 1.1618,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 1.2222222222222223,
1007
+ "grad_norm": 0.3049664795398712,
1008
+ "learning_rate": 0.00016119309925508078,
1009
+ "loss": 0.7262,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 1.2307692307692308,
1014
+ "grad_norm": 0.38781028985977173,
1015
+ "learning_rate": 0.0001606491484836782,
1016
+ "loss": 0.8057,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 1.2393162393162394,
1021
+ "grad_norm": 0.3604777455329895,
1022
+ "learning_rate": 0.00016010234412083086,
1023
+ "loss": 0.8435,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 1.2478632478632479,
1028
+ "grad_norm": 0.3753257691860199,
1029
+ "learning_rate": 0.00015955271189412598,
1030
+ "loss": 0.8945,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 1.2564102564102564,
1035
+ "grad_norm": 0.35498958826065063,
1036
+ "learning_rate": 0.00015900027766420393,
1037
+ "loss": 0.7545,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 1.264957264957265,
1042
+ "grad_norm": 0.337697833776474,
1043
+ "learning_rate": 0.00015844506742354164,
1044
+ "loss": 0.8178,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 1.2735042735042734,
1049
+ "grad_norm": 0.34326887130737305,
1050
+ "learning_rate": 0.00015788710729522953,
1051
+ "loss": 0.9658,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 1.282051282051282,
1056
+ "grad_norm": 0.3605210483074188,
1057
+ "learning_rate": 0.00015732642353174259,
1058
+ "loss": 1.1598,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 1.2905982905982907,
1063
+ "grad_norm": 0.2907405197620392,
1064
+ "learning_rate": 0.0001567630425137049,
1065
+ "loss": 0.6474,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 1.2991452991452992,
1070
+ "grad_norm": 0.36666378378868103,
1071
+ "learning_rate": 0.00015619699074864864,
1072
+ "loss": 0.772,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 1.3076923076923077,
1077
+ "grad_norm": 0.42435774207115173,
1078
+ "learning_rate": 0.00015562829486976673,
1079
+ "loss": 0.8633,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 1.3162393162393162,
1084
+ "grad_norm": 0.34810835123062134,
1085
+ "learning_rate": 0.00015505698163465986,
1086
+ "loss": 0.982,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 1.3247863247863247,
1091
+ "grad_norm": 0.38605523109436035,
1092
+ "learning_rate": 0.00015448307792407734,
1093
+ "loss": 0.7854,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 1.3333333333333333,
1098
+ "grad_norm": 0.3216642439365387,
1099
+ "learning_rate": 0.00015390661074065256,
1100
+ "loss": 0.7786,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 1.341880341880342,
1105
+ "grad_norm": 0.3482376039028168,
1106
+ "learning_rate": 0.00015332760720763232,
1107
+ "loss": 1.1516,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 1.3504273504273505,
1112
+ "grad_norm": 0.4383181035518646,
1113
+ "learning_rate": 0.00015274609456760073,
1114
+ "loss": 0.8356,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 1.358974358974359,
1119
+ "grad_norm": 0.415587842464447,
1120
+ "learning_rate": 0.00015216210018119733,
1121
+ "loss": 1.0019,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 1.3675213675213675,
1126
+ "grad_norm": 0.36597633361816406,
1127
+ "learning_rate": 0.00015157565152583002,
1128
+ "loss": 0.7382,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 1.376068376068376,
1133
+ "grad_norm": 0.36167895793914795,
1134
+ "learning_rate": 0.0001509867761943818,
1135
+ "loss": 0.9089,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 1.3846153846153846,
1140
+ "grad_norm": 0.35900619626045227,
1141
+ "learning_rate": 0.00015039550189391298,
1142
+ "loss": 0.7338,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 1.393162393162393,
1147
+ "grad_norm": 0.3245941996574402,
1148
+ "learning_rate": 0.0001498018564443571,
1149
+ "loss": 1.0774,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 1.4017094017094016,
1154
+ "grad_norm": 0.3721596896648407,
1155
+ "learning_rate": 0.0001492058677772123,
1156
+ "loss": 0.9292,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 1.4102564102564101,
1161
+ "grad_norm": 0.37743324041366577,
1162
+ "learning_rate": 0.000148607563934227,
1163
+ "loss": 0.812,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 1.4188034188034189,
1168
+ "grad_norm": 0.30644622445106506,
1169
+ "learning_rate": 0.00014800697306608044,
1170
+ "loss": 0.6427,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 1.4273504273504274,
1175
+ "grad_norm": 0.39433762431144714,
1176
+ "learning_rate": 0.00014740412343105828,
1177
+ "loss": 0.9262,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 1.435897435897436,
1182
+ "grad_norm": 0.34150931239128113,
1183
+ "learning_rate": 0.00014679904339372302,
1184
+ "loss": 0.7721,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 1.4444444444444444,
1189
+ "grad_norm": 0.3927769064903259,
1190
+ "learning_rate": 0.00014619176142357935,
1191
+ "loss": 0.7861,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 1.452991452991453,
1196
+ "grad_norm": 0.3742867410182953,
1197
+ "learning_rate": 0.0001455823060937347,
1198
+ "loss": 0.8983,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 1.4615384615384617,
1203
+ "grad_norm": 0.3988594114780426,
1204
+ "learning_rate": 0.00014497070607955476,
1205
+ "loss": 0.7946,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 1.4700854700854702,
1210
+ "grad_norm": 0.3588651418685913,
1211
+ "learning_rate": 0.00014435699015731448,
1212
+ "loss": 0.7881,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 1.4786324786324787,
1217
+ "grad_norm": 0.3405568599700928,
1218
+ "learning_rate": 0.00014374118720284388,
1219
+ "loss": 0.8645,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 1.4871794871794872,
1224
+ "grad_norm": 0.2791353762149811,
1225
+ "learning_rate": 0.00014312332619016965,
1226
+ "loss": 0.9498,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 1.4957264957264957,
1231
+ "grad_norm": 0.3834662139415741,
1232
+ "learning_rate": 0.0001425034361901516,
1233
+ "loss": 0.8281,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 1.5042735042735043,
1238
+ "grad_norm": 0.40144065022468567,
1239
+ "learning_rate": 0.00014188154636911524,
1240
+ "loss": 1.4235,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 1.5128205128205128,
1245
+ "grad_norm": 0.4115220606327057,
1246
+ "learning_rate": 0.0001412576859874791,
1247
+ "loss": 0.7451,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 1.5213675213675213,
1252
+ "grad_norm": 0.3392897844314575,
1253
+ "learning_rate": 0.00014063188439837832,
1254
+ "loss": 0.7047,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 1.5299145299145298,
1259
+ "grad_norm": 0.3308214545249939,
1260
+ "learning_rate": 0.0001400041710462833,
1261
+ "loss": 0.7011,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 1.5384615384615383,
1266
+ "grad_norm": 0.3544357419013977,
1267
+ "learning_rate": 0.0001393745754656146,
1268
+ "loss": 0.7985,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 1.547008547008547,
1273
+ "grad_norm": 0.3125544488430023,
1274
+ "learning_rate": 0.00013874312727935292,
1275
+ "loss": 0.7115,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 1.5555555555555556,
1280
+ "grad_norm": 0.31898999214172363,
1281
+ "learning_rate": 0.00013810985619764572,
1282
+ "loss": 1.1459,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 1.564102564102564,
1287
+ "grad_norm": 0.3448270857334137,
1288
+ "learning_rate": 0.00013747479201640914,
1289
+ "loss": 0.6875,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 1.5726495726495726,
1294
+ "grad_norm": 0.4556581676006317,
1295
+ "learning_rate": 0.00013683796461592604,
1296
+ "loss": 0.8871,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 1.5811965811965814,
1301
+ "grad_norm": 0.3367992341518402,
1302
+ "learning_rate": 0.00013619940395944027,
1303
+ "loss": 0.7687,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 1.5897435897435899,
1308
+ "grad_norm": 0.35872966051101685,
1309
+ "learning_rate": 0.00013555914009174663,
1310
+ "loss": 0.8261,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 1.5982905982905984,
1315
+ "grad_norm": 0.3715200424194336,
1316
+ "learning_rate": 0.00013491720313777756,
1317
+ "loss": 1.3308,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 1.606837606837607,
1322
+ "grad_norm": 0.3741316497325897,
1323
+ "learning_rate": 0.00013427362330118543,
1324
+ "loss": 0.7169,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 1.6153846153846154,
1329
+ "grad_norm": 0.3634923994541168,
1330
+ "learning_rate": 0.0001336284308629216,
1331
+ "loss": 0.9805,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 1.623931623931624,
1336
+ "grad_norm": 0.3144815266132355,
1337
+ "learning_rate": 0.00013298165617981172,
1338
+ "loss": 1.0045,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 1.6324786324786325,
1343
+ "grad_norm": 0.4095522463321686,
1344
+ "learning_rate": 0.00013233332968312715,
1345
+ "loss": 1.1136,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 1.641025641025641,
1350
+ "grad_norm": 0.35933032631874084,
1351
+ "learning_rate": 0.0001316834818771535,
1352
+ "loss": 0.8102,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 1.6495726495726495,
1357
+ "grad_norm": 0.4028998911380768,
1358
+ "learning_rate": 0.00013103214333775521,
1359
+ "loss": 0.843,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 1.658119658119658,
1364
+ "grad_norm": 0.401076078414917,
1365
+ "learning_rate": 0.00013037934471093682,
1366
+ "loss": 0.6997,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 1.6666666666666665,
1371
+ "grad_norm": 0.36478322744369507,
1372
+ "learning_rate": 0.00012972511671140125,
1373
+ "loss": 0.7362,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 1.6752136752136753,
1378
+ "grad_norm": 0.3325231969356537,
1379
+ "learning_rate": 0.00012906949012110456,
1380
+ "loss": 0.9889,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 1.6837606837606838,
1385
+ "grad_norm": 0.3909556567668915,
1386
+ "learning_rate": 0.00012841249578780757,
1387
+ "loss": 0.8985,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 1.6923076923076923,
1392
+ "grad_norm": 0.31815868616104126,
1393
+ "learning_rate": 0.00012775416462362457,
1394
+ "loss": 0.8205,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.7008547008547008,
1399
+ "grad_norm": 0.3717130124568939,
1400
+ "learning_rate": 0.00012709452760356884,
1401
+ "loss": 1.2108,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.7094017094017095,
1406
+ "grad_norm": 0.3459589183330536,
1407
+ "learning_rate": 0.00012643361576409516,
1408
+ "loss": 0.8245,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.717948717948718,
1413
+ "grad_norm": 0.3962521255016327,
1414
+ "learning_rate": 0.00012577146020163968,
1415
+ "loss": 0.8364,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.7264957264957266,
1420
+ "grad_norm": 0.41842907667160034,
1421
+ "learning_rate": 0.00012510809207115666,
1422
+ "loss": 0.7526,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.735042735042735,
1427
+ "grad_norm": 0.3551943302154541,
1428
+ "learning_rate": 0.00012444354258465268,
1429
+ "loss": 0.7563,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.7435897435897436,
1434
+ "grad_norm": 0.3701689541339874,
1435
+ "learning_rate": 0.00012377784300971807,
1436
+ "loss": 1.0242,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.7521367521367521,
1441
+ "grad_norm": 0.34136760234832764,
1442
+ "learning_rate": 0.0001231110246680558,
1443
+ "loss": 1.1623,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.7606837606837606,
1448
+ "grad_norm": 0.45741143822669983,
1449
+ "learning_rate": 0.00012244311893400763,
1450
+ "loss": 0.912,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.7692307692307692,
1455
+ "grad_norm": 0.44242578744888306,
1456
+ "learning_rate": 0.00012177415723307808,
1457
+ "loss": 0.7916,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.7777777777777777,
1462
+ "grad_norm": 0.3459125757217407,
1463
+ "learning_rate": 0.00012110417104045575,
1464
+ "loss": 0.6614,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.7863247863247862,
1469
+ "grad_norm": 0.3435271382331848,
1470
+ "learning_rate": 0.00012043319187953241,
1471
+ "loss": 0.8433,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.7948717948717947,
1476
+ "grad_norm": 0.404305636882782,
1477
+ "learning_rate": 0.00011976125132041974,
1478
+ "loss": 0.8646,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.8034188034188035,
1483
+ "grad_norm": 0.5799421668052673,
1484
+ "learning_rate": 0.00011908838097846404,
1485
+ "loss": 1.3677,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.811965811965812,
1490
+ "grad_norm": 0.370825856924057,
1491
+ "learning_rate": 0.00011841461251275867,
1492
+ "loss": 1.0736,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.8205128205128205,
1497
+ "grad_norm": 0.43012121319770813,
1498
+ "learning_rate": 0.00011773997762465429,
1499
+ "loss": 0.8208,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.8290598290598292,
1504
+ "grad_norm": 0.33933213353157043,
1505
+ "learning_rate": 0.0001170645080562676,
1506
+ "loss": 0.7598,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.8376068376068377,
1511
+ "grad_norm": 0.35830000042915344,
1512
+ "learning_rate": 0.00011638823558898762,
1513
+ "loss": 0.7402,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.8461538461538463,
1518
+ "grad_norm": 0.37512725591659546,
1519
+ "learning_rate": 0.00011571119204198037,
1520
+ "loss": 0.7306,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.8547008547008548,
1525
+ "grad_norm": 0.35193270444869995,
1526
+ "learning_rate": 0.00011503340927069189,
1527
+ "loss": 0.8577,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.8632478632478633,
1532
+ "grad_norm": 0.3259103000164032,
1533
+ "learning_rate": 0.00011435491916534919,
1534
+ "loss": 0.7147,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.8717948717948718,
1539
+ "grad_norm": 0.3664517402648926,
1540
+ "learning_rate": 0.00011367575364946006,
1541
+ "loss": 0.7411,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.8803418803418803,
1546
+ "grad_norm": 0.428186297416687,
1547
+ "learning_rate": 0.00011299594467831078,
1548
+ "loss": 0.7532,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.8888888888888888,
1553
+ "grad_norm": 0.4050661623477936,
1554
+ "learning_rate": 0.00011231552423746283,
1555
+ "loss": 0.7799,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.8974358974358974,
1560
+ "grad_norm": 0.3434165120124817,
1561
+ "learning_rate": 0.00011163452434124773,
1562
+ "loss": 0.7433,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.9059829059829059,
1567
+ "grad_norm": 0.4107282757759094,
1568
+ "learning_rate": 0.00011095297703126093,
1569
+ "loss": 0.7374,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.9145299145299144,
1574
+ "grad_norm": 0.4014933109283447,
1575
+ "learning_rate": 0.00011027091437485404,
1576
+ "loss": 0.9252,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.9230769230769231,
1581
+ "grad_norm": 0.3325748145580292,
1582
+ "learning_rate": 0.00010958836846362621,
1583
+ "loss": 0.9575,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.9316239316239316,
1588
+ "grad_norm": 0.3845024108886719,
1589
+ "learning_rate": 0.00010890537141191417,
1590
+ "loss": 0.7212,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.9401709401709402,
1595
+ "grad_norm": 0.3581906855106354,
1596
+ "learning_rate": 0.00010822195535528106,
1597
+ "loss": 1.015,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.9487179487179487,
1602
+ "grad_norm": 0.38040146231651306,
1603
+ "learning_rate": 0.00010753815244900458,
1604
+ "loss": 0.6995,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.9572649572649574,
1609
+ "grad_norm": 0.4363343119621277,
1610
+ "learning_rate": 0.00010685399486656406,
1611
+ "loss": 0.7875,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.965811965811966,
1616
+ "grad_norm": 0.374661386013031,
1617
+ "learning_rate": 0.00010616951479812658,
1618
+ "loss": 0.7548,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.9743589743589745,
1623
+ "grad_norm": 0.37670278549194336,
1624
+ "learning_rate": 0.00010548474444903247,
1625
+ "loss": 0.6929,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.982905982905983,
1630
+ "grad_norm": 0.3678586483001709,
1631
+ "learning_rate": 0.00010479971603828,
1632
+ "loss": 0.6928,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.9914529914529915,
1637
+ "grad_norm": 0.33861783146858215,
1638
+ "learning_rate": 0.00010411446179700943,
1639
+ "loss": 0.7386,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 2.0,
1644
+ "grad_norm": 0.8249924182891846,
1645
+ "learning_rate": 0.00010342901396698659,
1646
+ "loss": 1.1202,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 2.0085470085470085,
1651
+ "grad_norm": 0.3209660053253174,
1652
+ "learning_rate": 0.00010274340479908568,
1653
+ "loss": 0.5614,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 2.017094017094017,
1658
+ "grad_norm": 0.35706081986427307,
1659
+ "learning_rate": 0.00010205766655177215,
1660
+ "loss": 0.6367,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 2.0256410256410255,
1665
+ "grad_norm": 0.3861965537071228,
1666
+ "learning_rate": 0.00010137183148958463,
1667
+ "loss": 0.7618,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 2.034188034188034,
1672
+ "grad_norm": 0.3865705728530884,
1673
+ "learning_rate": 0.00010068593188161697,
1674
+ "loss": 0.6082,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 2.0427350427350426,
1679
+ "grad_norm": 0.4773464798927307,
1680
+ "learning_rate": 0.0001,
1681
+ "loss": 0.7599,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 2.051282051282051,
1686
+ "grad_norm": 0.40682271122932434,
1687
+ "learning_rate": 9.931406811838308e-05,
1688
+ "loss": 0.5965,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 2.0598290598290596,
1693
+ "grad_norm": 0.44999873638153076,
1694
+ "learning_rate": 9.862816851041541e-05,
1695
+ "loss": 0.6273,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 2.0683760683760686,
1700
+ "grad_norm": 0.3938470184803009,
1701
+ "learning_rate": 9.79423334482279e-05,
1702
+ "loss": 0.7883,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 2.076923076923077,
1707
+ "grad_norm": 0.40996649861335754,
1708
+ "learning_rate": 9.725659520091433e-05,
1709
+ "loss": 0.6598,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 2.0854700854700856,
1714
+ "grad_norm": 0.41541314125061035,
1715
+ "learning_rate": 9.657098603301346e-05,
1716
+ "loss": 0.7229,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 2.094017094017094,
1721
+ "grad_norm": 0.353305846452713,
1722
+ "learning_rate": 9.588553820299056e-05,
1723
+ "loss": 0.5847,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 2.1025641025641026,
1728
+ "grad_norm": 0.4282464385032654,
1729
+ "learning_rate": 9.520028396172003e-05,
1730
+ "loss": 0.8587,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 2.111111111111111,
1735
+ "grad_norm": 0.41154712438583374,
1736
+ "learning_rate": 9.451525555096753e-05,
1737
+ "loss": 0.636,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 2.1196581196581197,
1742
+ "grad_norm": 0.40562766790390015,
1743
+ "learning_rate": 9.383048520187344e-05,
1744
+ "loss": 0.6537,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 2.128205128205128,
1749
+ "grad_norm": 0.39767637848854065,
1750
+ "learning_rate": 9.314600513343595e-05,
1751
+ "loss": 0.5577,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 2.1367521367521367,
1756
+ "grad_norm": 0.40367597341537476,
1757
+ "learning_rate": 9.246184755099545e-05,
1758
+ "loss": 1.046,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 2.1452991452991452,
1763
+ "grad_norm": 0.36436665058135986,
1764
+ "learning_rate": 9.177804464471898e-05,
1765
+ "loss": 0.969,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 2.1538461538461537,
1770
+ "grad_norm": 0.44953399896621704,
1771
+ "learning_rate": 9.109462858808586e-05,
1772
+ "loss": 1.1065,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 2.1623931623931623,
1777
+ "grad_norm": 0.4293656051158905,
1778
+ "learning_rate": 9.041163153637381e-05,
1779
+ "loss": 0.6931,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 2.1709401709401708,
1784
+ "grad_norm": 0.6912404298782349,
1785
+ "learning_rate": 8.972908562514598e-05,
1786
+ "loss": 0.8489,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 2.1794871794871793,
1791
+ "grad_norm": 0.5662364363670349,
1792
+ "learning_rate": 8.904702296873912e-05,
1793
+ "loss": 0.7001,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 2.1880341880341883,
1798
+ "grad_norm": 0.43007197976112366,
1799
+ "learning_rate": 8.836547565875227e-05,
1800
+ "loss": 0.6258,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 2.1965811965811968,
1805
+ "grad_norm": 0.4075295925140381,
1806
+ "learning_rate": 8.76844757625372e-05,
1807
+ "loss": 1.0233,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 2.2051282051282053,
1812
+ "grad_norm": 0.4470670521259308,
1813
+ "learning_rate": 8.70040553216892e-05,
1814
+ "loss": 0.5802,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 2.213675213675214,
1819
+ "grad_norm": 0.5310265421867371,
1820
+ "learning_rate": 8.632424635053997e-05,
1821
+ "loss": 0.8648,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 2.2222222222222223,
1826
+ "grad_norm": 0.3991585373878479,
1827
+ "learning_rate": 8.564508083465079e-05,
1828
+ "loss": 0.6131,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 2.230769230769231,
1833
+ "grad_norm": 0.4161868989467621,
1834
+ "learning_rate": 8.496659072930813e-05,
1835
+ "loss": 0.6663,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 2.2393162393162394,
1840
+ "grad_norm": 0.3924509882926941,
1841
+ "learning_rate": 8.428880795801965e-05,
1842
+ "loss": 0.5843,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 2.247863247863248,
1847
+ "grad_norm": 0.4469972550868988,
1848
+ "learning_rate": 8.36117644110124e-05,
1849
+ "loss": 0.9308,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 2.2564102564102564,
1854
+ "grad_norm": 0.43694007396698,
1855
+ "learning_rate": 8.293549194373243e-05,
1856
+ "loss": 0.5301,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 2.264957264957265,
1861
+ "grad_norm": 0.36313438415527344,
1862
+ "learning_rate": 8.226002237534572e-05,
1863
+ "loss": 0.6025,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 2.2735042735042734,
1868
+ "grad_norm": 0.5126502513885498,
1869
+ "learning_rate": 8.158538748724139e-05,
1870
+ "loss": 1.0082,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 2.282051282051282,
1875
+ "grad_norm": 0.7607345581054688,
1876
+ "learning_rate": 8.091161902153595e-05,
1877
+ "loss": 0.8165,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 2.2905982905982905,
1882
+ "grad_norm": 0.40674644708633423,
1883
+ "learning_rate": 8.023874867958027e-05,
1884
+ "loss": 0.9011,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 2.299145299145299,
1889
+ "grad_norm": 0.4444192051887512,
1890
+ "learning_rate": 7.95668081204676e-05,
1891
+ "loss": 0.9077,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 2.3076923076923075,
1896
+ "grad_norm": 0.47018325328826904,
1897
+ "learning_rate": 7.889582895954427e-05,
1898
+ "loss": 0.6565,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 2.316239316239316,
1903
+ "grad_norm": 0.45229724049568176,
1904
+ "learning_rate": 7.822584276692191e-05,
1905
+ "loss": 0.5789,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 2.324786324786325,
1910
+ "grad_norm": 0.4436100125312805,
1911
+ "learning_rate": 7.755688106599241e-05,
1912
+ "loss": 0.5985,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 2.3333333333333335,
1917
+ "grad_norm": 0.43845564126968384,
1918
+ "learning_rate": 7.688897533194424e-05,
1919
+ "loss": 0.7054,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 2.341880341880342,
1924
+ "grad_norm": 0.5257022976875305,
1925
+ "learning_rate": 7.622215699028196e-05,
1926
+ "loss": 0.6775,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 2.3504273504273505,
1931
+ "grad_norm": 0.38463449478149414,
1932
+ "learning_rate": 7.555645741534736e-05,
1933
+ "loss": 0.5418,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 2.358974358974359,
1938
+ "grad_norm": 0.4846791625022888,
1939
+ "learning_rate": 7.489190792884338e-05,
1940
+ "loss": 1.1746,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 2.3675213675213675,
1945
+ "grad_norm": 0.599614143371582,
1946
+ "learning_rate": 7.422853979836034e-05,
1947
+ "loss": 0.9562,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 2.376068376068376,
1952
+ "grad_norm": 0.44910863041877747,
1953
+ "learning_rate": 7.356638423590485e-05,
1954
+ "loss": 0.6637,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 2.3846153846153846,
1959
+ "grad_norm": 0.41623038053512573,
1960
+ "learning_rate": 7.290547239643117e-05,
1961
+ "loss": 0.6137,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 2.393162393162393,
1966
+ "grad_norm": 0.41245952248573303,
1967
+ "learning_rate": 7.224583537637544e-05,
1968
+ "loss": 0.701,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 2.4017094017094016,
1973
+ "grad_norm": 0.437512069940567,
1974
+ "learning_rate": 7.158750421219244e-05,
1975
+ "loss": 1.0071,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 2.41025641025641,
1980
+ "grad_norm": 0.47157779335975647,
1981
+ "learning_rate": 7.093050987889547e-05,
1982
+ "loss": 0.6301,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 2.4188034188034186,
1987
+ "grad_norm": 0.4809150695800781,
1988
+ "learning_rate": 7.027488328859876e-05,
1989
+ "loss": 0.6223,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 2.427350427350427,
1994
+ "grad_norm": 0.4056383967399597,
1995
+ "learning_rate": 6.96206552890632e-05,
1996
+ "loss": 0.7179,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 2.435897435897436,
2001
+ "grad_norm": 0.4516913890838623,
2002
+ "learning_rate": 6.896785666224481e-05,
2003
+ "loss": 0.6584,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 2.4444444444444446,
2008
+ "grad_norm": 0.5465108752250671,
2009
+ "learning_rate": 6.831651812284652e-05,
2010
+ "loss": 0.6704,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 2.452991452991453,
2015
+ "grad_norm": 0.4418526589870453,
2016
+ "learning_rate": 6.766667031687286e-05,
2017
+ "loss": 0.6599,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 2.4615384615384617,
2022
+ "grad_norm": 0.5614168047904968,
2023
+ "learning_rate": 6.701834382018832e-05,
2024
+ "loss": 0.682,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 2.47008547008547,
2029
+ "grad_norm": 0.4477944076061249,
2030
+ "learning_rate": 6.637156913707839e-05,
2031
+ "loss": 0.5673,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 2.4786324786324787,
2036
+ "grad_norm": 0.4335084855556488,
2037
+ "learning_rate": 6.572637669881458e-05,
2038
+ "loss": 0.649,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 2.4871794871794872,
2043
+ "grad_norm": 0.5068711638450623,
2044
+ "learning_rate": 6.508279686222243e-05,
2045
+ "loss": 0.9612,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 2.4957264957264957,
2050
+ "grad_norm": 0.45187613368034363,
2051
+ "learning_rate": 6.444085990825338e-05,
2052
+ "loss": 0.7145,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 2.5042735042735043,
2057
+ "grad_norm": 0.43183228373527527,
2058
+ "learning_rate": 6.380059604055974e-05,
2059
+ "loss": 0.6139,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 2.5128205128205128,
2064
+ "grad_norm": 0.5947943329811096,
2065
+ "learning_rate": 6.316203538407397e-05,
2066
+ "loss": 0.7478,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 2.5213675213675213,
2071
+ "grad_norm": 0.4441166818141937,
2072
+ "learning_rate": 6.252520798359092e-05,
2073
+ "loss": 0.5858,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 2.52991452991453,
2078
+ "grad_norm": 0.4649028778076172,
2079
+ "learning_rate": 6.18901438023543e-05,
2080
+ "loss": 0.611,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 2.5384615384615383,
2085
+ "grad_norm": 0.4889965355396271,
2086
+ "learning_rate": 6.125687272064713e-05,
2087
+ "loss": 0.6749,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 2.547008547008547,
2092
+ "grad_norm": 0.3767229914665222,
2093
+ "learning_rate": 6.0625424534385425e-05,
2094
+ "loss": 0.8812,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 2.5555555555555554,
2099
+ "grad_norm": 0.5386160016059875,
2100
+ "learning_rate": 5.9995828953716695e-05,
2101
+ "loss": 0.6275,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 2.564102564102564,
2106
+ "grad_norm": 0.49474480748176575,
2107
+ "learning_rate": 5.936811560162169e-05,
2108
+ "loss": 0.7034,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 2.5726495726495724,
2113
+ "grad_norm": 0.45355015993118286,
2114
+ "learning_rate": 5.87423140125209e-05,
2115
+ "loss": 0.5933,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 2.5811965811965814,
2120
+ "grad_norm": 0.4447164833545685,
2121
+ "learning_rate": 5.811845363088477e-05,
2122
+ "loss": 0.5839,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 2.58974358974359,
2127
+ "grad_norm": 0.48180091381073,
2128
+ "learning_rate": 5.749656380984844e-05,
2129
+ "loss": 0.6213,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 2.5982905982905984,
2134
+ "grad_norm": 0.46600985527038574,
2135
+ "learning_rate": 5.687667380983037e-05,
2136
+ "loss": 0.5586,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 2.606837606837607,
2141
+ "grad_norm": 0.4069865345954895,
2142
+ "learning_rate": 5.625881279715615e-05,
2143
+ "loss": 0.5236,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 2.6153846153846154,
2148
+ "grad_norm": 0.427859365940094,
2149
+ "learning_rate": 5.5643009842685554e-05,
2150
+ "loss": 1.0195,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 2.623931623931624,
2155
+ "grad_norm": 0.4362795948982239,
2156
+ "learning_rate": 5.502929392044528e-05,
2157
+ "loss": 0.6477,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 2.6324786324786325,
2162
+ "grad_norm": 0.4781452417373657,
2163
+ "learning_rate": 5.4417693906265365e-05,
2164
+ "loss": 0.5336,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 2.641025641025641,
2169
+ "grad_norm": 0.4984622895717621,
2170
+ "learning_rate": 5.380823857642069e-05,
2171
+ "loss": 0.6726,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 2.6495726495726495,
2176
+ "grad_norm": 0.6048721075057983,
2177
+ "learning_rate": 5.3200956606277006e-05,
2178
+ "loss": 0.9416,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 2.658119658119658,
2183
+ "grad_norm": 0.42853838205337524,
2184
+ "learning_rate": 5.259587656894174e-05,
2185
+ "loss": 0.559,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 2.6666666666666665,
2190
+ "grad_norm": 0.5723150968551636,
2191
+ "learning_rate": 5.199302693391959e-05,
2192
+ "loss": 0.7749,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 2.6752136752136755,
2197
+ "grad_norm": 0.5739536285400391,
2198
+ "learning_rate": 5.139243606577302e-05,
2199
+ "loss": 0.7624,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 2.683760683760684,
2204
+ "grad_norm": 0.597714364528656,
2205
+ "learning_rate": 5.0794132222787707e-05,
2206
+ "loss": 0.6945,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 2.6923076923076925,
2211
+ "grad_norm": 0.47430750727653503,
2212
+ "learning_rate": 5.019814355564292e-05,
2213
+ "loss": 0.6807,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 2.700854700854701,
2218
+ "grad_norm": 0.4511941969394684,
2219
+ "learning_rate": 4.960449810608705e-05,
2220
+ "loss": 0.793,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 2.7094017094017095,
2225
+ "grad_norm": 0.4567405879497528,
2226
+ "learning_rate": 4.90132238056182e-05,
2227
+ "loss": 0.6009,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 2.717948717948718,
2232
+ "grad_norm": 0.4015594720840454,
2233
+ "learning_rate": 4.8424348474170014e-05,
2234
+ "loss": 1.0635,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 2.7264957264957266,
2239
+ "grad_norm": 0.502829372882843,
2240
+ "learning_rate": 4.783789981880267e-05,
2241
+ "loss": 0.6601,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 2.735042735042735,
2246
+ "grad_norm": 0.4572563171386719,
2247
+ "learning_rate": 4.725390543239929e-05,
2248
+ "loss": 0.6075,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 2.7435897435897436,
2253
+ "grad_norm": 0.4478137791156769,
2254
+ "learning_rate": 4.667239279236768e-05,
2255
+ "loss": 0.7446,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 2.752136752136752,
2260
+ "grad_norm": 0.533441424369812,
2261
+ "learning_rate": 4.609338925934743e-05,
2262
+ "loss": 0.5933,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 2.7606837606837606,
2267
+ "grad_norm": 0.4419093132019043,
2268
+ "learning_rate": 4.551692207592265e-05,
2269
+ "loss": 0.9199,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 2.769230769230769,
2274
+ "grad_norm": 0.4668772220611572,
2275
+ "learning_rate": 4.494301836534016e-05,
2276
+ "loss": 0.6787,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 2.7777777777777777,
2281
+ "grad_norm": 0.560838520526886,
2282
+ "learning_rate": 4.4371705130233275e-05,
2283
+ "loss": 0.6768,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 2.786324786324786,
2288
+ "grad_norm": 0.47518014907836914,
2289
+ "learning_rate": 4.380300925135138e-05,
2290
+ "loss": 0.6669,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 2.7948717948717947,
2295
+ "grad_norm": 0.43352407217025757,
2296
+ "learning_rate": 4.3236957486295115e-05,
2297
+ "loss": 1.0962,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 2.8034188034188032,
2302
+ "grad_norm": 0.39011329412460327,
2303
+ "learning_rate": 4.267357646825746e-05,
2304
+ "loss": 1.311,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 2.8119658119658117,
2309
+ "grad_norm": 0.4802456200122833,
2310
+ "learning_rate": 4.211289270477047e-05,
2311
+ "loss": 0.5656,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 2.8205128205128203,
2316
+ "grad_norm": 0.4346143305301666,
2317
+ "learning_rate": 4.1554932576458415e-05,
2318
+ "loss": 0.621,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 2.8290598290598292,
2323
+ "grad_norm": 0.546248733997345,
2324
+ "learning_rate": 4.0999722335796075e-05,
2325
+ "loss": 1.156,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 2.8376068376068377,
2330
+ "grad_norm": 0.49097940325737,
2331
+ "learning_rate": 4.044728810587406e-05,
2332
+ "loss": 0.6616,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 2.8461538461538463,
2337
+ "grad_norm": 0.4826516807079315,
2338
+ "learning_rate": 3.989765587916914e-05,
2339
+ "loss": 0.5668,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 2.8547008547008548,
2344
+ "grad_norm": 0.49177631735801697,
2345
+ "learning_rate": 3.935085151632185e-05,
2346
+ "loss": 0.8622,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 2.8632478632478633,
2351
+ "grad_norm": 0.4546498954296112,
2352
+ "learning_rate": 3.8806900744919205e-05,
2353
+ "loss": 0.4802,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 2.871794871794872,
2358
+ "grad_norm": 0.5135761499404907,
2359
+ "learning_rate": 3.826582915828468e-05,
2360
+ "loss": 0.7947,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 2.8803418803418803,
2365
+ "grad_norm": 0.5024504065513611,
2366
+ "learning_rate": 3.7727662214273495e-05,
2367
+ "loss": 0.6771,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 2.888888888888889,
2372
+ "grad_norm": 0.4174403250217438,
2373
+ "learning_rate": 3.719242523407539e-05,
2374
+ "loss": 0.5623,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 2.8974358974358974,
2379
+ "grad_norm": 0.4062444865703583,
2380
+ "learning_rate": 3.666014340102268e-05,
2381
+ "loss": 0.8662,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 2.905982905982906,
2386
+ "grad_norm": 0.435547411441803,
2387
+ "learning_rate": 3.613084175940578e-05,
2388
+ "loss": 0.9646,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 2.9145299145299144,
2393
+ "grad_norm": 0.420063853263855,
2394
+ "learning_rate": 3.5604545213294616e-05,
2395
+ "loss": 1.0064,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 2.9230769230769234,
2400
+ "grad_norm": 0.41142135858535767,
2401
+ "learning_rate": 3.508127852536698e-05,
2402
+ "loss": 0.913,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 2.931623931623932,
2407
+ "grad_norm": 0.5464742183685303,
2408
+ "learning_rate": 3.456106631574336e-05,
2409
+ "loss": 0.7721,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 2.9401709401709404,
2414
+ "grad_norm": 0.4335322678089142,
2415
+ "learning_rate": 3.4043933060828605e-05,
2416
+ "loss": 0.6868,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 2.948717948717949,
2421
+ "grad_norm": 0.43466970324516296,
2422
+ "learning_rate": 3.352990309216022e-05,
2423
+ "loss": 0.9365,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 2.9572649572649574,
2428
+ "grad_norm": 0.6501834988594055,
2429
+ "learning_rate": 3.3019000595263574e-05,
2430
+ "loss": 0.7254,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 2.965811965811966,
2435
+ "grad_norm": 0.4817217290401459,
2436
+ "learning_rate": 3.251124960851408e-05,
2437
+ "loss": 0.5734,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 2.9743589743589745,
2442
+ "grad_norm": 0.5768493413925171,
2443
+ "learning_rate": 3.200667402200586e-05,
2444
+ "loss": 0.725,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 2.982905982905983,
2449
+ "grad_norm": 0.5193359851837158,
2450
+ "learning_rate": 3.1505297576428075e-05,
2451
+ "loss": 0.6118,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 2.9914529914529915,
2456
+ "grad_norm": 0.4567442834377289,
2457
+ "learning_rate": 3.100714386194757e-05,
2458
+ "loss": 0.644,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 3.0,
2463
+ "grad_norm": 0.5161424279212952,
2464
+ "learning_rate": 3.0512236317099175e-05,
2465
+ "loss": 0.5467,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 3.0085470085470085,
2470
+ "grad_norm": 0.432476282119751,
2471
+ "learning_rate": 3.0020598227682795e-05,
2472
+ "loss": 0.5932,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 3.017094017094017,
2477
+ "grad_norm": 0.4859013855457306,
2478
+ "learning_rate": 2.953225272566782e-05,
2479
+ "loss": 0.6396,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 3.0256410256410255,
2484
+ "grad_norm": 0.4495466649532318,
2485
+ "learning_rate": 2.904722278810471e-05,
2486
+ "loss": 0.5486,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 3.034188034188034,
2491
+ "grad_norm": 0.4782976508140564,
2492
+ "learning_rate": 2.8565531236043997e-05,
2493
+ "loss": 0.5215,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 3.0427350427350426,
2498
+ "grad_norm": 0.45352649688720703,
2499
+ "learning_rate": 2.8087200733462425e-05,
2500
+ "loss": 0.6103,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 3.051282051282051,
2505
+ "grad_norm": 0.42064645886421204,
2506
+ "learning_rate": 2.7612253786196664e-05,
2507
+ "loss": 0.8181,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 3.0598290598290596,
2512
+ "grad_norm": 0.44320201873779297,
2513
+ "learning_rate": 2.7140712740884376e-05,
2514
+ "loss": 0.5321,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 3.0683760683760686,
2519
+ "grad_norm": 0.5104656219482422,
2520
+ "learning_rate": 2.667259978391281e-05,
2521
+ "loss": 0.6237,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 3.076923076923077,
2526
+ "grad_norm": 0.5268502235412598,
2527
+ "learning_rate": 2.6207936940374767e-05,
2528
+ "loss": 0.512,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 3.0854700854700856,
2533
+ "grad_norm": 0.477899968624115,
2534
+ "learning_rate": 2.5746746073032625e-05,
2535
+ "loss": 0.7468,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 3.094017094017094,
2540
+ "grad_norm": 0.3833640515804291,
2541
+ "learning_rate": 2.5289048881289256e-05,
2542
+ "loss": 0.4871,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 3.1025641025641026,
2547
+ "grad_norm": 0.4910704493522644,
2548
+ "learning_rate": 2.4834866900167475e-05,
2549
+ "loss": 0.8109,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 3.111111111111111,
2554
+ "grad_norm": 0.45201513171195984,
2555
+ "learning_rate": 2.4384221499296466e-05,
2556
+ "loss": 0.4565,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 3.1196581196581197,
2561
+ "grad_norm": 0.45033562183380127,
2562
+ "learning_rate": 2.393713388190648e-05,
2563
+ "loss": 0.5157,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 3.128205128205128,
2568
+ "grad_norm": 0.41118234395980835,
2569
+ "learning_rate": 2.3493625083831217e-05,
2570
+ "loss": 0.8319,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 3.1367521367521367,
2575
+ "grad_norm": 0.46484169363975525,
2576
+ "learning_rate": 2.3053715972518e-05,
2577
+ "loss": 0.5624,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 3.1452991452991452,
2582
+ "grad_norm": 0.5951083898544312,
2583
+ "learning_rate": 2.2617427246045973e-05,
2584
+ "loss": 0.9742,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 3.1538461538461537,
2589
+ "grad_norm": 0.5053535103797913,
2590
+ "learning_rate": 2.218477943215229e-05,
2591
+ "loss": 0.8724,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 3.1623931623931623,
2596
+ "grad_norm": 0.5111372470855713,
2597
+ "learning_rate": 2.1755792887266234e-05,
2598
+ "loss": 0.6747,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 3.1709401709401708,
2603
+ "grad_norm": 0.5125324726104736,
2604
+ "learning_rate": 2.133048779555129e-05,
2605
+ "loss": 0.8119,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 3.1794871794871793,
2610
+ "grad_norm": 0.5035610198974609,
2611
+ "learning_rate": 2.0908884167955824e-05,
2612
+ "loss": 0.7457,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 3.1880341880341883,
2617
+ "grad_norm": 0.45542699098587036,
2618
+ "learning_rate": 2.0491001841271074e-05,
2619
+ "loss": 0.5188,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 3.1965811965811968,
2624
+ "grad_norm": 0.4475596845149994,
2625
+ "learning_rate": 2.0076860477198313e-05,
2626
+ "loss": 0.4572,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 3.2051282051282053,
2631
+ "grad_norm": 0.47550082206726074,
2632
+ "learning_rate": 1.9666479561423244e-05,
2633
+ "loss": 0.6165,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 3.213675213675214,
2638
+ "grad_norm": 0.5418599843978882,
2639
+ "learning_rate": 1.9259878402699705e-05,
2640
+ "loss": 0.492,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 3.2222222222222223,
2645
+ "grad_norm": 0.47926467657089233,
2646
+ "learning_rate": 1.8857076131940642e-05,
2647
+ "loss": 0.4223,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 3.230769230769231,
2652
+ "grad_norm": 0.4752774238586426,
2653
+ "learning_rate": 1.8458091701318504e-05,
2654
+ "loss": 0.6779,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 3.2393162393162394,
2659
+ "grad_norm": 0.49570101499557495,
2660
+ "learning_rate": 1.806294388337305e-05,
2661
+ "loss": 0.6057,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 3.247863247863248,
2666
+ "grad_norm": 0.4735018014907837,
2667
+ "learning_rate": 1.7671651270128532e-05,
2668
+ "loss": 0.5465,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 3.2564102564102564,
2673
+ "grad_norm": 0.47246113419532776,
2674
+ "learning_rate": 1.7284232272218504e-05,
2675
+ "loss": 0.4708,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 3.264957264957265,
2680
+ "grad_norm": 0.44055983424186707,
2681
+ "learning_rate": 1.69007051180199e-05,
2682
+ "loss": 1.1284,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 3.2735042735042734,
2687
+ "grad_norm": 0.5428217053413391,
2688
+ "learning_rate": 1.652108785279526e-05,
2689
+ "loss": 0.4995,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 3.282051282051282,
2694
+ "grad_norm": 0.499870628118515,
2695
+ "learning_rate": 1.6145398337843652e-05,
2696
+ "loss": 0.4588,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 3.2905982905982905,
2701
+ "grad_norm": 0.4916006326675415,
2702
+ "learning_rate": 1.577365424966034e-05,
2703
+ "loss": 0.4461,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 3.299145299145299,
2708
+ "grad_norm": 0.475249707698822,
2709
+ "learning_rate": 1.540587307910508e-05,
2710
+ "loss": 0.8355,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 3.3076923076923075,
2715
+ "grad_norm": 0.4446876645088196,
2716
+ "learning_rate": 1.504207213057912e-05,
2717
+ "loss": 0.8669,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 3.316239316239316,
2722
+ "grad_norm": 0.49318838119506836,
2723
+ "learning_rate": 1.4682268521211073e-05,
2724
+ "loss": 0.9858,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 3.324786324786325,
2729
+ "grad_norm": 0.4661453068256378,
2730
+ "learning_rate": 1.43264791800515e-05,
2731
+ "loss": 0.5198,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 3.3333333333333335,
2736
+ "grad_norm": 0.44970130920410156,
2737
+ "learning_rate": 1.3974720847276412e-05,
2738
+ "loss": 0.4179,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 3.341880341880342,
2743
+ "grad_norm": 0.48371121287345886,
2744
+ "learning_rate": 1.3627010073399604e-05,
2745
+ "loss": 0.5995,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 3.3504273504273505,
2750
+ "grad_norm": 0.5372329354286194,
2751
+ "learning_rate": 1.328336321849396e-05,
2752
+ "loss": 0.5387,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 3.358974358974359,
2757
+ "grad_norm": 0.4512379467487335,
2758
+ "learning_rate": 1.2943796451421686e-05,
2759
+ "loss": 0.8612,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 3.3675213675213675,
2764
+ "grad_norm": 0.5511676073074341,
2765
+ "learning_rate": 1.2608325749073591e-05,
2766
+ "loss": 0.5139,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 3.376068376068376,
2771
+ "grad_norm": 0.5037629008293152,
2772
+ "learning_rate": 1.227696689561727e-05,
2773
+ "loss": 0.5295,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 3.3846153846153846,
2778
+ "grad_norm": 0.4861893355846405,
2779
+ "learning_rate": 1.1949735481754565e-05,
2780
+ "loss": 0.3975,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 3.393162393162393,
2785
+ "grad_norm": 0.5022242069244385,
2786
+ "learning_rate": 1.1626646903987904e-05,
2787
+ "loss": 0.5914,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 3.4017094017094016,
2792
+ "grad_norm": 0.5696412920951843,
2793
+ "learning_rate": 1.130771636389596e-05,
2794
+ "loss": 0.5474,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 3.41025641025641,
2799
+ "grad_norm": 1.0413963794708252,
2800
+ "learning_rate": 1.0992958867418357e-05,
2801
+ "loss": 0.6993,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 3.4188034188034186,
2806
+ "grad_norm": 0.5105499625205994,
2807
+ "learning_rate": 1.0682389224149647e-05,
2808
+ "loss": 0.5094,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 3.427350427350427,
2813
+ "grad_norm": 0.4821983277797699,
2814
+ "learning_rate": 1.037602204664252e-05,
2815
+ "loss": 0.4672,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 3.435897435897436,
2820
+ "grad_norm": 0.5047407150268555,
2821
+ "learning_rate": 1.0073871749720221e-05,
2822
+ "loss": 0.5717,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 3.4444444444444446,
2827
+ "grad_norm": 0.4420361816883087,
2828
+ "learning_rate": 9.775952549798406e-06,
2829
+ "loss": 0.5139,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 3.452991452991453,
2834
+ "grad_norm": 0.44600561261177063,
2835
+ "learning_rate": 9.482278464216121e-06,
2836
+ "loss": 0.9526,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 3.4615384615384617,
2841
+ "grad_norm": 0.6344321966171265,
2842
+ "learning_rate": 9.192863310576472e-06,
2843
+ "loss": 0.903,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 3.47008547008547,
2848
+ "grad_norm": 0.4921269118785858,
2849
+ "learning_rate": 8.907720706096224e-06,
2850
+ "loss": 1.0396,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 3.4786324786324787,
2855
+ "grad_norm": 0.45052459836006165,
2856
+ "learning_rate": 8.626864066965402e-06,
2857
+ "loss": 0.4986,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 3.4871794871794872,
2862
+ "grad_norm": 0.4790460467338562,
2863
+ "learning_rate": 8.350306607715774e-06,
2864
+ "loss": 0.5851,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 3.4957264957264957,
2869
+ "grad_norm": 0.68207848072052,
2870
+ "learning_rate": 8.07806134059933e-06,
2871
+ "loss": 0.6133,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 3.5042735042735043,
2876
+ "grad_norm": 0.5524874329566956,
2877
+ "learning_rate": 7.810141074975818e-06,
2878
+ "loss": 0.7759,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 3.5128205128205128,
2883
+ "grad_norm": 0.5197821259498596,
2884
+ "learning_rate": 7.546558416710292e-06,
2885
+ "loss": 0.4578,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 3.5213675213675213,
2890
+ "grad_norm": 0.5898919105529785,
2891
+ "learning_rate": 7.287325767579756e-06,
2892
+ "loss": 0.5773,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 3.52991452991453,
2897
+ "grad_norm": 0.5639104247093201,
2898
+ "learning_rate": 7.032455324689902e-06,
2899
+ "loss": 0.5694,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 3.5384615384615383,
2904
+ "grad_norm": 0.4479619264602661,
2905
+ "learning_rate": 6.781959079900957e-06,
2906
+ "loss": 0.7276,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 3.547008547008547,
2911
+ "grad_norm": 0.5495937466621399,
2912
+ "learning_rate": 6.535848819263679e-06,
2913
+ "loss": 0.8734,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 3.5555555555555554,
2918
+ "grad_norm": 0.5533643960952759,
2919
+ "learning_rate": 6.2941361224647e-06,
2920
+ "loss": 0.5099,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 3.564102564102564,
2925
+ "grad_norm": 0.4663257598876953,
2926
+ "learning_rate": 6.056832362281728e-06,
2927
+ "loss": 0.4911,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 3.5726495726495724,
2932
+ "grad_norm": 0.5104941725730896,
2933
+ "learning_rate": 5.823948704048443e-06,
2934
+ "loss": 0.583,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 3.5811965811965814,
2939
+ "grad_norm": 0.5188202261924744,
2940
+ "learning_rate": 5.5954961051291384e-06,
2941
+ "loss": 0.542,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 3.58974358974359,
2946
+ "grad_norm": 0.5502235293388367,
2947
+ "learning_rate": 5.371485314403202e-06,
2948
+ "loss": 0.6601,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 3.5982905982905984,
2953
+ "grad_norm": 0.5603145956993103,
2954
+ "learning_rate": 5.151926871759349e-06,
2955
+ "loss": 0.5393,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 3.606837606837607,
2960
+ "grad_norm": 0.6100255250930786,
2961
+ "learning_rate": 4.936831107599749e-06,
2962
+ "loss": 0.5637,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 3.6153846153846154,
2967
+ "grad_norm": 0.4928048253059387,
2968
+ "learning_rate": 4.7262081423538716e-06,
2969
+ "loss": 0.9873,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 3.623931623931624,
2974
+ "grad_norm": 0.5345721244812012,
2975
+ "learning_rate": 4.5200678860024885e-06,
2976
+ "loss": 0.887,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 3.6324786324786325,
2981
+ "grad_norm": 0.5226996541023254,
2982
+ "learning_rate": 4.3184200376111815e-06,
2983
+ "loss": 0.4535,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 3.641025641025641,
2988
+ "grad_norm": 0.4665580093860626,
2989
+ "learning_rate": 4.121274084874194e-06,
2990
+ "loss": 0.4766,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 3.6495726495726495,
2995
+ "grad_norm": 0.4971340000629425,
2996
+ "learning_rate": 3.928639303667891e-06,
2997
+ "loss": 0.5244,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 3.658119658119658,
3002
+ "grad_norm": 0.49675774574279785,
3003
+ "learning_rate": 3.7405247576144054e-06,
3004
+ "loss": 0.4952,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 3.6666666666666665,
3009
+ "grad_norm": 0.564612627029419,
3010
+ "learning_rate": 3.556939297655115e-06,
3011
+ "loss": 0.7133,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 3.6752136752136755,
3016
+ "grad_norm": 0.5266879200935364,
3017
+ "learning_rate": 3.3778915616342943e-06,
3018
+ "loss": 0.5005,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 3.683760683760684,
3023
+ "grad_norm": 0.47107401490211487,
3024
+ "learning_rate": 3.203389973892579e-06,
3025
+ "loss": 0.4649,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 3.6923076923076925,
3030
+ "grad_norm": 0.52373868227005,
3031
+ "learning_rate": 3.0334427448706847e-06,
3032
+ "loss": 0.5057,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 3.700854700854701,
3037
+ "grad_norm": 0.4677347242832184,
3038
+ "learning_rate": 2.868057870723073e-06,
3039
+ "loss": 0.4749,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 3.7094017094017095,
3044
+ "grad_norm": 0.45977145433425903,
3045
+ "learning_rate": 2.707243132941717e-06,
3046
+ "loss": 0.4782,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 3.717948717948718,
3051
+ "grad_norm": 0.5039238929748535,
3052
+ "learning_rate": 2.5510060979899607e-06,
3053
+ "loss": 0.5701,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 3.7264957264957266,
3058
+ "grad_norm": 0.52474445104599,
3059
+ "learning_rate": 2.3993541169465837e-06,
3060
+ "loss": 1.1264,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 3.735042735042735,
3065
+ "grad_norm": 0.581494152545929,
3066
+ "learning_rate": 2.2522943251597873e-06,
3067
+ "loss": 0.5112,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 3.7435897435897436,
3072
+ "grad_norm": 0.5092493295669556,
3073
+ "learning_rate": 2.1098336419116625e-06,
3074
+ "loss": 0.6031,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 3.752136752136752,
3079
+ "grad_norm": 0.5847536325454712,
3080
+ "learning_rate": 1.971978770092431e-06,
3081
+ "loss": 0.633,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 3.7606837606837606,
3086
+ "grad_norm": 0.6317140460014343,
3087
+ "learning_rate": 1.838736195885238e-06,
3088
+ "loss": 0.8404,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 3.769230769230769,
3093
+ "grad_norm": 0.4925064444541931,
3094
+ "learning_rate": 1.710112188460844e-06,
3095
+ "loss": 0.5501,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 3.7777777777777777,
3100
+ "grad_norm": 0.5513454675674438,
3101
+ "learning_rate": 1.5861127996827597e-06,
3102
+ "loss": 0.4741,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 3.786324786324786,
3107
+ "grad_norm": 0.5285286903381348,
3108
+ "learning_rate": 1.4667438638224062e-06,
3109
+ "loss": 0.4904,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 3.7948717948717947,
3114
+ "grad_norm": 0.5031417012214661,
3115
+ "learning_rate": 1.3520109972846917e-06,
3116
+ "loss": 0.9795,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 3.8034188034188032,
3121
+ "grad_norm": 0.49472323060035706,
3122
+ "learning_rate": 1.2419195983436881e-06,
3123
+ "loss": 0.5859,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 3.8119658119658117,
3128
+ "grad_norm": 0.504725992679596,
3129
+ "learning_rate": 1.1364748468886687e-06,
3130
+ "loss": 1.013,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 3.8205128205128203,
3135
+ "grad_norm": 0.4433304965496063,
3136
+ "learning_rate": 1.0356817041804246e-06,
3137
+ "loss": 1.1472,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 3.8290598290598292,
3142
+ "grad_norm": 0.49413543939590454,
3143
+ "learning_rate": 9.395449126177291e-07,
3144
+ "loss": 0.4891,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 3.8376068376068377,
3149
+ "grad_norm": 0.4493185877799988,
3150
+ "learning_rate": 8.480689955143395e-07,
3151
+ "loss": 0.7415,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 3.8461538461538463,
3156
+ "grad_norm": 0.49365293979644775,
3157
+ "learning_rate": 7.612582568860549e-07,
3158
+ "loss": 0.5212,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 3.8547008547008548,
3163
+ "grad_norm": 0.44033104181289673,
3164
+ "learning_rate": 6.791167812483012e-07,
3165
+ "loss": 0.9516,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 3.8632478632478633,
3170
+ "grad_norm": 0.5583679676055908,
3171
+ "learning_rate": 6.016484334238515e-07,
3172
+ "loss": 0.7344,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 3.871794871794872,
3177
+ "grad_norm": 0.47058144211769104,
3178
+ "learning_rate": 5.288568583610931e-07,
3179
+ "loss": 0.4733,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 3.8803418803418803,
3184
+ "grad_norm": 0.4706791639328003,
3185
+ "learning_rate": 4.607454809624434e-07,
3186
+ "loss": 0.5012,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 3.888888888888889,
3191
+ "grad_norm": 0.484102725982666,
3192
+ "learning_rate": 3.9731750592325587e-07,
3193
+ "loss": 0.4663,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 3.8974358974358974,
3198
+ "grad_norm": 0.4835210144519806,
3199
+ "learning_rate": 3.385759175809966e-07,
3200
+ "loss": 0.514,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 3.905982905982906,
3205
+ "grad_norm": 0.4924904406070709,
3206
+ "learning_rate": 2.845234797748897e-07,
3207
+ "loss": 0.8048,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 3.9145299145299144,
3212
+ "grad_norm": 0.49779048562049866,
3213
+ "learning_rate": 2.3516273571577708e-07,
3214
+ "loss": 0.5174,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 3.9230769230769234,
3219
+ "grad_norm": 0.4864768087863922,
3220
+ "learning_rate": 1.9049600786658073e-07,
3221
+ "loss": 0.5889,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 3.931623931623932,
3226
+ "grad_norm": 0.48100584745407104,
3227
+ "learning_rate": 1.505253978329235e-07,
3228
+ "loss": 0.8333,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 3.9401709401709404,
3233
+ "grad_norm": 0.5254265666007996,
3234
+ "learning_rate": 1.1525278626431934e-07,
3235
+ "loss": 0.5569,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 3.948717948717949,
3240
+ "grad_norm": 0.3904174268245697,
3241
+ "learning_rate": 8.467983276563284e-08,
3242
+ "loss": 1.0959,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 3.9572649572649574,
3247
+ "grad_norm": 0.48969635367393494,
3248
+ "learning_rate": 5.880797581904185e-08,
3249
+ "loss": 0.5382,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 3.965811965811966,
3254
+ "grad_norm": 0.49644437432289124,
3255
+ "learning_rate": 3.763843271631373e-08,
3256
+ "loss": 0.7438,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 3.9743589743589745,
3261
+ "grad_norm": 1.0798722505569458,
3262
+ "learning_rate": 2.1172199501573455e-08,
3263
+ "loss": 0.9713,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 3.982905982905983,
3268
+ "grad_norm": 0.6396527290344238,
3269
+ "learning_rate": 9.410050924374415e-09,
3270
+ "loss": 0.6965,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 3.9914529914529915,
3275
+ "grad_norm": 0.5995266437530518,
3276
+ "learning_rate": 2.3525404033275523e-09,
3277
+ "loss": 0.598,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 4.0,
3282
+ "grad_norm": 0.5415430068969727,
3283
+ "learning_rate": 0.0,
3284
+ "loss": 0.5118,
3285
+ "step": 468
3286
+ }
3287
+ ],
3288
+ "logging_steps": 1,
3289
+ "max_steps": 468,
3290
+ "num_input_tokens_seen": 0,
3291
+ "num_train_epochs": 4,
3292
+ "save_steps": 117,
3293
+ "stateful_callbacks": {
3294
+ "TrainerControl": {
3295
+ "args": {
3296
+ "should_epoch_stop": false,
3297
+ "should_evaluate": false,
3298
+ "should_log": false,
3299
+ "should_save": true,
3300
+ "should_training_stop": true
3301
+ },
3302
+ "attributes": {}
3303
+ }
3304
+ },
3305
+ "total_flos": 9.151813521506304e+16,
3306
+ "train_batch_size": 2,
3307
+ "trial_name": null,
3308
+ "trial_params": null
3309
+ }
checkpoint-468/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c808f6ec67547ffc25e425768bac91068256414f8730443120d2ab7c48580d
3
+ size 6200
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.45.1",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
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
+ }