RayDu0010 commited on
Commit
2f70ee6
·
verified ·
1 Parent(s): 1bb2c9b

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 +54 -0
  2. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/adapter_config.json +39 -0
  3. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/adapter_model.safetensors +3 -0
  4. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/all_results.json +9 -0
  5. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/chat_template.jinja +109 -0
  6. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/config.json +39 -0
  7. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/generation_config.json +12 -0
  8. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/special_tokens_map.json +17 -0
  9. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/tokenizer.json +3 -0
  10. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/tokenizer_config.json +2063 -0
  11. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/train_results.json +9 -0
  12. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/trainer_state.json +288 -0
  13. hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/training_args.bin +3 -0
  14. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/adapter_config.json +39 -0
  15. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/adapter_model.safetensors +3 -0
  16. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/all_results.json +9 -0
  17. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/chat_template.jinja +109 -0
  18. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/config.json +39 -0
  19. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/generation_config.json +12 -0
  20. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/special_tokens_map.json +17 -0
  21. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/tokenizer.json +3 -0
  22. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/tokenizer_config.json +2063 -0
  23. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/train_results.json +9 -0
  24. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/trainer_state.json +288 -0
  25. hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/training_args.bin +3 -0
  26. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/README.md +63 -0
  27. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_config.json +39 -0
  28. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_model.safetensors +3 -0
  29. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/all_results.json +9 -0
  30. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/config.json +35 -0
  31. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/special_tokens_map.json +17 -0
  32. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer.json +3 -0
  33. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer_config.json +2063 -0
  34. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/train_results.json +9 -0
  35. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/trainer_state.json +1982 -0
  36. hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/training_args.bin +3 -0
  37. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/README.md +63 -0
  38. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_config.json +39 -0
  39. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_model.safetensors +3 -0
  40. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/all_results.json +9 -0
  41. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/config.json +35 -0
  42. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/special_tokens_map.json +17 -0
  43. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/tokenizer.json +3 -0
  44. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/tokenizer_config.json +2063 -0
  45. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/train_results.json +9 -0
  46. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/trainer_state.json +1639 -0
  47. hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/training_args.bin +3 -0
  48. hotpotqa_test_knowledge_50_base/2_128_e3_3e-5/README.md +63 -0
  49. hotpotqa_test_knowledge_50_base/2_128_e3_3e-5/adapter_config.json +39 -0
  50. hotpotqa_test_knowledge_50_base/2_128_e3_3e-5/adapter_model.safetensors +3 -0
.gitattributes CHANGED
@@ -57,3 +57,57 @@ barexam_qa_train_knowledge_100_instruct/5_128_e3_3e-5/tokenizer.json filter=lfs
57
  barexam_qa_train_knowledge_100_instruct/6_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
  barexam_qa_train_knowledge_100_instruct/7_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
  barexam_qa_train_knowledge_100_instruct/8_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
  barexam_qa_train_knowledge_100_instruct/6_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
58
  barexam_qa_train_knowledge_100_instruct/7_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
59
  barexam_qa_train_knowledge_100_instruct/8_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
60
+ hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/tokenizer.json filter=lfs diff=lfs merge=lfs -text
61
+ hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/tokenizer.json filter=lfs diff=lfs merge=lfs -text
62
+ hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
63
+ hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
64
+ hotpotqa_test_knowledge_50_base/2_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
65
+ hotpotqa_test_knowledge_50_base/3_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
66
+ hotpotqa_test_knowledge_50_base/4_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
67
+ hotpotqa_test_knowledge_50_base/5_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
68
+ hotpotqa_test_knowledge_50_instruct/0_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
69
+ hotpotqa_test_knowledge_50_instruct/1_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
70
+ hotpotqa_test_knowledge_50_instruct/2_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
71
+ hotpotqa_test_knowledge_50_instruct/3_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
72
+ hotpotqa_test_knowledge_50_instruct/4_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
73
+ hotpotqa_test_knowledge_50_instruct/5_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
74
+ hotpotqa_train_knowledge_50_base/0_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
75
+ hotpotqa_train_knowledge_50_base/10_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
76
+ hotpotqa_train_knowledge_50_base/11_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
77
+ hotpotqa_train_knowledge_50_base/12_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
78
+ hotpotqa_train_knowledge_50_base/13_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
79
+ hotpotqa_train_knowledge_50_base/14_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
80
+ hotpotqa_train_knowledge_50_base/15_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
81
+ hotpotqa_train_knowledge_50_base/16_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
82
+ hotpotqa_train_knowledge_50_base/17_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
83
+ hotpotqa_train_knowledge_50_base/18_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
84
+ hotpotqa_train_knowledge_50_base/19_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
85
+ hotpotqa_train_knowledge_50_base/1_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
86
+ hotpotqa_train_knowledge_50_base/2_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
87
+ hotpotqa_train_knowledge_50_base/3_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
88
+ hotpotqa_train_knowledge_50_base/4_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
89
+ hotpotqa_train_knowledge_50_base/5_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
90
+ hotpotqa_train_knowledge_50_base/6_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
91
+ hotpotqa_train_knowledge_50_base/7_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
92
+ hotpotqa_train_knowledge_50_base/8_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
93
+ hotpotqa_train_knowledge_50_base/9_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
94
+ hotpotqa_train_knowledge_50_instruct/0_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
95
+ hotpotqa_train_knowledge_50_instruct/10_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
96
+ hotpotqa_train_knowledge_50_instruct/11_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
97
+ hotpotqa_train_knowledge_50_instruct/12_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
98
+ hotpotqa_train_knowledge_50_instruct/13_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
99
+ hotpotqa_train_knowledge_50_instruct/14_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
100
+ hotpotqa_train_knowledge_50_instruct/15_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
101
+ hotpotqa_train_knowledge_50_instruct/16_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
102
+ hotpotqa_train_knowledge_50_instruct/17_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
103
+ hotpotqa_train_knowledge_50_instruct/18_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
104
+ hotpotqa_train_knowledge_50_instruct/19_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
105
+ hotpotqa_train_knowledge_50_instruct/1_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
106
+ hotpotqa_train_knowledge_50_instruct/2_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
107
+ hotpotqa_train_knowledge_50_instruct/3_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
108
+ hotpotqa_train_knowledge_50_instruct/4_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
109
+ hotpotqa_train_knowledge_50_instruct/5_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
110
+ hotpotqa_train_knowledge_50_instruct/6_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
111
+ hotpotqa_train_knowledge_50_instruct/7_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
112
+ hotpotqa_train_knowledge_50_instruct/8_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
113
+ hotpotqa_train_knowledge_50_instruct/9_128_e3_3e-5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": false,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "up_proj",
29
+ "k_proj",
30
+ "down_proj",
31
+ "q_proj",
32
+ "o_proj",
33
+ "gate_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7755f47750ba602d4c0d1bd4d6eab9c703219eafa33741dd03c79b6c0f9d51b9
3
+ size 335605144
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 3.9356831750946816e+17,
4
+ "train_loss": 3.96218955618414,
5
+ "train_runtime": 277.7455,
6
+ "train_samples": 2802,
7
+ "train_samples_per_second": 10.088,
8
+ "train_steps_per_second": 0.634
9
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.52.4",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.52.4"
12
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_247|>"
17
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|reserved_special_token_247|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 3.9356831750946816e+17,
4
+ "train_loss": 3.96218955618414,
5
+ "train_runtime": 277.7455,
6
+ "train_samples": 2802,
7
+ "train_samples_per_second": 10.088,
8
+ "train_steps_per_second": 0.634
9
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/trainer_state.json ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 176,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.028530670470756064,
14
+ "grad_norm": 98.07823944091797,
15
+ "learning_rate": 6.666666666666667e-06,
16
+ "loss": 11.8227,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.05706134094151213,
21
+ "grad_norm": 48.8634033203125,
22
+ "learning_rate": 1.5e-05,
23
+ "loss": 10.705,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.08559201141226819,
28
+ "grad_norm": 22.390178680419922,
29
+ "learning_rate": 2.3333333333333336e-05,
30
+ "loss": 7.2769,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.11412268188302425,
35
+ "grad_norm": 11.743159294128418,
36
+ "learning_rate": 2.9997034946550984e-05,
37
+ "loss": 5.1852,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.14265335235378032,
42
+ "grad_norm": 11.406346321105957,
43
+ "learning_rate": 2.98933811055296e-05,
44
+ "loss": 4.8695,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.17118402282453637,
49
+ "grad_norm": 9.969062805175781,
50
+ "learning_rate": 2.9642644716285765e-05,
51
+ "loss": 4.1906,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.19971469329529243,
56
+ "grad_norm": 6.9679951667785645,
57
+ "learning_rate": 2.924730197591674e-05,
58
+ "loss": 3.4173,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.2282453637660485,
63
+ "grad_norm": 13.462809562683105,
64
+ "learning_rate": 2.871125717031052e-05,
65
+ "loss": 4.063,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.25677603423680456,
70
+ "grad_norm": 11.700884819030762,
71
+ "learning_rate": 2.8039804116593743e-05,
72
+ "loss": 3.9671,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.28530670470756064,
77
+ "grad_norm": 9.339689254760742,
78
+ "learning_rate": 2.7239573882987418e-05,
79
+ "loss": 3.4171,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.31383737517831667,
84
+ "grad_norm": 7.5099921226501465,
85
+ "learning_rate": 2.6318469302373453e-05,
86
+ "loss": 3.5813,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.34236804564907275,
91
+ "grad_norm": 6.536746025085449,
92
+ "learning_rate": 2.52855869262962e-05,
93
+ "loss": 3.5958,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.37089871611982883,
98
+ "grad_norm": 8.016010284423828,
99
+ "learning_rate": 2.4151127190157864e-05,
100
+ "loss": 3.6182,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.39942938659058486,
105
+ "grad_norm": 6.370848178863525,
106
+ "learning_rate": 2.2926293676789295e-05,
107
+ "loss": 3.6103,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.42796005706134094,
112
+ "grad_norm": 8.359729766845703,
113
+ "learning_rate": 2.162318247323868e-05,
114
+ "loss": 3.5373,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.456490727532097,
119
+ "grad_norm": 6.346542835235596,
120
+ "learning_rate": 2.0254662713457366e-05,
121
+ "loss": 3.3341,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.48502139800285304,
126
+ "grad_norm": 13.426467895507812,
127
+ "learning_rate": 1.883424948660712e-05,
128
+ "loss": 3.3211,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.5135520684736091,
133
+ "grad_norm": 7.283843994140625,
134
+ "learning_rate": 1.7375970366108225e-05,
135
+ "loss": 3.2597,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.5420827389443652,
140
+ "grad_norm": 9.1486234664917,
141
+ "learning_rate": 1.5894226877547298e-05,
142
+ "loss": 3.4157,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.5706134094151213,
147
+ "grad_norm": 8.91500186920166,
148
+ "learning_rate": 1.4403652273546118e-05,
149
+ "loss": 3.1861,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.5991440798858774,
154
+ "grad_norm": 8.01885986328125,
155
+ "learning_rate": 1.2918967020163978e-05,
156
+ "loss": 3.2207,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.6276747503566333,
161
+ "grad_norm": 13.87535285949707,
162
+ "learning_rate": 1.1454833422006428e-05,
163
+ "loss": 3.2422,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.6562054208273894,
168
+ "grad_norm": 6.999363422393799,
169
+ "learning_rate": 1.0025710821718983e-05,
170
+ "loss": 3.2623,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.6847360912981455,
175
+ "grad_norm": 12.511735916137695,
176
+ "learning_rate": 8.645712803872084e-06,
177
+ "loss": 3.4606,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.7132667617689016,
182
+ "grad_norm": 7.841530799865723,
183
+ "learning_rate": 7.3284678134486685e-06,
184
+ "loss": 2.9957,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.7417974322396577,
189
+ "grad_norm": 7.247511863708496,
190
+ "learning_rate": 6.086984565424345e-06,
191
+ "loss": 2.9632,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.7703281027104137,
196
+ "grad_norm": 6.871656894683838,
197
+ "learning_rate": 4.933523574614447e-06,
198
+ "loss": 3.1,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.7988587731811697,
203
+ "grad_norm": 9.417755126953125,
204
+ "learning_rate": 3.879476074520731e-06,
205
+ "loss": 2.9654,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.8273894436519258,
210
+ "grad_norm": 6.606371879577637,
211
+ "learning_rate": 2.935251520938528e-06,
212
+ "loss": 2.7702,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.8559201141226819,
217
+ "grad_norm": 10.26504898071289,
218
+ "learning_rate": 2.1101747913050855e-06,
219
+ "loss": 2.9336,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.884450784593438,
224
+ "grad_norm": 10.80896282196045,
225
+ "learning_rate": 1.412394095017151e-06,
226
+ "loss": 3.0025,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.912981455064194,
231
+ "grad_norm": 8.550090789794922,
232
+ "learning_rate": 8.488005041679842e-07,
233
+ "loss": 2.9469,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.9415121255349501,
238
+ "grad_norm": 7.228885173797607,
239
+ "learning_rate": 4.2495989939384916e-07,
240
+ "loss": 3.1122,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.9700427960057061,
245
+ "grad_norm": 7.973071575164795,
246
+ "learning_rate": 1.4505800291247207e-07,
247
+ "loss": 2.9233,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.9985734664764622,
252
+ "grad_norm": 7.4301252365112305,
253
+ "learning_rate": 1.1859041590472352e-08,
254
+ "loss": 3.0535,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 1.0,
259
+ "step": 176,
260
+ "total_flos": 3.9356831750946816e+17,
261
+ "train_loss": 3.96218955618414,
262
+ "train_runtime": 277.7455,
263
+ "train_samples_per_second": 10.088,
264
+ "train_steps_per_second": 0.634
265
+ }
266
+ ],
267
+ "logging_steps": 5,
268
+ "max_steps": 176,
269
+ "num_input_tokens_seen": 0,
270
+ "num_train_epochs": 1,
271
+ "save_steps": 500,
272
+ "stateful_callbacks": {
273
+ "TrainerControl": {
274
+ "args": {
275
+ "should_epoch_stop": false,
276
+ "should_evaluate": false,
277
+ "should_log": false,
278
+ "should_save": false,
279
+ "should_training_stop": false
280
+ },
281
+ "attributes": {}
282
+ }
283
+ },
284
+ "total_flos": 3.9356831750946816e+17,
285
+ "train_batch_size": 1,
286
+ "trial_name": null,
287
+ "trial_params": null
288
+ }
hotpotqa_skill_paraphrase_4_base_3epoch/64_e1_3.0e-05/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6862db60ffd6c2d4a1dce55316821419a6e148ca0aecc445e6cdfd3caffc17fe
3
+ size 8081
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": false,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 128,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 64,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "up_proj",
28
+ "q_proj",
29
+ "k_proj",
30
+ "v_proj",
31
+ "o_proj",
32
+ "down_proj",
33
+ "gate_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1bac12a9912ed22832f19e576e20188109ebeffec16a0490193d4d1d0fecb43
3
+ size 335605144
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 3.941173665328005e+17,
4
+ "train_loss": 1.885472126643766,
5
+ "train_runtime": 151.7112,
6
+ "train_samples": 2802,
7
+ "train_samples_per_second": 18.469,
8
+ "train_steps_per_second": 1.16
9
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/chat_template.jinja ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}
2
+ {%- if custom_tools is defined %}
3
+ {%- set tools = custom_tools %}
4
+ {%- endif %}
5
+ {%- if not tools_in_user_message is defined %}
6
+ {%- set tools_in_user_message = true %}
7
+ {%- endif %}
8
+ {%- if not date_string is defined %}
9
+ {%- set date_string = "26 Jul 2024" %}
10
+ {%- endif %}
11
+ {%- if not tools is defined %}
12
+ {%- set tools = none %}
13
+ {%- endif %}
14
+
15
+ {#- This block extracts the system message, so we can slot it into the right place. #}
16
+ {%- if messages[0]['role'] == 'system' %}
17
+ {%- set system_message = messages[0]['content']|trim %}
18
+ {%- set messages = messages[1:] %}
19
+ {%- else %}
20
+ {%- set system_message = "" %}
21
+ {%- endif %}
22
+
23
+ {#- System message + builtin tools #}
24
+ {{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
25
+ {%- if builtin_tools is defined or tools is not none %}
26
+ {{- "Environment: ipython\n" }}
27
+ {%- endif %}
28
+ {%- if builtin_tools is defined %}
29
+ {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
30
+ {%- endif %}
31
+ {{- "Cutting Knowledge Date: December 2023\n" }}
32
+ {{- "Today Date: " + date_string + "\n\n" }}
33
+ {%- if tools is not none and not tools_in_user_message %}
34
+ {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
35
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
36
+ {{- "Do not use variables.\n\n" }}
37
+ {%- for t in tools %}
38
+ {{- t | tojson(indent=4) }}
39
+ {{- "\n\n" }}
40
+ {%- endfor %}
41
+ {%- endif %}
42
+ {{- system_message }}
43
+ {{- "<|eot_id|>" }}
44
+
45
+ {#- Custom tools are passed in a user message with some extra guidance #}
46
+ {%- if tools_in_user_message and not tools is none %}
47
+ {#- Extract the first user message so we can plug it in here #}
48
+ {%- if messages | length != 0 %}
49
+ {%- set first_user_message = messages[0]['content']|trim %}
50
+ {%- set messages = messages[1:] %}
51
+ {%- else %}
52
+ {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
53
+ {%- endif %}
54
+ {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
55
+ {{- "Given the following functions, please respond with a JSON for a function call " }}
56
+ {{- "with its proper arguments that best answers the given prompt.\n\n" }}
57
+ {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
58
+ {{- "Do not use variables.\n\n" }}
59
+ {%- for t in tools %}
60
+ {{- t | tojson(indent=4) }}
61
+ {{- "\n\n" }}
62
+ {%- endfor %}
63
+ {{- first_user_message + "<|eot_id|>"}}
64
+ {%- endif %}
65
+
66
+ {%- for message in messages %}
67
+ {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
68
+ {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
69
+ {%- elif 'tool_calls' in message %}
70
+ {%- if not message.tool_calls|length == 1 %}
71
+ {{- raise_exception("This model only supports single tool-calls at once!") }}
72
+ {%- endif %}
73
+ {%- set tool_call = message.tool_calls[0].function %}
74
+ {%- if builtin_tools is defined and tool_call.name in builtin_tools %}
75
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
76
+ {{- "<|python_tag|>" + tool_call.name + ".call(" }}
77
+ {%- for arg_name, arg_val in tool_call.arguments | items %}
78
+ {{- arg_name + '="' + arg_val + '"' }}
79
+ {%- if not loop.last %}
80
+ {{- ", " }}
81
+ {%- endif %}
82
+ {%- endfor %}
83
+ {{- ")" }}
84
+ {%- else %}
85
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
86
+ {{- '{"name": "' + tool_call.name + '", ' }}
87
+ {{- '"parameters": ' }}
88
+ {{- tool_call.arguments | tojson }}
89
+ {{- "}" }}
90
+ {%- endif %}
91
+ {%- if builtin_tools is defined %}
92
+ {#- This means we're in ipython mode #}
93
+ {{- "<|eom_id|>" }}
94
+ {%- else %}
95
+ {{- "<|eot_id|>" }}
96
+ {%- endif %}
97
+ {%- elif message.role == "tool" or message.role == "ipython" %}
98
+ {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
99
+ {%- if message.content is mapping or message.content is iterable %}
100
+ {{- message.content | tojson }}
101
+ {%- else %}
102
+ {{- message.content }}
103
+ {%- endif %}
104
+ {{- "<|eot_id|>" }}
105
+ {%- endif %}
106
+ {%- endfor %}
107
+ {%- if add_generation_prompt %}
108
+ {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
109
+ {%- endif %}
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 128,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 14336,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 8.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "bfloat16",
36
+ "transformers_version": "4.52.4",
37
+ "use_cache": true,
38
+ "vocab_size": 128256
39
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.52.4"
12
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|reserved_special_token_247|>"
17
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|eot_id|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|reserved_special_token_247|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 3.941173665328005e+17,
4
+ "train_loss": 1.885472126643766,
5
+ "train_runtime": 151.7112,
6
+ "train_samples": 2802,
7
+ "train_samples_per_second": 18.469,
8
+ "train_steps_per_second": 1.16
9
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/trainer_state.json ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 176,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.02849002849002849,
14
+ "grad_norm": 41.54158401489258,
15
+ "learning_rate": 6.666666666666667e-06,
16
+ "loss": 4.6986,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.05698005698005698,
21
+ "grad_norm": 22.764928817749023,
22
+ "learning_rate": 1.5e-05,
23
+ "loss": 4.3109,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.08547008547008547,
28
+ "grad_norm": 10.573023796081543,
29
+ "learning_rate": 2.3333333333333336e-05,
30
+ "loss": 3.3624,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.11396011396011396,
35
+ "grad_norm": 6.423072338104248,
36
+ "learning_rate": 2.9997034946550984e-05,
37
+ "loss": 2.5337,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.14245014245014245,
42
+ "grad_norm": 6.361787796020508,
43
+ "learning_rate": 2.98933811055296e-05,
44
+ "loss": 2.4237,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.17094017094017094,
49
+ "grad_norm": 4.749721527099609,
50
+ "learning_rate": 2.9642644716285765e-05,
51
+ "loss": 2.0534,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.19943019943019943,
56
+ "grad_norm": 3.451364517211914,
57
+ "learning_rate": 2.924730197591674e-05,
58
+ "loss": 1.7088,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.22792022792022792,
63
+ "grad_norm": 8.959653854370117,
64
+ "learning_rate": 2.871125717031052e-05,
65
+ "loss": 2.0079,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.2564102564102564,
70
+ "grad_norm": 7.419877052307129,
71
+ "learning_rate": 2.8039804116593743e-05,
72
+ "loss": 1.9297,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.2849002849002849,
77
+ "grad_norm": 4.485551357269287,
78
+ "learning_rate": 2.7239573882987418e-05,
79
+ "loss": 1.7006,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.31339031339031337,
84
+ "grad_norm": 4.072010517120361,
85
+ "learning_rate": 2.6318469302373453e-05,
86
+ "loss": 1.7362,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.3418803418803419,
91
+ "grad_norm": 3.5165116786956787,
92
+ "learning_rate": 2.52855869262962e-05,
93
+ "loss": 1.791,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.37037037037037035,
98
+ "grad_norm": 3.970125198364258,
99
+ "learning_rate": 2.4151127190157864e-05,
100
+ "loss": 1.8049,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.39886039886039887,
105
+ "grad_norm": 3.4378178119659424,
106
+ "learning_rate": 2.2926293676789295e-05,
107
+ "loss": 1.7725,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.42735042735042733,
112
+ "grad_norm": 4.609078407287598,
113
+ "learning_rate": 2.162318247323868e-05,
114
+ "loss": 1.7165,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.45584045584045585,
119
+ "grad_norm": 3.251359224319458,
120
+ "learning_rate": 2.0254662713457366e-05,
121
+ "loss": 1.6442,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.4843304843304843,
126
+ "grad_norm": 5.737546443939209,
127
+ "learning_rate": 1.883424948660712e-05,
128
+ "loss": 1.6232,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.5128205128205128,
133
+ "grad_norm": 4.057260036468506,
134
+ "learning_rate": 1.7375970366108225e-05,
135
+ "loss": 1.5908,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.5413105413105413,
140
+ "grad_norm": 4.2831315994262695,
141
+ "learning_rate": 1.5894226877547298e-05,
142
+ "loss": 1.7128,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.5698005698005698,
147
+ "grad_norm": 3.8855299949645996,
148
+ "learning_rate": 1.4403652273546118e-05,
149
+ "loss": 1.5593,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.5982905982905983,
154
+ "grad_norm": 3.7846293449401855,
155
+ "learning_rate": 1.2918967020163978e-05,
156
+ "loss": 1.5821,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.6267806267806267,
161
+ "grad_norm": 6.312170505523682,
162
+ "learning_rate": 1.1454833422006428e-05,
163
+ "loss": 1.5836,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.6552706552706553,
168
+ "grad_norm": 3.63012433052063,
169
+ "learning_rate": 1.0025710821718983e-05,
170
+ "loss": 1.584,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.6837606837606838,
175
+ "grad_norm": 5.612448692321777,
176
+ "learning_rate": 8.645712803872084e-06,
177
+ "loss": 1.7054,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.7122507122507122,
182
+ "grad_norm": 3.9694271087646484,
183
+ "learning_rate": 7.3284678134486685e-06,
184
+ "loss": 1.4795,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.7407407407407407,
189
+ "grad_norm": 3.8035147190093994,
190
+ "learning_rate": 6.086984565424345e-06,
191
+ "loss": 1.4751,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.7692307692307693,
196
+ "grad_norm": 3.422909736633301,
197
+ "learning_rate": 4.933523574614447e-06,
198
+ "loss": 1.5283,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.7977207977207977,
203
+ "grad_norm": 4.461482524871826,
204
+ "learning_rate": 3.879476074520731e-06,
205
+ "loss": 1.4482,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.8262108262108262,
210
+ "grad_norm": 3.229851722717285,
211
+ "learning_rate": 2.935251520938528e-06,
212
+ "loss": 1.3772,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.8547008547008547,
217
+ "grad_norm": 4.533471584320068,
218
+ "learning_rate": 2.1101747913050855e-06,
219
+ "loss": 1.4373,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.8831908831908832,
224
+ "grad_norm": 4.994824409484863,
225
+ "learning_rate": 1.412394095017151e-06,
226
+ "loss": 1.4558,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.9116809116809117,
231
+ "grad_norm": 3.992816925048828,
232
+ "learning_rate": 8.488005041679842e-07,
233
+ "loss": 1.4463,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.9401709401709402,
238
+ "grad_norm": 3.7581281661987305,
239
+ "learning_rate": 4.2495989939384916e-07,
240
+ "loss": 1.5126,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.9686609686609686,
245
+ "grad_norm": 3.792056083679199,
246
+ "learning_rate": 1.4505800291247207e-07,
247
+ "loss": 1.4521,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.9971509971509972,
252
+ "grad_norm": 4.3386077880859375,
253
+ "learning_rate": 1.1859041590472352e-08,
254
+ "loss": 1.4799,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 1.0,
259
+ "step": 176,
260
+ "total_flos": 3.941173665328005e+17,
261
+ "train_loss": 1.885472126643766,
262
+ "train_runtime": 151.7112,
263
+ "train_samples_per_second": 18.469,
264
+ "train_steps_per_second": 1.16
265
+ }
266
+ ],
267
+ "logging_steps": 5,
268
+ "max_steps": 176,
269
+ "num_input_tokens_seen": 0,
270
+ "num_train_epochs": 1,
271
+ "save_steps": 500,
272
+ "stateful_callbacks": {
273
+ "TrainerControl": {
274
+ "args": {
275
+ "should_epoch_stop": false,
276
+ "should_evaluate": false,
277
+ "should_log": false,
278
+ "should_save": false,
279
+ "should_training_stop": false
280
+ },
281
+ "attributes": {}
282
+ }
283
+ },
284
+ "total_flos": 3.941173665328005e+17,
285
+ "train_batch_size": 1,
286
+ "trial_name": null,
287
+ "trial_params": null
288
+ }
hotpotqa_skill_paraphrase_4_instruct_3epoch/64_e1_3.0e-05/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82e6575c7eaad6eeba26b1b2ae8bdc165ab078951c886c5486c4becfad525d8e
3
+ size 8081
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B
5
+ tags:
6
+ - alignment-handbook
7
+ - generated_from_trainer
8
+ datasets:
9
+ - data/hotpotqa/test/processed/knowledge_50
10
+ model-index:
11
+ - name: 0_128_e3_3e-5
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # 0_128_e3_3e-5
19
+
20
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the data/hotpotqa/test/processed/knowledge_50 dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 4
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.05
51
+ - num_epochs: 3.0
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.15.2
60
+ - Transformers 4.52.4
61
+ - Pytorch 2.7.0+cu126
62
+ - Datasets 3.6.0
63
+ - Tokenizers 0.21.2
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 256,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "q_proj",
28
+ "gate_proj",
29
+ "v_proj",
30
+ "o_proj",
31
+ "down_proj",
32
+ "up_proj",
33
+ "k_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0fa3bcf3a2a32b41ca909dabbb5384252c18ec8b72131d784cda5fceaf33253
3
+ size 671150064
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.8970279091854377e+18,
4
+ "train_loss": 0.46635930327050884,
5
+ "train_runtime": 1484.7838,
6
+ "train_samples": 14795,
7
+ "train_samples_per_second": 29.893,
8
+ "train_steps_per_second": 0.935
9
+ }
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
+ "rope_theta": 500000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.52.4",
33
+ "use_cache": true,
34
+ "vocab_size": 128256
35
+ }
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|reserved_special_token_247|>"
17
+ }
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384a7e7c676f7be2e5d2e8449c508be9b00e5b18c5b3c39ebc626e96b3f4b988
3
+ size 17210019
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|reserved_special_token_247|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.8970279091854377e+18,
4
+ "train_loss": 0.46635930327050884,
5
+ "train_runtime": 1484.7838,
6
+ "train_samples": 14795,
7
+ "train_samples_per_second": 29.893,
8
+ "train_steps_per_second": 0.935
9
+ }
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1982 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1389,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.010810810810810811,
14
+ "grad_norm": 0.6749756932258606,
15
+ "learning_rate": 1.7142857142857143e-06,
16
+ "loss": 1.6002,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.021621621621621623,
21
+ "grad_norm": 0.6739484667778015,
22
+ "learning_rate": 3.857142857142857e-06,
23
+ "loss": 1.6545,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.032432432432432434,
28
+ "grad_norm": 0.5106654167175293,
29
+ "learning_rate": 6e-06,
30
+ "loss": 1.5524,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.043243243243243246,
35
+ "grad_norm": 0.5350106954574585,
36
+ "learning_rate": 8.142857142857142e-06,
37
+ "loss": 1.627,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.05405405405405406,
42
+ "grad_norm": 0.4918515980243683,
43
+ "learning_rate": 1.0285714285714286e-05,
44
+ "loss": 1.5917,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.06486486486486487,
49
+ "grad_norm": 0.5422373414039612,
50
+ "learning_rate": 1.242857142857143e-05,
51
+ "loss": 1.5633,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.07567567567567568,
56
+ "grad_norm": 0.5008731484413147,
57
+ "learning_rate": 1.4571428571428571e-05,
58
+ "loss": 1.5382,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.08648648648648649,
63
+ "grad_norm": 0.452938973903656,
64
+ "learning_rate": 1.6714285714285716e-05,
65
+ "loss": 1.5515,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.0972972972972973,
70
+ "grad_norm": 0.49676385521888733,
71
+ "learning_rate": 1.8857142857142856e-05,
72
+ "loss": 1.5271,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.10810810810810811,
77
+ "grad_norm": 0.5166845321655273,
78
+ "learning_rate": 2.1e-05,
79
+ "loss": 1.5582,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.11891891891891893,
84
+ "grad_norm": 0.4737708270549774,
85
+ "learning_rate": 2.3142857142857145e-05,
86
+ "loss": 1.454,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.12972972972972974,
91
+ "grad_norm": 0.5474684834480286,
92
+ "learning_rate": 2.5285714285714285e-05,
93
+ "loss": 1.418,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.14054054054054055,
98
+ "grad_norm": 0.5287275314331055,
99
+ "learning_rate": 2.7428571428571428e-05,
100
+ "loss": 1.4695,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.15135135135135136,
105
+ "grad_norm": 0.6109984517097473,
106
+ "learning_rate": 2.9571428571428575e-05,
107
+ "loss": 1.431,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.16216216216216217,
112
+ "grad_norm": 0.6882091164588928,
113
+ "learning_rate": 2.999931924927058e-05,
114
+ "loss": 1.3871,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.17297297297297298,
119
+ "grad_norm": 0.6718704104423523,
120
+ "learning_rate": 2.999655380533103e-05,
121
+ "loss": 1.4817,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.1837837837837838,
126
+ "grad_norm": 0.6657449007034302,
127
+ "learning_rate": 2.999166151316113e-05,
128
+ "loss": 1.4664,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.1945945945945946,
133
+ "grad_norm": 0.6535046100616455,
134
+ "learning_rate": 2.9984643066597815e-05,
135
+ "loss": 1.3768,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.20540540540540542,
140
+ "grad_norm": 0.6701520085334778,
141
+ "learning_rate": 2.997549946101448e-05,
142
+ "loss": 1.2797,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.21621621621621623,
147
+ "grad_norm": 0.6286271214485168,
148
+ "learning_rate": 2.9964231993179804e-05,
149
+ "loss": 1.315,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.22702702702702704,
154
+ "grad_norm": 0.6639678478240967,
155
+ "learning_rate": 2.9950842261073867e-05,
156
+ "loss": 1.3076,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.23783783783783785,
161
+ "grad_norm": 0.6478069424629211,
162
+ "learning_rate": 2.9935332163661465e-05,
163
+ "loss": 1.2784,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.24864864864864866,
168
+ "grad_norm": 0.653148353099823,
169
+ "learning_rate": 2.9917703900622867e-05,
170
+ "loss": 1.3221,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.2594594594594595,
175
+ "grad_norm": 0.6923774480819702,
176
+ "learning_rate": 2.9897959972041778e-05,
177
+ "loss": 1.3407,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.2702702702702703,
182
+ "grad_norm": 0.7054397463798523,
183
+ "learning_rate": 2.9876103178050833e-05,
184
+ "loss": 1.2499,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.2810810810810811,
189
+ "grad_norm": 0.7252037525177002,
190
+ "learning_rate": 2.9852136618434435e-05,
191
+ "loss": 1.1914,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.2918918918918919,
196
+ "grad_norm": 0.8995503187179565,
197
+ "learning_rate": 2.9826063692189152e-05,
198
+ "loss": 1.2278,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.3027027027027027,
203
+ "grad_norm": 0.8531567454338074,
204
+ "learning_rate": 2.9797888097041656e-05,
205
+ "loss": 1.1881,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.31351351351351353,
210
+ "grad_norm": 0.8225644826889038,
211
+ "learning_rate": 2.9767613828924316e-05,
212
+ "loss": 1.1099,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.32432432432432434,
217
+ "grad_norm": 0.7384702563285828,
218
+ "learning_rate": 2.9735245181408466e-05,
219
+ "loss": 1.124,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.33513513513513515,
224
+ "grad_norm": 0.7921214699745178,
225
+ "learning_rate": 2.9700786745095483e-05,
226
+ "loss": 1.1146,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.34594594594594597,
231
+ "grad_norm": 0.8876392841339111,
232
+ "learning_rate": 2.966424340696577e-05,
233
+ "loss": 1.0549,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.3567567567567568,
238
+ "grad_norm": 0.8177557587623596,
239
+ "learning_rate": 2.9625620349685617e-05,
240
+ "loss": 1.1194,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.3675675675675676,
245
+ "grad_norm": 0.9204846620559692,
246
+ "learning_rate": 2.9584923050872218e-05,
247
+ "loss": 1.147,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.3783783783783784,
252
+ "grad_norm": 0.962609052658081,
253
+ "learning_rate": 2.9542157282316822e-05,
254
+ "loss": 1.0603,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.3891891891891892,
259
+ "grad_norm": 0.9691535234451294,
260
+ "learning_rate": 2.9497329109166154e-05,
261
+ "loss": 1.0567,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.4,
266
+ "grad_norm": 0.9528350234031677,
267
+ "learning_rate": 2.9450444889062243e-05,
268
+ "loss": 1.119,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.41081081081081083,
273
+ "grad_norm": 1.0783238410949707,
274
+ "learning_rate": 2.940151127124076e-05,
275
+ "loss": 1.0226,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.42162162162162165,
280
+ "grad_norm": 0.9221756458282471,
281
+ "learning_rate": 2.935053519558802e-05,
282
+ "loss": 1.0075,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.43243243243243246,
287
+ "grad_norm": 0.9663214683532715,
288
+ "learning_rate": 2.929752389165673e-05,
289
+ "loss": 1.0586,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.44324324324324327,
294
+ "grad_norm": 1.1029077768325806,
295
+ "learning_rate": 2.9242484877640706e-05,
296
+ "loss": 0.969,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.4540540540540541,
301
+ "grad_norm": 0.9367722272872925,
302
+ "learning_rate": 2.9185425959308596e-05,
303
+ "loss": 0.9634,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.4648648648648649,
308
+ "grad_norm": 1.0548895597457886,
309
+ "learning_rate": 2.912635522889686e-05,
310
+ "loss": 1.0103,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.4756756756756757,
315
+ "grad_norm": 1.347251534461975,
316
+ "learning_rate": 2.9065281063962106e-05,
317
+ "loss": 0.94,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.4864864864864865,
322
+ "grad_norm": 1.0111850500106812,
323
+ "learning_rate": 2.900221212619297e-05,
324
+ "loss": 0.9342,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.4972972972972973,
329
+ "grad_norm": 0.9622715711593628,
330
+ "learning_rate": 2.893715736018168e-05,
331
+ "loss": 1.0053,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.5081081081081081,
336
+ "grad_norm": 1.0898102521896362,
337
+ "learning_rate": 2.8870125992155527e-05,
338
+ "loss": 0.9361,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.518918918918919,
343
+ "grad_norm": 1.1396633386611938,
344
+ "learning_rate": 2.8801127528668372e-05,
345
+ "loss": 0.921,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.5297297297297298,
350
+ "grad_norm": 0.9959793090820312,
351
+ "learning_rate": 2.87301717552524e-05,
352
+ "loss": 0.8875,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.5405405405405406,
357
+ "grad_norm": 1.1547890901565552,
358
+ "learning_rate": 2.8657268735030316e-05,
359
+ "loss": 0.8682,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.5513513513513514,
364
+ "grad_norm": 1.0546422004699707,
365
+ "learning_rate": 2.8582428807288182e-05,
366
+ "loss": 0.8818,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.5621621621621622,
371
+ "grad_norm": 1.1594375371932983,
372
+ "learning_rate": 2.850566258600903e-05,
373
+ "loss": 0.8826,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.572972972972973,
378
+ "grad_norm": 1.2605596780776978,
379
+ "learning_rate": 2.8426980958367618e-05,
380
+ "loss": 0.8348,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.5837837837837838,
385
+ "grad_norm": 1.194010853767395,
386
+ "learning_rate": 2.8346395083186336e-05,
387
+ "loss": 0.8428,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.5945945945945946,
392
+ "grad_norm": 1.0932097434997559,
393
+ "learning_rate": 2.8263916389352673e-05,
394
+ "loss": 0.7917,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.6054054054054054,
399
+ "grad_norm": 1.2288398742675781,
400
+ "learning_rate": 2.8179556574198312e-05,
401
+ "loss": 0.8138,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.6162162162162163,
406
+ "grad_norm": 1.1970932483673096,
407
+ "learning_rate": 2.80933276018402e-05,
408
+ "loss": 0.8412,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.6270270270270271,
413
+ "grad_norm": 1.0771979093551636,
414
+ "learning_rate": 2.800524170148377e-05,
415
+ "loss": 0.7551,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.6378378378378379,
420
+ "grad_norm": 1.191752552986145,
421
+ "learning_rate": 2.7915311365688562e-05,
422
+ "loss": 0.7675,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.6486486486486487,
427
+ "grad_norm": 1.2224516868591309,
428
+ "learning_rate": 2.78235493485965e-05,
429
+ "loss": 0.7927,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.6594594594594595,
434
+ "grad_norm": 1.2681128978729248,
435
+ "learning_rate": 2.7729968664123056e-05,
436
+ "loss": 0.765,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.6702702702702703,
441
+ "grad_norm": 1.0764217376708984,
442
+ "learning_rate": 2.7634582584111605e-05,
443
+ "loss": 0.7519,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.6810810810810811,
448
+ "grad_norm": 1.1778703927993774,
449
+ "learning_rate": 2.753740463645115e-05,
450
+ "loss": 0.7052,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.6918918918918919,
455
+ "grad_norm": 1.1717065572738647,
456
+ "learning_rate": 2.7438448603157802e-05,
457
+ "loss": 0.7107,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.7027027027027027,
462
+ "grad_norm": 1.1341768503189087,
463
+ "learning_rate": 2.7337728518420143e-05,
464
+ "loss": 0.7493,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.7135135135135136,
469
+ "grad_norm": 1.397209644317627,
470
+ "learning_rate": 2.723525866660889e-05,
471
+ "loss": 0.7303,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.7243243243243244,
476
+ "grad_norm": 1.1951305866241455,
477
+ "learning_rate": 2.713105358025104e-05,
478
+ "loss": 0.7071,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.7351351351351352,
483
+ "grad_norm": 1.187578797340393,
484
+ "learning_rate": 2.7025128037968824e-05,
485
+ "loss": 0.66,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.745945945945946,
490
+ "grad_norm": 1.2162693738937378,
491
+ "learning_rate": 2.6917497062383776e-05,
492
+ "loss": 0.7046,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.7567567567567568,
497
+ "grad_norm": 1.1686859130859375,
498
+ "learning_rate": 2.680817591798619e-05,
499
+ "loss": 0.6775,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 0.7675675675675676,
504
+ "grad_norm": 1.3530421257019043,
505
+ "learning_rate": 2.669718010897026e-05,
506
+ "loss": 0.6515,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 0.7783783783783784,
511
+ "grad_norm": 1.2877717018127441,
512
+ "learning_rate": 2.6584525377035257e-05,
513
+ "loss": 0.633,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 0.7891891891891892,
518
+ "grad_norm": 1.2025889158248901,
519
+ "learning_rate": 2.6470227699152975e-05,
520
+ "loss": 0.6563,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 0.8,
525
+ "grad_norm": 1.236899971961975,
526
+ "learning_rate": 2.635430328530186e-05,
527
+ "loss": 0.6818,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 0.8108108108108109,
532
+ "grad_norm": 1.1630672216415405,
533
+ "learning_rate": 2.6236768576168065e-05,
534
+ "loss": 0.6385,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 0.8216216216216217,
539
+ "grad_norm": 1.5487016439437866,
540
+ "learning_rate": 2.611764024081378e-05,
541
+ "loss": 0.6651,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 0.8324324324324325,
546
+ "grad_norm": 1.2410399913787842,
547
+ "learning_rate": 2.5996935174313215e-05,
548
+ "loss": 0.5957,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 0.8432432432432433,
553
+ "grad_norm": 1.1955680847167969,
554
+ "learning_rate": 2.587467049535645e-05,
555
+ "loss": 0.5786,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 0.8540540540540541,
560
+ "grad_norm": 1.2050449848175049,
561
+ "learning_rate": 2.575086354382167e-05,
562
+ "loss": 0.5923,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 0.8648648648648649,
567
+ "grad_norm": 1.3376110792160034,
568
+ "learning_rate": 2.5625531878315956e-05,
569
+ "loss": 0.6241,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 0.8756756756756757,
574
+ "grad_norm": 1.433042049407959,
575
+ "learning_rate": 2.5498693273685074e-05,
576
+ "loss": 0.5906,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 0.8864864864864865,
581
+ "grad_norm": 1.1621979475021362,
582
+ "learning_rate": 2.5370365718492615e-05,
583
+ "loss": 0.5668,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 0.8972972972972973,
588
+ "grad_norm": 1.1963423490524292,
589
+ "learning_rate": 2.5240567412468816e-05,
590
+ "loss": 0.5354,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 0.9081081081081082,
595
+ "grad_norm": 1.2802984714508057,
596
+ "learning_rate": 2.5109316763929414e-05,
597
+ "loss": 0.6125,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 0.918918918918919,
602
+ "grad_norm": 1.1878982782363892,
603
+ "learning_rate": 2.497663238716495e-05,
604
+ "loss": 0.5889,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 0.9297297297297298,
609
+ "grad_norm": 1.6462504863739014,
610
+ "learning_rate": 2.4842533099800822e-05,
611
+ "loss": 0.5493,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 0.9405405405405406,
616
+ "grad_norm": 1.3050243854522705,
617
+ "learning_rate": 2.4707037920128554e-05,
618
+ "loss": 0.5801,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 0.9513513513513514,
623
+ "grad_norm": 1.1411267518997192,
624
+ "learning_rate": 2.4570166064408556e-05,
625
+ "loss": 0.6013,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 0.9621621621621622,
630
+ "grad_norm": 1.378894567489624,
631
+ "learning_rate": 2.4431936944144818e-05,
632
+ "loss": 0.4858,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 0.972972972972973,
637
+ "grad_norm": 1.3321566581726074,
638
+ "learning_rate": 2.4292370163331936e-05,
639
+ "loss": 0.525,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 0.9837837837837838,
644
+ "grad_norm": 1.2378548383712769,
645
+ "learning_rate": 2.4151485515674837e-05,
646
+ "loss": 0.5759,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 0.9945945945945946,
651
+ "grad_norm": 1.3089052438735962,
652
+ "learning_rate": 2.400930298178155e-05,
653
+ "loss": 0.5343,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.0043243243243243,
658
+ "grad_norm": 1.2367912530899048,
659
+ "learning_rate": 2.3865842726329556e-05,
660
+ "loss": 0.5467,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.0151351351351352,
665
+ "grad_norm": 1.1718990802764893,
666
+ "learning_rate": 2.3721125095205935e-05,
667
+ "loss": 0.4462,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.025945945945946,
672
+ "grad_norm": 1.3019416332244873,
673
+ "learning_rate": 2.357517061262189e-05,
674
+ "loss": 0.4097,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.0367567567567568,
679
+ "grad_norm": 1.4085646867752075,
680
+ "learning_rate": 2.3427999978201956e-05,
681
+ "loss": 0.5282,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.0475675675675675,
686
+ "grad_norm": 1.1572306156158447,
687
+ "learning_rate": 2.3279634064048308e-05,
688
+ "loss": 0.4134,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.0583783783783784,
693
+ "grad_norm": 1.244713306427002,
694
+ "learning_rate": 2.3130093911780642e-05,
695
+ "loss": 0.4335,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.0691891891891891,
700
+ "grad_norm": 1.173665165901184,
701
+ "learning_rate": 2.2979400729552014e-05,
702
+ "loss": 0.444,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.08,
707
+ "grad_norm": 1.407321810722351,
708
+ "learning_rate": 2.2827575889041007e-05,
709
+ "loss": 0.4337,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.0908108108108108,
714
+ "grad_norm": 1.3847451210021973,
715
+ "learning_rate": 2.267464092242078e-05,
716
+ "loss": 0.4213,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.1016216216216217,
721
+ "grad_norm": 1.4645717144012451,
722
+ "learning_rate": 2.2520617519305325e-05,
723
+ "loss": 0.4171,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.1124324324324324,
728
+ "grad_norm": 1.3133924007415771,
729
+ "learning_rate": 2.2365527523673368e-05,
730
+ "loss": 0.4461,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.1232432432432433,
735
+ "grad_norm": 1.4021127223968506,
736
+ "learning_rate": 2.2209392930770424e-05,
737
+ "loss": 0.4047,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.134054054054054,
742
+ "grad_norm": 1.2070517539978027,
743
+ "learning_rate": 2.2052235883989355e-05,
744
+ "loss": 0.4069,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.144864864864865,
749
+ "grad_norm": 1.3282095193862915,
750
+ "learning_rate": 2.189407867172997e-05,
751
+ "loss": 0.406,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.1556756756756756,
756
+ "grad_norm": 1.159316062927246,
757
+ "learning_rate": 2.1734943724237986e-05,
758
+ "loss": 0.4207,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.1664864864864866,
763
+ "grad_norm": 1.5306358337402344,
764
+ "learning_rate": 2.157485361042398e-05,
765
+ "loss": 0.388,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.1772972972972973,
770
+ "grad_norm": 1.1564973592758179,
771
+ "learning_rate": 2.1413831034662536e-05,
772
+ "loss": 0.395,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.1881081081081082,
777
+ "grad_norm": 1.439918875694275,
778
+ "learning_rate": 2.1251898833572303e-05,
779
+ "loss": 0.3825,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.1989189189189189,
784
+ "grad_norm": 1.30429208278656,
785
+ "learning_rate": 2.1089079972777238e-05,
786
+ "loss": 0.3605,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.2097297297297298,
791
+ "grad_norm": 1.2694649696350098,
792
+ "learning_rate": 2.092539754364957e-05,
793
+ "loss": 0.3555,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.2205405405405405,
798
+ "grad_norm": 1.301515817642212,
799
+ "learning_rate": 2.07608747600349e-05,
800
+ "loss": 0.3516,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.2313513513513514,
805
+ "grad_norm": 1.297397255897522,
806
+ "learning_rate": 2.0595534954959984e-05,
807
+ "loss": 0.3977,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.2421621621621621,
812
+ "grad_norm": 1.3568118810653687,
813
+ "learning_rate": 2.0429401577323576e-05,
814
+ "loss": 0.3798,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.252972972972973,
819
+ "grad_norm": 1.360713243484497,
820
+ "learning_rate": 2.0262498188570855e-05,
821
+ "loss": 0.3432,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.2637837837837838,
826
+ "grad_norm": 1.4393284320831299,
827
+ "learning_rate": 2.0094848459351853e-05,
828
+ "loss": 0.34,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.2745945945945947,
833
+ "grad_norm": 1.3435497283935547,
834
+ "learning_rate": 1.992647616616447e-05,
835
+ "loss": 0.3989,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.2854054054054054,
840
+ "grad_norm": 1.312248945236206,
841
+ "learning_rate": 1.9757405187982397e-05,
842
+ "loss": 0.3532,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.2962162162162163,
847
+ "grad_norm": 1.5269815921783447,
848
+ "learning_rate": 1.9587659502868546e-05,
849
+ "loss": 0.3891,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.307027027027027,
854
+ "grad_norm": 1.4130357503890991,
855
+ "learning_rate": 1.9417263184574453e-05,
856
+ "loss": 0.3713,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.3178378378378377,
861
+ "grad_norm": 1.3583375215530396,
862
+ "learning_rate": 1.9246240399126036e-05,
863
+ "loss": 0.3474,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.3286486486486486,
868
+ "grad_norm": 1.3835967779159546,
869
+ "learning_rate": 1.907461540139633e-05,
870
+ "loss": 0.3497,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.3394594594594595,
875
+ "grad_norm": 1.390000820159912,
876
+ "learning_rate": 1.8902412531665613e-05,
877
+ "loss": 0.3002,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.3502702702702702,
882
+ "grad_norm": 1.2552826404571533,
883
+ "learning_rate": 1.872965621216938e-05,
884
+ "loss": 0.2847,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.361081081081081,
889
+ "grad_norm": 1.3595759868621826,
890
+ "learning_rate": 1.855637094363474e-05,
891
+ "loss": 0.3211,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.3718918918918919,
896
+ "grad_norm": 1.2867708206176758,
897
+ "learning_rate": 1.8382581301805676e-05,
898
+ "loss": 0.3547,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.3827027027027028,
903
+ "grad_norm": 1.43692946434021,
904
+ "learning_rate": 1.8208311933957606e-05,
905
+ "loss": 0.3251,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 1.3935135135135135,
910
+ "grad_norm": 1.396464467048645,
911
+ "learning_rate": 1.80335875554019e-05,
912
+ "loss": 0.2924,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 1.4043243243243242,
917
+ "grad_norm": 1.2472106218338013,
918
+ "learning_rate": 1.7858432945980645e-05,
919
+ "loss": 0.3178,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 1.4151351351351351,
924
+ "grad_norm": 1.4300161600112915,
925
+ "learning_rate": 1.7682872946552352e-05,
926
+ "loss": 0.3295,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 1.425945945945946,
931
+ "grad_norm": 1.3491531610488892,
932
+ "learning_rate": 1.750693245546893e-05,
933
+ "loss": 0.3242,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 1.4367567567567567,
938
+ "grad_norm": 1.2698180675506592,
939
+ "learning_rate": 1.7330636425044553e-05,
940
+ "loss": 0.2917,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 1.4475675675675674,
945
+ "grad_norm": 1.3012919425964355,
946
+ "learning_rate": 1.7154009858016867e-05,
947
+ "loss": 0.3006,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 1.4583783783783784,
952
+ "grad_norm": 1.333957314491272,
953
+ "learning_rate": 1.697707780400102e-05,
954
+ "loss": 0.2756,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 1.4691891891891893,
959
+ "grad_norm": 1.436802625656128,
960
+ "learning_rate": 1.67998653559371e-05,
961
+ "loss": 0.3122,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 1.48,
966
+ "grad_norm": 1.6837379932403564,
967
+ "learning_rate": 1.6622397646531352e-05,
968
+ "loss": 0.2826,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 1.4908108108108107,
973
+ "grad_norm": 1.2060457468032837,
974
+ "learning_rate": 1.644469984469182e-05,
975
+ "loss": 0.2958,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 1.5016216216216216,
980
+ "grad_norm": 1.5616896152496338,
981
+ "learning_rate": 1.6266797151958815e-05,
982
+ "loss": 0.3542,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 1.5124324324324325,
987
+ "grad_norm": 1.284088134765625,
988
+ "learning_rate": 1.6088714798930806e-05,
989
+ "loss": 0.3139,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 1.5232432432432432,
994
+ "grad_norm": 1.1483250856399536,
995
+ "learning_rate": 1.59104780416861e-05,
996
+ "loss": 0.2875,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 1.534054054054054,
1001
+ "grad_norm": 1.4885141849517822,
1002
+ "learning_rate": 1.5732112158200995e-05,
1003
+ "loss": 0.2942,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 1.5448648648648649,
1008
+ "grad_norm": 1.228744626045227,
1009
+ "learning_rate": 1.5553642444764808e-05,
1010
+ "loss": 0.2939,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 1.5556756756756758,
1015
+ "grad_norm": 1.2387549877166748,
1016
+ "learning_rate": 1.5375094212392253e-05,
1017
+ "loss": 0.2882,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 1.5664864864864865,
1022
+ "grad_norm": 1.2862504720687866,
1023
+ "learning_rate": 1.5196492783233815e-05,
1024
+ "loss": 0.2975,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 1.5772972972972972,
1029
+ "grad_norm": 1.3139840364456177,
1030
+ "learning_rate": 1.501786348698446e-05,
1031
+ "loss": 0.2802,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 1.588108108108108,
1036
+ "grad_norm": 1.3352205753326416,
1037
+ "learning_rate": 1.4839231657291343e-05,
1038
+ "loss": 0.2577,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 1.598918918918919,
1043
+ "grad_norm": 1.234085202217102,
1044
+ "learning_rate": 1.4660622628160921e-05,
1045
+ "loss": 0.2855,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 1.6097297297297297,
1050
+ "grad_norm": 1.0972801446914673,
1051
+ "learning_rate": 1.4482061730366009e-05,
1052
+ "loss": 0.2314,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 1.6205405405405404,
1057
+ "grad_norm": 1.3880709409713745,
1058
+ "learning_rate": 1.4303574287853324e-05,
1059
+ "loss": 0.2443,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 1.6313513513513513,
1064
+ "grad_norm": 1.198792576789856,
1065
+ "learning_rate": 1.4125185614151967e-05,
1066
+ "loss": 0.217,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 1.6421621621621623,
1071
+ "grad_norm": 1.3121585845947266,
1072
+ "learning_rate": 1.3946921008783418e-05,
1073
+ "loss": 0.2606,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 1.652972972972973,
1078
+ "grad_norm": 1.3656197786331177,
1079
+ "learning_rate": 1.3768805753673465e-05,
1080
+ "loss": 0.2372,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 1.6637837837837837,
1085
+ "grad_norm": 1.1282933950424194,
1086
+ "learning_rate": 1.359086510956668e-05,
1087
+ "loss": 0.2716,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 1.6745945945945946,
1092
+ "grad_norm": 1.2672842741012573,
1093
+ "learning_rate": 1.3413124312443874e-05,
1094
+ "loss": 0.2448,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 1.6854054054054055,
1099
+ "grad_norm": 1.3546538352966309,
1100
+ "learning_rate": 1.3235608569943059e-05,
1101
+ "loss": 0.2314,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 1.6962162162162162,
1106
+ "grad_norm": 1.421842336654663,
1107
+ "learning_rate": 1.3058343057784458e-05,
1108
+ "loss": 0.2107,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 1.707027027027027,
1113
+ "grad_norm": 1.2018187046051025,
1114
+ "learning_rate": 1.2881352916199988e-05,
1115
+ "loss": 0.2513,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 1.7178378378378378,
1120
+ "grad_norm": 1.2349228858947754,
1121
+ "learning_rate": 1.270466324636786e-05,
1122
+ "loss": 0.2437,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 1.7286486486486488,
1127
+ "grad_norm": 1.2098289728164673,
1128
+ "learning_rate": 1.252829910685263e-05,
1129
+ "loss": 0.2504,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 1.7394594594594595,
1134
+ "grad_norm": 1.5244630575180054,
1135
+ "learning_rate": 1.2352285510051324e-05,
1136
+ "loss": 0.2744,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 1.7502702702702702,
1141
+ "grad_norm": 1.1220543384552002,
1142
+ "learning_rate": 1.2176647418646156e-05,
1143
+ "loss": 0.27,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 1.761081081081081,
1148
+ "grad_norm": 1.3971467018127441,
1149
+ "learning_rate": 1.2001409742064245e-05,
1150
+ "loss": 0.2063,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 1.771891891891892,
1155
+ "grad_norm": 1.285480260848999,
1156
+ "learning_rate": 1.1826597332944873e-05,
1157
+ "loss": 0.2465,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 1.7827027027027027,
1162
+ "grad_norm": 1.1862159967422485,
1163
+ "learning_rate": 1.1652234983614848e-05,
1164
+ "loss": 0.1919,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 1.7935135135135134,
1169
+ "grad_norm": 1.2218137979507446,
1170
+ "learning_rate": 1.1478347422572396e-05,
1171
+ "loss": 0.2234,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 1.8043243243243243,
1176
+ "grad_norm": 1.3611098527908325,
1177
+ "learning_rate": 1.1304959310980097e-05,
1178
+ "loss": 0.242,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 1.8151351351351352,
1183
+ "grad_norm": 1.190139889717102,
1184
+ "learning_rate": 1.113209523916737e-05,
1185
+ "loss": 0.2234,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 1.825945945945946,
1190
+ "grad_norm": 1.226676344871521,
1191
+ "learning_rate": 1.0959779723143024e-05,
1192
+ "loss": 0.2093,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 1.8367567567567566,
1197
+ "grad_norm": 1.5197325944900513,
1198
+ "learning_rate": 1.0788037201118346e-05,
1199
+ "loss": 0.1876,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 1.8475675675675676,
1204
+ "grad_norm": 1.2957510948181152,
1205
+ "learning_rate": 1.0616892030041184e-05,
1206
+ "loss": 0.1993,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 1.8583783783783785,
1211
+ "grad_norm": 1.3621931076049805,
1212
+ "learning_rate": 1.0446368482141612e-05,
1213
+ "loss": 0.2042,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 1.8691891891891892,
1218
+ "grad_norm": 1.3100106716156006,
1219
+ "learning_rate": 1.027649074148956e-05,
1220
+ "loss": 0.2088,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 1.88,
1225
+ "grad_norm": 1.2206536531448364,
1226
+ "learning_rate": 1.0107282900565009e-05,
1227
+ "loss": 0.1825,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 1.8908108108108108,
1232
+ "grad_norm": 1.2510806322097778,
1233
+ "learning_rate": 9.938768956841077e-06,
1234
+ "loss": 0.1935,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 1.9016216216216217,
1239
+ "grad_norm": 1.1333528757095337,
1240
+ "learning_rate": 9.770972809380696e-06,
1241
+ "loss": 0.2062,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 1.9124324324324324,
1246
+ "grad_norm": 1.1528996229171753,
1247
+ "learning_rate": 9.603918255447141e-06,
1248
+ "loss": 0.1802,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 1.9232432432432431,
1253
+ "grad_norm": 1.113772988319397,
1254
+ "learning_rate": 9.437628987129084e-06,
1255
+ "loss": 0.1865,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 1.934054054054054,
1260
+ "grad_norm": 1.3337033987045288,
1261
+ "learning_rate": 9.272128587980498e-06,
1262
+ "loss": 0.2258,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 1.944864864864865,
1267
+ "grad_norm": 1.5289134979248047,
1268
+ "learning_rate": 9.107440529675971e-06,
1269
+ "loss": 0.1924,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 1.9556756756756757,
1274
+ "grad_norm": 1.144655704498291,
1275
+ "learning_rate": 8.943588168681937e-06,
1276
+ "loss": 0.1913,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 1.9664864864864864,
1281
+ "grad_norm": 1.1703957319259644,
1282
+ "learning_rate": 8.780594742944159e-06,
1283
+ "loss": 0.1671,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 1.9772972972972973,
1288
+ "grad_norm": 1.2245736122131348,
1289
+ "learning_rate": 8.618483368592088e-06,
1290
+ "loss": 0.1922,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 1.9881081081081082,
1295
+ "grad_norm": 1.141701102256775,
1296
+ "learning_rate": 8.457277036660463e-06,
1297
+ "loss": 0.1909,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 1.998918918918919,
1302
+ "grad_norm": 1.3344765901565552,
1303
+ "learning_rate": 8.296998609828704e-06,
1304
+ "loss": 0.1666,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.0086486486486486,
1309
+ "grad_norm": 1.3570910692214966,
1310
+ "learning_rate": 8.13767081917841e-06,
1311
+ "loss": 0.1632,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.0194594594594593,
1316
+ "grad_norm": 1.010612964630127,
1317
+ "learning_rate": 7.97931626096964e-06,
1318
+ "loss": 0.1403,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.0302702702702704,
1323
+ "grad_norm": 1.2923632860183716,
1324
+ "learning_rate": 7.821957393436202e-06,
1325
+ "loss": 0.1433,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.041081081081081,
1330
+ "grad_norm": 1.1319085359573364,
1331
+ "learning_rate": 7.665616533600628e-06,
1332
+ "loss": 0.15,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.051891891891892,
1337
+ "grad_norm": 1.172631025314331,
1338
+ "learning_rate": 7.5103158541090665e-06,
1339
+ "loss": 0.1367,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.0627027027027025,
1344
+ "grad_norm": 1.079500675201416,
1345
+ "learning_rate": 7.356077380086726e-06,
1346
+ "loss": 0.1169,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.0735135135135137,
1351
+ "grad_norm": 1.3374136686325073,
1352
+ "learning_rate": 7.202922986014228e-06,
1353
+ "loss": 0.1247,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.0843243243243244,
1358
+ "grad_norm": 1.0975528955459595,
1359
+ "learning_rate": 7.050874392625302e-06,
1360
+ "loss": 0.1366,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 2.095135135135135,
1365
+ "grad_norm": 1.2024213075637817,
1366
+ "learning_rate": 6.899953163826292e-06,
1367
+ "loss": 0.1312,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 2.1059459459459458,
1372
+ "grad_norm": 1.082950472831726,
1373
+ "learning_rate": 6.7501807036379125e-06,
1374
+ "loss": 0.1357,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 2.116756756756757,
1379
+ "grad_norm": 1.2047678232192993,
1380
+ "learning_rate": 6.601578253159698e-06,
1381
+ "loss": 0.151,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 2.1275675675675676,
1386
+ "grad_norm": 1.2053114175796509,
1387
+ "learning_rate": 6.454166887557508e-06,
1388
+ "loss": 0.1277,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 2.1383783783783783,
1393
+ "grad_norm": 1.0474656820297241,
1394
+ "learning_rate": 6.307967513074605e-06,
1395
+ "loss": 0.1319,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 2.149189189189189,
1400
+ "grad_norm": 1.2605841159820557,
1401
+ "learning_rate": 6.163000864066698e-06,
1402
+ "loss": 0.1478,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 2.16,
1407
+ "grad_norm": 0.9077703952789307,
1408
+ "learning_rate": 6.019287500061326e-06,
1409
+ "loss": 0.1534,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 2.170810810810811,
1414
+ "grad_norm": 1.0507147312164307,
1415
+ "learning_rate": 5.876847802842052e-06,
1416
+ "loss": 0.1381,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 2.1816216216216215,
1421
+ "grad_norm": 1.0697144269943237,
1422
+ "learning_rate": 5.73570197355788e-06,
1423
+ "loss": 0.1324,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 2.1924324324324322,
1428
+ "grad_norm": 1.0238703489303589,
1429
+ "learning_rate": 5.595870029858268e-06,
1430
+ "loss": 0.1278,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 2.2032432432432434,
1435
+ "grad_norm": 1.0087915658950806,
1436
+ "learning_rate": 5.4573718030541965e-06,
1437
+ "loss": 0.1288,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 2.214054054054054,
1442
+ "grad_norm": 0.9904815554618835,
1443
+ "learning_rate": 5.320226935305609e-06,
1444
+ "loss": 0.1173,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 2.224864864864865,
1449
+ "grad_norm": 1.0402568578720093,
1450
+ "learning_rate": 5.184454876835746e-06,
1451
+ "loss": 0.1243,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 2.2356756756756755,
1456
+ "grad_norm": 1.169760823249817,
1457
+ "learning_rate": 5.05007488317265e-06,
1458
+ "loss": 0.1212,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 2.2464864864864866,
1463
+ "grad_norm": 1.160381555557251,
1464
+ "learning_rate": 4.917106012418294e-06,
1465
+ "loss": 0.1327,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 2.2572972972972973,
1470
+ "grad_norm": 0.8716002106666565,
1471
+ "learning_rate": 4.7855671225457225e-06,
1472
+ "loss": 0.1173,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 2.268108108108108,
1477
+ "grad_norm": 0.8988707065582275,
1478
+ "learning_rate": 4.655476868724566e-06,
1479
+ "loss": 0.1179,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 2.2789189189189187,
1484
+ "grad_norm": 1.1103434562683105,
1485
+ "learning_rate": 4.526853700675325e-06,
1486
+ "loss": 0.1284,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 2.28972972972973,
1491
+ "grad_norm": 1.0457454919815063,
1492
+ "learning_rate": 4.399715860052781e-06,
1493
+ "loss": 0.1293,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 2.3005405405405406,
1498
+ "grad_norm": 0.9258773326873779,
1499
+ "learning_rate": 4.274081377858909e-06,
1500
+ "loss": 0.0914,
1501
+ "step": 1065
1502
+ },
1503
+ {
1504
+ "epoch": 2.3113513513513513,
1505
+ "grad_norm": 1.0390188694000244,
1506
+ "learning_rate": 4.149968071885682e-06,
1507
+ "loss": 0.1125,
1508
+ "step": 1070
1509
+ },
1510
+ {
1511
+ "epoch": 2.322162162162162,
1512
+ "grad_norm": 1.0505141019821167,
1513
+ "learning_rate": 4.027393544188129e-06,
1514
+ "loss": 0.122,
1515
+ "step": 1075
1516
+ },
1517
+ {
1518
+ "epoch": 2.332972972972973,
1519
+ "grad_norm": 1.2161805629730225,
1520
+ "learning_rate": 3.9063751785879365e-06,
1521
+ "loss": 0.109,
1522
+ "step": 1080
1523
+ },
1524
+ {
1525
+ "epoch": 2.343783783783784,
1526
+ "grad_norm": 1.097092628479004,
1527
+ "learning_rate": 3.786930138208046e-06,
1528
+ "loss": 0.1149,
1529
+ "step": 1085
1530
+ },
1531
+ {
1532
+ "epoch": 2.3545945945945945,
1533
+ "grad_norm": 0.751530647277832,
1534
+ "learning_rate": 3.6690753630385436e-06,
1535
+ "loss": 0.1093,
1536
+ "step": 1090
1537
+ },
1538
+ {
1539
+ "epoch": 2.3654054054054052,
1540
+ "grad_norm": 0.966195821762085,
1541
+ "learning_rate": 3.552827567534186e-06,
1542
+ "loss": 0.1116,
1543
+ "step": 1095
1544
+ },
1545
+ {
1546
+ "epoch": 2.3762162162162164,
1547
+ "grad_norm": 1.1819593906402588,
1548
+ "learning_rate": 3.4382032382439036e-06,
1549
+ "loss": 0.1167,
1550
+ "step": 1100
1551
+ },
1552
+ {
1553
+ "epoch": 2.387027027027027,
1554
+ "grad_norm": 0.9405239224433899,
1555
+ "learning_rate": 3.3252186314726447e-06,
1556
+ "loss": 0.1174,
1557
+ "step": 1105
1558
+ },
1559
+ {
1560
+ "epoch": 2.3978378378378378,
1561
+ "grad_norm": 1.1678102016448975,
1562
+ "learning_rate": 3.213889770975881e-06,
1563
+ "loss": 0.1196,
1564
+ "step": 1110
1565
+ },
1566
+ {
1567
+ "epoch": 2.4086486486486485,
1568
+ "grad_norm": 0.9688264727592468,
1569
+ "learning_rate": 3.1042324456870514e-06,
1570
+ "loss": 0.119,
1571
+ "step": 1115
1572
+ },
1573
+ {
1574
+ "epoch": 2.4194594594594596,
1575
+ "grad_norm": 0.8630348443984985,
1576
+ "learning_rate": 2.996262207478356e-06,
1577
+ "loss": 0.1265,
1578
+ "step": 1120
1579
+ },
1580
+ {
1581
+ "epoch": 2.4302702702702703,
1582
+ "grad_norm": 0.9478833079338074,
1583
+ "learning_rate": 2.8899943689551493e-06,
1584
+ "loss": 0.122,
1585
+ "step": 1125
1586
+ },
1587
+ {
1588
+ "epoch": 2.441081081081081,
1589
+ "grad_norm": 0.9283960461616516,
1590
+ "learning_rate": 2.7854440012842684e-06,
1591
+ "loss": 0.1087,
1592
+ "step": 1130
1593
+ },
1594
+ {
1595
+ "epoch": 2.4518918918918917,
1596
+ "grad_norm": 0.8862292766571045,
1597
+ "learning_rate": 2.6826259320565903e-06,
1598
+ "loss": 0.1025,
1599
+ "step": 1135
1600
+ },
1601
+ {
1602
+ "epoch": 2.462702702702703,
1603
+ "grad_norm": 1.147686243057251,
1604
+ "learning_rate": 2.581554743184158e-06,
1605
+ "loss": 0.1315,
1606
+ "step": 1140
1607
+ },
1608
+ {
1609
+ "epoch": 2.4735135135135136,
1610
+ "grad_norm": 0.9898723363876343,
1611
+ "learning_rate": 2.482244768832146e-06,
1612
+ "loss": 0.1242,
1613
+ "step": 1145
1614
+ },
1615
+ {
1616
+ "epoch": 2.4843243243243243,
1617
+ "grad_norm": 1.0704761743545532,
1618
+ "learning_rate": 2.384710093385929e-06,
1619
+ "loss": 0.115,
1620
+ "step": 1150
1621
+ },
1622
+ {
1623
+ "epoch": 2.495135135135135,
1624
+ "grad_norm": 0.9278268814086914,
1625
+ "learning_rate": 2.288964549453633e-06,
1626
+ "loss": 0.1071,
1627
+ "step": 1155
1628
+ },
1629
+ {
1630
+ "epoch": 2.505945945945946,
1631
+ "grad_norm": 0.8467145562171936,
1632
+ "learning_rate": 2.1950217159043197e-06,
1633
+ "loss": 0.114,
1634
+ "step": 1160
1635
+ },
1636
+ {
1637
+ "epoch": 2.516756756756757,
1638
+ "grad_norm": 1.036379337310791,
1639
+ "learning_rate": 2.102894915942243e-06,
1640
+ "loss": 0.1097,
1641
+ "step": 1165
1642
+ },
1643
+ {
1644
+ "epoch": 2.5275675675675675,
1645
+ "grad_norm": 0.9519475102424622,
1646
+ "learning_rate": 2.0125972152172777e-06,
1647
+ "loss": 0.1218,
1648
+ "step": 1170
1649
+ },
1650
+ {
1651
+ "epoch": 2.538378378378378,
1652
+ "grad_norm": 0.8463801741600037,
1653
+ "learning_rate": 1.924141419971949e-06,
1654
+ "loss": 0.0968,
1655
+ "step": 1175
1656
+ },
1657
+ {
1658
+ "epoch": 2.5491891891891894,
1659
+ "grad_norm": 0.900498628616333,
1660
+ "learning_rate": 1.8375400752251943e-06,
1661
+ "loss": 0.1054,
1662
+ "step": 1180
1663
+ },
1664
+ {
1665
+ "epoch": 2.56,
1666
+ "grad_norm": 0.8663133382797241,
1667
+ "learning_rate": 1.75280546299322e-06,
1668
+ "loss": 0.0968,
1669
+ "step": 1185
1670
+ },
1671
+ {
1672
+ "epoch": 2.5708108108108108,
1673
+ "grad_norm": 0.8068374395370483,
1674
+ "learning_rate": 1.6699496005476244e-06,
1675
+ "loss": 0.099,
1676
+ "step": 1190
1677
+ },
1678
+ {
1679
+ "epoch": 2.581621621621622,
1680
+ "grad_norm": 0.7136590480804443,
1681
+ "learning_rate": 1.5889842387110742e-06,
1682
+ "loss": 0.1047,
1683
+ "step": 1195
1684
+ },
1685
+ {
1686
+ "epoch": 2.5924324324324326,
1687
+ "grad_norm": 0.948045551776886,
1688
+ "learning_rate": 1.5099208601907777e-06,
1689
+ "loss": 0.1039,
1690
+ "step": 1200
1691
+ },
1692
+ {
1693
+ "epoch": 2.6032432432432433,
1694
+ "grad_norm": 0.7788717150688171,
1695
+ "learning_rate": 1.4327706779499927e-06,
1696
+ "loss": 0.0927,
1697
+ "step": 1205
1698
+ },
1699
+ {
1700
+ "epoch": 2.614054054054054,
1701
+ "grad_norm": 0.8725752830505371,
1702
+ "learning_rate": 1.3575446336177506e-06,
1703
+ "loss": 0.099,
1704
+ "step": 1210
1705
+ },
1706
+ {
1707
+ "epoch": 2.6248648648648647,
1708
+ "grad_norm": 0.8788983225822449,
1709
+ "learning_rate": 1.2842533959371066e-06,
1710
+ "loss": 0.116,
1711
+ "step": 1215
1712
+ },
1713
+ {
1714
+ "epoch": 2.6356756756756754,
1715
+ "grad_norm": 0.6774969100952148,
1716
+ "learning_rate": 1.2129073592520685e-06,
1717
+ "loss": 0.1077,
1718
+ "step": 1220
1719
+ },
1720
+ {
1721
+ "epoch": 2.6464864864864865,
1722
+ "grad_norm": 0.8134023547172546,
1723
+ "learning_rate": 1.1435166420334436e-06,
1724
+ "loss": 0.0987,
1725
+ "step": 1225
1726
+ },
1727
+ {
1728
+ "epoch": 2.6572972972972972,
1729
+ "grad_norm": 0.9484908580780029,
1730
+ "learning_rate": 1.0760910854438104e-06,
1731
+ "loss": 0.104,
1732
+ "step": 1230
1733
+ },
1734
+ {
1735
+ "epoch": 2.668108108108108,
1736
+ "grad_norm": 1.2464313507080078,
1737
+ "learning_rate": 1.0106402519418173e-06,
1738
+ "loss": 0.1009,
1739
+ "step": 1235
1740
+ },
1741
+ {
1742
+ "epoch": 2.678918918918919,
1743
+ "grad_norm": 0.9004675149917603,
1744
+ "learning_rate": 9.471734239260288e-07,
1745
+ "loss": 0.1111,
1746
+ "step": 1240
1747
+ },
1748
+ {
1749
+ "epoch": 2.68972972972973,
1750
+ "grad_norm": 0.7725552916526794,
1751
+ "learning_rate": 8.856996024184477e-07,
1752
+ "loss": 0.0994,
1753
+ "step": 1245
1754
+ },
1755
+ {
1756
+ "epoch": 2.7005405405405405,
1757
+ "grad_norm": 1.1223211288452148,
1758
+ "learning_rate": 8.262275057879926e-07,
1759
+ "loss": 0.0939,
1760
+ "step": 1250
1761
+ },
1762
+ {
1763
+ "epoch": 2.711351351351351,
1764
+ "grad_norm": 0.8283373117446899,
1765
+ "learning_rate": 7.6876556851401e-07,
1766
+ "loss": 0.108,
1767
+ "step": 1255
1768
+ },
1769
+ {
1770
+ "epoch": 2.722162162162162,
1771
+ "grad_norm": 0.9991348385810852,
1772
+ "learning_rate": 7.133219399901097e-07,
1773
+ "loss": 0.1004,
1774
+ "step": 1260
1775
+ },
1776
+ {
1777
+ "epoch": 2.732972972972973,
1778
+ "grad_norm": 0.8724759221076965,
1779
+ "learning_rate": 6.599044833683632e-07,
1780
+ "loss": 0.099,
1781
+ "step": 1265
1782
+ },
1783
+ {
1784
+ "epoch": 2.7437837837837837,
1785
+ "grad_norm": 0.7052216529846191,
1786
+ "learning_rate": 6.085207744441529e-07,
1787
+ "loss": 0.1017,
1788
+ "step": 1270
1789
+ },
1790
+ {
1791
+ "epoch": 2.7545945945945944,
1792
+ "grad_norm": 0.71845543384552,
1793
+ "learning_rate": 5.591781005817542e-07,
1794
+ "loss": 0.1031,
1795
+ "step": 1275
1796
+ },
1797
+ {
1798
+ "epoch": 2.7654054054054056,
1799
+ "grad_norm": 0.7921403050422668,
1800
+ "learning_rate": 5.11883459680812e-07,
1801
+ "loss": 0.1163,
1802
+ "step": 1280
1803
+ },
1804
+ {
1805
+ "epoch": 2.7762162162162163,
1806
+ "grad_norm": 1.055810570716858,
1807
+ "learning_rate": 4.6664355918389244e-07,
1808
+ "loss": 0.1208,
1809
+ "step": 1285
1810
+ },
1811
+ {
1812
+ "epoch": 2.787027027027027,
1813
+ "grad_norm": 0.9086781740188599,
1814
+ "learning_rate": 4.234648151252063e-07,
1815
+ "loss": 0.0968,
1816
+ "step": 1290
1817
+ },
1818
+ {
1819
+ "epoch": 2.7978378378378377,
1820
+ "grad_norm": 0.786642849445343,
1821
+ "learning_rate": 3.823533512206845e-07,
1822
+ "loss": 0.0949,
1823
+ "step": 1295
1824
+ },
1825
+ {
1826
+ "epoch": 2.8086486486486484,
1827
+ "grad_norm": 0.7988888621330261,
1828
+ "learning_rate": 3.4331499799948484e-07,
1829
+ "loss": 0.0983,
1830
+ "step": 1300
1831
+ },
1832
+ {
1833
+ "epoch": 2.8194594594594595,
1834
+ "grad_norm": 0.8628491759300232,
1835
+ "learning_rate": 3.063552919770984e-07,
1836
+ "loss": 0.1036,
1837
+ "step": 1305
1838
+ },
1839
+ {
1840
+ "epoch": 2.8302702702702702,
1841
+ "grad_norm": 0.9562894701957703,
1842
+ "learning_rate": 2.7147947487014434e-07,
1843
+ "loss": 0.1116,
1844
+ "step": 1310
1845
+ },
1846
+ {
1847
+ "epoch": 2.841081081081081,
1848
+ "grad_norm": 0.8303439617156982,
1849
+ "learning_rate": 2.38692492852986e-07,
1850
+ "loss": 0.0981,
1851
+ "step": 1315
1852
+ },
1853
+ {
1854
+ "epoch": 2.851891891891892,
1855
+ "grad_norm": 0.7052004933357239,
1856
+ "learning_rate": 2.0799899585623894e-07,
1857
+ "loss": 0.1065,
1858
+ "step": 1320
1859
+ },
1860
+ {
1861
+ "epoch": 2.8627027027027028,
1862
+ "grad_norm": 0.8546080589294434,
1863
+ "learning_rate": 1.7940333690731004e-07,
1864
+ "loss": 0.1014,
1865
+ "step": 1325
1866
+ },
1867
+ {
1868
+ "epoch": 2.8735135135135135,
1869
+ "grad_norm": 0.9116050601005554,
1870
+ "learning_rate": 1.5290957151304795e-07,
1871
+ "loss": 0.0956,
1872
+ "step": 1330
1873
+ },
1874
+ {
1875
+ "epoch": 2.884324324324324,
1876
+ "grad_norm": 0.8937197923660278,
1877
+ "learning_rate": 1.2852145708457498e-07,
1878
+ "loss": 0.1015,
1879
+ "step": 1335
1880
+ },
1881
+ {
1882
+ "epoch": 2.895135135135135,
1883
+ "grad_norm": 0.7416398525238037,
1884
+ "learning_rate": 1.0624245240439811e-07,
1885
+ "loss": 0.101,
1886
+ "step": 1340
1887
+ },
1888
+ {
1889
+ "epoch": 2.905945945945946,
1890
+ "grad_norm": 0.8376498222351074,
1891
+ "learning_rate": 8.607571713588502e-08,
1892
+ "loss": 0.1156,
1893
+ "step": 1345
1894
+ },
1895
+ {
1896
+ "epoch": 2.9167567567567567,
1897
+ "grad_norm": 0.795005738735199,
1898
+ "learning_rate": 6.802411137514897e-08,
1899
+ "loss": 0.0931,
1900
+ "step": 1350
1901
+ },
1902
+ {
1903
+ "epoch": 2.9275675675675674,
1904
+ "grad_norm": 0.8672885298728943,
1905
+ "learning_rate": 5.20901952454167e-08,
1906
+ "loss": 0.1028,
1907
+ "step": 1355
1908
+ },
1909
+ {
1910
+ "epoch": 2.9383783783783786,
1911
+ "grad_norm": 0.8281853795051575,
1912
+ "learning_rate": 3.827622853395551e-08,
1913
+ "loss": 0.1112,
1914
+ "step": 1360
1915
+ },
1916
+ {
1917
+ "epoch": 2.9491891891891893,
1918
+ "grad_norm": 0.7827093005180359,
1919
+ "learning_rate": 2.6584170371578008e-08,
1920
+ "loss": 0.1049,
1921
+ "step": 1365
1922
+ },
1923
+ {
1924
+ "epoch": 2.96,
1925
+ "grad_norm": 0.9035359025001526,
1926
+ "learning_rate": 1.701567895479761e-08,
1927
+ "loss": 0.1101,
1928
+ "step": 1370
1929
+ },
1930
+ {
1931
+ "epoch": 2.9708108108108107,
1932
+ "grad_norm": 0.763901948928833,
1933
+ "learning_rate": 9.572111310653387e-09,
1934
+ "loss": 0.114,
1935
+ "step": 1375
1936
+ },
1937
+ {
1938
+ "epoch": 2.9816216216216214,
1939
+ "grad_norm": 0.7890019416809082,
1940
+ "learning_rate": 4.254523104260666e-09,
1941
+ "loss": 0.0989,
1942
+ "step": 1380
1943
+ },
1944
+ {
1945
+ "epoch": 2.9924324324324325,
1946
+ "grad_norm": 0.8369008898735046,
1947
+ "learning_rate": 1.0636684890874548e-09,
1948
+ "loss": 0.1054,
1949
+ "step": 1385
1950
+ },
1951
+ {
1952
+ "epoch": 3.0,
1953
+ "step": 1389,
1954
+ "total_flos": 1.8970279091854377e+18,
1955
+ "train_loss": 0.46635930327050884,
1956
+ "train_runtime": 1484.7838,
1957
+ "train_samples_per_second": 29.893,
1958
+ "train_steps_per_second": 0.935
1959
+ }
1960
+ ],
1961
+ "logging_steps": 5,
1962
+ "max_steps": 1389,
1963
+ "num_input_tokens_seen": 0,
1964
+ "num_train_epochs": 3,
1965
+ "save_steps": 20,
1966
+ "stateful_callbacks": {
1967
+ "TrainerControl": {
1968
+ "args": {
1969
+ "should_epoch_stop": false,
1970
+ "should_evaluate": false,
1971
+ "should_log": false,
1972
+ "should_save": false,
1973
+ "should_training_stop": false
1974
+ },
1975
+ "attributes": {}
1976
+ }
1977
+ },
1978
+ "total_flos": 1.8970279091854377e+18,
1979
+ "train_batch_size": 2,
1980
+ "trial_name": null,
1981
+ "trial_params": null
1982
+ }
hotpotqa_test_knowledge_50_base/0_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca2c8fad61cb5da023e117eb207700e10c3f0189451255b0c236d77f226fd46
3
+ size 8273
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B
5
+ tags:
6
+ - alignment-handbook
7
+ - generated_from_trainer
8
+ datasets:
9
+ - data/hotpotqa/test/processed/knowledge_50
10
+ model-index:
11
+ - name: 1_128_e3_3e-5
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # 1_128_e3_3e-5
19
+
20
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the data/hotpotqa/test/processed/knowledge_50 dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 4
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.05
51
+ - num_epochs: 3.0
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.15.2
60
+ - Transformers 4.52.4
61
+ - Pytorch 2.7.0+cu126
62
+ - Datasets 3.6.0
63
+ - Tokenizers 0.21.2
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 256,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "v_proj",
28
+ "k_proj",
29
+ "o_proj",
30
+ "up_proj",
31
+ "down_proj",
32
+ "q_proj",
33
+ "gate_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed4d41ecf7958a8a30a5c6c928360a38dd3d50f62f800bcd8d0ec4147294b27
3
+ size 671150064
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.508233453999489e+18,
4
+ "train_loss": 0.4364819198012456,
5
+ "train_runtime": 1183.9617,
6
+ "train_samples": 12174,
7
+ "train_samples_per_second": 30.847,
8
+ "train_steps_per_second": 0.965
9
+ }
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 131072,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": {
23
+ "factor": 8.0,
24
+ "high_freq_factor": 4.0,
25
+ "low_freq_factor": 1.0,
26
+ "original_max_position_embeddings": 8192,
27
+ "rope_type": "llama3"
28
+ },
29
+ "rope_theta": 500000.0,
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "bfloat16",
32
+ "transformers_version": "4.52.4",
33
+ "use_cache": true,
34
+ "vocab_size": 128256
35
+ }
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|reserved_special_token_247|>"
17
+ }
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:384a7e7c676f7be2e5d2e8449c508be9b00e5b18c5b3c39ebc626e96b3f4b988
3
+ size 17210019
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/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
+ "clean_up_tokenization_spaces": true,
2054
+ "eos_token": "<|end_of_text|>",
2055
+ "extra_special_tokens": {},
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|reserved_special_token_247|>",
2062
+ "tokenizer_class": "PreTrainedTokenizer"
2063
+ }
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 1.508233453999489e+18,
4
+ "train_loss": 0.4364819198012456,
5
+ "train_runtime": 1183.9617,
6
+ "train_samples": 12174,
7
+ "train_samples_per_second": 30.847,
8
+ "train_steps_per_second": 0.965
9
+ }
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/trainer_state.json ADDED
@@ -0,0 +1,1639 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 1143,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.013140604467805518,
14
+ "grad_norm": 0.6000319719314575,
15
+ "learning_rate": 2.068965517241379e-06,
16
+ "loss": 1.4972,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.026281208935611037,
21
+ "grad_norm": 0.5496951937675476,
22
+ "learning_rate": 4.655172413793104e-06,
23
+ "loss": 1.5573,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.03942181340341656,
28
+ "grad_norm": 0.5497358441352844,
29
+ "learning_rate": 7.241379310344828e-06,
30
+ "loss": 1.5677,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.052562417871222074,
35
+ "grad_norm": 0.47274050116539,
36
+ "learning_rate": 9.827586206896551e-06,
37
+ "loss": 1.5092,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.0657030223390276,
42
+ "grad_norm": 0.5257453918457031,
43
+ "learning_rate": 1.2413793103448277e-05,
44
+ "loss": 1.5321,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.07884362680683311,
49
+ "grad_norm": 0.49069836735725403,
50
+ "learning_rate": 1.5e-05,
51
+ "loss": 1.4581,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.09198423127463863,
56
+ "grad_norm": 0.6515851616859436,
57
+ "learning_rate": 1.7586206896551724e-05,
58
+ "loss": 1.4119,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.10512483574244415,
63
+ "grad_norm": 0.4764103591442108,
64
+ "learning_rate": 2.017241379310345e-05,
65
+ "loss": 1.4419,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.11826544021024968,
70
+ "grad_norm": 0.49834540486335754,
71
+ "learning_rate": 2.275862068965517e-05,
72
+ "loss": 1.461,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.1314060446780552,
77
+ "grad_norm": 0.5335782170295715,
78
+ "learning_rate": 2.5344827586206897e-05,
79
+ "loss": 1.3978,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.1445466491458607,
84
+ "grad_norm": 0.5069740414619446,
85
+ "learning_rate": 2.793103448275862e-05,
86
+ "loss": 1.3683,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.15768725361366623,
91
+ "grad_norm": 0.5438121557235718,
92
+ "learning_rate": 2.999993712163665e-05,
93
+ "loss": 1.3693,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.17082785808147175,
98
+ "grad_norm": 0.631446897983551,
99
+ "learning_rate": 2.9997736434270605e-05,
100
+ "loss": 1.3212,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.18396846254927726,
105
+ "grad_norm": 0.5521685481071472,
106
+ "learning_rate": 2.9992392355875752e-05,
107
+ "loss": 1.3559,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.19710906701708278,
112
+ "grad_norm": 0.6499108076095581,
113
+ "learning_rate": 2.9983906006522986e-05,
114
+ "loss": 1.2451,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.2102496714848883,
119
+ "grad_norm": 0.6416671872138977,
120
+ "learning_rate": 2.9972279164875014e-05,
121
+ "loss": 1.2699,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.2233902759526938,
126
+ "grad_norm": 0.6594803333282471,
127
+ "learning_rate": 2.9957514267813553e-05,
128
+ "loss": 1.2558,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.23653088042049936,
133
+ "grad_norm": 0.6575009822845459,
134
+ "learning_rate": 2.993961440992859e-05,
135
+ "loss": 1.2514,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.24967148488830487,
140
+ "grad_norm": 0.6749443411827087,
141
+ "learning_rate": 2.9918583342869767e-05,
142
+ "loss": 1.1903,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.2628120893561104,
147
+ "grad_norm": 0.7291126251220703,
148
+ "learning_rate": 2.989442547456011e-05,
149
+ "loss": 1.1976,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.2759526938239159,
154
+ "grad_norm": 0.8062726855278015,
155
+ "learning_rate": 2.986714586827211e-05,
156
+ "loss": 1.1337,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.2890932982917214,
161
+ "grad_norm": 0.7285217046737671,
162
+ "learning_rate": 2.9836750241566558e-05,
163
+ "loss": 1.1208,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.30223390275952694,
168
+ "grad_norm": 0.7911546230316162,
169
+ "learning_rate": 2.9803244965094165e-05,
170
+ "loss": 1.0985,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.31537450722733246,
175
+ "grad_norm": 0.8114403486251831,
176
+ "learning_rate": 2.976663706126034e-05,
177
+ "loss": 1.082,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.328515111695138,
182
+ "grad_norm": 0.771315336227417,
183
+ "learning_rate": 2.972693420275336e-05,
184
+ "loss": 1.1007,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.3416557161629435,
189
+ "grad_norm": 0.7282198667526245,
190
+ "learning_rate": 2.9684144710936236e-05,
191
+ "loss": 1.1099,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.354796320630749,
196
+ "grad_norm": 0.9147740006446838,
197
+ "learning_rate": 2.9638277554102636e-05,
198
+ "loss": 1.0721,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.3679369250985545,
203
+ "grad_norm": 0.8092377781867981,
204
+ "learning_rate": 2.9589342345597218e-05,
205
+ "loss": 1.0411,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.38107752956636004,
210
+ "grad_norm": 0.8536360263824463,
211
+ "learning_rate": 2.953734934180073e-05,
212
+ "loss": 0.9824,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.39421813403416556,
217
+ "grad_norm": 0.9517012238502502,
218
+ "learning_rate": 2.9482309439980404e-05,
219
+ "loss": 0.9272,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.4073587385019711,
224
+ "grad_norm": 0.829008162021637,
225
+ "learning_rate": 2.9424234176005957e-05,
226
+ "loss": 1.0328,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.4204993429697766,
231
+ "grad_norm": 0.9455755352973938,
232
+ "learning_rate": 2.9363135721931798e-05,
233
+ "loss": 0.9775,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.4336399474375821,
238
+ "grad_norm": 0.9267396926879883,
239
+ "learning_rate": 2.9299026883445846e-05,
240
+ "loss": 0.964,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.4467805519053876,
245
+ "grad_norm": 0.9962680339813232,
246
+ "learning_rate": 2.9231921097185604e-05,
247
+ "loss": 0.9039,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.45992115637319314,
252
+ "grad_norm": 0.9546060562133789,
253
+ "learning_rate": 2.916183242792194e-05,
254
+ "loss": 0.9568,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.4730617608409987,
259
+ "grad_norm": 1.0466433763504028,
260
+ "learning_rate": 2.9088775565611248e-05,
261
+ "loss": 0.8752,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.48620236530880423,
266
+ "grad_norm": 0.9733150005340576,
267
+ "learning_rate": 2.901276582231656e-05,
268
+ "loss": 0.8709,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.49934296977660975,
273
+ "grad_norm": 1.132362723350525,
274
+ "learning_rate": 2.893381912899826e-05,
275
+ "loss": 0.8662,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.5124835742444153,
280
+ "grad_norm": 1.0795292854309082,
281
+ "learning_rate": 2.8851952032175136e-05,
282
+ "loss": 0.8259,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.5256241787122208,
287
+ "grad_norm": 1.2181341648101807,
288
+ "learning_rate": 2.8767181690456345e-05,
289
+ "loss": 0.8681,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.5387647831800263,
294
+ "grad_norm": 1.0852538347244263,
295
+ "learning_rate": 2.867952587094512e-05,
296
+ "loss": 0.8088,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.5519053876478318,
301
+ "grad_norm": 0.9409130215644836,
302
+ "learning_rate": 2.8589002945514987e-05,
303
+ "loss": 0.8163,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.5650459921156373,
308
+ "grad_norm": 1.0253455638885498,
309
+ "learning_rate": 2.8495631886959126e-05,
310
+ "loss": 0.7571,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.5781865965834428,
315
+ "grad_norm": 1.0371079444885254,
316
+ "learning_rate": 2.8399432265013887e-05,
317
+ "loss": 0.7087,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.5913272010512484,
322
+ "grad_norm": 1.0996919870376587,
323
+ "learning_rate": 2.8300424242257125e-05,
324
+ "loss": 0.7642,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.6044678055190539,
329
+ "grad_norm": 1.1715346574783325,
330
+ "learning_rate": 2.8198628569882328e-05,
331
+ "loss": 0.7629,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.6176084099868594,
336
+ "grad_norm": 1.1301043033599854,
337
+ "learning_rate": 2.809406658334933e-05,
338
+ "loss": 0.7807,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.6307490144546649,
343
+ "grad_norm": 1.1367380619049072,
344
+ "learning_rate": 2.7986760197912594e-05,
345
+ "loss": 0.7807,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.6438896189224704,
350
+ "grad_norm": 1.2245783805847168,
351
+ "learning_rate": 2.7876731904027994e-05,
352
+ "loss": 0.7522,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.657030223390276,
357
+ "grad_norm": 1.1590607166290283,
358
+ "learning_rate": 2.7764004762638977e-05,
359
+ "loss": 0.669,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.6701708278580815,
364
+ "grad_norm": 1.0896775722503662,
365
+ "learning_rate": 2.7648602400343235e-05,
366
+ "loss": 0.7041,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.683311432325887,
371
+ "grad_norm": 1.1343854665756226,
372
+ "learning_rate": 2.7530549004440757e-05,
373
+ "loss": 0.7048,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.6964520367936925,
378
+ "grad_norm": 1.302240252494812,
379
+ "learning_rate": 2.7409869317864406e-05,
380
+ "loss": 0.6561,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.709592641261498,
385
+ "grad_norm": 1.1845916509628296,
386
+ "learning_rate": 2.7286588633994e-05,
387
+ "loss": 0.6793,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.7227332457293035,
392
+ "grad_norm": 1.3149752616882324,
393
+ "learning_rate": 2.7160732791355076e-05,
394
+ "loss": 0.634,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.735873850197109,
399
+ "grad_norm": 1.091576099395752,
400
+ "learning_rate": 2.7032328168203327e-05,
401
+ "loss": 0.664,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.7490144546649146,
406
+ "grad_norm": 1.1638708114624023,
407
+ "learning_rate": 2.6901401676996e-05,
408
+ "loss": 0.6405,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.7621550591327201,
413
+ "grad_norm": 1.1364482641220093,
414
+ "learning_rate": 2.6767980758751264e-05,
415
+ "loss": 0.6211,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.7752956636005256,
420
+ "grad_norm": 1.2141324281692505,
421
+ "learning_rate": 2.6632093377296796e-05,
422
+ "loss": 0.6661,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.7884362680683311,
427
+ "grad_norm": 1.4334216117858887,
428
+ "learning_rate": 2.649376801340887e-05,
429
+ "loss": 0.5666,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.8015768725361366,
434
+ "grad_norm": 1.2394732236862183,
435
+ "learning_rate": 2.6353033658842996e-05,
436
+ "loss": 0.5991,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.8147174770039421,
441
+ "grad_norm": 1.3286678791046143,
442
+ "learning_rate": 2.6209919810257514e-05,
443
+ "loss": 0.5626,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.8278580814717477,
448
+ "grad_norm": 1.191128134727478,
449
+ "learning_rate": 2.606445646303138e-05,
450
+ "loss": 0.587,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.8409986859395532,
455
+ "grad_norm": 1.3281301259994507,
456
+ "learning_rate": 2.591667410497738e-05,
457
+ "loss": 0.5776,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.8541392904073587,
462
+ "grad_norm": 1.1658596992492676,
463
+ "learning_rate": 2.5766603709952184e-05,
464
+ "loss": 0.5748,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.8672798948751642,
469
+ "grad_norm": 1.0998756885528564,
470
+ "learning_rate": 2.561427673136446e-05,
471
+ "loss": 0.5435,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.8804204993429697,
476
+ "grad_norm": 1.2171285152435303,
477
+ "learning_rate": 2.5459725095582577e-05,
478
+ "loss": 0.591,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.8935611038107752,
483
+ "grad_norm": 1.1682820320129395,
484
+ "learning_rate": 2.5302981195243083e-05,
485
+ "loss": 0.5622,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.9067017082785808,
490
+ "grad_norm": 1.2696325778961182,
491
+ "learning_rate": 2.5144077882461516e-05,
492
+ "loss": 0.5228,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.9198423127463863,
497
+ "grad_norm": 1.2294542789459229,
498
+ "learning_rate": 2.4983048461946893e-05,
499
+ "loss": 0.5008,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 0.9329829172141918,
504
+ "grad_norm": 1.1982229948043823,
505
+ "learning_rate": 2.4819926684021342e-05,
506
+ "loss": 0.5068,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 0.9461235216819974,
511
+ "grad_norm": 1.2754900455474854,
512
+ "learning_rate": 2.4654746737546328e-05,
513
+ "loss": 0.4912,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 0.9592641261498029,
518
+ "grad_norm": 1.1950724124908447,
519
+ "learning_rate": 2.4487543242756993e-05,
520
+ "loss": 0.5285,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 0.9724047306176085,
525
+ "grad_norm": 1.1647367477416992,
526
+ "learning_rate": 2.4318351244006055e-05,
527
+ "loss": 0.5249,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 0.985545335085414,
532
+ "grad_norm": 1.2416152954101562,
533
+ "learning_rate": 2.4147206202418812e-05,
534
+ "loss": 0.4966,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 0.9986859395532195,
539
+ "grad_norm": 1.1909600496292114,
540
+ "learning_rate": 2.3974143988460838e-05,
541
+ "loss": 0.4392,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 1.0105124835742445,
546
+ "grad_norm": 1.1483696699142456,
547
+ "learning_rate": 2.3799200874419827e-05,
548
+ "loss": 0.4171,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 1.02365308804205,
553
+ "grad_norm": 1.298833966255188,
554
+ "learning_rate": 2.3622413526803273e-05,
555
+ "loss": 0.3912,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 1.0367936925098555,
560
+ "grad_norm": 1.4780399799346924,
561
+ "learning_rate": 2.3443818998653464e-05,
562
+ "loss": 0.4052,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 1.049934296977661,
567
+ "grad_norm": 1.4238592386245728,
568
+ "learning_rate": 2.3263454721781537e-05,
569
+ "loss": 0.4899,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 1.0630749014454666,
574
+ "grad_norm": 1.241113543510437,
575
+ "learning_rate": 2.308135849892208e-05,
576
+ "loss": 0.4632,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 1.076215505913272,
581
+ "grad_norm": 1.2949522733688354,
582
+ "learning_rate": 2.2897568495810022e-05,
583
+ "loss": 0.3383,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 1.0893561103810776,
588
+ "grad_norm": 1.3433641195297241,
589
+ "learning_rate": 2.271212323318144e-05,
590
+ "loss": 0.4163,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 1.1024967148488831,
595
+ "grad_norm": 1.3279451131820679,
596
+ "learning_rate": 2.2525061578699962e-05,
597
+ "loss": 0.3814,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 1.1156373193166886,
602
+ "grad_norm": 1.310359239578247,
603
+ "learning_rate": 2.233642273881045e-05,
604
+ "loss": 0.3702,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 1.1287779237844942,
609
+ "grad_norm": 1.6063209772109985,
610
+ "learning_rate": 2.2146246250521677e-05,
611
+ "loss": 0.3602,
612
+ "step": 430
613
+ },
614
+ {
615
+ "epoch": 1.1419185282522997,
616
+ "grad_norm": 1.2085447311401367,
617
+ "learning_rate": 2.1954571973119726e-05,
618
+ "loss": 0.3885,
619
+ "step": 435
620
+ },
621
+ {
622
+ "epoch": 1.1550591327201052,
623
+ "grad_norm": 1.2866445779800415,
624
+ "learning_rate": 2.1761440079813845e-05,
625
+ "loss": 0.3897,
626
+ "step": 440
627
+ },
628
+ {
629
+ "epoch": 1.1681997371879107,
630
+ "grad_norm": 1.2492274045944214,
631
+ "learning_rate": 2.1566891049316515e-05,
632
+ "loss": 0.372,
633
+ "step": 445
634
+ },
635
+ {
636
+ "epoch": 1.1813403416557162,
637
+ "grad_norm": 1.3012983798980713,
638
+ "learning_rate": 2.137096565735943e-05,
639
+ "loss": 0.3672,
640
+ "step": 450
641
+ },
642
+ {
643
+ "epoch": 1.1944809461235217,
644
+ "grad_norm": 1.2833282947540283,
645
+ "learning_rate": 2.1173704968147327e-05,
646
+ "loss": 0.3211,
647
+ "step": 455
648
+ },
649
+ {
650
+ "epoch": 1.2076215505913273,
651
+ "grad_norm": 1.3121607303619385,
652
+ "learning_rate": 2.0975150325751262e-05,
653
+ "loss": 0.3702,
654
+ "step": 460
655
+ },
656
+ {
657
+ "epoch": 1.2207621550591328,
658
+ "grad_norm": 1.1029564142227173,
659
+ "learning_rate": 2.0775343345443267e-05,
660
+ "loss": 0.3338,
661
+ "step": 465
662
+ },
663
+ {
664
+ "epoch": 1.2339027595269383,
665
+ "grad_norm": 1.213159441947937,
666
+ "learning_rate": 2.057432590497418e-05,
667
+ "loss": 0.3315,
668
+ "step": 470
669
+ },
670
+ {
671
+ "epoch": 1.2470433639947438,
672
+ "grad_norm": 1.377474308013916,
673
+ "learning_rate": 2.0372140135796407e-05,
674
+ "loss": 0.373,
675
+ "step": 475
676
+ },
677
+ {
678
+ "epoch": 1.2601839684625493,
679
+ "grad_norm": 1.1862900257110596,
680
+ "learning_rate": 2.01688284142336e-05,
681
+ "loss": 0.3438,
682
+ "step": 480
683
+ },
684
+ {
685
+ "epoch": 1.2733245729303548,
686
+ "grad_norm": 1.2109731435775757,
687
+ "learning_rate": 1.9964433352598913e-05,
688
+ "loss": 0.323,
689
+ "step": 485
690
+ },
691
+ {
692
+ "epoch": 1.2864651773981604,
693
+ "grad_norm": 1.1861048936843872,
694
+ "learning_rate": 1.975899779026386e-05,
695
+ "loss": 0.3499,
696
+ "step": 490
697
+ },
698
+ {
699
+ "epoch": 1.2996057818659659,
700
+ "grad_norm": 1.3072450160980225,
701
+ "learning_rate": 1.955256478467959e-05,
702
+ "loss": 0.308,
703
+ "step": 495
704
+ },
705
+ {
706
+ "epoch": 1.3127463863337714,
707
+ "grad_norm": 1.4458948373794556,
708
+ "learning_rate": 1.9345177602352386e-05,
709
+ "loss": 0.3279,
710
+ "step": 500
711
+ },
712
+ {
713
+ "epoch": 1.325886990801577,
714
+ "grad_norm": 1.1371740102767944,
715
+ "learning_rate": 1.9136879709775424e-05,
716
+ "loss": 0.3243,
717
+ "step": 505
718
+ },
719
+ {
720
+ "epoch": 1.3390275952693824,
721
+ "grad_norm": 1.408117651939392,
722
+ "learning_rate": 1.8927714764318588e-05,
723
+ "loss": 0.3347,
724
+ "step": 510
725
+ },
726
+ {
727
+ "epoch": 1.352168199737188,
728
+ "grad_norm": 1.39098060131073,
729
+ "learning_rate": 1.871772660507826e-05,
730
+ "loss": 0.3161,
731
+ "step": 515
732
+ },
733
+ {
734
+ "epoch": 1.3653088042049935,
735
+ "grad_norm": 1.3169364929199219,
736
+ "learning_rate": 1.8506959243689043e-05,
737
+ "loss": 0.2942,
738
+ "step": 520
739
+ },
740
+ {
741
+ "epoch": 1.378449408672799,
742
+ "grad_norm": 1.1352839469909668,
743
+ "learning_rate": 1.829545685509934e-05,
744
+ "loss": 0.3084,
745
+ "step": 525
746
+ },
747
+ {
748
+ "epoch": 1.3915900131406045,
749
+ "grad_norm": 1.2993459701538086,
750
+ "learning_rate": 1.8083263768312645e-05,
751
+ "loss": 0.3009,
752
+ "step": 530
753
+ },
754
+ {
755
+ "epoch": 1.40473061760841,
756
+ "grad_norm": 1.206346869468689,
757
+ "learning_rate": 1.7870424457096593e-05,
758
+ "loss": 0.2734,
759
+ "step": 535
760
+ },
761
+ {
762
+ "epoch": 1.4178712220762155,
763
+ "grad_norm": 1.3716164827346802,
764
+ "learning_rate": 1.765698353066169e-05,
765
+ "loss": 0.2508,
766
+ "step": 540
767
+ },
768
+ {
769
+ "epoch": 1.431011826544021,
770
+ "grad_norm": 1.2523376941680908,
771
+ "learning_rate": 1.7442985724311566e-05,
772
+ "loss": 0.2903,
773
+ "step": 545
774
+ },
775
+ {
776
+ "epoch": 1.4441524310118266,
777
+ "grad_norm": 1.4354424476623535,
778
+ "learning_rate": 1.7228475890066908e-05,
779
+ "loss": 0.3164,
780
+ "step": 550
781
+ },
782
+ {
783
+ "epoch": 1.457293035479632,
784
+ "grad_norm": 1.2621711492538452,
785
+ "learning_rate": 1.7013498987264832e-05,
786
+ "loss": 0.2945,
787
+ "step": 555
788
+ },
789
+ {
790
+ "epoch": 1.4704336399474376,
791
+ "grad_norm": 1.4864765405654907,
792
+ "learning_rate": 1.6798100073135865e-05,
793
+ "loss": 0.2666,
794
+ "step": 560
795
+ },
796
+ {
797
+ "epoch": 1.483574244415243,
798
+ "grad_norm": 1.1217767000198364,
799
+ "learning_rate": 1.6582324293360298e-05,
800
+ "loss": 0.2586,
801
+ "step": 565
802
+ },
803
+ {
804
+ "epoch": 1.4967148488830486,
805
+ "grad_norm": 1.280014157295227,
806
+ "learning_rate": 1.6366216872606098e-05,
807
+ "loss": 0.2636,
808
+ "step": 570
809
+ },
810
+ {
811
+ "epoch": 1.5098554533508541,
812
+ "grad_norm": 1.2222352027893066,
813
+ "learning_rate": 1.6149823105050187e-05,
814
+ "loss": 0.2545,
815
+ "step": 575
816
+ },
817
+ {
818
+ "epoch": 1.5229960578186597,
819
+ "grad_norm": 1.3205738067626953,
820
+ "learning_rate": 1.5933188344885232e-05,
821
+ "loss": 0.2863,
822
+ "step": 580
823
+ },
824
+ {
825
+ "epoch": 1.5361366622864652,
826
+ "grad_norm": 1.3537684679031372,
827
+ "learning_rate": 1.5716357996813773e-05,
828
+ "loss": 0.2505,
829
+ "step": 585
830
+ },
831
+ {
832
+ "epoch": 1.5492772667542707,
833
+ "grad_norm": 1.2179908752441406,
834
+ "learning_rate": 1.5499377506531818e-05,
835
+ "loss": 0.2522,
836
+ "step": 590
837
+ },
838
+ {
839
+ "epoch": 1.5624178712220762,
840
+ "grad_norm": 1.3018555641174316,
841
+ "learning_rate": 1.5282292351203847e-05,
842
+ "loss": 0.2543,
843
+ "step": 595
844
+ },
845
+ {
846
+ "epoch": 1.5755584756898817,
847
+ "grad_norm": 1.1383919715881348,
848
+ "learning_rate": 1.5065148029931195e-05,
849
+ "loss": 0.2768,
850
+ "step": 600
851
+ },
852
+ {
853
+ "epoch": 1.5886990801576872,
854
+ "grad_norm": 1.245634913444519,
855
+ "learning_rate": 1.484799005421584e-05,
856
+ "loss": 0.2381,
857
+ "step": 605
858
+ },
859
+ {
860
+ "epoch": 1.6018396846254928,
861
+ "grad_norm": 1.0681072473526,
862
+ "learning_rate": 1.4630863938421603e-05,
863
+ "loss": 0.2664,
864
+ "step": 610
865
+ },
866
+ {
867
+ "epoch": 1.6149802890932983,
868
+ "grad_norm": 1.3179540634155273,
869
+ "learning_rate": 1.4413815190234777e-05,
870
+ "loss": 0.2588,
871
+ "step": 615
872
+ },
873
+ {
874
+ "epoch": 1.6281208935611038,
875
+ "grad_norm": 1.1153942346572876,
876
+ "learning_rate": 1.419688930112607e-05,
877
+ "loss": 0.2759,
878
+ "step": 620
879
+ },
880
+ {
881
+ "epoch": 1.6412614980289093,
882
+ "grad_norm": 1.6008579730987549,
883
+ "learning_rate": 1.3980131736816048e-05,
884
+ "loss": 0.2377,
885
+ "step": 625
886
+ },
887
+ {
888
+ "epoch": 1.6544021024967148,
889
+ "grad_norm": 1.1769739389419556,
890
+ "learning_rate": 1.3763587927745898e-05,
891
+ "loss": 0.2258,
892
+ "step": 630
893
+ },
894
+ {
895
+ "epoch": 1.6675427069645203,
896
+ "grad_norm": 1.1792428493499756,
897
+ "learning_rate": 1.3547303259555625e-05,
898
+ "loss": 0.2356,
899
+ "step": 635
900
+ },
901
+ {
902
+ "epoch": 1.6806833114323259,
903
+ "grad_norm": 1.315924048423767,
904
+ "learning_rate": 1.3331323063571647e-05,
905
+ "loss": 0.2526,
906
+ "step": 640
907
+ },
908
+ {
909
+ "epoch": 1.6938239159001314,
910
+ "grad_norm": 1.220938801765442,
911
+ "learning_rate": 1.3115692607305718e-05,
912
+ "loss": 0.2136,
913
+ "step": 645
914
+ },
915
+ {
916
+ "epoch": 1.7069645203679369,
917
+ "grad_norm": 1.235229253768921,
918
+ "learning_rate": 1.2900457084967302e-05,
919
+ "loss": 0.2392,
920
+ "step": 650
921
+ },
922
+ {
923
+ "epoch": 1.7201051248357424,
924
+ "grad_norm": 1.2829138040542603,
925
+ "learning_rate": 1.2685661607991238e-05,
926
+ "loss": 0.232,
927
+ "step": 655
928
+ },
929
+ {
930
+ "epoch": 1.733245729303548,
931
+ "grad_norm": 1.139499545097351,
932
+ "learning_rate": 1.2471351195582811e-05,
933
+ "loss": 0.1879,
934
+ "step": 660
935
+ },
936
+ {
937
+ "epoch": 1.7463863337713534,
938
+ "grad_norm": 1.2732905149459839,
939
+ "learning_rate": 1.2257570765282127e-05,
940
+ "loss": 0.2086,
941
+ "step": 665
942
+ },
943
+ {
944
+ "epoch": 1.759526938239159,
945
+ "grad_norm": 1.077530860900879,
946
+ "learning_rate": 1.2044365123549791e-05,
947
+ "loss": 0.2101,
948
+ "step": 670
949
+ },
950
+ {
951
+ "epoch": 1.7726675427069645,
952
+ "grad_norm": 1.1747920513153076,
953
+ "learning_rate": 1.183177895637589e-05,
954
+ "loss": 0.2287,
955
+ "step": 675
956
+ },
957
+ {
958
+ "epoch": 1.78580814717477,
959
+ "grad_norm": 1.350934624671936,
960
+ "learning_rate": 1.1619856819914186e-05,
961
+ "loss": 0.2231,
962
+ "step": 680
963
+ },
964
+ {
965
+ "epoch": 1.7989487516425755,
966
+ "grad_norm": 1.1574058532714844,
967
+ "learning_rate": 1.1408643131143566e-05,
968
+ "loss": 0.1953,
969
+ "step": 685
970
+ },
971
+ {
972
+ "epoch": 1.812089356110381,
973
+ "grad_norm": 1.9376565217971802,
974
+ "learning_rate": 1.1198182158558638e-05,
975
+ "loss": 0.1884,
976
+ "step": 690
977
+ },
978
+ {
979
+ "epoch": 1.8252299605781865,
980
+ "grad_norm": 1.1832637786865234,
981
+ "learning_rate": 1.098851801289144e-05,
982
+ "loss": 0.2011,
983
+ "step": 695
984
+ },
985
+ {
986
+ "epoch": 1.838370565045992,
987
+ "grad_norm": 1.1152653694152832,
988
+ "learning_rate": 1.0779694637866257e-05,
989
+ "loss": 0.1729,
990
+ "step": 700
991
+ },
992
+ {
993
+ "epoch": 1.8515111695137976,
994
+ "grad_norm": 1.2615498304367065,
995
+ "learning_rate": 1.0571755800989367e-05,
996
+ "loss": 0.1862,
997
+ "step": 705
998
+ },
999
+ {
1000
+ "epoch": 1.864651773981603,
1001
+ "grad_norm": 1.2463351488113403,
1002
+ "learning_rate": 1.036474508437579e-05,
1003
+ "loss": 0.1971,
1004
+ "step": 710
1005
+ },
1006
+ {
1007
+ "epoch": 1.8777923784494086,
1008
+ "grad_norm": 1.2754261493682861,
1009
+ "learning_rate": 1.0158705875614877e-05,
1010
+ "loss": 0.1672,
1011
+ "step": 715
1012
+ },
1013
+ {
1014
+ "epoch": 1.8909329829172141,
1015
+ "grad_norm": 1.2041103839874268,
1016
+ "learning_rate": 9.953681358676622e-06,
1017
+ "loss": 0.1718,
1018
+ "step": 720
1019
+ },
1020
+ {
1021
+ "epoch": 1.9040735873850196,
1022
+ "grad_norm": 1.223314642906189,
1023
+ "learning_rate": 9.749714504860753e-06,
1024
+ "loss": 0.173,
1025
+ "step": 725
1026
+ },
1027
+ {
1028
+ "epoch": 1.9172141918528252,
1029
+ "grad_norm": 1.2831774950027466,
1030
+ "learning_rate": 9.54684806379026e-06,
1031
+ "loss": 0.1908,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 1.9303547963206307,
1036
+ "grad_norm": 1.1934982538223267,
1037
+ "learning_rate": 9.345124554451506e-06,
1038
+ "loss": 0.1715,
1039
+ "step": 735
1040
+ },
1041
+ {
1042
+ "epoch": 1.9434954007884362,
1043
+ "grad_norm": 1.3165861368179321,
1044
+ "learning_rate": 9.144586256282619e-06,
1045
+ "loss": 0.1691,
1046
+ "step": 740
1047
+ },
1048
+ {
1049
+ "epoch": 1.9566360052562417,
1050
+ "grad_norm": 1.2910155057907104,
1051
+ "learning_rate": 8.945275200312085e-06,
1052
+ "loss": 0.1665,
1053
+ "step": 745
1054
+ },
1055
+ {
1056
+ "epoch": 1.9697766097240472,
1057
+ "grad_norm": 1.0195131301879883,
1058
+ "learning_rate": 8.747233160349434e-06,
1059
+ "loss": 0.2066,
1060
+ "step": 750
1061
+ },
1062
+ {
1063
+ "epoch": 1.9829172141918527,
1064
+ "grad_norm": 1.1912403106689453,
1065
+ "learning_rate": 8.550501644229846e-06,
1066
+ "loss": 0.1763,
1067
+ "step": 755
1068
+ },
1069
+ {
1070
+ "epoch": 1.9960578186596583,
1071
+ "grad_norm": 1.1489989757537842,
1072
+ "learning_rate": 8.355121885114439e-06,
1073
+ "loss": 0.1569,
1074
+ "step": 760
1075
+ },
1076
+ {
1077
+ "epoch": 2.0078843626806835,
1078
+ "grad_norm": 0.9988665580749512,
1079
+ "learning_rate": 8.161134832848186e-06,
1080
+ "loss": 0.1521,
1081
+ "step": 765
1082
+ },
1083
+ {
1084
+ "epoch": 2.021024967148489,
1085
+ "grad_norm": 1.0327770709991455,
1086
+ "learning_rate": 7.968581145377205e-06,
1087
+ "loss": 0.1561,
1088
+ "step": 770
1089
+ },
1090
+ {
1091
+ "epoch": 2.0341655716162945,
1092
+ "grad_norm": 0.9528421759605408,
1093
+ "learning_rate": 7.777501180227199e-06,
1094
+ "loss": 0.1392,
1095
+ "step": 775
1096
+ },
1097
+ {
1098
+ "epoch": 2.0473061760841,
1099
+ "grad_norm": 1.0644992589950562,
1100
+ "learning_rate": 7.587934986044916e-06,
1101
+ "loss": 0.137,
1102
+ "step": 780
1103
+ },
1104
+ {
1105
+ "epoch": 2.0604467805519056,
1106
+ "grad_norm": 1.3147528171539307,
1107
+ "learning_rate": 7.3999222942042635e-06,
1108
+ "loss": 0.141,
1109
+ "step": 785
1110
+ },
1111
+ {
1112
+ "epoch": 2.073587385019711,
1113
+ "grad_norm": 1.1737008094787598,
1114
+ "learning_rate": 7.213502510478993e-06,
1115
+ "loss": 0.1148,
1116
+ "step": 790
1117
+ },
1118
+ {
1119
+ "epoch": 2.0867279894875166,
1120
+ "grad_norm": 0.9637901186943054,
1121
+ "learning_rate": 7.028714706783626e-06,
1122
+ "loss": 0.1268,
1123
+ "step": 795
1124
+ },
1125
+ {
1126
+ "epoch": 2.099868593955322,
1127
+ "grad_norm": 0.9228414297103882,
1128
+ "learning_rate": 6.845597612984288e-06,
1129
+ "loss": 0.1322,
1130
+ "step": 800
1131
+ },
1132
+ {
1133
+ "epoch": 2.1130091984231276,
1134
+ "grad_norm": 0.8965508341789246,
1135
+ "learning_rate": 6.664189608781295e-06,
1136
+ "loss": 0.1472,
1137
+ "step": 805
1138
+ },
1139
+ {
1140
+ "epoch": 2.126149802890933,
1141
+ "grad_norm": 1.1861528158187866,
1142
+ "learning_rate": 6.484528715665131e-06,
1143
+ "loss": 0.13,
1144
+ "step": 810
1145
+ },
1146
+ {
1147
+ "epoch": 2.1392904073587387,
1148
+ "grad_norm": 0.9378185272216797,
1149
+ "learning_rate": 6.306652588947454e-06,
1150
+ "loss": 0.1244,
1151
+ "step": 815
1152
+ },
1153
+ {
1154
+ "epoch": 2.152431011826544,
1155
+ "grad_norm": 1.1733484268188477,
1156
+ "learning_rate": 6.130598509868895e-06,
1157
+ "loss": 0.1194,
1158
+ "step": 820
1159
+ },
1160
+ {
1161
+ "epoch": 2.1655716162943497,
1162
+ "grad_norm": 0.8082630038261414,
1163
+ "learning_rate": 5.95640337778525e-06,
1164
+ "loss": 0.1337,
1165
+ "step": 825
1166
+ },
1167
+ {
1168
+ "epoch": 2.178712220762155,
1169
+ "grad_norm": 0.8850849866867065,
1170
+ "learning_rate": 5.784103702433685e-06,
1171
+ "loss": 0.1245,
1172
+ "step": 830
1173
+ },
1174
+ {
1175
+ "epoch": 2.1918528252299607,
1176
+ "grad_norm": 1.1383304595947266,
1177
+ "learning_rate": 5.613735596280661e-06,
1178
+ "loss": 0.1305,
1179
+ "step": 835
1180
+ },
1181
+ {
1182
+ "epoch": 2.2049934296977662,
1183
+ "grad_norm": 1.2028309106826782,
1184
+ "learning_rate": 5.445334766953037e-06,
1185
+ "loss": 0.1279,
1186
+ "step": 840
1187
+ },
1188
+ {
1189
+ "epoch": 2.2181340341655718,
1190
+ "grad_norm": 0.9609809517860413,
1191
+ "learning_rate": 5.278936509754112e-06,
1192
+ "loss": 0.1321,
1193
+ "step": 845
1194
+ },
1195
+ {
1196
+ "epoch": 2.2312746386333773,
1197
+ "grad_norm": 1.1674765348434448,
1198
+ "learning_rate": 5.114575700266024e-06,
1199
+ "loss": 0.117,
1200
+ "step": 850
1201
+ },
1202
+ {
1203
+ "epoch": 2.244415243101183,
1204
+ "grad_norm": 0.9462134838104248,
1205
+ "learning_rate": 4.95228678704014e-06,
1206
+ "loss": 0.1091,
1207
+ "step": 855
1208
+ },
1209
+ {
1210
+ "epoch": 2.2575558475689883,
1211
+ "grad_norm": 0.9706594944000244,
1212
+ "learning_rate": 4.7921037843769614e-06,
1213
+ "loss": 0.1166,
1214
+ "step": 860
1215
+ },
1216
+ {
1217
+ "epoch": 2.270696452036794,
1218
+ "grad_norm": 1.1274670362472534,
1219
+ "learning_rate": 4.6340602651970304e-06,
1220
+ "loss": 0.1172,
1221
+ "step": 865
1222
+ },
1223
+ {
1224
+ "epoch": 2.2838370565045993,
1225
+ "grad_norm": 1.4383842945098877,
1226
+ "learning_rate": 4.478189354004334e-06,
1227
+ "loss": 0.1325,
1228
+ "step": 870
1229
+ },
1230
+ {
1231
+ "epoch": 2.296977660972405,
1232
+ "grad_norm": 0.9975386261940002,
1233
+ "learning_rate": 4.324523719943716e-06,
1234
+ "loss": 0.1352,
1235
+ "step": 875
1236
+ },
1237
+ {
1238
+ "epoch": 2.3101182654402104,
1239
+ "grad_norm": 1.0504313707351685,
1240
+ "learning_rate": 4.173095569953708e-06,
1241
+ "loss": 0.103,
1242
+ "step": 880
1243
+ },
1244
+ {
1245
+ "epoch": 2.323258869908016,
1246
+ "grad_norm": 1.1191004514694214,
1247
+ "learning_rate": 4.023936642016266e-06,
1248
+ "loss": 0.1276,
1249
+ "step": 885
1250
+ },
1251
+ {
1252
+ "epoch": 2.3363994743758214,
1253
+ "grad_norm": 0.8486424088478088,
1254
+ "learning_rate": 3.87707819850474e-06,
1255
+ "loss": 0.118,
1256
+ "step": 890
1257
+ },
1258
+ {
1259
+ "epoch": 2.349540078843627,
1260
+ "grad_norm": 1.0684998035430908,
1261
+ "learning_rate": 3.7325510196315964e-06,
1262
+ "loss": 0.1137,
1263
+ "step": 895
1264
+ },
1265
+ {
1266
+ "epoch": 2.3626806833114324,
1267
+ "grad_norm": 0.7870803475379944,
1268
+ "learning_rate": 3.5903853969971335e-06,
1269
+ "loss": 0.089,
1270
+ "step": 900
1271
+ },
1272
+ {
1273
+ "epoch": 2.375821287779238,
1274
+ "grad_norm": 1.016579270362854,
1275
+ "learning_rate": 3.450611127240646e-06,
1276
+ "loss": 0.1046,
1277
+ "step": 905
1278
+ },
1279
+ {
1280
+ "epoch": 2.3889618922470435,
1281
+ "grad_norm": 1.0224157571792603,
1282
+ "learning_rate": 3.313257505795317e-06,
1283
+ "loss": 0.1013,
1284
+ "step": 910
1285
+ },
1286
+ {
1287
+ "epoch": 2.402102496714849,
1288
+ "grad_norm": 0.7343006730079651,
1289
+ "learning_rate": 3.1783533207481537e-06,
1290
+ "loss": 0.0943,
1291
+ "step": 915
1292
+ },
1293
+ {
1294
+ "epoch": 2.4152431011826545,
1295
+ "grad_norm": 1.0326985120773315,
1296
+ "learning_rate": 3.045926846806277e-06,
1297
+ "loss": 0.1095,
1298
+ "step": 920
1299
+ },
1300
+ {
1301
+ "epoch": 2.42838370565046,
1302
+ "grad_norm": 0.957417368888855,
1303
+ "learning_rate": 2.9160058393707656e-06,
1304
+ "loss": 0.1114,
1305
+ "step": 925
1306
+ },
1307
+ {
1308
+ "epoch": 2.4415243101182655,
1309
+ "grad_norm": 1.1126303672790527,
1310
+ "learning_rate": 2.7886175287194142e-06,
1311
+ "loss": 0.1006,
1312
+ "step": 930
1313
+ },
1314
+ {
1315
+ "epoch": 2.454664914586071,
1316
+ "grad_norm": 0.755524218082428,
1317
+ "learning_rate": 2.6637886142994725e-06,
1318
+ "loss": 0.0962,
1319
+ "step": 935
1320
+ },
1321
+ {
1322
+ "epoch": 2.4678055190538766,
1323
+ "grad_norm": 0.8578504323959351,
1324
+ "learning_rate": 2.5415452591317023e-06,
1325
+ "loss": 0.1128,
1326
+ "step": 940
1327
+ },
1328
+ {
1329
+ "epoch": 2.480946123521682,
1330
+ "grad_norm": 0.9237407445907593,
1331
+ "learning_rate": 2.4219130843268362e-06,
1332
+ "loss": 0.1326,
1333
+ "step": 945
1334
+ },
1335
+ {
1336
+ "epoch": 2.4940867279894876,
1337
+ "grad_norm": 0.7806246876716614,
1338
+ "learning_rate": 2.304917163715636e-06,
1339
+ "loss": 0.1042,
1340
+ "step": 950
1341
+ },
1342
+ {
1343
+ "epoch": 2.507227332457293,
1344
+ "grad_norm": 0.7509581446647644,
1345
+ "learning_rate": 2.1905820185936172e-06,
1346
+ "loss": 0.0879,
1347
+ "step": 955
1348
+ },
1349
+ {
1350
+ "epoch": 2.5203679369250986,
1351
+ "grad_norm": 1.1201022863388062,
1352
+ "learning_rate": 2.0789316125816275e-06,
1353
+ "loss": 0.1126,
1354
+ "step": 960
1355
+ },
1356
+ {
1357
+ "epoch": 2.533508541392904,
1358
+ "grad_norm": 0.8480803966522217,
1359
+ "learning_rate": 1.9699893466032733e-06,
1360
+ "loss": 0.101,
1361
+ "step": 965
1362
+ },
1363
+ {
1364
+ "epoch": 2.5466491458607097,
1365
+ "grad_norm": 0.7627381086349487,
1366
+ "learning_rate": 1.8637780539803118e-06,
1367
+ "loss": 0.1037,
1368
+ "step": 970
1369
+ },
1370
+ {
1371
+ "epoch": 2.559789750328515,
1372
+ "grad_norm": 1.0410747528076172,
1373
+ "learning_rate": 1.760319995646968e-06,
1374
+ "loss": 0.0976,
1375
+ "step": 975
1376
+ },
1377
+ {
1378
+ "epoch": 2.5729303547963207,
1379
+ "grad_norm": 0.8388499021530151,
1380
+ "learning_rate": 1.6596368554842673e-06,
1381
+ "loss": 0.109,
1382
+ "step": 980
1383
+ },
1384
+ {
1385
+ "epoch": 2.5860709592641262,
1386
+ "grad_norm": 0.7287879586219788,
1387
+ "learning_rate": 1.5617497357752724e-06,
1388
+ "loss": 0.0952,
1389
+ "step": 985
1390
+ },
1391
+ {
1392
+ "epoch": 2.5992115637319317,
1393
+ "grad_norm": 0.8424334526062012,
1394
+ "learning_rate": 1.4666791527822377e-06,
1395
+ "loss": 0.0934,
1396
+ "step": 990
1397
+ },
1398
+ {
1399
+ "epoch": 2.6123521681997373,
1400
+ "grad_norm": 0.7682844996452332,
1401
+ "learning_rate": 1.374445032446588e-06,
1402
+ "loss": 0.0814,
1403
+ "step": 995
1404
+ },
1405
+ {
1406
+ "epoch": 2.6254927726675428,
1407
+ "grad_norm": 0.7012391686439514,
1408
+ "learning_rate": 1.285066706212612e-06,
1409
+ "loss": 0.1003,
1410
+ "step": 1000
1411
+ },
1412
+ {
1413
+ "epoch": 2.6386333771353483,
1414
+ "grad_norm": 0.7718296647071838,
1415
+ "learning_rate": 1.1985629069757847e-06,
1416
+ "loss": 0.1093,
1417
+ "step": 1005
1418
+ },
1419
+ {
1420
+ "epoch": 2.651773981603154,
1421
+ "grad_norm": 0.8238117098808289,
1422
+ "learning_rate": 1.1149517651564944e-06,
1423
+ "loss": 0.1307,
1424
+ "step": 1010
1425
+ },
1426
+ {
1427
+ "epoch": 2.6649145860709593,
1428
+ "grad_norm": 0.7402698993682861,
1429
+ "learning_rate": 1.034250804900081e-06,
1430
+ "loss": 0.1022,
1431
+ "step": 1015
1432
+ },
1433
+ {
1434
+ "epoch": 2.678055190538765,
1435
+ "grad_norm": 0.9563916325569153,
1436
+ "learning_rate": 9.56476940403942e-07,
1437
+ "loss": 0.1193,
1438
+ "step": 1020
1439
+ },
1440
+ {
1441
+ "epoch": 2.6911957950065704,
1442
+ "grad_norm": 0.8082496523857117,
1443
+ "learning_rate": 8.816464723724504e-07,
1444
+ "loss": 0.0984,
1445
+ "step": 1025
1446
+ },
1447
+ {
1448
+ "epoch": 2.704336399474376,
1449
+ "grad_norm": 0.810088038444519,
1450
+ "learning_rate": 8.097750846004909e-07,
1451
+ "loss": 0.0873,
1452
+ "step": 1030
1453
+ },
1454
+ {
1455
+ "epoch": 2.7174770039421814,
1456
+ "grad_norm": 0.8148086071014404,
1457
+ "learning_rate": 7.40877840686257e-07,
1458
+ "loss": 0.0998,
1459
+ "step": 1035
1460
+ },
1461
+ {
1462
+ "epoch": 2.730617608409987,
1463
+ "grad_norm": 1.008510708808899,
1464
+ "learning_rate": 6.749691808740777e-07,
1465
+ "loss": 0.0973,
1466
+ "step": 1040
1467
+ },
1468
+ {
1469
+ "epoch": 2.7437582128777924,
1470
+ "grad_norm": 0.5810213088989258,
1471
+ "learning_rate": 6.120629190278554e-07,
1472
+ "loss": 0.0787,
1473
+ "step": 1045
1474
+ },
1475
+ {
1476
+ "epoch": 2.756898817345598,
1477
+ "grad_norm": 0.7217281460762024,
1478
+ "learning_rate": 5.521722397358132e-07,
1479
+ "loss": 0.0849,
1480
+ "step": 1050
1481
+ },
1482
+ {
1483
+ "epoch": 2.7700394218134035,
1484
+ "grad_norm": 0.8091464042663574,
1485
+ "learning_rate": 4.953096955471142e-07,
1486
+ "loss": 0.0937,
1487
+ "step": 1055
1488
+ },
1489
+ {
1490
+ "epoch": 2.783180026281209,
1491
+ "grad_norm": 0.7312224507331848,
1492
+ "learning_rate": 4.414872043409757e-07,
1493
+ "loss": 0.0951,
1494
+ "step": 1060
1495
+ },
1496
+ {
1497
+ "epoch": 2.7963206307490145,
1498
+ "grad_norm": 0.834337592124939,
1499
+ "learning_rate": 3.907160468287707e-07,
1500
+ "loss": 0.1011,
1501
+ "step": 1065
1502
+ },
1503
+ {
1504
+ "epoch": 2.80946123521682,
1505
+ "grad_norm": 0.7655376195907593,
1506
+ "learning_rate": 3.4300686418970383e-07,
1507
+ "loss": 0.0961,
1508
+ "step": 1070
1509
+ },
1510
+ {
1511
+ "epoch": 2.8226018396846255,
1512
+ "grad_norm": 0.7533838152885437,
1513
+ "learning_rate": 2.9836965584051303e-07,
1514
+ "loss": 0.0909,
1515
+ "step": 1075
1516
+ },
1517
+ {
1518
+ "epoch": 2.835742444152431,
1519
+ "grad_norm": 0.8285064101219177,
1520
+ "learning_rate": 2.568137773396745e-07,
1521
+ "loss": 0.0974,
1522
+ "step": 1080
1523
+ },
1524
+ {
1525
+ "epoch": 2.8488830486202366,
1526
+ "grad_norm": 0.8482531309127808,
1527
+ "learning_rate": 2.183479384265713e-07,
1528
+ "loss": 0.0947,
1529
+ "step": 1085
1530
+ },
1531
+ {
1532
+ "epoch": 2.862023653088042,
1533
+ "grad_norm": 0.7816241383552551,
1534
+ "learning_rate": 1.8298020119600856e-07,
1535
+ "loss": 0.0947,
1536
+ "step": 1090
1537
+ },
1538
+ {
1539
+ "epoch": 2.8751642575558476,
1540
+ "grad_norm": 0.6632421612739563,
1541
+ "learning_rate": 1.5071797840846336e-07,
1542
+ "loss": 0.0974,
1543
+ "step": 1095
1544
+ },
1545
+ {
1546
+ "epoch": 2.888304862023653,
1547
+ "grad_norm": 0.7103014588356018,
1548
+ "learning_rate": 1.215680319364443e-07,
1549
+ "loss": 0.0868,
1550
+ "step": 1100
1551
+ },
1552
+ {
1553
+ "epoch": 2.9014454664914586,
1554
+ "grad_norm": 0.7530989646911621,
1555
+ "learning_rate": 9.553647134726173e-08,
1556
+ "loss": 0.093,
1557
+ "step": 1105
1558
+ },
1559
+ {
1560
+ "epoch": 2.914586070959264,
1561
+ "grad_norm": 0.7976528406143188,
1562
+ "learning_rate": 7.262875262251389e-08,
1563
+ "loss": 0.0912,
1564
+ "step": 1110
1565
+ },
1566
+ {
1567
+ "epoch": 2.9277266754270697,
1568
+ "grad_norm": 0.6478866338729858,
1569
+ "learning_rate": 5.2849677014566445e-08,
1570
+ "loss": 0.0896,
1571
+ "step": 1115
1572
+ },
1573
+ {
1574
+ "epoch": 2.940867279894875,
1575
+ "grad_norm": 0.8027013540267944,
1576
+ "learning_rate": 3.620339004025086e-08,
1577
+ "loss": 0.0939,
1578
+ "step": 1120
1579
+ },
1580
+ {
1581
+ "epoch": 2.9540078843626807,
1582
+ "grad_norm": 0.6769530773162842,
1583
+ "learning_rate": 2.2693380612002767e-08,
1584
+ "loss": 0.09,
1585
+ "step": 1125
1586
+ },
1587
+ {
1588
+ "epoch": 2.967148488830486,
1589
+ "grad_norm": 0.7123112082481384,
1590
+ "learning_rate": 1.2322480306615202e-08,
1591
+ "loss": 0.0866,
1592
+ "step": 1130
1593
+ },
1594
+ {
1595
+ "epoch": 2.9802890932982917,
1596
+ "grad_norm": 0.9540034532546997,
1597
+ "learning_rate": 5.092862771765017e-09,
1598
+ "loss": 0.1049,
1599
+ "step": 1135
1600
+ },
1601
+ {
1602
+ "epoch": 2.9934296977660972,
1603
+ "grad_norm": 1.0238860845565796,
1604
+ "learning_rate": 1.006043270438961e-09,
1605
+ "loss": 0.1015,
1606
+ "step": 1140
1607
+ },
1608
+ {
1609
+ "epoch": 3.0,
1610
+ "step": 1143,
1611
+ "total_flos": 1.508233453999489e+18,
1612
+ "train_loss": 0.4364819198012456,
1613
+ "train_runtime": 1183.9617,
1614
+ "train_samples_per_second": 30.847,
1615
+ "train_steps_per_second": 0.965
1616
+ }
1617
+ ],
1618
+ "logging_steps": 5,
1619
+ "max_steps": 1143,
1620
+ "num_input_tokens_seen": 0,
1621
+ "num_train_epochs": 3,
1622
+ "save_steps": 20,
1623
+ "stateful_callbacks": {
1624
+ "TrainerControl": {
1625
+ "args": {
1626
+ "should_epoch_stop": false,
1627
+ "should_evaluate": false,
1628
+ "should_log": false,
1629
+ "should_save": false,
1630
+ "should_training_stop": false
1631
+ },
1632
+ "attributes": {}
1633
+ }
1634
+ },
1635
+ "total_flos": 1.508233453999489e+18,
1636
+ "train_batch_size": 2,
1637
+ "trial_name": null,
1638
+ "trial_params": null
1639
+ }
hotpotqa_test_knowledge_50_base/1_128_e3_3e-5/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fbd0eef003e2f5dd7807d65c62b330bfd1dbcc0887fd028a054614f6c7c2f5d
3
+ size 8273
hotpotqa_test_knowledge_50_base/2_128_e3_3e-5/README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: llama3.1
4
+ base_model: meta-llama/Llama-3.1-8B
5
+ tags:
6
+ - alignment-handbook
7
+ - generated_from_trainer
8
+ datasets:
9
+ - data/hotpotqa/test/processed/knowledge_50
10
+ model-index:
11
+ - name: 2_128_e3_3e-5
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # 2_128_e3_3e-5
19
+
20
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the data/hotpotqa/test/processed/knowledge_50 dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 2
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 4
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 32
47
+ - total_eval_batch_size: 4
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.05
51
+ - num_epochs: 3.0
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - PEFT 0.15.2
60
+ - Transformers 4.52.4
61
+ - Pytorch 2.7.0+cu126
62
+ - Datasets 3.6.0
63
+ - Tokenizers 0.21.2
hotpotqa_test_knowledge_50_base/2_128_e3_3e-5/adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 256,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.05,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "up_proj",
29
+ "k_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "down_proj",
33
+ "q_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
hotpotqa_test_knowledge_50_base/2_128_e3_3e-5/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee9c608d5aa05e65acb2d222a78ab062e4110749e2cc3159ea1b02a9b5b6e87
3
+ size 671150064