Kajiura Teruno commited on
Commit
afc1d11
·
1 Parent(s): e930f37

tokenizer

Browse files
Files changed (2) hide show
  1. removed.jsonl +70 -0
  2. vocamaru_log.txt +209 -0
removed.jsonl ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"in": "<nl>", "out": "▁01.03.", "idx": 238722, "score": -15.112902641296387}
2
+ {"in": "<tab>", "out": "4.84", "idx": 238721, "score": -15.11288833618164}
3
+ {"in": "<sep>", "out": "1,43", "idx": 238710, "score": -15.11279010772705}
4
+ {"in": "<code>", "out": "そんな中", "idx": 238702, "score": -15.112638473510742}
5
+ {"in": "</code>", "out": "8560", "idx": 238700, "score": -15.112624168395996}
6
+ {"in": "None", "out": "2019-09-21", "idx": 238699, "score": -15.112618446350098}
7
+ {"in": "await", "out": "02/10", "idx": 238691, "score": -15.112505912780762}
8
+ {"in": "elif", "out": "1.3.2", "idx": 238688, "score": -15.112445831298828}
9
+ {"in": "finally", "out": "7.26", "idx": 238682, "score": -15.112358093261719}
10
+ {"in": "nonlocal", "out": "周辺で", "idx": 238679, "score": -15.112297058105469}
11
+ {"in": "yield", "out": "6626", "idx": 238676, "score": -15.112284660339355}
12
+ {"in": "▁False", "out": "4584", "idx": 238670, "score": -15.112183570861816}
13
+ {"in": "▁None", "out": "8458", "idx": 238669, "score": -15.112176895141602}
14
+ {"in": "▁async", "out": "8553", "idx": 238662, "score": -15.112029075622559}
15
+ {"in": "▁await", "out": "したりする", "idx": 238661, "score": -15.112025260925293}
16
+ {"in": "▁lambda", "out": "8,500", "idx": 238657, "score": -15.111969947814941}
17
+ {"in": ":=", "out": "19.06", "idx": 238649, "score": -15.111923217773438}
18
+ {"in": "▁-", "out": "0229", "idx": 238629, "score": -15.111686706542969}
19
+ {"in": "▁/", "out": "6541", "idx": 238622, "score": -15.1116361618042}
20
+ {"in": "▁<=", "out": "10.31", "idx": 238619, "score": -15.111579895019531}
21
+ {"in": "▁>=", "out": "4948", "idx": 238617, "score": -15.11154842376709}
22
+ {"in": "▁!=", "out": "2776", "idx": 238616, "score": -15.111540794372559}
23
+ {"in": "▁:=", "out": "5926", "idx": 238609, "score": -15.111485481262207}
24
+ {"in": "numpy", "out": "[2][3]", "idx": 238607, "score": -15.11143684387207}
25
+ {"in": "opts", "out": "3058", "idx": 238604, "score": -15.111367225646973}
26
+ {"in": "sorted", "out": "3179", "idx": 238600, "score": -15.111340522766113}
27
+ {"in": "enumerate", "out": "5413", "idx": 238573, "score": -15.111017227172852}
28
+ {"in": "exists", "out": "8083", "idx": 238568, "score": -15.110990524291992}
29
+ {"in": "startswith", "out": "8990", "idx": 238567, "score": -15.110979080200195}
30
+ {"in": "cols", "out": "なんですよね", "idx": 238562, "score": -15.110893249511719}
31
+ {"in": "indices", "out": "9897", "idx": 238542, "score": -15.11055850982666}
32
+ {"in": "zeros", "out": "0619", "idx": 238541, "score": -15.110529899597168}
33
+ {"in": "paths", "out": "6617", "idx": 238540, "score": -15.110528945922852}
34
+ {"in": "verbose", "out": "15,4", "idx": 238534, "score": -15.110383987426758}
35
+ {"in": "attrs", "out": "4994", "idx": 238527, "score": -15.110167503356934}
36
+ {"in": "cl", "out": "8.27", "idx": 238518, "score": -15.110030174255371}
37
+ {"in": "vals", "out": "2.51", "idx": 238515, "score": -15.109957695007324}
38
+ {"in": "subprocess", "out": "り出し", "idx": 238512, "score": -15.109935760498047}
39
+ {"in": "io", "out": "3.96", "idx": 238510, "score": -15.109899520874023}
40
+ {"in": "ct", "out": "7155", "idx": 238508, "score": -15.109868049621582}
41
+ {"in": "weights", "out": "5235", "idx": 238503, "score": -15.109780311584473}
42
+ {"in": "propertie", "out": "8579", "idx": 238502, "score": -15.109764099121094}
43
+ {"in": "ctypes", "out": "6657", "idx": 238500, "score": -15.1097412109375}
44
+ {"in": "vars", "out": "3554", "idx": 238497, "score": -15.109720230102539}
45
+ {"in": "coords", "out": "7.27", "idx": 238494, "score": -15.109648704528809}
46
+ {"in": "seconds", "out": "たちも", "idx": 238489, "score": -15.109630584716797}
47
+ {"in": "ts", "out": "2292", "idx": 238487, "score": -15.109574317932129}
48
+ {"in": "parsed", "out": "であることは", "idx": 238486, "score": -15.109561920166016}
49
+ {"in": "counts", "out": "4095", "idx": 238484, "score": -15.109527587890625}
50
+ {"in": "comp", "out": "という思い", "idx": 238478, "score": -15.109454154968262}
51
+ {"in": "dumps", "out": "7813", "idx": 238469, "score": -15.109336853027344}
52
+ {"in": "inputs", "out": "5870", "idx": 238464, "score": -15.109211921691895}
53
+ {"in": "cr", "out": "4979", "idx": 238456, "score": -15.10916805267334}
54
+ {"in": "methods", "out": "2813", "idx": 238455, "score": -15.109151840209961}
55
+ {"in": "colors", "out": "2.52", "idx": 238454, "score": -15.10914134979248}
56
+ {"in": "Qt", "out": "4075", "idx": 238453, "score": -15.109111785888672}
57
+ {"in": "ax", "out": "の両方", "idx": 238445, "score": -15.109016418457031}
58
+ {"in": "oo", "out": "2614", "idx": 238441, "score": -15.108963012695312}
59
+ {"in": "ep", "out": "お天気", "idx": 238439, "score": -15.108939170837402}
60
+ {"in": "astype", "out": "04.06", "idx": 238435, "score": -15.10892105102539}
61
+ {"in": "dims", "out": "9406", "idx": 238430, "score": -15.108654022216797}
62
+ {"in": "rs", "out": "||||||", "idx": 238428, "score": -15.108624458312988}
63
+ {"in": "ay", "out": "5565", "idx": 238427, "score": -15.10861587524414}
64
+ {"in": "endswith", "out": "3427", "idx": 238426, "score": -15.108598709106445}
65
+ {"in": "exceptions", "out": "4475", "idx": 238424, "score": -15.108597755432129}
66
+ {"in": "defaults", "out": "5848", "idx": 238425, "score": -15.108597755432129}
67
+ {"in": "DEFAULT", "out": "3949", "idx": 238412, "score": -15.108419418334961}
68
+ {"in": "warnings", "out": "楽しさ", "idx": 238411, "score": -15.10840892791748}
69
+ {"in": "itertool", "out": "3872", "idx": 238410, "score": -15.108405113220215}
70
+ {"in": "verify", "out": "5157", "idx": 238406, "score": -15.108345985412598}
vocamaru_log.txt ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [パラメータ数] google/mt5-small 300176768
2
+ [新しいモデルの保存先] mt5_py500
3
+ [LOG] 特殊語彙 id=0 type=3 <pad> 0.0
4
+ [LOG] 特殊語彙 id=1 type=3 </s> 0.0
5
+ [LOG] 特殊語彙 id=2 type=2 <unk> 0.0
6
+ [LOG] 特殊語彙 id=250000 type=4 ▁<extra_id_99> 0.0
7
+ [LOG] 特殊語彙 id=250001 type=4 ▁<extra_id_98> 0.0
8
+ [LOG] 特殊語彙 id=250002 type=4 ▁<extra_id_97> 0.0
9
+ [LOG] 特殊語彙 id=250003 type=4 ▁<extra_id_96> 0.0
10
+ [LOG] 特殊語彙 id=250004 type=4 ▁<extra_id_95> 0.0
11
+ [LOG] 特殊語彙 id=250005 type=4 ▁<extra_id_94> 0.0
12
+ [LOG] 特殊語彙 id=250006 type=4 ▁<extra_id_93> 0.0
13
+ [LOG] 特殊語彙 id=250007 type=4 ▁<extra_id_92> 0.0
14
+ [LOG] 特殊語彙 id=250008 type=4 ▁<extra_id_91> 0.0
15
+ [LOG] 特殊語彙 id=250009 type=4 ▁<extra_id_90> 0.0
16
+ [LOG] 特殊語彙 id=250010 type=4 ▁<extra_id_89> 0.0
17
+ [LOG] 特殊語彙 id=250011 type=4 ▁<extra_id_88> 0.0
18
+ [LOG] 特殊語彙 id=250012 type=4 ▁<extra_id_87> 0.0
19
+ [LOG] 特殊語彙 id=250013 type=4 ▁<extra_id_86> 0.0
20
+ [LOG] 特殊語彙 id=250014 type=4 ▁<extra_id_85> 0.0
21
+ [LOG] 特殊語彙 id=250015 type=4 ▁<extra_id_84> 0.0
22
+ [LOG] 特殊語彙 id=250016 type=4 ▁<extra_id_83> 0.0
23
+ [LOG] 特殊語彙 id=250017 type=4 ▁<extra_id_82> 0.0
24
+ [LOG] 特殊語彙 id=250018 type=4 ▁<extra_id_81> 0.0
25
+ [LOG] 特殊語彙 id=250019 type=4 ▁<extra_id_80> 0.0
26
+ [LOG] 特殊語彙 id=250020 type=4 ▁<extra_id_79> 0.0
27
+ [LOG] 特殊語彙 id=250021 type=4 ▁<extra_id_78> 0.0
28
+ [LOG] 特殊語彙 id=250022 type=4 ▁<extra_id_77> 0.0
29
+ [LOG] 特殊語彙 id=250023 type=4 ▁<extra_id_76> 0.0
30
+ [LOG] 特殊語彙 id=250024 type=4 ▁<extra_id_75> 0.0
31
+ [LOG] 特殊語彙 id=250025 type=4 ▁<extra_id_74> 0.0
32
+ [LOG] 特殊語彙 id=250026 type=4 ▁<extra_id_73> 0.0
33
+ [LOG] 特殊語彙 id=250027 type=4 ▁<extra_id_72> 0.0
34
+ [LOG] 特殊語彙 id=250028 type=4 ▁<extra_id_71> 0.0
35
+ [LOG] 特殊語彙 id=250029 type=4 ▁<extra_id_70> 0.0
36
+ [LOG] 特殊語彙 id=250030 type=4 ▁<extra_id_69> 0.0
37
+ [LOG] 特殊語彙 id=250031 type=4 ▁<extra_id_68> 0.0
38
+ [LOG] 特殊語彙 id=250032 type=4 ▁<extra_id_67> 0.0
39
+ [LOG] 特殊語彙 id=250033 type=4 ▁<extra_id_66> 0.0
40
+ [LOG] 特殊語彙 id=250034 type=4 ▁<extra_id_65> 0.0
41
+ [LOG] 特殊語彙 id=250035 type=4 ▁<extra_id_64> 0.0
42
+ [LOG] 特殊語彙 id=250036 type=4 ▁<extra_id_63> 0.0
43
+ [LOG] 特殊語彙 id=250037 type=4 ▁<extra_id_62> 0.0
44
+ [LOG] 特殊語彙 id=250038 type=4 ▁<extra_id_61> 0.0
45
+ [LOG] 特殊語彙 id=250039 type=4 ▁<extra_id_60> 0.0
46
+ [LOG] 特殊語彙 id=250040 type=4 ▁<extra_id_59> 0.0
47
+ [LOG] 特殊語彙 id=250041 type=4 ▁<extra_id_58> 0.0
48
+ [LOG] 特殊語彙 id=250042 type=4 ▁<extra_id_57> 0.0
49
+ [LOG] 特殊語彙 id=250043 type=4 ▁<extra_id_56> 0.0
50
+ [LOG] 特殊語彙 id=250044 type=4 ▁<extra_id_55> 0.0
51
+ [LOG] 特殊語彙 id=250045 type=4 ▁<extra_id_54> 0.0
52
+ [LOG] 特殊語彙 id=250046 type=4 ▁<extra_id_53> 0.0
53
+ [LOG] 特殊語彙 id=250047 type=4 ▁<extra_id_52> 0.0
54
+ [LOG] 特殊語彙 id=250048 type=4 ▁<extra_id_51> 0.0
55
+ [LOG] 特殊語彙 id=250049 type=4 ▁<extra_id_50> 0.0
56
+ [LOG] 特殊語彙 id=250050 type=4 ▁<extra_id_49> 0.0
57
+ [LOG] 特殊語彙 id=250051 type=4 ▁<extra_id_48> 0.0
58
+ [LOG] 特殊語彙 id=250052 type=4 ▁<extra_id_47> 0.0
59
+ [LOG] 特殊語彙 id=250053 type=4 ▁<extra_id_46> 0.0
60
+ [LOG] 特殊語彙 id=250054 type=4 ▁<extra_id_45> 0.0
61
+ [LOG] 特殊語彙 id=250055 type=4 ▁<extra_id_44> 0.0
62
+ [LOG] 特殊語彙 id=250056 type=4 ▁<extra_id_43> 0.0
63
+ [LOG] 特殊語彙 id=250057 type=4 ▁<extra_id_42> 0.0
64
+ [LOG] 特殊語彙 id=250058 type=4 ▁<extra_id_41> 0.0
65
+ [LOG] 特殊語彙 id=250059 type=4 ▁<extra_id_40> 0.0
66
+ [LOG] 特殊語彙 id=250060 type=4 ▁<extra_id_39> 0.0
67
+ [LOG] 特殊語彙 id=250061 type=4 ▁<extra_id_38> 0.0
68
+ [LOG] 特殊語彙 id=250062 type=4 ▁<extra_id_37> 0.0
69
+ [LOG] 特殊語彙 id=250063 type=4 ▁<extra_id_36> 0.0
70
+ [LOG] 特殊語彙 id=250064 type=4 ▁<extra_id_35> 0.0
71
+ [LOG] 特殊語彙 id=250065 type=4 ▁<extra_id_34> 0.0
72
+ [LOG] 特殊語彙 id=250066 type=4 ▁<extra_id_33> 0.0
73
+ [LOG] 特殊語彙 id=250067 type=4 ▁<extra_id_32> 0.0
74
+ [LOG] 特殊語彙 id=250068 type=4 ▁<extra_id_31> 0.0
75
+ [LOG] 特殊語彙 id=250069 type=4 ▁<extra_id_30> 0.0
76
+ [LOG] 特殊語彙 id=250070 type=4 ▁<extra_id_29> 0.0
77
+ [LOG] 特殊語彙 id=250071 type=4 ▁<extra_id_28> 0.0
78
+ [LOG] 特殊語彙 id=250072 type=4 ▁<extra_id_27> 0.0
79
+ [LOG] 特殊語彙 id=250073 type=4 ▁<extra_id_26> 0.0
80
+ [LOG] 特殊語彙 id=250074 type=4 ▁<extra_id_25> 0.0
81
+ [LOG] 特殊語彙 id=250075 type=4 ▁<extra_id_24> 0.0
82
+ [LOG] 特殊語彙 id=250076 type=4 ▁<extra_id_23> 0.0
83
+ [LOG] 特殊語彙 id=250077 type=4 ▁<extra_id_22> 0.0
84
+ [LOG] 特殊語彙 id=250078 type=4 ▁<extra_id_21> 0.0
85
+ [LOG] 特殊語彙 id=250079 type=4 ▁<extra_id_20> 0.0
86
+ [LOG] 特殊語彙 id=250080 type=4 ▁<extra_id_19> 0.0
87
+ [LOG] 特殊語彙 id=250081 type=4 ▁<extra_id_18> 0.0
88
+ [LOG] 特殊語彙 id=250082 type=4 ▁<extra_id_17> 0.0
89
+ [LOG] 特殊語彙 id=250083 type=4 ▁<extra_id_16> 0.0
90
+ [LOG] 特��語彙 id=250084 type=4 ▁<extra_id_15> 0.0
91
+ [LOG] 特殊語彙 id=250085 type=4 ▁<extra_id_14> 0.0
92
+ [LOG] 特殊語彙 id=250086 type=4 ▁<extra_id_13> 0.0
93
+ [LOG] 特殊語彙 id=250087 type=4 ▁<extra_id_12> 0.0
94
+ [LOG] 特殊語彙 id=250088 type=4 ▁<extra_id_11> 0.0
95
+ [LOG] 特殊語彙 id=250089 type=4 ▁<extra_id_10> 0.0
96
+ [LOG] 特殊語彙 id=250090 type=4 ▁<extra_id_9> 0.0
97
+ [LOG] 特殊語彙 id=250091 type=4 ▁<extra_id_8> 0.0
98
+ [LOG] 特殊語彙 id=250092 type=4 ▁<extra_id_7> 0.0
99
+ [LOG] 特殊語彙 id=250093 type=4 ▁<extra_id_6> 0.0
100
+ [LOG] 特殊語彙 id=250094 type=4 ▁<extra_id_5> 0.0
101
+ [LOG] 特殊語彙 id=250095 type=4 ▁<extra_id_4> 0.0
102
+ [LOG] 特殊語彙 id=250096 type=4 ▁<extra_id_3> 0.0
103
+ [LOG] 特殊語彙 id=250097 type=4 ▁<extra_id_2> 0.0
104
+ [LOG] 特殊語彙 id=250098 type=4 ▁<extra_id_1> 0.0
105
+ [LOG] 特殊語彙 id=250099 type=4 ▁<extra_id_0> 0.0
106
+ [全語彙数] 249741
107
+ [スコア統計] s
108
+ count 249741.000000
109
+ mean -13.801495
110
+ std 1.294186
111
+ min -20.280148
112
+ 25% -14.515090
113
+ 50% -13.899386
114
+ 75% -13.113684
115
+ max -2.320359
116
+ [置き換える語彙数] 70
117
+ [重複語数] 3612 トリム数 0
118
+ 全角ゴミ 189
119
+ 半角ゴミ 10054
120
+ 記号ゴミ 231
121
+ [記号ゴミ] 10474
122
+ 数字ゴミ 7052
123
+ [数字重複] 7052
124
+ [消去可能な字句] 21138
125
+ [実際に置き換える語] 70
126
+ {"in": "<nl>", "out": "▁01.03.", "idx": 238722, "score": -15.112902641296387}
127
+ {"in": "<tab>", "out": "4.84", "idx": 238721, "score": -15.11288833618164}
128
+ {"in": "<sep>", "out": "1,43", "idx": 238710, "score": -15.11279010772705}
129
+ {"in": "<code>", "out": "そんな中", "idx": 238702, "score": -15.112638473510742}
130
+ {"in": "</code>", "out": "8560", "idx": 238700, "score": -15.112624168395996}
131
+ {"in": "None", "out": "2019-09-21", "idx": 238699, "score": -15.112618446350098}
132
+ {"in": "await", "out": "02/10", "idx": 238691, "score": -15.112505912780762}
133
+ {"in": "elif", "out": "1.3.2", "idx": 238688, "score": -15.112445831298828}
134
+ {"in": "finally", "out": "7.26", "idx": 238682, "score": -15.112358093261719}
135
+ {"in": "nonlocal", "out": "周辺で", "idx": 238679, "score": -15.112297058105469}
136
+ {"in": "yield", "out": "6626", "idx": 238676, "score": -15.112284660339355}
137
+ {"in": "▁False", "out": "4584", "idx": 238670, "score": -15.112183570861816}
138
+ {"in": "▁None", "out": "8458", "idx": 238669, "score": -15.112176895141602}
139
+ {"in": "▁async", "out": "8553", "idx": 238662, "score": -15.112029075622559}
140
+ {"in": "▁await", "out": "したりする", "idx": 238661, "score": -15.112025260925293}
141
+ {"in": "▁lambda", "out": "8,500", "idx": 238657, "score": -15.111969947814941}
142
+ {"in": ":=", "out": "19.06", "idx": 238649, "score": -15.111923217773438}
143
+ {"in": "▁-", "out": "0229", "idx": 238629, "score": -15.111686706542969}
144
+ {"in": "▁/", "out": "6541", "idx": 238622, "score": -15.1116361618042}
145
+ {"in": "▁<=", "out": "10.31", "idx": 238619, "score": -15.111579895019531}
146
+ {"in": "▁>=", "out": "4948", "idx": 238617, "score": -15.11154842376709}
147
+ {"in": "▁!=", "out": "2776", "idx": 238616, "score": -15.111540794372559}
148
+ {"in": "▁:=", "out": "5926", "idx": 238609, "score": -15.111485481262207}
149
+ {"in": "numpy", "out": "[2][3]", "idx": 238607, "score": -15.11143684387207}
150
+ {"in": "opts", "out": "3058", "idx": 238604, "score": -15.111367225646973}
151
+ {"in": "sorted", "out": "3179", "idx": 238600, "score": -15.111340522766113}
152
+ {"in": "enumerate", "out": "5413", "idx": 238573, "score": -15.111017227172852}
153
+ {"in": "exists", "out": "8083", "idx": 238568, "score": -15.110990524291992}
154
+ {"in": "startswith", "out": "8990", "idx": 238567, "score": -15.110979080200195}
155
+ {"in": "cols", "out": "なんですよね", "idx": 238562, "score": -15.110893249511719}
156
+ {"in": "indices", "out": "9897", "idx": 238542, "score": -15.11055850982666}
157
+ {"in": "zeros", "out": "0619", "idx": 238541, "score": -15.110529899597168}
158
+ {"in": "paths", "out": "6617", "idx": 238540, "score": -15.110528945922852}
159
+ {"in": "verbose", "out": "15,4", "idx": 238534, "score": -15.110383987426758}
160
+ {"in": "attrs", "out": "4994", "idx": 238527, "score": -15.110167503356934}
161
+ {"in": "cl", "out": "8.27", "idx": 238518, "score": -15.110030174255371}
162
+ {"in": "vals", "out": "2.51", "idx": 238515, "score": -15.109957695007324}
163
+ {"in": "subprocess", "out": "り出し", "idx": 238512, "score": -15.109935760498047}
164
+ {"in": "io", "out": "3.96", "idx": 238510, "score": -15.109899520874023}
165
+ {"in": "ct", "out": "7155", "idx": 238508, "score": -15.109868049621582}
166
+ {"in": "weights", "out": "5235", "idx": 238503, "score": -15.109780311584473}
167
+ {"in": "propertie", "out": "8579", "idx": 238502, "score": -15.109764099121094}
168
+ {"in": "ctypes", "out": "6657", "idx": 238500, "score": -15.1097412109375}
169
+ {"in": "vars", "out": "3554", "idx": 238497, "score": -15.109720230102539}
170
+ {"in": "coords", "out": "7.27", "idx": 238494, "score": -15.109648704528809}
171
+ {"in": "seconds", "out": "たちも", "idx": 238489, "score": -15.109630584716797}
172
+ {"in": "ts", "out": "2292", "idx": 238487, "score": -15.109574317932129}
173
+ {"in": "parsed", "out": "であることは", "idx": 238486, "score": -15.109561920166016}
174
+ {"in": "counts", "out": "4095", "idx": 238484, "score": -15.109527587890625}
175
+ {"in": "comp", "out": "という思い", "idx": 238478, "score": -15.109454154968262}
176
+ {"in": "dumps", "out": "7813", "idx": 238469, "score": -15.109336853027344}
177
+ {"in": "inputs", "out": "5870", "idx": 238464, "score": -15.109211921691895}
178
+ {"in": "cr", "out": "4979", "idx": 238456, "score": -15.10916805267334}
179
+ {"in": "methods", "out": "2813", "idx": 238455, "score": -15.109151840209961}
180
+ {"in": "colors", "out": "2.52", "idx": 238454, "score": -15.10914134979248}
181
+ {"in": "Qt", "out": "4075", "idx": 238453, "score": -15.109111785888672}
182
+ {"in": "ax", "out": "の両方", "idx": 238445, "score": -15.109016418457031}
183
+ {"in": "oo", "out": "2614", "idx": 238441, "score": -15.108963012695312}
184
+ {"in": "ep", "out": "お天気", "idx": 238439, "score": -15.108939170837402}
185
+ {"in": "astype", "out": "04.06", "idx": 238435, "score": -15.10892105102539}
186
+ {"in": "dims", "out": "9406", "idx": 238430, "score": -15.108654022216797}
187
+ {"in": "rs", "out": "||||||", "idx": 238428, "score": -15.108624458312988}
188
+ {"in": "ay", "out": "5565", "idx": 238427, "score": -15.10861587524414}
189
+ {"in": "endswith", "out": "3427", "idx": 238426, "score": -15.108598709106445}
190
+ {"in": "exceptions", "out": "4475", "idx": 238424, "score": -15.108597755432129}
191
+ {"in": "defaults", "out": "5848", "idx": 238425, "score": -15.108597755432129}
192
+ {"in": "DEFAULT", "out": "3949", "idx": 238412, "score": -15.108419418334961}
193
+ {"in": "warnings", "out": "楽しさ", "idx": 238411, "score": -15.10840892791748}
194
+ {"in": "itertool", "out": "3872", "idx": 238410, "score": -15.108405113220215}
195
+ {"in": "verify", "out": "5157", "idx": 238406, "score": -15.108345985412598}
196
+ mt5_py500 PreTrainedTokenizer(name_or_path='mt5_py500', vocab_size=250100, model_max_len=1000000000000000019884624838656, is_fast=False, padding_side='right', truncation_side='right', special_tokens={'eos_token': '</s>', 'unk_token': '<unk>', 'pad_token': '<pad>'})
197
+ [ミス] := 4 [259, 267, 349, 1]
198
+ [ミス] ▁:= 4 [259, 267, 349, 1]
199
+ [ミス] io 4 [259, 266, 268, 1]
200
+ [ミス] ts 4 [259, 270, 263, 1]
201
+ [ミス] ep 4 [259, 265, 325, 1]
202
+ [ミス] rs 4 [259, 286, 263, 1]
203
+ [ミス] defaults 4 [259, 2164, 263, 1]
204
+ <nl><nl> [259, 238722, 238722, 1]
205
+ <123> <100> <1> [1042, 11352, 669, 1042, 2251, 669, 1042, 153002, 1]
206
+ <extra_id_0><extra_id_99> [250099, 250000, 1]
207
+
208
+
209
+ [1]