bayartsogt commited on
Commit
7aa917b
1 Parent(s): cf00d05

End of training

Browse files
added_tokens.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|af|>": 50327,
3
+ "<|am|>": 50334,
4
+ "<|ar|>": 50272,
5
+ "<|as|>": 50350,
6
+ "<|az|>": 50304,
7
+ "<|ba|>": 50355,
8
+ "<|be|>": 50330,
9
+ "<|bg|>": 50292,
10
+ "<|bn|>": 50302,
11
+ "<|bo|>": 50347,
12
+ "<|br|>": 50309,
13
+ "<|bs|>": 50315,
14
+ "<|ca|>": 50270,
15
+ "<|cs|>": 50283,
16
+ "<|cy|>": 50297,
17
+ "<|da|>": 50285,
18
+ "<|de|>": 50261,
19
+ "<|el|>": 50281,
20
+ "<|endoftext|>": 50257,
21
+ "<|en|>": 50259,
22
+ "<|es|>": 50262,
23
+ "<|et|>": 50307,
24
+ "<|eu|>": 50310,
25
+ "<|fa|>": 50300,
26
+ "<|fi|>": 50277,
27
+ "<|fo|>": 50338,
28
+ "<|fr|>": 50265,
29
+ "<|gl|>": 50319,
30
+ "<|gu|>": 50333,
31
+ "<|haw|>": 50352,
32
+ "<|ha|>": 50354,
33
+ "<|hi|>": 50276,
34
+ "<|hr|>": 50291,
35
+ "<|ht|>": 50339,
36
+ "<|hu|>": 50286,
37
+ "<|hy|>": 50312,
38
+ "<|id|>": 50275,
39
+ "<|is|>": 50311,
40
+ "<|it|>": 50274,
41
+ "<|iw|>": 50279,
42
+ "<|ja|>": 50266,
43
+ "<|jw|>": 50356,
44
+ "<|ka|>": 50329,
45
+ "<|kk|>": 50316,
46
+ "<|km|>": 50323,
47
+ "<|kn|>": 50306,
48
+ "<|ko|>": 50264,
49
+ "<|la|>": 50294,
50
+ "<|lb|>": 50345,
51
+ "<|ln|>": 50353,
52
+ "<|lo|>": 50336,
53
+ "<|lt|>": 50293,
54
+ "<|lv|>": 50301,
55
+ "<|mg|>": 50349,
56
+ "<|mi|>": 50295,
57
+ "<|mk|>": 50308,
58
+ "<|ml|>": 50296,
59
+ "<|mn|>": 50314,
60
+ "<|mr|>": 50320,
61
+ "<|ms|>": 50282,
62
+ "<|mt|>": 50343,
63
+ "<|my|>": 50346,
64
+ "<|ne|>": 50313,
65
+ "<|nl|>": 50271,
66
+ "<|nn|>": 50342,
67
+ "<|nocaptions|>": 50362,
68
+ "<|notimestamps|>": 50363,
69
+ "<|no|>": 50288,
70
+ "<|oc|>": 50328,
71
+ "<|pa|>": 50321,
72
+ "<|pl|>": 50269,
73
+ "<|ps|>": 50340,
74
+ "<|pt|>": 50267,
75
+ "<|ro|>": 50284,
76
+ "<|ru|>": 50263,
77
+ "<|sa|>": 50344,
78
+ "<|sd|>": 50332,
79
+ "<|si|>": 50322,
80
+ "<|sk|>": 50298,
81
+ "<|sl|>": 50305,
82
+ "<|sn|>": 50324,
83
+ "<|so|>": 50326,
84
+ "<|sq|>": 50317,
85
+ "<|sr|>": 50303,
86
+ "<|startoflm|>": 50360,
87
+ "<|startofprev|>": 50361,
88
+ "<|startoftranscript|>": 50258,
89
+ "<|su|>": 50357,
90
+ "<|sv|>": 50273,
91
+ "<|sw|>": 50318,
92
+ "<|ta|>": 50287,
93
+ "<|te|>": 50299,
94
+ "<|tg|>": 50331,
95
+ "<|th|>": 50289,
96
+ "<|tk|>": 50341,
97
+ "<|tl|>": 50348,
98
+ "<|transcribe|>": 50359,
99
+ "<|translate|>": 50358,
100
+ "<|tr|>": 50268,
101
+ "<|tt|>": 50351,
102
+ "<|uk|>": 50280,
103
+ "<|ur|>": 50290,
104
+ "<|uz|>": 50337,
105
+ "<|vi|>": 50278,
106
+ "<|yi|>": 50335,
107
+ "<|yo|>": 50325,
108
+ "<|zh|>": 50260
109
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
normalizer.json ADDED
@@ -0,0 +1,1742 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "accessorise": "accessorize",
3
+ "accessorised": "accessorized",
4
+ "accessorises": "accessorizes",
5
+ "accessorising": "accessorizing",
6
+ "acclimatisation": "acclimatization",
7
+ "acclimatise": "acclimatize",
8
+ "acclimatised": "acclimatized",
9
+ "acclimatises": "acclimatizes",
10
+ "acclimatising": "acclimatizing",
11
+ "accoutrements": "accouterments",
12
+ "aeon": "eon",
13
+ "aeons": "eons",
14
+ "aerogramme": "aerogram",
15
+ "aerogrammes": "aerograms",
16
+ "aeroplane": "airplane",
17
+ "aeroplanes": "airplanes",
18
+ "aesthete": "esthete",
19
+ "aesthetes": "esthetes",
20
+ "aesthetic": "esthetic",
21
+ "aesthetically": "esthetically",
22
+ "aesthetics": "esthetics",
23
+ "aetiology": "etiology",
24
+ "ageing": "aging",
25
+ "aggrandisement": "aggrandizement",
26
+ "agonise": "agonize",
27
+ "agonised": "agonized",
28
+ "agonises": "agonizes",
29
+ "agonising": "agonizing",
30
+ "agonisingly": "agonizingly",
31
+ "almanack": "almanac",
32
+ "almanacks": "almanacs",
33
+ "aluminium": "aluminum",
34
+ "amortisable": "amortizable",
35
+ "amortisation": "amortization",
36
+ "amortisations": "amortizations",
37
+ "amortise": "amortize",
38
+ "amortised": "amortized",
39
+ "amortises": "amortizes",
40
+ "amortising": "amortizing",
41
+ "amphitheatre": "amphitheater",
42
+ "amphitheatres": "amphitheaters",
43
+ "anaemia": "anemia",
44
+ "anaemic": "anemic",
45
+ "anaesthesia": "anesthesia",
46
+ "anaesthetic": "anesthetic",
47
+ "anaesthetics": "anesthetics",
48
+ "anaesthetise": "anesthetize",
49
+ "anaesthetised": "anesthetized",
50
+ "anaesthetises": "anesthetizes",
51
+ "anaesthetising": "anesthetizing",
52
+ "anaesthetist": "anesthetist",
53
+ "anaesthetists": "anesthetists",
54
+ "anaesthetize": "anesthetize",
55
+ "anaesthetized": "anesthetized",
56
+ "anaesthetizes": "anesthetizes",
57
+ "anaesthetizing": "anesthetizing",
58
+ "analogue": "analog",
59
+ "analogues": "analogs",
60
+ "analyse": "analyze",
61
+ "analysed": "analyzed",
62
+ "analyses": "analyzes",
63
+ "analysing": "analyzing",
64
+ "anglicise": "anglicize",
65
+ "anglicised": "anglicized",
66
+ "anglicises": "anglicizes",
67
+ "anglicising": "anglicizing",
68
+ "annualised": "annualized",
69
+ "antagonise": "antagonize",
70
+ "antagonised": "antagonized",
71
+ "antagonises": "antagonizes",
72
+ "antagonising": "antagonizing",
73
+ "apologise": "apologize",
74
+ "apologised": "apologized",
75
+ "apologises": "apologizes",
76
+ "apologising": "apologizing",
77
+ "appal": "appall",
78
+ "appals": "appalls",
79
+ "appetiser": "appetizer",
80
+ "appetisers": "appetizers",
81
+ "appetising": "appetizing",
82
+ "appetisingly": "appetizingly",
83
+ "arbour": "arbor",
84
+ "arbours": "arbors",
85
+ "archaeologically": "archeologically",
86
+ "archaeologist": "archeologist",
87
+ "archaeologists": "archeologists",
88
+ "archaeology": "archeology</span>",
89
+ "archeological": "archaeological",
90
+ "ardour": "ardor",
91
+ "armour": "armor",
92
+ "armoured": "armored",
93
+ "armourer": "armorer",
94
+ "armourers": "armorers",
95
+ "armouries": "armories",
96
+ "armoury": "armory",
97
+ "artefact": "artifact",
98
+ "artefacts": "artifacts",
99
+ "authorise": "authorize",
100
+ "authorised": "authorized",
101
+ "authorises": "authorizes",
102
+ "authorising": "authorizing",
103
+ "axe": "ax",
104
+ "backpedalled": "backpedaled",
105
+ "backpedalling": "backpedaling",
106
+ "bannister": "banister",
107
+ "bannisters": "banisters",
108
+ "baptise": "baptize",
109
+ "baptised": "baptized",
110
+ "baptises": "baptizes",
111
+ "baptising": "baptizing",
112
+ "bastardise": "bastardize",
113
+ "bastardised": "bastardized",
114
+ "bastardises": "bastardizes",
115
+ "bastardising": "bastardizing",
116
+ "battleax": "battleaxe",
117
+ "baulk": "balk",
118
+ "baulked": "balked",
119
+ "baulking": "balking",
120
+ "baulks": "balks",
121
+ "bedevilled": "bedeviled",
122
+ "bedevilling": "bedeviling",
123
+ "behaviour": "behavior",
124
+ "behavioural": "behavioral",
125
+ "behaviourism": "behaviorism",
126
+ "behaviourist": "behaviorist",
127
+ "behaviourists": "behaviorists",
128
+ "behaviours": "behaviors",
129
+ "behove": "behoove",
130
+ "behoved": "behooved",
131
+ "behoves": "behooves",
132
+ "bejewelled": "bejeweled",
133
+ "belabour": "belabor",
134
+ "belaboured": "belabored",
135
+ "belabouring": "belaboring",
136
+ "belabours": "belabors",
137
+ "bevelled": "beveled",
138
+ "bevvies": "bevies",
139
+ "bevvy": "bevy",
140
+ "biassed": "biased",
141
+ "biassing": "biasing",
142
+ "bingeing": "binging",
143
+ "bougainvillaea": "bougainvillea",
144
+ "bougainvillaeas": "bougainvilleas",
145
+ "bowdlerise": "bowdlerize",
146
+ "bowdlerised": "bowdlerized",
147
+ "bowdlerises": "bowdlerizes",
148
+ "bowdlerising": "bowdlerizing",
149
+ "breathalyse": "breathalyze",
150
+ "breathalysed": "breathalyzed",
151
+ "breathalyser": "breathalyzer",
152
+ "breathalysers": "breathalyzers",
153
+ "breathalyses": "breathalyzes",
154
+ "breathalysing": "breathalyzing",
155
+ "brutalise": "brutalize",
156
+ "brutalised": "brutalized",
157
+ "brutalises": "brutalizes",
158
+ "brutalising": "brutalizing",
159
+ "busses": "buses",
160
+ "bussing": "busing",
161
+ "caesarean": "cesarean",
162
+ "caesareans": "cesareans",
163
+ "calibre": "caliber",
164
+ "calibres": "calibers",
165
+ "calliper": "caliper",
166
+ "callipers": "calipers",
167
+ "callisthenics": "calisthenics",
168
+ "canalise": "canalize",
169
+ "canalised": "canalized",
170
+ "canalises": "canalizes",
171
+ "canalising": "canalizing",
172
+ "cancelation": "cancellation",
173
+ "cancelations": "cancellations",
174
+ "cancelled": "canceled",
175
+ "cancelling": "canceling",
176
+ "candour": "candor",
177
+ "cannibalise": "cannibalize",
178
+ "cannibalised": "cannibalized",
179
+ "cannibalises": "cannibalizes",
180
+ "cannibalising": "cannibalizing",
181
+ "canonise": "canonize",
182
+ "canonised": "canonized",
183
+ "canonises": "canonizes",
184
+ "canonising": "canonizing",
185
+ "capitalise": "capitalize",
186
+ "capitalised": "capitalized",
187
+ "capitalises": "capitalizes",
188
+ "capitalising": "capitalizing",
189
+ "caramelise": "caramelize",
190
+ "caramelised": "caramelized",
191
+ "caramelises": "caramelizes",
192
+ "caramelising": "caramelizing",
193
+ "carbonise": "carbonize",
194
+ "carbonised": "carbonized",
195
+ "carbonises": "carbonizes",
196
+ "carbonising": "carbonizing",
197
+ "carolled": "caroled",
198
+ "carolling": "caroling",
199
+ "catalogue": "catalog",
200
+ "catalogued": "cataloged",
201
+ "catalogues": "catalogs",
202
+ "cataloguing": "cataloging",
203
+ "catalyse": "catalyze",
204
+ "catalysed": "catalyzed",
205
+ "catalyses": "catalyzes",
206
+ "catalysing": "catalyzing",
207
+ "categorise": "categorize",
208
+ "categorised": "categorized",
209
+ "categorises": "categorizes",
210
+ "categorising": "categorizing",
211
+ "cauterise": "cauterize",
212
+ "cauterised": "cauterized",
213
+ "cauterises": "cauterizes",
214
+ "cauterising": "cauterizing",
215
+ "cavilled": "caviled",
216
+ "cavilling": "caviling",
217
+ "centigramme": "centigram",
218
+ "centigrammes": "centigrams",
219
+ "centilitre": "centiliter",
220
+ "centilitres": "centiliters",
221
+ "centimetre": "centimeter",
222
+ "centimetres": "centimeters",
223
+ "centralise": "centralize",
224
+ "centralised": "centralized",
225
+ "centralises": "centralizes",
226
+ "centralising": "centralizing",
227
+ "centre": "center",
228
+ "centred": "centered",
229
+ "centrefold": "centerfold",
230
+ "centrefolds": "centerfolds",
231
+ "centrepiece": "centerpiece",
232
+ "centrepieces": "centerpieces",
233
+ "centres": "centers",
234
+ "channelled": "channeled",
235
+ "channelling": "channeling",
236
+ "characterise": "characterize",
237
+ "characterised": "characterized",
238
+ "characterises": "characterizes",
239
+ "characterising": "characterizing",
240
+ "cheque": "check",
241
+ "chequebook": "checkbook",
242
+ "chequebooks": "checkbooks",
243
+ "chequered": "checkered",
244
+ "cheques": "checks",
245
+ "chilli": "chili",
246
+ "chimaera": "chimera",
247
+ "chimaeras": "chimeras",
248
+ "chiselled": "chiseled",
249
+ "chiselling": "chiseling",
250
+ "circularise": "circularize",
251
+ "circularised": "circularized",
252
+ "circularises": "circularizes",
253
+ "circularising": "circularizing",
254
+ "civilise": "civilize",
255
+ "civilised": "civilized",
256
+ "civilises": "civilizes",
257
+ "civilising": "civilizing",
258
+ "clamour": "clamor",
259
+ "clamoured": "clamored",
260
+ "clamouring": "clamoring",
261
+ "clamours": "clamors",
262
+ "clangour": "clangor",
263
+ "clarinettist": "clarinetist",
264
+ "clarinettists": "clarinetists",
265
+ "collectivise": "collectivize",
266
+ "collectivised": "collectivized",
267
+ "collectivises": "collectivizes",
268
+ "collectivising": "collectivizing",
269
+ "colonisation": "colonization",
270
+ "colonise": "colonize",
271
+ "colonised": "colonized",
272
+ "coloniser": "colonizer",
273
+ "colonisers": "colonizers",
274
+ "colonises": "colonizes",
275
+ "colonising": "colonizing",
276
+ "colour": "color",
277
+ "colourant": "colorant",
278
+ "colourants": "colorants",
279
+ "coloured": "colored",
280
+ "coloureds": "coloreds",
281
+ "colourful": "colorful",
282
+ "colourfully": "colorfully",
283
+ "colouring": "coloring",
284
+ "colourize": "colorize",
285
+ "colourized": "colorized",
286
+ "colourizes": "colorizes",
287
+ "colourizing": "colorizing",
288
+ "colourless": "colorless",
289
+ "colours": "colors",
290
+ "commercialise": "commercialize",
291
+ "commercialised": "commercialized",
292
+ "commercialises": "commercializes",
293
+ "commercialising": "commercializing",
294
+ "compartmentalise": "compartmentalize",
295
+ "compartmentalised": "compartmentalized",
296
+ "compartmentalises": "compartmentalizes",
297
+ "compartmentalising": "compartmentalizing",
298
+ "computerise": "computerize",
299
+ "computerised": "computerized",
300
+ "computerises": "computerizes",
301
+ "computerising": "computerizing",
302
+ "conceptualise": "conceptualize",
303
+ "conceptualised": "conceptualized",
304
+ "conceptualises": "conceptualizes",
305
+ "conceptualising": "conceptualizing",
306
+ "connexion": "connection",
307
+ "connexions": "connections",
308
+ "contextualise": "contextualize",
309
+ "contextualised": "contextualized",
310
+ "contextualises": "contextualizes",
311
+ "contextualising": "contextualizing",
312
+ "cosier": "cozier",
313
+ "cosies": "cozies",
314
+ "cosiest": "coziest",
315
+ "cosily": "cozily",
316
+ "cosiness": "coziness",
317
+ "cosy": "cozy",
318
+ "councillor": "councilor",
319
+ "councillors": "councilors",
320
+ "counselled": "counseled",
321
+ "counselling": "counseling",
322
+ "counsellor": "counselor",
323
+ "counsellors": "counselors",
324
+ "crenelated": "crenellated",
325
+ "criminalise": "criminalize",
326
+ "criminalised": "criminalized",
327
+ "criminalises": "criminalizes",
328
+ "criminalising": "criminalizing",
329
+ "criticise": "criticize",
330
+ "criticised": "criticized",
331
+ "criticises": "criticizes",
332
+ "criticising": "criticizing",
333
+ "crueller": "crueler",
334
+ "cruellest": "cruelest",
335
+ "crystallisation": "crystallization",
336
+ "crystallise": "crystallize",
337
+ "crystallised": "crystallized",
338
+ "crystallises": "crystallizes",
339
+ "crystallising": "crystallizing",
340
+ "cudgelled": "cudgeled",
341
+ "cudgelling": "cudgeling",
342
+ "customise": "customize",
343
+ "customised": "customized",
344
+ "customises": "customizes",
345
+ "customising": "customizing",
346
+ "cypher": "cipher",
347
+ "cyphers": "ciphers",
348
+ "decentralisation": "decentralization",
349
+ "decentralise": "decentralize",
350
+ "decentralised": "decentralized",
351
+ "decentralises": "decentralizes",
352
+ "decentralising": "decentralizing",
353
+ "decriminalisation": "decriminalization",
354
+ "decriminalise": "decriminalize",
355
+ "decriminalised": "decriminalized",
356
+ "decriminalises": "decriminalizes",
357
+ "decriminalising": "decriminalizing",
358
+ "defence": "defense",
359
+ "defenceless": "defenseless",
360
+ "defences": "defenses",
361
+ "dehumanisation": "dehumanization",
362
+ "dehumanise": "dehumanize",
363
+ "dehumanised": "dehumanized",
364
+ "dehumanises": "dehumanizes",
365
+ "dehumanising": "dehumanizing",
366
+ "demeanour": "demeanor",
367
+ "demilitarisation": "demilitarization",
368
+ "demilitarise": "demilitarize",
369
+ "demilitarised": "demilitarized",
370
+ "demilitarises": "demilitarizes",
371
+ "demilitarising": "demilitarizing",
372
+ "demobilisation": "demobilization",
373
+ "demobilise": "demobilize",
374
+ "demobilised": "demobilized",
375
+ "demobilises": "demobilizes",
376
+ "demobilising": "demobilizing",
377
+ "democratisation": "democratization",
378
+ "democratise": "democratize",
379
+ "democratised": "democratized",
380
+ "democratises": "democratizes",
381
+ "democratising": "democratizing",
382
+ "demonise": "demonize",
383
+ "demonised": "demonized",
384
+ "demonises": "demonizes",
385
+ "demonising": "demonizing",
386
+ "demoralisation": "demoralization",
387
+ "demoralise": "demoralize",
388
+ "demoralised": "demoralized",
389
+ "demoralises": "demoralizes",
390
+ "demoralising": "demoralizing",
391
+ "denationalisation": "denationalization",
392
+ "denationalise": "denationalize",
393
+ "denationalised": "denationalized",
394
+ "denationalises": "denationalizes",
395
+ "denationalising": "denationalizing",
396
+ "deodorise": "deodorize",
397
+ "deodorised": "deodorized",
398
+ "deodorises": "deodorizes",
399
+ "deodorising": "deodorizing",
400
+ "depersonalise": "depersonalize",
401
+ "depersonalised": "depersonalized",
402
+ "depersonalises": "depersonalizes",
403
+ "depersonalising": "depersonalizing",
404
+ "deputise": "deputize",
405
+ "deputised": "deputized",
406
+ "deputises": "deputizes",
407
+ "deputising": "deputizing",
408
+ "desensitisation": "desensitization",
409
+ "desensitise": "desensitize",
410
+ "desensitised": "desensitized",
411
+ "desensitises": "desensitizes",
412
+ "desensitising": "desensitizing",
413
+ "destabilisation": "destabilization",
414
+ "destabilise": "destabilize",
415
+ "destabilised": "destabilized",
416
+ "destabilises": "destabilizes",
417
+ "destabilising": "destabilizing",
418
+ "dialled": "dialed",
419
+ "dialling": "dialing",
420
+ "dialogue": "dialog",
421
+ "dialogues": "dialogs",
422
+ "diarrhoea": "diarrhea",
423
+ "digitise": "digitize",
424
+ "digitised": "digitized",
425
+ "digitises": "digitizes",
426
+ "digitising": "digitizing",
427
+ "disc": "disk",
428
+ "discolour": "discolor",
429
+ "discoloured": "discolored",
430
+ "discolouring": "discoloring",
431
+ "discolours": "discolors",
432
+ "discs": "disks",
433
+ "disembowelled": "disemboweled",
434
+ "disembowelling": "disemboweling",
435
+ "disfavour": "disfavor",
436
+ "dishevelled": "disheveled",
437
+ "dishonour": "dishonor",
438
+ "dishonourable": "dishonorable",
439
+ "dishonourably": "dishonorably",
440
+ "dishonoured": "dishonored",
441
+ "dishonouring": "dishonoring",
442
+ "dishonours": "dishonors",
443
+ "disorganisation": "disorganization",
444
+ "disorganised": "disorganized",
445
+ "distil": "distill",
446
+ "distils": "distills",
447
+ "dramatisation": "dramatization",
448
+ "dramatisations": "dramatizations",
449
+ "dramatise": "dramatize",
450
+ "dramatised": "dramatized",
451
+ "dramatises": "dramatizes",
452
+ "dramatising": "dramatizing",
453
+ "draught": "draft",
454
+ "draughtboard": "draftboard",
455
+ "draughtboards": "draftboards",
456
+ "draughtier": "draftier",
457
+ "draughtiest": "draftiest",
458
+ "draughts": "drafts",
459
+ "draughtsman": "draftsman",
460
+ "draughtsmanship": "draftsmanship",
461
+ "draughtsmen": "draftsmen",
462
+ "draughtswoman": "draftswoman",
463
+ "draughtswomen": "draftswomen",
464
+ "draughty": "drafty",
465
+ "drivelled": "driveled",
466
+ "drivelling": "driveling",
467
+ "duelled": "dueled",
468
+ "duelling": "dueling",
469
+ "economise": "economize",
470
+ "economised": "economized",
471
+ "economises": "economizes",
472
+ "economising": "economizing",
473
+ "editorialise": "editorialize",
474
+ "editorialised": "editorialized",
475
+ "editorialises": "editorializes",
476
+ "editorialising": "editorializing",
477
+ "edoema": "edema",
478
+ "empathise": "empathize",
479
+ "empathised": "empathized",
480
+ "empathises": "empathizes",
481
+ "empathising": "empathizing",
482
+ "emphasise": "emphasize",
483
+ "emphasised": "emphasized",
484
+ "emphasises": "emphasizes",
485
+ "emphasising": "emphasizing",
486
+ "enamelled": "enameled",
487
+ "enamelling": "enameling",
488
+ "enamoured": "enamored",
489
+ "encyclopaedia": "encyclopedia",
490
+ "encyclopaedias": "encyclopedias",
491
+ "encyclopaedic": "encyclopedic",
492
+ "endeavour": "endeavor",
493
+ "endeavoured": "endeavored",
494
+ "endeavouring": "endeavoring",
495
+ "endeavours": "endeavors",
496
+ "energise": "energize",
497
+ "energised": "energized",
498
+ "energises": "energizes",
499
+ "energising": "energizing",
500
+ "enrol": "enroll",
501
+ "enrols": "enrolls",
502
+ "enthral": "enthrall",
503
+ "enthrals": "enthralls",
504
+ "epaulette": "epaulet",
505
+ "epaulettes": "epaulets",
506
+ "epicentre": "epicenter",
507
+ "epicentres": "epicenters",
508
+ "epilogue": "epilog",
509
+ "epilogues": "epilogs",
510
+ "epitomise": "epitomize",
511
+ "epitomised": "epitomized",
512
+ "epitomises": "epitomizes",
513
+ "epitomising": "epitomizing",
514
+ "equalisation": "equalization",
515
+ "equalise": "equalize",
516
+ "equalised": "equalized",
517
+ "equaliser": "equalizer",
518
+ "equalisers": "equalizers",
519
+ "equalises": "equalizes",
520
+ "equalising": "equalizing",
521
+ "eulogise": "eulogize",
522
+ "eulogised": "eulogized",
523
+ "eulogises": "eulogizes",
524
+ "eulogising": "eulogizing",
525
+ "evangelise": "evangelize",
526
+ "evangelised": "evangelized",
527
+ "evangelises": "evangelizes",
528
+ "evangelising": "evangelizing",
529
+ "exorcise": "exorcize",
530
+ "exorcised": "exorcized",
531
+ "exorcises": "exorcizes",
532
+ "exorcising": "exorcizing",
533
+ "extemporisation": "extemporization",
534
+ "extemporise": "extemporize",
535
+ "extemporised": "extemporized",
536
+ "extemporises": "extemporizes",
537
+ "extemporising": "extemporizing",
538
+ "externalisation": "externalization",
539
+ "externalisations": "externalizations",
540
+ "externalise": "externalize",
541
+ "externalised": "externalized",
542
+ "externalises": "externalizes",
543
+ "externalising": "externalizing",
544
+ "factorise": "factorize",
545
+ "factorised": "factorized",
546
+ "factorises": "factorizes",
547
+ "factorising": "factorizing",
548
+ "faecal": "fecal",
549
+ "faeces": "feces",
550
+ "familiarisation": "familiarization",
551
+ "familiarise": "familiarize",
552
+ "familiarised": "familiarized",
553
+ "familiarises": "familiarizes",
554
+ "familiarising": "familiarizing",
555
+ "fantasise": "fantasize",
556
+ "fantasised": "fantasized",
557
+ "fantasises": "fantasizes",
558
+ "fantasising": "fantasizing",
559
+ "favour": "favor",
560
+ "favourable": "favorable",
561
+ "favourably": "favorably",
562
+ "favoured": "favored",
563
+ "favouring": "favoring",
564
+ "favourite": "favorite",
565
+ "favourites": "favorites",
566
+ "favouritism": "favoritism",
567
+ "favours": "favors",
568
+ "feminise": "feminize",
569
+ "feminised": "feminized",
570
+ "feminises": "feminizes",
571
+ "feminising": "feminizing",
572
+ "fertilisation": "fertilization",
573
+ "fertilise": "fertilize",
574
+ "fertilised": "fertilized",
575
+ "fertiliser": "fertilizer",
576
+ "fertilisers": "fertilizers",
577
+ "fertilises": "fertilizes",
578
+ "fertilising": "fertilizing",
579
+ "fervour": "fervor",
580
+ "fibre": "fiber",
581
+ "fibreglass": "fiberglass",
582
+ "fibres": "fibers",
583
+ "fictionalisation": "fictionalization",
584
+ "fictionalisations": "fictionalizations",
585
+ "fictionalise": "fictionalize",
586
+ "fictionalised": "fictionalized",
587
+ "fictionalises": "fictionalizes",
588
+ "fictionalising": "fictionalizing",
589
+ "fillet": "filet",
590
+ "filleted": "fileted",
591
+ "filleting": "fileting",
592
+ "fillets": "filets",
593
+ "finalisation": "finalization",
594
+ "finalise": "finalize",
595
+ "finalised": "finalized",
596
+ "finalises": "finalizes",
597
+ "finalising": "finalizing",
598
+ "flautist": "flutist",
599
+ "flautists": "flutists",
600
+ "flavour": "flavor",
601
+ "flavoured": "flavored",
602
+ "flavouring": "flavoring",
603
+ "flavourings": "flavorings",
604
+ "flavourless": "flavorless",
605
+ "flavours": "flavors",
606
+ "flavoursome": "flavorsome",
607
+ "flyer / flier": "flier / flyer",
608
+ "foetal": "fetal",
609
+ "foetid": "fetid",
610
+ "foetus": "fetus",
611
+ "foetuses": "fetuses",
612
+ "formalisation": "formalization",
613
+ "formalise": "formalize",
614
+ "formalised": "formalized",
615
+ "formalises": "formalizes",
616
+ "formalising": "formalizing",
617
+ "fossilisation": "fossilization",
618
+ "fossilise": "fossilize",
619
+ "fossilised": "fossilized",
620
+ "fossilises": "fossilizes",
621
+ "fossilising": "fossilizing",
622
+ "fraternisation": "fraternization",
623
+ "fraternise": "fraternize",
624
+ "fraternised": "fraternized",
625
+ "fraternises": "fraternizes",
626
+ "fraternising": "fraternizing",
627
+ "fulfil": "fulfill",
628
+ "fulfilment": "fulfillment",
629
+ "fulfils": "fulfills",
630
+ "funnelled": "funneled",
631
+ "funnelling": "funneling",
632
+ "gage": "gauge",
633
+ "gaged": "gauged",
634
+ "gages": "gauges",
635
+ "gaging": "gauging",
636
+ "galvanise": "galvanize",
637
+ "galvanised": "galvanized",
638
+ "galvanises": "galvanizes",
639
+ "galvanising": "galvanizing",
640
+ "gambolled": "gamboled",
641
+ "gambolling": "gamboling",
642
+ "gaol": "jail",
643
+ "gaolbird": "jailbird",
644
+ "gaolbirds": "jailbirds",
645
+ "gaolbreak": "jailbreak",
646
+ "gaolbreaks": "jailbreaks",
647
+ "gaoled": "jailed",
648
+ "gaoler": "jailer",
649
+ "gaolers": "jailers",
650
+ "gaoling": "jailing",
651
+ "gaols": "jails",
652
+ "gasses": "gases",
653
+ "generalisation": "generalization",
654
+ "generalisations": "generalizations",
655
+ "generalise": "generalize",
656
+ "generalised": "generalized",
657
+ "generalises": "generalizes",
658
+ "generalising": "generalizing",
659
+ "ghettoise": "ghettoize",
660
+ "ghettoised": "ghettoized",
661
+ "ghettoises": "ghettoizes",
662
+ "ghettoising": "ghettoizing",
663
+ "gipsies": "gypsies",
664
+ "glamor": "glamour",
665
+ "glamorise": "glamorize",
666
+ "glamorised": "glamorized",
667
+ "glamorises": "glamorizes",
668
+ "glamorising": "glamorizing",
669
+ "globalisation": "globalization",
670
+ "globalise": "globalize",
671
+ "globalised": "globalized",
672
+ "globalises": "globalizes",
673
+ "globalising": "globalizing",
674
+ "glueing": "gluing",
675
+ "goitre": "goiter",
676
+ "goitres": "goiters",
677
+ "gonorrhoea": "gonorrhea",
678
+ "gramme": "gram",
679
+ "grammes": "grams",
680
+ "gravelled": "graveled",
681
+ "grey": "gray",
682
+ "greyed": "grayed",
683
+ "greying": "graying",
684
+ "greyish": "grayish",
685
+ "greyness": "grayness",
686
+ "greys": "grays",
687
+ "grovelled": "groveled",
688
+ "grovelling": "groveling",
689
+ "groyne": "groin",
690
+ "groynes": "groins",
691
+ "gruelling": "grueling",
692
+ "gruellingly": "gruelingly",
693
+ "gryphon": "griffin",
694
+ "gryphons": "griffins",
695
+ "gynaecological": "gynecological",
696
+ "gynaecologist": "gynecologist",
697
+ "gynaecologists": "gynecologists",
698
+ "gynaecology": "gynecology",
699
+ "haematological": "hematological",
700
+ "haematologist": "hematologist",
701
+ "haematologists": "hematologists",
702
+ "haematology": "hematology",
703
+ "haemoglobin": "hemoglobin",
704
+ "haemophilia": "hemophilia",
705
+ "haemophiliac": "hemophiliac",
706
+ "haemophiliacs": "hemophiliacs",
707
+ "haemorrhage": "hemorrhage",
708
+ "haemorrhaged": "hemorrhaged",
709
+ "haemorrhages": "hemorrhages",
710
+ "haemorrhaging": "hemorrhaging",
711
+ "haemorrhoids": "hemorrhoids",
712
+ "harbour": "harbor",
713
+ "harboured": "harbored",
714
+ "harbouring": "harboring",
715
+ "harbours": "harbors",
716
+ "harmonisation": "harmonization",
717
+ "harmonise": "harmonize",
718
+ "harmonised": "harmonized",
719
+ "harmonises": "harmonizes",
720
+ "harmonising": "harmonizing",
721
+ "homoeopath": "homeopath",
722
+ "homoeopathic": "homeopathic",
723
+ "homoeopaths": "homeopaths",
724
+ "homoeopathy": "homeopathy",
725
+ "homogenise": "homogenize",
726
+ "homogenised": "homogenized",
727
+ "homogenises": "homogenizes",
728
+ "homogenising": "homogenizing",
729
+ "honour": "honor",
730
+ "honourable": "honorable",
731
+ "honourably": "honorably",
732
+ "honoured": "honored",
733
+ "honouring": "honoring",
734
+ "honours": "honors",
735
+ "hospitalisation": "hospitalization",
736
+ "hospitalise": "hospitalize",
737
+ "hospitalised": "hospitalized",
738
+ "hospitalises": "hospitalizes",
739
+ "hospitalising": "hospitalizing",
740
+ "humanise": "humanize",
741
+ "humanised": "humanized",
742
+ "humanises": "humanizes",
743
+ "humanising": "humanizing",
744
+ "humour": "humor",
745
+ "humoured": "humored",
746
+ "humouring": "humoring",
747
+ "humourless": "humorless",
748
+ "humours": "humors",
749
+ "hybridise": "hybridize",
750
+ "hybridised": "hybridized",
751
+ "hybridises": "hybridizes",
752
+ "hybridising": "hybridizing",
753
+ "hypnotise": "hypnotize",
754
+ "hypnotised": "hypnotized",
755
+ "hypnotises": "hypnotizes",
756
+ "hypnotising": "hypnotizing",
757
+ "hypothesise": "hypothesize",
758
+ "hypothesised": "hypothesized",
759
+ "hypothesises": "hypothesizes",
760
+ "hypothesising": "hypothesizing",
761
+ "idealisation": "idealization",
762
+ "idealise": "idealize",
763
+ "idealised": "idealized",
764
+ "idealises": "idealizes",
765
+ "idealising": "idealizing",
766
+ "idolise": "idolize",
767
+ "idolised": "idolized",
768
+ "idolises": "idolizes",
769
+ "idolising": "idolizing",
770
+ "immobilisation": "immobilization",
771
+ "immobilise": "immobilize",
772
+ "immobilised": "immobilized",
773
+ "immobiliser": "immobilizer",
774
+ "immobilisers": "immobilizers",
775
+ "immobilises": "immobilizes",
776
+ "immobilising": "immobilizing",
777
+ "immortalise": "immortalize",
778
+ "immortalised": "immortalized",
779
+ "immortalises": "immortalizes",
780
+ "immortalising": "immortalizing",
781
+ "immunisation": "immunization",
782
+ "immunise": "immunize",
783
+ "immunised": "immunized",
784
+ "immunises": "immunizes",
785
+ "immunising": "immunizing",
786
+ "impanelled": "impaneled",
787
+ "impanelling": "impaneling",
788
+ "imperilled": "imperiled",
789
+ "imperilling": "imperiling",
790
+ "individualise": "individualize",
791
+ "individualised": "individualized",
792
+ "individualises": "individualizes",
793
+ "individualising": "individualizing",
794
+ "industrialise": "industrialize",
795
+ "industrialised": "industrialized",
796
+ "industrialises": "industrializes",
797
+ "industrialising": "industrializing",
798
+ "inflexion": "inflection",
799
+ "inflexions": "inflections",
800
+ "initialise": "initialize",
801
+ "initialised": "initialized",
802
+ "initialises": "initializes",
803
+ "initialising": "initializing",
804
+ "initialled": "initialed",
805
+ "initialling": "initialing",
806
+ "instal": "install",
807
+ "instalment": "installment",
808
+ "instalments": "installments",
809
+ "instals": "installs",
810
+ "instil": "instill",
811
+ "instils": "instills",
812
+ "institutionalisation": "institutionalization",
813
+ "institutionalise": "institutionalize",
814
+ "institutionalised": "institutionalized",
815
+ "institutionalises": "institutionalizes",
816
+ "institutionalising": "institutionalizing",
817
+ "intellectualise": "intellectualize",
818
+ "intellectualised": "intellectualized",
819
+ "intellectualises": "intellectualizes",
820
+ "intellectualising": "intellectualizing",
821
+ "internalisation": "internalization",
822
+ "internalise": "internalize",
823
+ "internalised": "internalized",
824
+ "internalises": "internalizes",
825
+ "internalising": "internalizing",
826
+ "internationalisation": "internationalization",
827
+ "internationalise": "internationalize",
828
+ "internationalised": "internationalized",
829
+ "internationalises": "internationalizes",
830
+ "internationalising": "internationalizing",
831
+ "ionisation": "ionization",
832
+ "ionise": "ionize",
833
+ "ionised": "ionized",
834
+ "ioniser": "ionizer",
835
+ "ionisers": "ionizers",
836
+ "ionises": "ionizes",
837
+ "ionising": "ionizing",
838
+ "italicise": "italicize",
839
+ "italicised": "italicized",
840
+ "italicises": "italicizes",
841
+ "italicising": "italicizing",
842
+ "itemise": "itemize",
843
+ "itemised": "itemized",
844
+ "itemises": "itemizes",
845
+ "itemising": "itemizing",
846
+ "jeopardise": "jeopardize",
847
+ "jeopardised": "jeopardized",
848
+ "jeopardises": "jeopardizes",
849
+ "jeopardising": "jeopardizing",
850
+ "jewelled": "jeweled",
851
+ "jeweller": "jeweler",
852
+ "jewellers": "jewelers",
853
+ "jewellery": "jewelry",
854
+ "judgement": "judgment",
855
+ "kilogramme": "kilogram",
856
+ "kilogrammes": "kilograms",
857
+ "kilometre": "kilometer",
858
+ "kilometres": "kilometers",
859
+ "labelled": "labeled",
860
+ "labelling": "labeling",
861
+ "labour": "labor",
862
+ "laboured": "labored",
863
+ "labourer": "laborer",
864
+ "labourers": "laborers",
865
+ "labouring": "laboring",
866
+ "labours": "labors",
867
+ "lacklustre": "lackluster",
868
+ "legalisation": "legalization",
869
+ "legalise": "legalize",
870
+ "legalised": "legalized",
871
+ "legalises": "legalizes",
872
+ "legalising": "legalizing",
873
+ "legitimise": "legitimize",
874
+ "legitimised": "legitimized",
875
+ "legitimises": "legitimizes",
876
+ "legitimising": "legitimizing",
877
+ "leukaemia": "leukemia",
878
+ "levelled": "leveled",
879
+ "leveller": "leveler",
880
+ "levellers": "levelers",
881
+ "levelling": "leveling",
882
+ "libelled": "libeled",
883
+ "libelling": "libeling",
884
+ "libellous": "libelous",
885
+ "liberalisation": "liberalization",
886
+ "liberalise": "liberalize",
887
+ "liberalised": "liberalized",
888
+ "liberalises": "liberalizes",
889
+ "liberalising": "liberalizing",
890
+ "licence": "license",
891
+ "licenced": "licensed",
892
+ "licences": "licenses",
893
+ "licencing": "licensing",
894
+ "likeable": "likable",
895
+ "lionisation": "lionization",
896
+ "lionise": "lionize",
897
+ "lionised": "lionized",
898
+ "lionises": "lionizes",
899
+ "lionising": "lionizing",
900
+ "liquidise": "liquidize",
901
+ "liquidised": "liquidized",
902
+ "liquidiser": "liquidizer",
903
+ "liquidisers": "liquidizers",
904
+ "liquidises": "liquidizes",
905
+ "liquidising": "liquidizing",
906
+ "litre": "liter",
907
+ "litres": "liters",
908
+ "localise": "localize",
909
+ "localised": "localized",
910
+ "localises": "localizes",
911
+ "localising": "localizing",
912
+ "louvre": "louver",
913
+ "louvred": "louvered",
914
+ "louvres": "louvers",
915
+ "lustre": "luster",
916
+ "magnetise": "magnetize",
917
+ "magnetised": "magnetized",
918
+ "magnetises": "magnetizes",
919
+ "magnetising": "magnetizing",
920
+ "manoeuvrability": "maneuverability",
921
+ "manoeuvrable": "maneuverable",
922
+ "manoeuvre": "maneuver",
923
+ "manoeuvred": "maneuvered",
924
+ "manoeuvres": "maneuvers",
925
+ "manoeuvring": "maneuvering",
926
+ "manoeuvrings": "maneuverings",
927
+ "marginalisation": "marginalization",
928
+ "marginalise": "marginalize",
929
+ "marginalised": "marginalized",
930
+ "marginalises": "marginalizes",
931
+ "marginalising": "marginalizing",
932
+ "marshalled": "marshaled",
933
+ "marshalling": "marshaling",
934
+ "marvelled": "marveled",
935
+ "marvelling": "marveling",
936
+ "marvellous": "marvelous",
937
+ "marvellously": "marvelously",
938
+ "materialisation": "materialization",
939
+ "materialise": "materialize",
940
+ "materialised": "materialized",
941
+ "materialises": "materializes",
942
+ "materialising": "materializing",
943
+ "maximisation": "maximization",
944
+ "maximise": "maximize",
945
+ "maximised": "maximized",
946
+ "maximises": "maximizes",
947
+ "maximising": "maximizing",
948
+ "meagre": "meager",
949
+ "mechanisation": "mechanization",
950
+ "mechanise": "mechanize",
951
+ "mechanised": "mechanized",
952
+ "mechanises": "mechanizes",
953
+ "mechanising": "mechanizing",
954
+ "mediaeval": "medieval",
955
+ "memorialise": "memorialize",
956
+ "memorialised": "memorialized",
957
+ "memorialises": "memorializes",
958
+ "memorialising": "memorializing",
959
+ "memorise": "memorize",
960
+ "memorised": "memorized",
961
+ "memorises": "memorizes",
962
+ "memorising": "memorizing",
963
+ "mesmerise": "mesmerize",
964
+ "mesmerised": "mesmerized",
965
+ "mesmerises": "mesmerizes",
966
+ "mesmerising": "mesmerizing",
967
+ "metabolise": "metabolize",
968
+ "metabolised": "metabolized",
969
+ "metabolises": "metabolizes",
970
+ "metabolising": "metabolizing",
971
+ "metre": "meter",
972
+ "metres": "meters",
973
+ "mhm": "hmm",
974
+ "micrometre": "micrometer",
975
+ "micrometres": "micrometers",
976
+ "militarise": "militarize",
977
+ "militarised": "militarized",
978
+ "militarises": "militarizes",
979
+ "militarising": "militarizing",
980
+ "milligramme": "milligram",
981
+ "milligrammes": "milligrams",
982
+ "millilitre": "milliliter",
983
+ "millilitres": "milliliters",
984
+ "millimetre": "millimeter",
985
+ "millimetres": "millimeters",
986
+ "miniaturisation": "miniaturization",
987
+ "miniaturise": "miniaturize",
988
+ "miniaturised": "miniaturized",
989
+ "miniaturises": "miniaturizes",
990
+ "miniaturising": "miniaturizing",
991
+ "minibusses": "minibuses",
992
+ "minimise": "minimize",
993
+ "minimised": "minimized",
994
+ "minimises": "minimizes",
995
+ "minimising": "minimizing",
996
+ "misbehaviour": "misbehavior",
997
+ "misdemeanour": "misdemeanor",
998
+ "misdemeanours": "misdemeanors",
999
+ "misspelt": "misspelled",
1000
+ "mitre": "miter",
1001
+ "mitres": "miters",
1002
+ "mm": "hmm",
1003
+ "mmm": "hmm",
1004
+ "mobilisation": "mobilization",
1005
+ "mobilise": "mobilize",
1006
+ "mobilised": "mobilized",
1007
+ "mobilises": "mobilizes",
1008
+ "mobilising": "mobilizing",
1009
+ "modelled": "modeled",
1010
+ "modeller": "modeler",
1011
+ "modellers": "modelers",
1012
+ "modelling": "modeling",
1013
+ "modernise": "modernize",
1014
+ "modernised": "modernized",
1015
+ "modernises": "modernizes",
1016
+ "modernising": "modernizing",
1017
+ "moisturise": "moisturize",
1018
+ "moisturised": "moisturized",
1019
+ "moisturiser": "moisturizer",
1020
+ "moisturisers": "moisturizers",
1021
+ "moisturises": "moisturizes",
1022
+ "moisturising": "moisturizing",
1023
+ "monologue": "monolog",
1024
+ "monologues": "monologs",
1025
+ "monopolisation": "monopolization",
1026
+ "monopolise": "monopolize",
1027
+ "monopolised": "monopolized",
1028
+ "monopolises": "monopolizes",
1029
+ "monopolising": "monopolizing",
1030
+ "moralise": "moralize",
1031
+ "moralised": "moralized",
1032
+ "moralises": "moralizes",
1033
+ "moralising": "moralizing",
1034
+ "motorised": "motorized",
1035
+ "mould": "mold",
1036
+ "moulded": "molded",
1037
+ "moulder": "molder",
1038
+ "mouldered": "moldered",
1039
+ "mouldering": "moldering",
1040
+ "moulders": "molders",
1041
+ "mouldier": "moldier",
1042
+ "mouldiest": "moldiest",
1043
+ "moulding": "molding",
1044
+ "mouldings": "moldings",
1045
+ "moulds": "molds",
1046
+ "mouldy": "moldy",
1047
+ "moult": "molt",
1048
+ "moulted": "molted",
1049
+ "moulting": "molting",
1050
+ "moults": "molts",
1051
+ "moustache": "mustache",
1052
+ "moustached": "mustached",
1053
+ "moustaches": "mustaches",
1054
+ "moustachioed": "mustachioed",
1055
+ "multicoloured": "multicolored",
1056
+ "nationalisation": "nationalization",
1057
+ "nationalisations": "nationalizations",
1058
+ "nationalise": "nationalize",
1059
+ "nationalised": "nationalized",
1060
+ "nationalises": "nationalizes",
1061
+ "nationalising": "nationalizing",
1062
+ "naturalisation": "naturalization",
1063
+ "naturalise": "naturalize",
1064
+ "naturalised": "naturalized",
1065
+ "naturalises": "naturalizes",
1066
+ "naturalising": "naturalizing",
1067
+ "neighbour": "neighbor",
1068
+ "neighbourhood": "neighborhood",
1069
+ "neighbourhoods": "neighborhoods",
1070
+ "neighbouring": "neighboring",
1071
+ "neighbourliness": "neighborliness",
1072
+ "neighbourly": "neighborly",
1073
+ "neighbours": "neighbors",
1074
+ "neutralisation": "neutralization",
1075
+ "neutralise": "neutralize",
1076
+ "neutralised": "neutralized",
1077
+ "neutralises": "neutralizes",
1078
+ "neutralising": "neutralizing",
1079
+ "normalisation": "normalization",
1080
+ "normalise": "normalize",
1081
+ "normalised": "normalized",
1082
+ "normalises": "normalizes",
1083
+ "normalising": "normalizing",
1084
+ "odour": "odor",
1085
+ "odourless": "odorless",
1086
+ "odours": "odors",
1087
+ "oesophagus": "esophagus",
1088
+ "oesophaguses": "esophaguses",
1089
+ "oestrogen": "estrogen",
1090
+ "offence": "offense",
1091
+ "offences": "offenses",
1092
+ "omelette": "omelet",
1093
+ "omelettes": "omelets",
1094
+ "optimise": "optimize",
1095
+ "optimised": "optimized",
1096
+ "optimises": "optimizes",
1097
+ "optimising": "optimizing",
1098
+ "organisation": "organization",
1099
+ "organisational": "organizational",
1100
+ "organisations": "organizations",
1101
+ "organise": "organize",
1102
+ "organised": "organized",
1103
+ "organiser": "organizer",
1104
+ "organisers": "organizers",
1105
+ "organises": "organizes",
1106
+ "organising": "organizing",
1107
+ "orthopaedic": "orthopedic",
1108
+ "orthopaedics": "orthopedics",
1109
+ "ostracise": "ostracize",
1110
+ "ostracised": "ostracized",
1111
+ "ostracises": "ostracizes",
1112
+ "ostracising": "ostracizing",
1113
+ "outmanoeuvre": "outmaneuver",
1114
+ "outmanoeuvred": "outmaneuvered",
1115
+ "outmanoeuvres": "outmaneuvers",
1116
+ "outmanoeuvring": "outmaneuvering",
1117
+ "overemphasise": "overemphasize",
1118
+ "overemphasised": "overemphasized",
1119
+ "overemphasises": "overemphasizes",
1120
+ "overemphasising": "overemphasizing",
1121
+ "oxidisation": "oxidization",
1122
+ "oxidise": "oxidize",
1123
+ "oxidised": "oxidized",
1124
+ "oxidises": "oxidizes",
1125
+ "oxidising": "oxidizing",
1126
+ "paederast": "pederast",
1127
+ "paederasts": "pederasts",
1128
+ "paediatric": "pediatric",
1129
+ "paediatrician": "pediatrician",
1130
+ "paediatricians": "pediatricians",
1131
+ "paediatrics": "pediatrics",
1132
+ "paedophile": "pedophile",
1133
+ "paedophiles": "pedophiles",
1134
+ "paedophilia": "pedophilia",
1135
+ "palaeolithic": "paleolithic",
1136
+ "palaeontologist": "paleontologist",
1137
+ "palaeontologists": "paleontologists",
1138
+ "palaeontology": "paleontology",
1139
+ "panelled": "paneled",
1140
+ "panelling": "paneling",
1141
+ "panellist": "panelist",
1142
+ "panellists": "panelists",
1143
+ "paralyse": "paralyze",
1144
+ "paralysed": "paralyzed",
1145
+ "paralyses": "paralyzes",
1146
+ "paralysing": "paralyzing",
1147
+ "parcelled": "parceled",
1148
+ "parcelling": "parceling",
1149
+ "parlour": "parlor",
1150
+ "parlours": "parlors",
1151
+ "particularise": "particularize",
1152
+ "particularised": "particularized",
1153
+ "particularises": "particularizes",
1154
+ "particularising": "particularizing",
1155
+ "passivisation": "passivization",
1156
+ "passivise": "passivize",
1157
+ "passivised": "passivized",
1158
+ "passivises": "passivizes",
1159
+ "passivising": "passivizing",
1160
+ "pasteurisation": "pasteurization",
1161
+ "pasteurise": "pasteurize",
1162
+ "pasteurised": "pasteurized",
1163
+ "pasteurises": "pasteurizes",
1164
+ "pasteurising": "pasteurizing",
1165
+ "patronise": "patronize",
1166
+ "patronised": "patronized",
1167
+ "patronises": "patronizes",
1168
+ "patronising": "patronizing",
1169
+ "patronisingly": "patronizingly",
1170
+ "pedalled": "pedaled",
1171
+ "pedalling": "pedaling",
1172
+ "pedestrianisation": "pedestrianization",
1173
+ "pedestrianise": "pedestrianize",
1174
+ "pedestrianised": "pedestrianized",
1175
+ "pedestrianises": "pedestrianizes",
1176
+ "pedestrianising": "pedestrianizing",
1177
+ "penalise": "penalize",
1178
+ "penalised": "penalized",
1179
+ "penalises": "penalizes",
1180
+ "penalising": "penalizing",
1181
+ "pencilled": "penciled",
1182
+ "pencilling": "penciling",
1183
+ "personalise": "personalize",
1184
+ "personalised": "personalized",
1185
+ "personalises": "personalizes",
1186
+ "personalising": "personalizing",
1187
+ "pharmacopoeia": "pharmacopeia",
1188
+ "pharmacopoeias": "pharmacopeias",
1189
+ "philosophise": "philosophize",
1190
+ "philosophised": "philosophized",
1191
+ "philosophises": "philosophizes",
1192
+ "philosophising": "philosophizing",
1193
+ "philtre": "filter",
1194
+ "philtres": "filters",
1195
+ "phoney": "phony",
1196
+ "plagiarise": "plagiarize",
1197
+ "plagiarised": "plagiarized",
1198
+ "plagiarises": "plagiarizes",
1199
+ "plagiarising": "plagiarizing",
1200
+ "plough": "plow",
1201
+ "ploughed": "plowed",
1202
+ "ploughing": "plowing",
1203
+ "ploughman": "plowman",
1204
+ "ploughmen": "plowmen",
1205
+ "ploughs": "plows",
1206
+ "ploughshare": "plowshare",
1207
+ "ploughshares": "plowshares",
1208
+ "polarisation": "polarization",
1209
+ "polarise": "polarize",
1210
+ "polarised": "polarized",
1211
+ "polarises": "polarizes",
1212
+ "polarising": "polarizing",
1213
+ "politicisation": "politicization",
1214
+ "politicise": "politicize",
1215
+ "politicised": "politicized",
1216
+ "politicises": "politicizes",
1217
+ "politicising": "politicizing",
1218
+ "popularisation": "popularization",
1219
+ "popularise": "popularize",
1220
+ "popularised": "popularized",
1221
+ "popularises": "popularizes",
1222
+ "popularising": "popularizing",
1223
+ "pouffe": "pouf",
1224
+ "pouffes": "poufs",
1225
+ "practise": "practice",
1226
+ "practised": "practiced",
1227
+ "practises": "practices",
1228
+ "practising": "practicing",
1229
+ "praesidium": "presidium",
1230
+ "praesidiums": "presidiums",
1231
+ "pressurisation": "pressurization",
1232
+ "pressurise": "pressurize",
1233
+ "pressurised": "pressurized",
1234
+ "pressurises": "pressurizes",
1235
+ "pressurising": "pressurizing",
1236
+ "pretence": "pretense",
1237
+ "pretences": "pretenses",
1238
+ "primaeval": "primeval",
1239
+ "prioritisation": "prioritization",
1240
+ "prioritise": "prioritize",
1241
+ "prioritised": "prioritized",
1242
+ "prioritises": "prioritizes",
1243
+ "prioritising": "prioritizing",
1244
+ "privatisation": "privatization",
1245
+ "privatisations": "privatizations",
1246
+ "privatise": "privatize",
1247
+ "privatised": "privatized",
1248
+ "privatises": "privatizes",
1249
+ "privatising": "privatizing",
1250
+ "professionalisation": "professionalization",
1251
+ "professionalise": "professionalize",
1252
+ "professionalised": "professionalized",
1253
+ "professionalises": "professionalizes",
1254
+ "professionalising": "professionalizing",
1255
+ "programme": "program",
1256
+ "programmes": "programs",
1257
+ "prologue": "prolog",
1258
+ "prologues": "prologs",
1259
+ "propagandise": "propagandize",
1260
+ "propagandised": "propagandized",
1261
+ "propagandises": "propagandizes",
1262
+ "propagandising": "propagandizing",
1263
+ "proselytise": "proselytize",
1264
+ "proselytised": "proselytized",
1265
+ "proselytiser": "proselytizer",
1266
+ "proselytisers": "proselytizers",
1267
+ "proselytises": "proselytizes",
1268
+ "proselytising": "proselytizing",
1269
+ "psychoanalyse": "psychoanalyze",
1270
+ "psychoanalysed": "psychoanalyzed",
1271
+ "psychoanalyses": "psychoanalyzes",
1272
+ "psychoanalysing": "psychoanalyzing",
1273
+ "publicise": "publicize",
1274
+ "publicised": "publicized",
1275
+ "publicises": "publicizes",
1276
+ "publicising": "publicizing",
1277
+ "pulverisation": "pulverization",
1278
+ "pulverise": "pulverize",
1279
+ "pulverised": "pulverized",
1280
+ "pulverises": "pulverizes",
1281
+ "pulverising": "pulverizing",
1282
+ "pummelled": "pummel",
1283
+ "pummelling": "pummeled",
1284
+ "pyjama": "pajama",
1285
+ "pyjamas": "pajamas",
1286
+ "pzazz": "pizzazz",
1287
+ "quarrelled": "quarreled",
1288
+ "quarrelling": "quarreling",
1289
+ "radicalise": "radicalize",
1290
+ "radicalised": "radicalized",
1291
+ "radicalises": "radicalizes",
1292
+ "radicalising": "radicalizing",
1293
+ "rancour": "rancor",
1294
+ "randomise": "randomize",
1295
+ "randomised": "randomized",
1296
+ "randomises": "randomizes",
1297
+ "randomising": "randomizing",
1298
+ "rationalisation": "rationalization",
1299
+ "rationalisations": "rationalizations",
1300
+ "rationalise": "rationalize",
1301
+ "rationalised": "rationalized",
1302
+ "rationalises": "rationalizes",
1303
+ "rationalising": "rationalizing",
1304
+ "ravelled": "raveled",
1305
+ "ravelling": "raveling",
1306
+ "realisable": "realizable",
1307
+ "realisation": "realization",
1308
+ "realisations": "realizations",
1309
+ "realise": "realize",
1310
+ "realised": "realized",
1311
+ "realises": "realizes",
1312
+ "realising": "realizing",
1313
+ "recognisable": "recognizable",
1314
+ "recognisably": "recognizably",
1315
+ "recognisance": "recognizance",
1316
+ "recognise": "recognize",
1317
+ "recognised": "recognized",
1318
+ "recognises": "recognizes",
1319
+ "recognising": "recognizing",
1320
+ "reconnoitre": "reconnoiter",
1321
+ "reconnoitred": "reconnoitered",
1322
+ "reconnoitres": "reconnoiters",
1323
+ "reconnoitring": "reconnoitering",
1324
+ "refuelled": "refueled",
1325
+ "refuelling": "refueling",
1326
+ "regularisation": "regularization",
1327
+ "regularise": "regularize",
1328
+ "regularised": "regularized",
1329
+ "regularises": "regularizes",
1330
+ "regularising": "regularizing",
1331
+ "remodelled": "remodeled",
1332
+ "remodelling": "remodeling",
1333
+ "remould": "remold",
1334
+ "remoulded": "remolded",
1335
+ "remoulding": "remolding",
1336
+ "remoulds": "remolds",
1337
+ "reorganisation": "reorganization",
1338
+ "reorganisations": "reorganizations",
1339
+ "reorganise": "reorganize",
1340
+ "reorganised": "reorganized",
1341
+ "reorganises": "reorganizes",
1342
+ "reorganising": "reorganizing",
1343
+ "revelled": "reveled",
1344
+ "reveller": "reveler",
1345
+ "revellers": "revelers",
1346
+ "revelling": "reveling",
1347
+ "revitalise": "revitalize",
1348
+ "revitalised": "revitalized",
1349
+ "revitalises": "revitalizes",
1350
+ "revitalising": "revitalizing",
1351
+ "revolutionise": "revolutionize",
1352
+ "revolutionised": "revolutionized",
1353
+ "revolutionises": "revolutionizes",
1354
+ "revolutionising": "revolutionizing",
1355
+ "rhapsodise": "rhapsodize",
1356
+ "rhapsodised": "rhapsodized",
1357
+ "rhapsodises": "rhapsodizes",
1358
+ "rhapsodising": "rhapsodizing",
1359
+ "rigour": "rigor",
1360
+ "rigours": "rigors",
1361
+ "ritualised": "ritualized",
1362
+ "rivalled": "rivaled",
1363
+ "rivalling": "rivaling",
1364
+ "romanticise": "romanticize",
1365
+ "romanticised": "romanticized",
1366
+ "romanticises": "romanticizes",
1367
+ "romanticising": "romanticizing",
1368
+ "rumour": "rumor",
1369
+ "rumoured": "rumored",
1370
+ "rumours": "rumors",
1371
+ "sabre": "saber",
1372
+ "sabres": "sabers",
1373
+ "saltpetre": "saltpeter",
1374
+ "sanitise": "sanitize",
1375
+ "sanitised": "sanitized",
1376
+ "sanitises": "sanitizes",
1377
+ "sanitising": "sanitizing",
1378
+ "satirise": "satirize",
1379
+ "satirised": "satirized",
1380
+ "satirises": "satirizes",
1381
+ "satirising": "satirizing",
1382
+ "saviour": "savior",
1383
+ "saviours": "saviors",
1384
+ "savour": "savor",
1385
+ "savoured": "savored",
1386
+ "savouries": "savories",
1387
+ "savouring": "savoring",
1388
+ "savours": "savors",
1389
+ "savoury": "savory",
1390
+ "scandalise": "scandalize",
1391
+ "scandalised": "scandalized",
1392
+ "scandalises": "scandalizes",
1393
+ "scandalising": "scandalizing",
1394
+ "sceptic": "skeptic",
1395
+ "sceptical": "skeptical",
1396
+ "sceptically": "skeptically",
1397
+ "scepticism": "skepticism",
1398
+ "sceptics": "skeptics",
1399
+ "sceptre": "scepter",
1400
+ "sceptres": "scepters",
1401
+ "scrutinise": "scrutinize",
1402
+ "scrutinised": "scrutinized",
1403
+ "scrutinises": "scrutinizes",
1404
+ "scrutinising": "scrutinizing",
1405
+ "secularisation": "secularization",
1406
+ "secularise": "secularize",
1407
+ "secularised": "secularized",
1408
+ "secularises": "secularizes",
1409
+ "secularising": "secularizing",
1410
+ "sensationalise": "sensationalize",
1411
+ "sensationalised": "sensationalized",
1412
+ "sensationalises": "sensationalizes",
1413
+ "sensationalising": "sensationalizing",
1414
+ "sensitise": "sensitize",
1415
+ "sensitised": "sensitized",
1416
+ "sensitises": "sensitizes",
1417
+ "sensitising": "sensitizing",
1418
+ "sentimentalise": "sentimentalize",
1419
+ "sentimentalised": "sentimentalized",
1420
+ "sentimentalises": "sentimentalizes",
1421
+ "sentimentalising": "sentimentalizing",
1422
+ "sepulchre": "sepulcher",
1423
+ "sepulchres": "sepulchers",
1424
+ "serialisation": "serialization",
1425
+ "serialisations": "serializations",
1426
+ "serialise": "serialize",
1427
+ "serialised": "serialized",
1428
+ "serialises": "serializes",
1429
+ "serialising": "serializing",
1430
+ "sermonise": "sermonize",
1431
+ "sermonised": "sermonized",
1432
+ "sermonises": "sermonizes",
1433
+ "sermonising": "sermonizing",
1434
+ "sheikh": "sheik",
1435
+ "shovelled": "shoveled",
1436
+ "shovelling": "shoveling",
1437
+ "shrivelled": "shriveled",
1438
+ "shrivelling": "shriveling",
1439
+ "signalise": "signalize",
1440
+ "signalised": "signalized",
1441
+ "signalises": "signalizes",
1442
+ "signalising": "signalizing",
1443
+ "signalled": "signaled",
1444
+ "signalling": "signaling",
1445
+ "smoulder": "smolder",
1446
+ "smouldered": "smoldered",
1447
+ "smouldering": "smoldering",
1448
+ "smoulders": "smolders",
1449
+ "snivelled": "sniveled",
1450
+ "snivelling": "sniveling",
1451
+ "snorkelled": "snorkeled",
1452
+ "snorkelling": "snorkeling",
1453
+ "snowplough": "snowplow",
1454
+ "snowploughs": "snowplow",
1455
+ "socialisation": "socialization",
1456
+ "socialise": "socialize",
1457
+ "socialised": "socialized",
1458
+ "socialises": "socializes",
1459
+ "socialising": "socializing",
1460
+ "sodomise": "sodomize",
1461
+ "sodomised": "sodomized",
1462
+ "sodomises": "sodomizes",
1463
+ "sodomising": "sodomizing",
1464
+ "solemnise": "solemnize",
1465
+ "solemnised": "solemnized",
1466
+ "solemnises": "solemnizes",
1467
+ "solemnising": "solemnizing",
1468
+ "sombre": "somber",
1469
+ "specialisation": "specialization",
1470
+ "specialisations": "specializations",
1471
+ "specialise": "specialize",
1472
+ "specialised": "specialized",
1473
+ "specialises": "specializes",
1474
+ "specialising": "specializing",
1475
+ "spectre": "specter",
1476
+ "spectres": "specters",
1477
+ "spiralled": "spiraled",
1478
+ "spiralling": "spiraling",
1479
+ "splendour": "splendor",
1480
+ "splendours": "splendors",
1481
+ "squirrelled": "squirreled",
1482
+ "squirrelling": "squirreling",
1483
+ "stabilisation": "stabilization",
1484
+ "stabilise": "stabilize",
1485
+ "stabilised": "stabilized",
1486
+ "stabiliser": "stabilizer",
1487
+ "stabilisers": "stabilizers",
1488
+ "stabilises": "stabilizes",
1489
+ "stabilising": "stabilizing",
1490
+ "standardisation": "standardization",
1491
+ "standardise": "standardize",
1492
+ "standardised": "standardized",
1493
+ "standardises": "standardizes",
1494
+ "standardising": "standardizing",
1495
+ "stencilled": "stenciled",
1496
+ "stencilling": "stenciling",
1497
+ "sterilisation": "sterilization",
1498
+ "sterilisations": "sterilizations",
1499
+ "sterilise": "sterilize",
1500
+ "sterilised": "sterilized",
1501
+ "steriliser": "sterilizer",
1502
+ "sterilisers": "sterilizers",
1503
+ "sterilises": "sterilizes",
1504
+ "sterilising": "sterilizing",
1505
+ "stigmatisation": "stigmatization",
1506
+ "stigmatise": "stigmatize",
1507
+ "stigmatised": "stigmatized",
1508
+ "stigmatises": "stigmatizes",
1509
+ "stigmatising": "stigmatizing",
1510
+ "storey": "story",
1511
+ "storeys": "stories",
1512
+ "subsidisation": "subsidization",
1513
+ "subsidise": "subsidize",
1514
+ "subsidised": "subsidized",
1515
+ "subsidiser": "subsidizer",
1516
+ "subsidisers": "subsidizers",
1517
+ "subsidises": "subsidizes",
1518
+ "subsidising": "subsidizing",
1519
+ "succour": "succor",
1520
+ "succoured": "succored",
1521
+ "succouring": "succoring",
1522
+ "succours": "succors",
1523
+ "sulphate": "sulfate",
1524
+ "sulphates": "sulfates",
1525
+ "sulphide": "sulfide",
1526
+ "sulphides": "sulfides",
1527
+ "sulphur": "sulfur",
1528
+ "sulphurous": "sulfurous",
1529
+ "summarise": "summarize",
1530
+ "summarised": "summarized",
1531
+ "summarises": "summarizes",
1532
+ "summarising": "summarizing",
1533
+ "swivelled": "swiveled",
1534
+ "swivelling": "swiveling",
1535
+ "symbolise": "symbolize",
1536
+ "symbolised": "symbolized",
1537
+ "symbolises": "symbolizes",
1538
+ "symbolising": "symbolizing",
1539
+ "sympathise": "sympathize",
1540
+ "sympathised": "sympathized",
1541
+ "sympathiser": "sympathizer",
1542
+ "sympathisers": "sympathizers",
1543
+ "sympathises": "sympathizes",
1544
+ "sympathising": "sympathizing",
1545
+ "synchronisation": "synchronization",
1546
+ "synchronise": "synchronize",
1547
+ "synchronised": "synchronized",
1548
+ "synchronises": "synchronizes",
1549
+ "synchronising": "synchronizing",
1550
+ "synthesise": "synthesize",
1551
+ "synthesised": "synthesized",
1552
+ "synthesiser": "synthesizer",
1553
+ "synthesisers": "synthesizers",
1554
+ "synthesises": "synthesizes",
1555
+ "synthesising": "synthesizing",
1556
+ "syphon": "siphon",
1557
+ "syphoned": "siphoned",
1558
+ "syphoning": "siphoning",
1559
+ "syphons": "siphons",
1560
+ "systematisation": "systematization",
1561
+ "systematise": "systematize",
1562
+ "systematised": "systematized",
1563
+ "systematises": "systematizes",
1564
+ "systematising": "systematizing",
1565
+ "tantalise": "tantalize",
1566
+ "tantalised": "tantalized",
1567
+ "tantalises": "tantalizes",
1568
+ "tantalising": "tantalizing",
1569
+ "tantalisingly": "tantalizingly",
1570
+ "tasselled": "tasseled",
1571
+ "technicolour": "technicolor",
1572
+ "temporise": "temporize",
1573
+ "temporised": "temporized",
1574
+ "temporises": "temporizes",
1575
+ "temporising": "temporizing",
1576
+ "tenderise": "tenderize",
1577
+ "tenderised": "tenderized",
1578
+ "tenderises": "tenderizes",
1579
+ "tenderising": "tenderizing",
1580
+ "terrorise": "terrorize",
1581
+ "terrorised": "terrorized",
1582
+ "terrorises": "terrorizes",
1583
+ "terrorising": "terrorizing",
1584
+ "theatre": "theater",
1585
+ "theatregoer": "theatergoer",
1586
+ "theatregoers": "theatergoers",
1587
+ "theatres": "theaters",
1588
+ "theorise": "theorize",
1589
+ "theorised": "theorized",
1590
+ "theorises": "theorizes",
1591
+ "theorising": "theorizing",
1592
+ "tonne": "ton",
1593
+ "tonnes": "tons",
1594
+ "towelled": "toweled",
1595
+ "towelling": "toweling",
1596
+ "toxaemia": "toxemia",
1597
+ "tranquillise": "tranquilize",
1598
+ "tranquillised": "tranquilized",
1599
+ "tranquilliser": "tranquilizer",
1600
+ "tranquillisers": "tranquilizers",
1601
+ "tranquillises": "tranquilizes",
1602
+ "tranquillising": "tranquilizing",
1603
+ "tranquillity": "tranquility",
1604
+ "tranquillize": "tranquilize",
1605
+ "tranquillized": "tranquilized",
1606
+ "tranquillizer": "tranquilizer",
1607
+ "tranquillizers": "tranquilizers",
1608
+ "tranquillizes": "tranquilizes",
1609
+ "tranquillizing": "tranquilizing",
1610
+ "tranquilly": "tranquility",
1611
+ "transistorised": "transistorized",
1612
+ "traumatise": "traumatize",
1613
+ "traumatised": "traumatized",
1614
+ "traumatises": "traumatizes",
1615
+ "traumatising": "traumatizing",
1616
+ "travelled": "traveled",
1617
+ "traveller": "traveler",
1618
+ "travellers": "travelers",
1619
+ "travelling": "traveling",
1620
+ "travelog": "travelogue",
1621
+ "travelogs": "travelogues",
1622
+ "trialled": "trialed",
1623
+ "trialling": "trialing",
1624
+ "tricolour": "tricolor",
1625
+ "tricolours": "tricolors",
1626
+ "trivialise": "trivialize",
1627
+ "trivialised": "trivialized",
1628
+ "trivialises": "trivializes",
1629
+ "trivialising": "trivializing",
1630
+ "tumour": "tumor",
1631
+ "tumours": "tumors",
1632
+ "tunnelled": "tunneled",
1633
+ "tunnelling": "tunneling",
1634
+ "tyrannise": "tyrannize",
1635
+ "tyrannised": "tyrannized",
1636
+ "tyrannises": "tyrannizes",
1637
+ "tyrannising": "tyrannizing",
1638
+ "tyre": "tire",
1639
+ "tyres": "tires",
1640
+ "unauthorised": "unauthorized",
1641
+ "uncivilised": "uncivilized",
1642
+ "underutilised": "underutilized",
1643
+ "unequalled": "unequaled",
1644
+ "unfavourable": "unfavorable",
1645
+ "unfavourably": "unfavorably",
1646
+ "unionisation": "unionization",
1647
+ "unionise": "unionize",
1648
+ "unionised": "unionized",
1649
+ "unionises": "unionizes",
1650
+ "unionising": "unionizing",
1651
+ "unorganised": "unorganized",
1652
+ "unravelled": "unraveled",
1653
+ "unravelling": "unraveling",
1654
+ "unrecognisable": "unrecognizable",
1655
+ "unrecognised": "unrecognized",
1656
+ "unrivalled": "unrivaled",
1657
+ "unsavoury": "unsavory",
1658
+ "untrammelled": "untrammeled",
1659
+ "urbanisation": "urbanization",
1660
+ "urbanise": "urbanize",
1661
+ "urbanised": "urbanized",
1662
+ "urbanises": "urbanizes",
1663
+ "urbanising": "urbanizing",
1664
+ "utilisable": "utilizable",
1665
+ "utilisation": "utilization",
1666
+ "utilise": "utilize",
1667
+ "utilised": "utilized",
1668
+ "utilises": "utilizes",
1669
+ "utilising": "utilizing",
1670
+ "valour": "valor",
1671
+ "vandalise": "vandalize",
1672
+ "vandalised": "vandalized",
1673
+ "vandalises": "vandalizes",
1674
+ "vandalising": "vandalizing",
1675
+ "vaporisation": "vaporization",
1676
+ "vaporise": "vaporize",
1677
+ "vaporised": "vaporized",
1678
+ "vaporises": "vaporizes",
1679
+ "vaporising": "vaporizing",
1680
+ "vapour": "vapor",
1681
+ "vapours": "vapors",
1682
+ "verbalise": "verbalize",
1683
+ "verbalised": "verbalized",
1684
+ "verbalises": "verbalizes",
1685
+ "verbalising": "verbalizing",
1686
+ "victimisation": "victimization",
1687
+ "victimise": "victimize",
1688
+ "victimised": "victimized",
1689
+ "victimises": "victimizes",
1690
+ "victimising": "victimizing",
1691
+ "videodisc": "videodisk",
1692
+ "videodiscs": "videodisks",
1693
+ "vigour": "vigor",
1694
+ "visualisation": "visualization",
1695
+ "visualisations": "visualizations",
1696
+ "visualise": "visualize",
1697
+ "visualised": "visualized",
1698
+ "visualises": "visualizes",
1699
+ "visualising": "visualizing",
1700
+ "vocalisation": "vocalization",
1701
+ "vocalisations": "vocalizations",
1702
+ "vocalise": "vocalize",
1703
+ "vocalised": "vocalized",
1704
+ "vocalises": "vocalizes",
1705
+ "vocalising": "vocalizing",
1706
+ "vulcanised": "vulcanized",
1707
+ "vulgarisation": "vulgarization",
1708
+ "vulgarise": "vulgarize",
1709
+ "vulgarised": "vulgarized",
1710
+ "vulgarises": "vulgarizes",
1711
+ "vulgarising": "vulgarizing",
1712
+ "waggon": "wagon",
1713
+ "waggons": "wagons",
1714
+ "watercolour": "watercolor",
1715
+ "watercolours": "watercolors",
1716
+ "weaselled": "weaseled",
1717
+ "weaselling": "weaseling",
1718
+ "westernisation": "westernization",
1719
+ "westernise": "westernize",
1720
+ "westernised": "westernized",
1721
+ "westernises": "westernizes",
1722
+ "westernising": "westernizing",
1723
+ "womanise": "womanize",
1724
+ "womanised": "womanized",
1725
+ "womaniser": "womanizer",
1726
+ "womanisers": "womanizers",
1727
+ "womanises": "womanizes",
1728
+ "womanising": "womanizing",
1729
+ "woollen": "woolen",
1730
+ "woollens": "woolens",
1731
+ "woollies": "woolies",
1732
+ "woolly": "wooly",
1733
+ "worshipped": "worshiped",
1734
+ "worshipper": "worshiper",
1735
+ "worshipping": "worshiping",
1736
+ "yodelled": "yodeled",
1737
+ "yodelling": "yodeling",
1738
+ "yoghourt": "yogurt",
1739
+ "yoghourts": "yogurts",
1740
+ "yoghurt": "yogurt",
1741
+ "yoghurts": "yogurts"
1742
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|startoftranscript|>",
5
+ "<|en|>",
6
+ "<|zh|>",
7
+ "<|de|>",
8
+ "<|es|>",
9
+ "<|ru|>",
10
+ "<|ko|>",
11
+ "<|fr|>",
12
+ "<|ja|>",
13
+ "<|pt|>",
14
+ "<|tr|>",
15
+ "<|pl|>",
16
+ "<|ca|>",
17
+ "<|nl|>",
18
+ "<|ar|>",
19
+ "<|sv|>",
20
+ "<|it|>",
21
+ "<|id|>",
22
+ "<|hi|>",
23
+ "<|fi|>",
24
+ "<|vi|>",
25
+ "<|iw|>",
26
+ "<|uk|>",
27
+ "<|el|>",
28
+ "<|ms|>",
29
+ "<|cs|>",
30
+ "<|ro|>",
31
+ "<|da|>",
32
+ "<|hu|>",
33
+ "<|ta|>",
34
+ "<|no|>",
35
+ "<|th|>",
36
+ "<|ur|>",
37
+ "<|hr|>",
38
+ "<|bg|>",
39
+ "<|lt|>",
40
+ "<|la|>",
41
+ "<|mi|>",
42
+ "<|ml|>",
43
+ "<|cy|>",
44
+ "<|sk|>",
45
+ "<|te|>",
46
+ "<|fa|>",
47
+ "<|lv|>",
48
+ "<|bn|>",
49
+ "<|sr|>",
50
+ "<|az|>",
51
+ "<|sl|>",
52
+ "<|kn|>",
53
+ "<|et|>",
54
+ "<|mk|>",
55
+ "<|br|>",
56
+ "<|eu|>",
57
+ "<|is|>",
58
+ "<|hy|>",
59
+ "<|ne|>",
60
+ "<|mn|>",
61
+ "<|bs|>",
62
+ "<|kk|>",
63
+ "<|sq|>",
64
+ "<|sw|>",
65
+ "<|gl|>",
66
+ "<|mr|>",
67
+ "<|pa|>",
68
+ "<|si|>",
69
+ "<|km|>",
70
+ "<|sn|>",
71
+ "<|yo|>",
72
+ "<|so|>",
73
+ "<|af|>",
74
+ "<|oc|>",
75
+ "<|ka|>",
76
+ "<|be|>",
77
+ "<|tg|>",
78
+ "<|sd|>",
79
+ "<|gu|>",
80
+ "<|am|>",
81
+ "<|yi|>",
82
+ "<|lo|>",
83
+ "<|uz|>",
84
+ "<|fo|>",
85
+ "<|ht|>",
86
+ "<|ps|>",
87
+ "<|tk|>",
88
+ "<|nn|>",
89
+ "<|mt|>",
90
+ "<|sa|>",
91
+ "<|lb|>",
92
+ "<|my|>",
93
+ "<|bo|>",
94
+ "<|tl|>",
95
+ "<|mg|>",
96
+ "<|as|>",
97
+ "<|tt|>",
98
+ "<|haw|>",
99
+ "<|ln|>",
100
+ "<|ha|>",
101
+ "<|ba|>",
102
+ "<|jw|>",
103
+ "<|su|>",
104
+ "<|translate|>",
105
+ "<|transcribe|>",
106
+ "<|startoflm|>",
107
+ "<|startofprev|>",
108
+ "<|nocaptions|>",
109
+ "<|notimestamps|>"
110
+ ],
111
+ "bos_token": {
112
+ "content": "<|endoftext|>",
113
+ "lstrip": false,
114
+ "normalized": true,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "eos_token": {
119
+ "content": "<|endoftext|>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ },
125
+ "pad_token": "<|endoftext|>",
126
+ "unk_token": {
127
+ "content": "",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false
132
+ }
133
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "openai/whisper-small",
23
+ "pad_token": null,
24
+ "processor_class": "WhisperProcessor",
25
+ "return_attention_mask": false,
26
+ "special_tokens_map_file": null,
27
+ "tokenizer_class": "WhisperTokenizer",
28
+ "unk_token": {
29
+ "__type": "AddedToken",
30
+ "content": "",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
trainer_state.json ADDED
@@ -0,0 +1,3785 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 32.64693030369237,
3
+ "best_model_checkpoint": "whisper-small-mn-7/checkpoint-8000",
4
+ "epoch": 9.129640900791236,
5
+ "global_step": 15000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.2000000000000006e-07,
13
+ "loss": 5.691,
14
+ "step": 25
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 9.200000000000001e-07,
19
+ "loss": 4.206,
20
+ "step": 50
21
+ },
22
+ {
23
+ "epoch": 0.05,
24
+ "learning_rate": 1.42e-06,
25
+ "loss": 3.2533,
26
+ "step": 75
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 1.9200000000000003e-06,
31
+ "loss": 2.548,
32
+ "step": 100
33
+ },
34
+ {
35
+ "epoch": 0.08,
36
+ "learning_rate": 2.42e-06,
37
+ "loss": 2.0535,
38
+ "step": 125
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "learning_rate": 2.92e-06,
43
+ "loss": 1.6564,
44
+ "step": 150
45
+ },
46
+ {
47
+ "epoch": 0.11,
48
+ "learning_rate": 3.4200000000000007e-06,
49
+ "loss": 1.4134,
50
+ "step": 175
51
+ },
52
+ {
53
+ "epoch": 0.12,
54
+ "learning_rate": 3.920000000000001e-06,
55
+ "loss": 1.2014,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 0.14,
60
+ "learning_rate": 4.42e-06,
61
+ "loss": 1.1119,
62
+ "step": 225
63
+ },
64
+ {
65
+ "epoch": 0.15,
66
+ "learning_rate": 4.92e-06,
67
+ "loss": 0.9855,
68
+ "step": 250
69
+ },
70
+ {
71
+ "epoch": 0.17,
72
+ "learning_rate": 5.420000000000001e-06,
73
+ "loss": 0.9054,
74
+ "step": 275
75
+ },
76
+ {
77
+ "epoch": 0.18,
78
+ "learning_rate": 5.92e-06,
79
+ "loss": 0.8482,
80
+ "step": 300
81
+ },
82
+ {
83
+ "epoch": 0.2,
84
+ "learning_rate": 6.42e-06,
85
+ "loss": 0.7802,
86
+ "step": 325
87
+ },
88
+ {
89
+ "epoch": 0.21,
90
+ "learning_rate": 6.92e-06,
91
+ "loss": 0.7257,
92
+ "step": 350
93
+ },
94
+ {
95
+ "epoch": 0.23,
96
+ "learning_rate": 7.420000000000001e-06,
97
+ "loss": 0.6824,
98
+ "step": 375
99
+ },
100
+ {
101
+ "epoch": 0.24,
102
+ "learning_rate": 7.92e-06,
103
+ "loss": 0.6309,
104
+ "step": 400
105
+ },
106
+ {
107
+ "epoch": 0.26,
108
+ "learning_rate": 8.42e-06,
109
+ "loss": 0.5707,
110
+ "step": 425
111
+ },
112
+ {
113
+ "epoch": 0.27,
114
+ "learning_rate": 8.920000000000001e-06,
115
+ "loss": 0.5509,
116
+ "step": 450
117
+ },
118
+ {
119
+ "epoch": 0.29,
120
+ "learning_rate": 9.42e-06,
121
+ "loss": 0.5282,
122
+ "step": 475
123
+ },
124
+ {
125
+ "epoch": 0.3,
126
+ "learning_rate": 9.920000000000002e-06,
127
+ "loss": 0.5208,
128
+ "step": 500
129
+ },
130
+ {
131
+ "epoch": 0.32,
132
+ "learning_rate": 9.98551724137931e-06,
133
+ "loss": 0.5146,
134
+ "step": 525
135
+ },
136
+ {
137
+ "epoch": 0.33,
138
+ "learning_rate": 9.968275862068967e-06,
139
+ "loss": 0.4817,
140
+ "step": 550
141
+ },
142
+ {
143
+ "epoch": 0.35,
144
+ "learning_rate": 9.951034482758622e-06,
145
+ "loss": 0.4618,
146
+ "step": 575
147
+ },
148
+ {
149
+ "epoch": 0.37,
150
+ "learning_rate": 9.933793103448277e-06,
151
+ "loss": 0.4439,
152
+ "step": 600
153
+ },
154
+ {
155
+ "epoch": 0.38,
156
+ "learning_rate": 9.916551724137932e-06,
157
+ "loss": 0.4296,
158
+ "step": 625
159
+ },
160
+ {
161
+ "epoch": 0.4,
162
+ "learning_rate": 9.899310344827588e-06,
163
+ "loss": 0.4261,
164
+ "step": 650
165
+ },
166
+ {
167
+ "epoch": 0.41,
168
+ "learning_rate": 9.882068965517241e-06,
169
+ "loss": 0.437,
170
+ "step": 675
171
+ },
172
+ {
173
+ "epoch": 0.43,
174
+ "learning_rate": 9.864827586206898e-06,
175
+ "loss": 0.418,
176
+ "step": 700
177
+ },
178
+ {
179
+ "epoch": 0.44,
180
+ "learning_rate": 9.847586206896553e-06,
181
+ "loss": 0.3974,
182
+ "step": 725
183
+ },
184
+ {
185
+ "epoch": 0.46,
186
+ "learning_rate": 9.830344827586208e-06,
187
+ "loss": 0.3983,
188
+ "step": 750
189
+ },
190
+ {
191
+ "epoch": 0.47,
192
+ "learning_rate": 9.813103448275862e-06,
193
+ "loss": 0.3983,
194
+ "step": 775
195
+ },
196
+ {
197
+ "epoch": 0.49,
198
+ "learning_rate": 9.795862068965517e-06,
199
+ "loss": 0.3891,
200
+ "step": 800
201
+ },
202
+ {
203
+ "epoch": 0.5,
204
+ "learning_rate": 9.778620689655172e-06,
205
+ "loss": 0.3657,
206
+ "step": 825
207
+ },
208
+ {
209
+ "epoch": 0.52,
210
+ "learning_rate": 9.761379310344829e-06,
211
+ "loss": 0.3769,
212
+ "step": 850
213
+ },
214
+ {
215
+ "epoch": 0.53,
216
+ "learning_rate": 9.744137931034484e-06,
217
+ "loss": 0.3729,
218
+ "step": 875
219
+ },
220
+ {
221
+ "epoch": 0.55,
222
+ "learning_rate": 9.726896551724139e-06,
223
+ "loss": 0.3643,
224
+ "step": 900
225
+ },
226
+ {
227
+ "epoch": 0.56,
228
+ "learning_rate": 9.709655172413795e-06,
229
+ "loss": 0.362,
230
+ "step": 925
231
+ },
232
+ {
233
+ "epoch": 0.58,
234
+ "learning_rate": 9.692413793103448e-06,
235
+ "loss": 0.357,
236
+ "step": 950
237
+ },
238
+ {
239
+ "epoch": 0.59,
240
+ "learning_rate": 9.675172413793105e-06,
241
+ "loss": 0.3408,
242
+ "step": 975
243
+ },
244
+ {
245
+ "epoch": 0.61,
246
+ "learning_rate": 9.65793103448276e-06,
247
+ "loss": 0.3416,
248
+ "step": 1000
249
+ },
250
+ {
251
+ "epoch": 0.61,
252
+ "eval_cer": 17.860752670058286,
253
+ "eval_loss": 0.4335484206676483,
254
+ "eval_runtime": 804.8505,
255
+ "eval_samples_per_second": 2.343,
256
+ "eval_steps_per_second": 0.073,
257
+ "eval_wer": 51.09788070788726,
258
+ "step": 1000
259
+ },
260
+ {
261
+ "epoch": 0.62,
262
+ "learning_rate": 9.640689655172415e-06,
263
+ "loss": 0.3431,
264
+ "step": 1025
265
+ },
266
+ {
267
+ "epoch": 0.64,
268
+ "learning_rate": 9.62344827586207e-06,
269
+ "loss": 0.3376,
270
+ "step": 1050
271
+ },
272
+ {
273
+ "epoch": 0.65,
274
+ "learning_rate": 9.606206896551726e-06,
275
+ "loss": 0.3226,
276
+ "step": 1075
277
+ },
278
+ {
279
+ "epoch": 0.67,
280
+ "learning_rate": 9.58896551724138e-06,
281
+ "loss": 0.3335,
282
+ "step": 1100
283
+ },
284
+ {
285
+ "epoch": 0.68,
286
+ "learning_rate": 9.571724137931036e-06,
287
+ "loss": 0.3309,
288
+ "step": 1125
289
+ },
290
+ {
291
+ "epoch": 0.7,
292
+ "learning_rate": 9.55448275862069e-06,
293
+ "loss": 0.324,
294
+ "step": 1150
295
+ },
296
+ {
297
+ "epoch": 0.72,
298
+ "learning_rate": 9.537241379310345e-06,
299
+ "loss": 0.3416,
300
+ "step": 1175
301
+ },
302
+ {
303
+ "epoch": 0.73,
304
+ "learning_rate": 9.52e-06,
305
+ "loss": 0.3299,
306
+ "step": 1200
307
+ },
308
+ {
309
+ "epoch": 0.75,
310
+ "learning_rate": 9.502758620689655e-06,
311
+ "loss": 0.3101,
312
+ "step": 1225
313
+ },
314
+ {
315
+ "epoch": 0.76,
316
+ "learning_rate": 9.48551724137931e-06,
317
+ "loss": 0.3209,
318
+ "step": 1250
319
+ },
320
+ {
321
+ "epoch": 0.78,
322
+ "learning_rate": 9.468275862068967e-06,
323
+ "loss": 0.3195,
324
+ "step": 1275
325
+ },
326
+ {
327
+ "epoch": 0.79,
328
+ "learning_rate": 9.451034482758622e-06,
329
+ "loss": 0.3106,
330
+ "step": 1300
331
+ },
332
+ {
333
+ "epoch": 0.81,
334
+ "learning_rate": 9.433793103448276e-06,
335
+ "loss": 0.3039,
336
+ "step": 1325
337
+ },
338
+ {
339
+ "epoch": 0.82,
340
+ "learning_rate": 9.416551724137933e-06,
341
+ "loss": 0.3025,
342
+ "step": 1350
343
+ },
344
+ {
345
+ "epoch": 0.84,
346
+ "learning_rate": 9.399310344827586e-06,
347
+ "loss": 0.3051,
348
+ "step": 1375
349
+ },
350
+ {
351
+ "epoch": 0.85,
352
+ "learning_rate": 9.382068965517243e-06,
353
+ "loss": 0.3031,
354
+ "step": 1400
355
+ },
356
+ {
357
+ "epoch": 0.87,
358
+ "learning_rate": 9.364827586206898e-06,
359
+ "loss": 0.3004,
360
+ "step": 1425
361
+ },
362
+ {
363
+ "epoch": 0.88,
364
+ "learning_rate": 9.347586206896552e-06,
365
+ "loss": 0.3013,
366
+ "step": 1450
367
+ },
368
+ {
369
+ "epoch": 0.9,
370
+ "learning_rate": 9.330344827586207e-06,
371
+ "loss": 0.2859,
372
+ "step": 1475
373
+ },
374
+ {
375
+ "epoch": 0.91,
376
+ "learning_rate": 9.313103448275864e-06,
377
+ "loss": 0.2892,
378
+ "step": 1500
379
+ },
380
+ {
381
+ "epoch": 0.93,
382
+ "learning_rate": 9.295862068965517e-06,
383
+ "loss": 0.2762,
384
+ "step": 1525
385
+ },
386
+ {
387
+ "epoch": 0.94,
388
+ "learning_rate": 9.278620689655174e-06,
389
+ "loss": 0.288,
390
+ "step": 1550
391
+ },
392
+ {
393
+ "epoch": 0.96,
394
+ "learning_rate": 9.261379310344828e-06,
395
+ "loss": 0.2889,
396
+ "step": 1575
397
+ },
398
+ {
399
+ "epoch": 0.97,
400
+ "learning_rate": 9.244137931034483e-06,
401
+ "loss": 0.2831,
402
+ "step": 1600
403
+ },
404
+ {
405
+ "epoch": 0.99,
406
+ "learning_rate": 9.226896551724138e-06,
407
+ "loss": 0.2911,
408
+ "step": 1625
409
+ },
410
+ {
411
+ "epoch": 1.0,
412
+ "learning_rate": 9.209655172413793e-06,
413
+ "loss": 0.2762,
414
+ "step": 1650
415
+ },
416
+ {
417
+ "epoch": 1.02,
418
+ "learning_rate": 9.192413793103448e-06,
419
+ "loss": 0.2414,
420
+ "step": 1675
421
+ },
422
+ {
423
+ "epoch": 1.03,
424
+ "learning_rate": 9.175172413793105e-06,
425
+ "loss": 0.244,
426
+ "step": 1700
427
+ },
428
+ {
429
+ "epoch": 1.05,
430
+ "learning_rate": 9.15793103448276e-06,
431
+ "loss": 0.2527,
432
+ "step": 1725
433
+ },
434
+ {
435
+ "epoch": 1.07,
436
+ "learning_rate": 9.140689655172414e-06,
437
+ "loss": 0.2372,
438
+ "step": 1750
439
+ },
440
+ {
441
+ "epoch": 1.08,
442
+ "learning_rate": 9.12344827586207e-06,
443
+ "loss": 0.2366,
444
+ "step": 1775
445
+ },
446
+ {
447
+ "epoch": 1.1,
448
+ "learning_rate": 9.106206896551724e-06,
449
+ "loss": 0.2423,
450
+ "step": 1800
451
+ },
452
+ {
453
+ "epoch": 1.11,
454
+ "learning_rate": 9.08896551724138e-06,
455
+ "loss": 0.2382,
456
+ "step": 1825
457
+ },
458
+ {
459
+ "epoch": 1.13,
460
+ "learning_rate": 9.071724137931035e-06,
461
+ "loss": 0.2267,
462
+ "step": 1850
463
+ },
464
+ {
465
+ "epoch": 1.14,
466
+ "learning_rate": 9.05448275862069e-06,
467
+ "loss": 0.2379,
468
+ "step": 1875
469
+ },
470
+ {
471
+ "epoch": 1.16,
472
+ "learning_rate": 9.037241379310345e-06,
473
+ "loss": 0.2426,
474
+ "step": 1900
475
+ },
476
+ {
477
+ "epoch": 1.17,
478
+ "learning_rate": 9.020000000000002e-06,
479
+ "loss": 0.2365,
480
+ "step": 1925
481
+ },
482
+ {
483
+ "epoch": 1.19,
484
+ "learning_rate": 9.002758620689655e-06,
485
+ "loss": 0.2384,
486
+ "step": 1950
487
+ },
488
+ {
489
+ "epoch": 1.2,
490
+ "learning_rate": 8.985517241379311e-06,
491
+ "loss": 0.2389,
492
+ "step": 1975
493
+ },
494
+ {
495
+ "epoch": 1.22,
496
+ "learning_rate": 8.968275862068966e-06,
497
+ "loss": 0.2266,
498
+ "step": 2000
499
+ },
500
+ {
501
+ "epoch": 1.22,
502
+ "eval_cer": 13.6467773996833,
503
+ "eval_loss": 0.3382589817047119,
504
+ "eval_runtime": 729.024,
505
+ "eval_samples_per_second": 2.587,
506
+ "eval_steps_per_second": 0.081,
507
+ "eval_wer": 39.53462967008958,
508
+ "step": 2000
509
+ },
510
+ {
511
+ "epoch": 1.23,
512
+ "learning_rate": 8.951034482758621e-06,
513
+ "loss": 0.2284,
514
+ "step": 2025
515
+ },
516
+ {
517
+ "epoch": 1.25,
518
+ "learning_rate": 8.933793103448276e-06,
519
+ "loss": 0.2326,
520
+ "step": 2050
521
+ },
522
+ {
523
+ "epoch": 1.26,
524
+ "learning_rate": 8.916551724137931e-06,
525
+ "loss": 0.2282,
526
+ "step": 2075
527
+ },
528
+ {
529
+ "epoch": 1.28,
530
+ "learning_rate": 8.899310344827588e-06,
531
+ "loss": 0.2421,
532
+ "step": 2100
533
+ },
534
+ {
535
+ "epoch": 1.29,
536
+ "learning_rate": 8.882068965517242e-06,
537
+ "loss": 0.2386,
538
+ "step": 2125
539
+ },
540
+ {
541
+ "epoch": 1.31,
542
+ "learning_rate": 8.864827586206897e-06,
543
+ "loss": 0.2433,
544
+ "step": 2150
545
+ },
546
+ {
547
+ "epoch": 1.32,
548
+ "learning_rate": 8.847586206896552e-06,
549
+ "loss": 0.2307,
550
+ "step": 2175
551
+ },
552
+ {
553
+ "epoch": 1.34,
554
+ "learning_rate": 8.830344827586209e-06,
555
+ "loss": 0.2264,
556
+ "step": 2200
557
+ },
558
+ {
559
+ "epoch": 1.35,
560
+ "learning_rate": 8.813103448275862e-06,
561
+ "loss": 0.2271,
562
+ "step": 2225
563
+ },
564
+ {
565
+ "epoch": 1.37,
566
+ "learning_rate": 8.795862068965518e-06,
567
+ "loss": 0.2271,
568
+ "step": 2250
569
+ },
570
+ {
571
+ "epoch": 1.38,
572
+ "learning_rate": 8.778620689655173e-06,
573
+ "loss": 0.2245,
574
+ "step": 2275
575
+ },
576
+ {
577
+ "epoch": 1.4,
578
+ "learning_rate": 8.761379310344828e-06,
579
+ "loss": 0.2359,
580
+ "step": 2300
581
+ },
582
+ {
583
+ "epoch": 1.42,
584
+ "learning_rate": 8.744137931034483e-06,
585
+ "loss": 0.2336,
586
+ "step": 2325
587
+ },
588
+ {
589
+ "epoch": 1.43,
590
+ "learning_rate": 8.72689655172414e-06,
591
+ "loss": 0.2352,
592
+ "step": 2350
593
+ },
594
+ {
595
+ "epoch": 1.45,
596
+ "learning_rate": 8.709655172413793e-06,
597
+ "loss": 0.2289,
598
+ "step": 2375
599
+ },
600
+ {
601
+ "epoch": 1.46,
602
+ "learning_rate": 8.69241379310345e-06,
603
+ "loss": 0.2239,
604
+ "step": 2400
605
+ },
606
+ {
607
+ "epoch": 1.48,
608
+ "learning_rate": 8.675172413793104e-06,
609
+ "loss": 0.2219,
610
+ "step": 2425
611
+ },
612
+ {
613
+ "epoch": 1.49,
614
+ "learning_rate": 8.657931034482759e-06,
615
+ "loss": 0.2212,
616
+ "step": 2450
617
+ },
618
+ {
619
+ "epoch": 1.51,
620
+ "learning_rate": 8.640689655172414e-06,
621
+ "loss": 0.2268,
622
+ "step": 2475
623
+ },
624
+ {
625
+ "epoch": 1.52,
626
+ "learning_rate": 8.623448275862069e-06,
627
+ "loss": 0.2314,
628
+ "step": 2500
629
+ },
630
+ {
631
+ "epoch": 1.54,
632
+ "learning_rate": 8.606206896551725e-06,
633
+ "loss": 0.2273,
634
+ "step": 2525
635
+ },
636
+ {
637
+ "epoch": 1.55,
638
+ "learning_rate": 8.58896551724138e-06,
639
+ "loss": 0.2156,
640
+ "step": 2550
641
+ },
642
+ {
643
+ "epoch": 1.57,
644
+ "learning_rate": 8.571724137931035e-06,
645
+ "loss": 0.2302,
646
+ "step": 2575
647
+ },
648
+ {
649
+ "epoch": 1.58,
650
+ "learning_rate": 8.55448275862069e-06,
651
+ "loss": 0.2265,
652
+ "step": 2600
653
+ },
654
+ {
655
+ "epoch": 1.6,
656
+ "learning_rate": 8.537241379310347e-06,
657
+ "loss": 0.2286,
658
+ "step": 2625
659
+ },
660
+ {
661
+ "epoch": 1.61,
662
+ "learning_rate": 8.52e-06,
663
+ "loss": 0.2213,
664
+ "step": 2650
665
+ },
666
+ {
667
+ "epoch": 1.63,
668
+ "learning_rate": 8.502758620689656e-06,
669
+ "loss": 0.2238,
670
+ "step": 2675
671
+ },
672
+ {
673
+ "epoch": 1.64,
674
+ "learning_rate": 8.485517241379311e-06,
675
+ "loss": 0.2126,
676
+ "step": 2700
677
+ },
678
+ {
679
+ "epoch": 1.66,
680
+ "learning_rate": 8.468275862068966e-06,
681
+ "loss": 0.206,
682
+ "step": 2725
683
+ },
684
+ {
685
+ "epoch": 1.67,
686
+ "learning_rate": 8.451034482758621e-06,
687
+ "loss": 0.2183,
688
+ "step": 2750
689
+ },
690
+ {
691
+ "epoch": 1.69,
692
+ "learning_rate": 8.433793103448277e-06,
693
+ "loss": 0.215,
694
+ "step": 2775
695
+ },
696
+ {
697
+ "epoch": 1.7,
698
+ "learning_rate": 8.41655172413793e-06,
699
+ "loss": 0.2155,
700
+ "step": 2800
701
+ },
702
+ {
703
+ "epoch": 1.72,
704
+ "learning_rate": 8.399310344827587e-06,
705
+ "loss": 0.2146,
706
+ "step": 2825
707
+ },
708
+ {
709
+ "epoch": 1.73,
710
+ "learning_rate": 8.382068965517242e-06,
711
+ "loss": 0.2218,
712
+ "step": 2850
713
+ },
714
+ {
715
+ "epoch": 1.75,
716
+ "learning_rate": 8.364827586206897e-06,
717
+ "loss": 0.221,
718
+ "step": 2875
719
+ },
720
+ {
721
+ "epoch": 1.77,
722
+ "learning_rate": 8.347586206896552e-06,
723
+ "loss": 0.2155,
724
+ "step": 2900
725
+ },
726
+ {
727
+ "epoch": 1.78,
728
+ "learning_rate": 8.330344827586208e-06,
729
+ "loss": 0.2144,
730
+ "step": 2925
731
+ },
732
+ {
733
+ "epoch": 1.8,
734
+ "learning_rate": 8.313103448275863e-06,
735
+ "loss": 0.2184,
736
+ "step": 2950
737
+ },
738
+ {
739
+ "epoch": 1.81,
740
+ "learning_rate": 8.295862068965518e-06,
741
+ "loss": 0.2116,
742
+ "step": 2975
743
+ },
744
+ {
745
+ "epoch": 1.83,
746
+ "learning_rate": 8.278620689655173e-06,
747
+ "loss": 0.2134,
748
+ "step": 3000
749
+ },
750
+ {
751
+ "epoch": 1.83,
752
+ "eval_cer": 12.167716721134733,
753
+ "eval_loss": 0.2994455397129059,
754
+ "eval_runtime": 728.3904,
755
+ "eval_samples_per_second": 2.589,
756
+ "eval_steps_per_second": 0.081,
757
+ "eval_wer": 35.65654358750273,
758
+ "step": 3000
759
+ },
760
+ {
761
+ "epoch": 1.84,
762
+ "learning_rate": 8.261379310344828e-06,
763
+ "loss": 0.2225,
764
+ "step": 3025
765
+ },
766
+ {
767
+ "epoch": 1.86,
768
+ "learning_rate": 8.244137931034484e-06,
769
+ "loss": 0.219,
770
+ "step": 3050
771
+ },
772
+ {
773
+ "epoch": 1.87,
774
+ "learning_rate": 8.226896551724138e-06,
775
+ "loss": 0.2144,
776
+ "step": 3075
777
+ },
778
+ {
779
+ "epoch": 1.89,
780
+ "learning_rate": 8.209655172413794e-06,
781
+ "loss": 0.2143,
782
+ "step": 3100
783
+ },
784
+ {
785
+ "epoch": 1.9,
786
+ "learning_rate": 8.192413793103449e-06,
787
+ "loss": 0.2075,
788
+ "step": 3125
789
+ },
790
+ {
791
+ "epoch": 1.92,
792
+ "learning_rate": 8.175172413793104e-06,
793
+ "loss": 0.2176,
794
+ "step": 3150
795
+ },
796
+ {
797
+ "epoch": 1.93,
798
+ "learning_rate": 8.157931034482759e-06,
799
+ "loss": 0.2099,
800
+ "step": 3175
801
+ },
802
+ {
803
+ "epoch": 1.95,
804
+ "learning_rate": 8.140689655172415e-06,
805
+ "loss": 0.216,
806
+ "step": 3200
807
+ },
808
+ {
809
+ "epoch": 1.96,
810
+ "learning_rate": 8.123448275862069e-06,
811
+ "loss": 0.2199,
812
+ "step": 3225
813
+ },
814
+ {
815
+ "epoch": 1.98,
816
+ "learning_rate": 8.106206896551725e-06,
817
+ "loss": 0.213,
818
+ "step": 3250
819
+ },
820
+ {
821
+ "epoch": 1.99,
822
+ "learning_rate": 8.08896551724138e-06,
823
+ "loss": 0.2178,
824
+ "step": 3275
825
+ },
826
+ {
827
+ "epoch": 2.01,
828
+ "learning_rate": 8.071724137931035e-06,
829
+ "loss": 0.1812,
830
+ "step": 3300
831
+ },
832
+ {
833
+ "epoch": 2.02,
834
+ "learning_rate": 8.054482758620691e-06,
835
+ "loss": 0.1656,
836
+ "step": 3325
837
+ },
838
+ {
839
+ "epoch": 2.04,
840
+ "learning_rate": 8.037241379310346e-06,
841
+ "loss": 0.1656,
842
+ "step": 3350
843
+ },
844
+ {
845
+ "epoch": 2.05,
846
+ "learning_rate": 8.020000000000001e-06,
847
+ "loss": 0.1718,
848
+ "step": 3375
849
+ },
850
+ {
851
+ "epoch": 2.07,
852
+ "learning_rate": 8.002758620689656e-06,
853
+ "loss": 0.1589,
854
+ "step": 3400
855
+ },
856
+ {
857
+ "epoch": 2.08,
858
+ "learning_rate": 7.985517241379311e-06,
859
+ "loss": 0.1664,
860
+ "step": 3425
861
+ },
862
+ {
863
+ "epoch": 2.1,
864
+ "learning_rate": 7.968275862068966e-06,
865
+ "loss": 0.1743,
866
+ "step": 3450
867
+ },
868
+ {
869
+ "epoch": 2.12,
870
+ "learning_rate": 7.951034482758622e-06,
871
+ "loss": 0.1635,
872
+ "step": 3475
873
+ },
874
+ {
875
+ "epoch": 2.13,
876
+ "learning_rate": 7.933793103448275e-06,
877
+ "loss": 0.1717,
878
+ "step": 3500
879
+ },
880
+ {
881
+ "epoch": 2.15,
882
+ "learning_rate": 7.916551724137932e-06,
883
+ "loss": 0.1768,
884
+ "step": 3525
885
+ },
886
+ {
887
+ "epoch": 2.16,
888
+ "learning_rate": 7.899310344827587e-06,
889
+ "loss": 0.1689,
890
+ "step": 3550
891
+ },
892
+ {
893
+ "epoch": 2.18,
894
+ "learning_rate": 7.882068965517242e-06,
895
+ "loss": 0.1688,
896
+ "step": 3575
897
+ },
898
+ {
899
+ "epoch": 2.19,
900
+ "learning_rate": 7.864827586206897e-06,
901
+ "loss": 0.1674,
902
+ "step": 3600
903
+ },
904
+ {
905
+ "epoch": 2.21,
906
+ "learning_rate": 7.847586206896553e-06,
907
+ "loss": 0.163,
908
+ "step": 3625
909
+ },
910
+ {
911
+ "epoch": 2.22,
912
+ "learning_rate": 7.830344827586206e-06,
913
+ "loss": 0.1668,
914
+ "step": 3650
915
+ },
916
+ {
917
+ "epoch": 2.24,
918
+ "learning_rate": 7.813103448275863e-06,
919
+ "loss": 0.1702,
920
+ "step": 3675
921
+ },
922
+ {
923
+ "epoch": 2.25,
924
+ "learning_rate": 7.795862068965518e-06,
925
+ "loss": 0.167,
926
+ "step": 3700
927
+ },
928
+ {
929
+ "epoch": 2.27,
930
+ "learning_rate": 7.778620689655173e-06,
931
+ "loss": 0.1655,
932
+ "step": 3725
933
+ },
934
+ {
935
+ "epoch": 2.28,
936
+ "learning_rate": 7.76137931034483e-06,
937
+ "loss": 0.1685,
938
+ "step": 3750
939
+ },
940
+ {
941
+ "epoch": 2.3,
942
+ "learning_rate": 7.744137931034484e-06,
943
+ "loss": 0.1683,
944
+ "step": 3775
945
+ },
946
+ {
947
+ "epoch": 2.31,
948
+ "learning_rate": 7.726896551724139e-06,
949
+ "loss": 0.1707,
950
+ "step": 3800
951
+ },
952
+ {
953
+ "epoch": 2.33,
954
+ "learning_rate": 7.709655172413794e-06,
955
+ "loss": 0.172,
956
+ "step": 3825
957
+ },
958
+ {
959
+ "epoch": 2.34,
960
+ "learning_rate": 7.692413793103449e-06,
961
+ "loss": 0.1638,
962
+ "step": 3850
963
+ },
964
+ {
965
+ "epoch": 2.36,
966
+ "learning_rate": 7.675172413793104e-06,
967
+ "loss": 0.1687,
968
+ "step": 3875
969
+ },
970
+ {
971
+ "epoch": 2.37,
972
+ "learning_rate": 7.65793103448276e-06,
973
+ "loss": 0.1719,
974
+ "step": 3900
975
+ },
976
+ {
977
+ "epoch": 2.39,
978
+ "learning_rate": 7.640689655172413e-06,
979
+ "loss": 0.1664,
980
+ "step": 3925
981
+ },
982
+ {
983
+ "epoch": 2.4,
984
+ "learning_rate": 7.62344827586207e-06,
985
+ "loss": 0.1653,
986
+ "step": 3950
987
+ },
988
+ {
989
+ "epoch": 2.42,
990
+ "learning_rate": 7.606206896551725e-06,
991
+ "loss": 0.157,
992
+ "step": 3975
993
+ },
994
+ {
995
+ "epoch": 2.43,
996
+ "learning_rate": 7.58896551724138e-06,
997
+ "loss": 0.165,
998
+ "step": 4000
999
+ },
1000
+ {
1001
+ "epoch": 2.43,
1002
+ "eval_cer": 11.46019338971059,
1003
+ "eval_loss": 0.29271554946899414,
1004
+ "eval_runtime": 726.3844,
1005
+ "eval_samples_per_second": 2.596,
1006
+ "eval_steps_per_second": 0.081,
1007
+ "eval_wer": 34.19270264365305,
1008
+ "step": 4000
1009
+ },
1010
+ {
1011
+ "epoch": 2.45,
1012
+ "learning_rate": 7.5717241379310345e-06,
1013
+ "loss": 0.162,
1014
+ "step": 4025
1015
+ },
1016
+ {
1017
+ "epoch": 2.47,
1018
+ "learning_rate": 7.55448275862069e-06,
1019
+ "loss": 0.1597,
1020
+ "step": 4050
1021
+ },
1022
+ {
1023
+ "epoch": 2.48,
1024
+ "learning_rate": 7.537241379310345e-06,
1025
+ "loss": 0.166,
1026
+ "step": 4075
1027
+ },
1028
+ {
1029
+ "epoch": 2.5,
1030
+ "learning_rate": 7.520000000000001e-06,
1031
+ "loss": 0.1611,
1032
+ "step": 4100
1033
+ },
1034
+ {
1035
+ "epoch": 2.51,
1036
+ "learning_rate": 7.5027586206896566e-06,
1037
+ "loss": 0.1664,
1038
+ "step": 4125
1039
+ },
1040
+ {
1041
+ "epoch": 2.53,
1042
+ "learning_rate": 7.485517241379311e-06,
1043
+ "loss": 0.1612,
1044
+ "step": 4150
1045
+ },
1046
+ {
1047
+ "epoch": 2.54,
1048
+ "learning_rate": 7.468275862068966e-06,
1049
+ "loss": 0.1562,
1050
+ "step": 4175
1051
+ },
1052
+ {
1053
+ "epoch": 2.56,
1054
+ "learning_rate": 7.451034482758621e-06,
1055
+ "loss": 0.1645,
1056
+ "step": 4200
1057
+ },
1058
+ {
1059
+ "epoch": 2.57,
1060
+ "learning_rate": 7.433793103448277e-06,
1061
+ "loss": 0.1727,
1062
+ "step": 4225
1063
+ },
1064
+ {
1065
+ "epoch": 2.59,
1066
+ "learning_rate": 7.416551724137932e-06,
1067
+ "loss": 0.1656,
1068
+ "step": 4250
1069
+ },
1070
+ {
1071
+ "epoch": 2.6,
1072
+ "learning_rate": 7.3993103448275875e-06,
1073
+ "loss": 0.1558,
1074
+ "step": 4275
1075
+ },
1076
+ {
1077
+ "epoch": 2.62,
1078
+ "learning_rate": 7.3820689655172415e-06,
1079
+ "loss": 0.1692,
1080
+ "step": 4300
1081
+ },
1082
+ {
1083
+ "epoch": 2.63,
1084
+ "learning_rate": 7.364827586206897e-06,
1085
+ "loss": 0.1699,
1086
+ "step": 4325
1087
+ },
1088
+ {
1089
+ "epoch": 2.65,
1090
+ "learning_rate": 7.347586206896552e-06,
1091
+ "loss": 0.1626,
1092
+ "step": 4350
1093
+ },
1094
+ {
1095
+ "epoch": 2.66,
1096
+ "learning_rate": 7.330344827586208e-06,
1097
+ "loss": 0.1624,
1098
+ "step": 4375
1099
+ },
1100
+ {
1101
+ "epoch": 2.68,
1102
+ "learning_rate": 7.313103448275863e-06,
1103
+ "loss": 0.1602,
1104
+ "step": 4400
1105
+ },
1106
+ {
1107
+ "epoch": 2.69,
1108
+ "learning_rate": 7.2958620689655175e-06,
1109
+ "loss": 0.1624,
1110
+ "step": 4425
1111
+ },
1112
+ {
1113
+ "epoch": 2.71,
1114
+ "learning_rate": 7.278620689655172e-06,
1115
+ "loss": 0.1661,
1116
+ "step": 4450
1117
+ },
1118
+ {
1119
+ "epoch": 2.72,
1120
+ "learning_rate": 7.261379310344828e-06,
1121
+ "loss": 0.1564,
1122
+ "step": 4475
1123
+ },
1124
+ {
1125
+ "epoch": 2.74,
1126
+ "learning_rate": 7.244137931034483e-06,
1127
+ "loss": 0.1649,
1128
+ "step": 4500
1129
+ },
1130
+ {
1131
+ "epoch": 2.75,
1132
+ "learning_rate": 7.226896551724139e-06,
1133
+ "loss": 0.1598,
1134
+ "step": 4525
1135
+ },
1136
+ {
1137
+ "epoch": 2.77,
1138
+ "learning_rate": 7.2096551724137944e-06,
1139
+ "loss": 0.1653,
1140
+ "step": 4550
1141
+ },
1142
+ {
1143
+ "epoch": 2.78,
1144
+ "learning_rate": 7.1924137931034485e-06,
1145
+ "loss": 0.1628,
1146
+ "step": 4575
1147
+ },
1148
+ {
1149
+ "epoch": 2.8,
1150
+ "learning_rate": 7.175172413793104e-06,
1151
+ "loss": 0.1681,
1152
+ "step": 4600
1153
+ },
1154
+ {
1155
+ "epoch": 2.81,
1156
+ "learning_rate": 7.157931034482759e-06,
1157
+ "loss": 0.1643,
1158
+ "step": 4625
1159
+ },
1160
+ {
1161
+ "epoch": 2.83,
1162
+ "learning_rate": 7.140689655172415e-06,
1163
+ "loss": 0.1612,
1164
+ "step": 4650
1165
+ },
1166
+ {
1167
+ "epoch": 2.85,
1168
+ "learning_rate": 7.12344827586207e-06,
1169
+ "loss": 0.1641,
1170
+ "step": 4675
1171
+ },
1172
+ {
1173
+ "epoch": 2.86,
1174
+ "learning_rate": 7.106206896551725e-06,
1175
+ "loss": 0.1609,
1176
+ "step": 4700
1177
+ },
1178
+ {
1179
+ "epoch": 2.88,
1180
+ "learning_rate": 7.088965517241379e-06,
1181
+ "loss": 0.1595,
1182
+ "step": 4725
1183
+ },
1184
+ {
1185
+ "epoch": 2.89,
1186
+ "learning_rate": 7.071724137931035e-06,
1187
+ "loss": 0.1647,
1188
+ "step": 4750
1189
+ },
1190
+ {
1191
+ "epoch": 2.91,
1192
+ "learning_rate": 7.05448275862069e-06,
1193
+ "loss": 0.1675,
1194
+ "step": 4775
1195
+ },
1196
+ {
1197
+ "epoch": 2.92,
1198
+ "learning_rate": 7.037241379310346e-06,
1199
+ "loss": 0.167,
1200
+ "step": 4800
1201
+ },
1202
+ {
1203
+ "epoch": 2.94,
1204
+ "learning_rate": 7.0200000000000006e-06,
1205
+ "loss": 0.1648,
1206
+ "step": 4825
1207
+ },
1208
+ {
1209
+ "epoch": 2.95,
1210
+ "learning_rate": 7.002758620689655e-06,
1211
+ "loss": 0.1579,
1212
+ "step": 4850
1213
+ },
1214
+ {
1215
+ "epoch": 2.97,
1216
+ "learning_rate": 6.98551724137931e-06,
1217
+ "loss": 0.1603,
1218
+ "step": 4875
1219
+ },
1220
+ {
1221
+ "epoch": 2.98,
1222
+ "learning_rate": 6.968275862068966e-06,
1223
+ "loss": 0.1632,
1224
+ "step": 4900
1225
+ },
1226
+ {
1227
+ "epoch": 3.0,
1228
+ "learning_rate": 6.951034482758622e-06,
1229
+ "loss": 0.1652,
1230
+ "step": 4925
1231
+ },
1232
+ {
1233
+ "epoch": 3.01,
1234
+ "learning_rate": 6.933793103448277e-06,
1235
+ "loss": 0.1348,
1236
+ "step": 4950
1237
+ },
1238
+ {
1239
+ "epoch": 3.03,
1240
+ "learning_rate": 6.916551724137932e-06,
1241
+ "loss": 0.1203,
1242
+ "step": 4975
1243
+ },
1244
+ {
1245
+ "epoch": 3.04,
1246
+ "learning_rate": 6.899310344827586e-06,
1247
+ "loss": 0.1205,
1248
+ "step": 5000
1249
+ },
1250
+ {
1251
+ "epoch": 3.04,
1252
+ "eval_cer": 11.30015835045989,
1253
+ "eval_loss": 0.2879413962364197,
1254
+ "eval_runtime": 732.4387,
1255
+ "eval_samples_per_second": 2.575,
1256
+ "eval_steps_per_second": 0.081,
1257
+ "eval_wer": 33.52086519554293,
1258
+ "step": 5000
1259
+ },
1260
+ {
1261
+ "epoch": 3.06,
1262
+ "learning_rate": 6.882068965517242e-06,
1263
+ "loss": 0.1151,
1264
+ "step": 5025
1265
+ },
1266
+ {
1267
+ "epoch": 3.07,
1268
+ "learning_rate": 6.864827586206897e-06,
1269
+ "loss": 0.1258,
1270
+ "step": 5050
1271
+ },
1272
+ {
1273
+ "epoch": 3.09,
1274
+ "learning_rate": 6.847586206896553e-06,
1275
+ "loss": 0.1201,
1276
+ "step": 5075
1277
+ },
1278
+ {
1279
+ "epoch": 3.1,
1280
+ "learning_rate": 6.8303448275862075e-06,
1281
+ "loss": 0.1232,
1282
+ "step": 5100
1283
+ },
1284
+ {
1285
+ "epoch": 3.12,
1286
+ "learning_rate": 6.813103448275863e-06,
1287
+ "loss": 0.1249,
1288
+ "step": 5125
1289
+ },
1290
+ {
1291
+ "epoch": 3.13,
1292
+ "learning_rate": 6.795862068965517e-06,
1293
+ "loss": 0.1213,
1294
+ "step": 5150
1295
+ },
1296
+ {
1297
+ "epoch": 3.15,
1298
+ "learning_rate": 6.778620689655173e-06,
1299
+ "loss": 0.1249,
1300
+ "step": 5175
1301
+ },
1302
+ {
1303
+ "epoch": 3.16,
1304
+ "learning_rate": 6.761379310344828e-06,
1305
+ "loss": 0.1252,
1306
+ "step": 5200
1307
+ },
1308
+ {
1309
+ "epoch": 3.18,
1310
+ "learning_rate": 6.7441379310344836e-06,
1311
+ "loss": 0.1169,
1312
+ "step": 5225
1313
+ },
1314
+ {
1315
+ "epoch": 3.2,
1316
+ "learning_rate": 6.7268965517241384e-06,
1317
+ "loss": 0.1239,
1318
+ "step": 5250
1319
+ },
1320
+ {
1321
+ "epoch": 3.21,
1322
+ "learning_rate": 6.709655172413793e-06,
1323
+ "loss": 0.123,
1324
+ "step": 5275
1325
+ },
1326
+ {
1327
+ "epoch": 3.23,
1328
+ "learning_rate": 6.692413793103448e-06,
1329
+ "loss": 0.1228,
1330
+ "step": 5300
1331
+ },
1332
+ {
1333
+ "epoch": 3.24,
1334
+ "learning_rate": 6.675172413793104e-06,
1335
+ "loss": 0.1241,
1336
+ "step": 5325
1337
+ },
1338
+ {
1339
+ "epoch": 3.26,
1340
+ "learning_rate": 6.65793103448276e-06,
1341
+ "loss": 0.1287,
1342
+ "step": 5350
1343
+ },
1344
+ {
1345
+ "epoch": 3.27,
1346
+ "learning_rate": 6.6406896551724145e-06,
1347
+ "loss": 0.1279,
1348
+ "step": 5375
1349
+ },
1350
+ {
1351
+ "epoch": 3.29,
1352
+ "learning_rate": 6.62344827586207e-06,
1353
+ "loss": 0.1252,
1354
+ "step": 5400
1355
+ },
1356
+ {
1357
+ "epoch": 3.3,
1358
+ "learning_rate": 6.606206896551724e-06,
1359
+ "loss": 0.1266,
1360
+ "step": 5425
1361
+ },
1362
+ {
1363
+ "epoch": 3.32,
1364
+ "learning_rate": 6.58896551724138e-06,
1365
+ "loss": 0.1272,
1366
+ "step": 5450
1367
+ },
1368
+ {
1369
+ "epoch": 3.33,
1370
+ "learning_rate": 6.571724137931035e-06,
1371
+ "loss": 0.1179,
1372
+ "step": 5475
1373
+ },
1374
+ {
1375
+ "epoch": 3.35,
1376
+ "learning_rate": 6.5544827586206905e-06,
1377
+ "loss": 0.1206,
1378
+ "step": 5500
1379
+ },
1380
+ {
1381
+ "epoch": 3.36,
1382
+ "learning_rate": 6.537241379310345e-06,
1383
+ "loss": 0.1204,
1384
+ "step": 5525
1385
+ },
1386
+ {
1387
+ "epoch": 3.38,
1388
+ "learning_rate": 6.520000000000001e-06,
1389
+ "loss": 0.118,
1390
+ "step": 5550
1391
+ },
1392
+ {
1393
+ "epoch": 3.39,
1394
+ "learning_rate": 6.502758620689655e-06,
1395
+ "loss": 0.1284,
1396
+ "step": 5575
1397
+ },
1398
+ {
1399
+ "epoch": 3.41,
1400
+ "learning_rate": 6.485517241379311e-06,
1401
+ "loss": 0.1259,
1402
+ "step": 5600
1403
+ },
1404
+ {
1405
+ "epoch": 3.42,
1406
+ "learning_rate": 6.468275862068966e-06,
1407
+ "loss": 0.1316,
1408
+ "step": 5625
1409
+ },
1410
+ {
1411
+ "epoch": 3.44,
1412
+ "learning_rate": 6.4510344827586214e-06,
1413
+ "loss": 0.1281,
1414
+ "step": 5650
1415
+ },
1416
+ {
1417
+ "epoch": 3.45,
1418
+ "learning_rate": 6.433793103448276e-06,
1419
+ "loss": 0.125,
1420
+ "step": 5675
1421
+ },
1422
+ {
1423
+ "epoch": 3.47,
1424
+ "learning_rate": 6.416551724137931e-06,
1425
+ "loss": 0.1203,
1426
+ "step": 5700
1427
+ },
1428
+ {
1429
+ "epoch": 3.48,
1430
+ "learning_rate": 6.399310344827587e-06,
1431
+ "loss": 0.1315,
1432
+ "step": 5725
1433
+ },
1434
+ {
1435
+ "epoch": 3.5,
1436
+ "learning_rate": 6.382068965517242e-06,
1437
+ "loss": 0.1268,
1438
+ "step": 5750
1439
+ },
1440
+ {
1441
+ "epoch": 3.51,
1442
+ "learning_rate": 6.3648275862068975e-06,
1443
+ "loss": 0.1201,
1444
+ "step": 5775
1445
+ },
1446
+ {
1447
+ "epoch": 3.53,
1448
+ "learning_rate": 6.347586206896552e-06,
1449
+ "loss": 0.1231,
1450
+ "step": 5800
1451
+ },
1452
+ {
1453
+ "epoch": 3.55,
1454
+ "learning_rate": 6.330344827586208e-06,
1455
+ "loss": 0.125,
1456
+ "step": 5825
1457
+ },
1458
+ {
1459
+ "epoch": 3.56,
1460
+ "learning_rate": 6.313103448275862e-06,
1461
+ "loss": 0.1327,
1462
+ "step": 5850
1463
+ },
1464
+ {
1465
+ "epoch": 3.58,
1466
+ "learning_rate": 6.295862068965518e-06,
1467
+ "loss": 0.1254,
1468
+ "step": 5875
1469
+ },
1470
+ {
1471
+ "epoch": 3.59,
1472
+ "learning_rate": 6.278620689655173e-06,
1473
+ "loss": 0.1257,
1474
+ "step": 5900
1475
+ },
1476
+ {
1477
+ "epoch": 3.61,
1478
+ "learning_rate": 6.261379310344828e-06,
1479
+ "loss": 0.1305,
1480
+ "step": 5925
1481
+ },
1482
+ {
1483
+ "epoch": 3.62,
1484
+ "learning_rate": 6.244137931034483e-06,
1485
+ "loss": 0.124,
1486
+ "step": 5950
1487
+ },
1488
+ {
1489
+ "epoch": 3.64,
1490
+ "learning_rate": 6.226896551724139e-06,
1491
+ "loss": 0.1251,
1492
+ "step": 5975
1493
+ },
1494
+ {
1495
+ "epoch": 3.65,
1496
+ "learning_rate": 6.209655172413793e-06,
1497
+ "loss": 0.1284,
1498
+ "step": 6000
1499
+ },
1500
+ {
1501
+ "epoch": 3.65,
1502
+ "eval_cer": 10.98851116876116,
1503
+ "eval_loss": 0.28836125135421753,
1504
+ "eval_runtime": 732.4508,
1505
+ "eval_samples_per_second": 2.575,
1506
+ "eval_steps_per_second": 0.081,
1507
+ "eval_wer": 32.75071007209963,
1508
+ "step": 6000
1509
+ },
1510
+ {
1511
+ "epoch": 3.67,
1512
+ "learning_rate": 6.192413793103449e-06,
1513
+ "loss": 0.1195,
1514
+ "step": 6025
1515
+ },
1516
+ {
1517
+ "epoch": 3.68,
1518
+ "learning_rate": 6.175172413793104e-06,
1519
+ "loss": 0.1237,
1520
+ "step": 6050
1521
+ },
1522
+ {
1523
+ "epoch": 3.7,
1524
+ "learning_rate": 6.157931034482759e-06,
1525
+ "loss": 0.1262,
1526
+ "step": 6075
1527
+ },
1528
+ {
1529
+ "epoch": 3.71,
1530
+ "learning_rate": 6.140689655172414e-06,
1531
+ "loss": 0.1306,
1532
+ "step": 6100
1533
+ },
1534
+ {
1535
+ "epoch": 3.73,
1536
+ "learning_rate": 6.123448275862069e-06,
1537
+ "loss": 0.121,
1538
+ "step": 6125
1539
+ },
1540
+ {
1541
+ "epoch": 3.74,
1542
+ "learning_rate": 6.106206896551725e-06,
1543
+ "loss": 0.1304,
1544
+ "step": 6150
1545
+ },
1546
+ {
1547
+ "epoch": 3.76,
1548
+ "learning_rate": 6.08896551724138e-06,
1549
+ "loss": 0.1198,
1550
+ "step": 6175
1551
+ },
1552
+ {
1553
+ "epoch": 3.77,
1554
+ "learning_rate": 6.071724137931035e-06,
1555
+ "loss": 0.1274,
1556
+ "step": 6200
1557
+ },
1558
+ {
1559
+ "epoch": 3.79,
1560
+ "learning_rate": 6.05448275862069e-06,
1561
+ "loss": 0.123,
1562
+ "step": 6225
1563
+ },
1564
+ {
1565
+ "epoch": 3.8,
1566
+ "learning_rate": 6.037241379310346e-06,
1567
+ "loss": 0.1247,
1568
+ "step": 6250
1569
+ },
1570
+ {
1571
+ "epoch": 3.82,
1572
+ "learning_rate": 6.02e-06,
1573
+ "loss": 0.1188,
1574
+ "step": 6275
1575
+ },
1576
+ {
1577
+ "epoch": 3.83,
1578
+ "learning_rate": 6.002758620689656e-06,
1579
+ "loss": 0.1226,
1580
+ "step": 6300
1581
+ },
1582
+ {
1583
+ "epoch": 3.85,
1584
+ "learning_rate": 5.9855172413793105e-06,
1585
+ "loss": 0.126,
1586
+ "step": 6325
1587
+ },
1588
+ {
1589
+ "epoch": 3.86,
1590
+ "learning_rate": 5.968275862068966e-06,
1591
+ "loss": 0.1238,
1592
+ "step": 6350
1593
+ },
1594
+ {
1595
+ "epoch": 3.88,
1596
+ "learning_rate": 5.951034482758621e-06,
1597
+ "loss": 0.1207,
1598
+ "step": 6375
1599
+ },
1600
+ {
1601
+ "epoch": 3.9,
1602
+ "learning_rate": 5.933793103448277e-06,
1603
+ "loss": 0.1228,
1604
+ "step": 6400
1605
+ },
1606
+ {
1607
+ "epoch": 3.91,
1608
+ "learning_rate": 5.916551724137931e-06,
1609
+ "loss": 0.1253,
1610
+ "step": 6425
1611
+ },
1612
+ {
1613
+ "epoch": 3.93,
1614
+ "learning_rate": 5.899310344827587e-06,
1615
+ "loss": 0.1243,
1616
+ "step": 6450
1617
+ },
1618
+ {
1619
+ "epoch": 3.94,
1620
+ "learning_rate": 5.8820689655172415e-06,
1621
+ "loss": 0.1235,
1622
+ "step": 6475
1623
+ },
1624
+ {
1625
+ "epoch": 3.96,
1626
+ "learning_rate": 5.864827586206897e-06,
1627
+ "loss": 0.1236,
1628
+ "step": 6500
1629
+ },
1630
+ {
1631
+ "epoch": 3.97,
1632
+ "learning_rate": 5.847586206896552e-06,
1633
+ "loss": 0.129,
1634
+ "step": 6525
1635
+ },
1636
+ {
1637
+ "epoch": 3.99,
1638
+ "learning_rate": 5.830344827586208e-06,
1639
+ "loss": 0.1281,
1640
+ "step": 6550
1641
+ },
1642
+ {
1643
+ "epoch": 4.0,
1644
+ "learning_rate": 5.813103448275863e-06,
1645
+ "loss": 0.1223,
1646
+ "step": 6575
1647
+ },
1648
+ {
1649
+ "epoch": 4.02,
1650
+ "learning_rate": 5.7958620689655175e-06,
1651
+ "loss": 0.0903,
1652
+ "step": 6600
1653
+ },
1654
+ {
1655
+ "epoch": 4.03,
1656
+ "learning_rate": 5.778620689655173e-06,
1657
+ "loss": 0.0886,
1658
+ "step": 6625
1659
+ },
1660
+ {
1661
+ "epoch": 4.05,
1662
+ "learning_rate": 5.761379310344828e-06,
1663
+ "loss": 0.0923,
1664
+ "step": 6650
1665
+ },
1666
+ {
1667
+ "epoch": 4.06,
1668
+ "learning_rate": 5.744137931034484e-06,
1669
+ "loss": 0.0866,
1670
+ "step": 6675
1671
+ },
1672
+ {
1673
+ "epoch": 4.08,
1674
+ "learning_rate": 5.726896551724138e-06,
1675
+ "loss": 0.095,
1676
+ "step": 6700
1677
+ },
1678
+ {
1679
+ "epoch": 4.09,
1680
+ "learning_rate": 5.7096551724137936e-06,
1681
+ "loss": 0.0865,
1682
+ "step": 6725
1683
+ },
1684
+ {
1685
+ "epoch": 4.11,
1686
+ "learning_rate": 5.692413793103448e-06,
1687
+ "loss": 0.0907,
1688
+ "step": 6750
1689
+ },
1690
+ {
1691
+ "epoch": 4.12,
1692
+ "learning_rate": 5.675172413793104e-06,
1693
+ "loss": 0.0875,
1694
+ "step": 6775
1695
+ },
1696
+ {
1697
+ "epoch": 4.14,
1698
+ "learning_rate": 5.657931034482759e-06,
1699
+ "loss": 0.0919,
1700
+ "step": 6800
1701
+ },
1702
+ {
1703
+ "epoch": 4.15,
1704
+ "learning_rate": 5.640689655172415e-06,
1705
+ "loss": 0.0884,
1706
+ "step": 6825
1707
+ },
1708
+ {
1709
+ "epoch": 4.17,
1710
+ "learning_rate": 5.623448275862069e-06,
1711
+ "loss": 0.0932,
1712
+ "step": 6850
1713
+ },
1714
+ {
1715
+ "epoch": 4.18,
1716
+ "learning_rate": 5.6062068965517245e-06,
1717
+ "loss": 0.0931,
1718
+ "step": 6875
1719
+ },
1720
+ {
1721
+ "epoch": 4.2,
1722
+ "learning_rate": 5.588965517241379e-06,
1723
+ "loss": 0.0939,
1724
+ "step": 6900
1725
+ },
1726
+ {
1727
+ "epoch": 4.21,
1728
+ "learning_rate": 5.571724137931035e-06,
1729
+ "loss": 0.0928,
1730
+ "step": 6925
1731
+ },
1732
+ {
1733
+ "epoch": 4.23,
1734
+ "learning_rate": 5.554482758620691e-06,
1735
+ "loss": 0.0944,
1736
+ "step": 6950
1737
+ },
1738
+ {
1739
+ "epoch": 4.25,
1740
+ "learning_rate": 5.537241379310346e-06,
1741
+ "loss": 0.0936,
1742
+ "step": 6975
1743
+ },
1744
+ {
1745
+ "epoch": 4.26,
1746
+ "learning_rate": 5.5200000000000005e-06,
1747
+ "loss": 0.0893,
1748
+ "step": 7000
1749
+ },
1750
+ {
1751
+ "epoch": 4.26,
1752
+ "eval_cer": 11.207506485630537,
1753
+ "eval_loss": 0.3021553158760071,
1754
+ "eval_runtime": 735.2629,
1755
+ "eval_samples_per_second": 2.565,
1756
+ "eval_steps_per_second": 0.08,
1757
+ "eval_wer": 33.08935984269172,
1758
+ "step": 7000
1759
+ },
1760
+ {
1761
+ "epoch": 4.28,
1762
+ "learning_rate": 5.502758620689655e-06,
1763
+ "loss": 0.0916,
1764
+ "step": 7025
1765
+ },
1766
+ {
1767
+ "epoch": 4.29,
1768
+ "learning_rate": 5.485517241379311e-06,
1769
+ "loss": 0.0937,
1770
+ "step": 7050
1771
+ },
1772
+ {
1773
+ "epoch": 4.31,
1774
+ "learning_rate": 5.468275862068966e-06,
1775
+ "loss": 0.0929,
1776
+ "step": 7075
1777
+ },
1778
+ {
1779
+ "epoch": 4.32,
1780
+ "learning_rate": 5.451034482758622e-06,
1781
+ "loss": 0.0855,
1782
+ "step": 7100
1783
+ },
1784
+ {
1785
+ "epoch": 4.34,
1786
+ "learning_rate": 5.433793103448276e-06,
1787
+ "loss": 0.0882,
1788
+ "step": 7125
1789
+ },
1790
+ {
1791
+ "epoch": 4.35,
1792
+ "learning_rate": 5.4165517241379314e-06,
1793
+ "loss": 0.0917,
1794
+ "step": 7150
1795
+ },
1796
+ {
1797
+ "epoch": 4.37,
1798
+ "learning_rate": 5.399310344827586e-06,
1799
+ "loss": 0.0924,
1800
+ "step": 7175
1801
+ },
1802
+ {
1803
+ "epoch": 4.38,
1804
+ "learning_rate": 5.382068965517242e-06,
1805
+ "loss": 0.0913,
1806
+ "step": 7200
1807
+ },
1808
+ {
1809
+ "epoch": 4.4,
1810
+ "learning_rate": 5.364827586206897e-06,
1811
+ "loss": 0.0958,
1812
+ "step": 7225
1813
+ },
1814
+ {
1815
+ "epoch": 4.41,
1816
+ "learning_rate": 5.347586206896553e-06,
1817
+ "loss": 0.0897,
1818
+ "step": 7250
1819
+ },
1820
+ {
1821
+ "epoch": 4.43,
1822
+ "learning_rate": 5.330344827586207e-06,
1823
+ "loss": 0.093,
1824
+ "step": 7275
1825
+ },
1826
+ {
1827
+ "epoch": 4.44,
1828
+ "learning_rate": 5.313103448275862e-06,
1829
+ "loss": 0.0913,
1830
+ "step": 7300
1831
+ },
1832
+ {
1833
+ "epoch": 4.46,
1834
+ "learning_rate": 5.295862068965517e-06,
1835
+ "loss": 0.0927,
1836
+ "step": 7325
1837
+ },
1838
+ {
1839
+ "epoch": 4.47,
1840
+ "learning_rate": 5.278620689655173e-06,
1841
+ "loss": 0.0923,
1842
+ "step": 7350
1843
+ },
1844
+ {
1845
+ "epoch": 4.49,
1846
+ "learning_rate": 5.261379310344829e-06,
1847
+ "loss": 0.0889,
1848
+ "step": 7375
1849
+ },
1850
+ {
1851
+ "epoch": 4.5,
1852
+ "learning_rate": 5.2441379310344835e-06,
1853
+ "loss": 0.0913,
1854
+ "step": 7400
1855
+ },
1856
+ {
1857
+ "epoch": 4.52,
1858
+ "learning_rate": 5.226896551724138e-06,
1859
+ "loss": 0.0934,
1860
+ "step": 7425
1861
+ },
1862
+ {
1863
+ "epoch": 4.53,
1864
+ "learning_rate": 5.209655172413793e-06,
1865
+ "loss": 0.0917,
1866
+ "step": 7450
1867
+ },
1868
+ {
1869
+ "epoch": 4.55,
1870
+ "learning_rate": 5.192413793103449e-06,
1871
+ "loss": 0.0876,
1872
+ "step": 7475
1873
+ },
1874
+ {
1875
+ "epoch": 4.56,
1876
+ "learning_rate": 5.175172413793104e-06,
1877
+ "loss": 0.0934,
1878
+ "step": 7500
1879
+ },
1880
+ {
1881
+ "epoch": 4.58,
1882
+ "learning_rate": 5.1579310344827596e-06,
1883
+ "loss": 0.0835,
1884
+ "step": 7525
1885
+ },
1886
+ {
1887
+ "epoch": 4.6,
1888
+ "learning_rate": 5.140689655172414e-06,
1889
+ "loss": 0.0935,
1890
+ "step": 7550
1891
+ },
1892
+ {
1893
+ "epoch": 4.61,
1894
+ "learning_rate": 5.123448275862069e-06,
1895
+ "loss": 0.0924,
1896
+ "step": 7575
1897
+ },
1898
+ {
1899
+ "epoch": 4.63,
1900
+ "learning_rate": 5.106206896551724e-06,
1901
+ "loss": 0.0936,
1902
+ "step": 7600
1903
+ },
1904
+ {
1905
+ "epoch": 4.64,
1906
+ "learning_rate": 5.08896551724138e-06,
1907
+ "loss": 0.0958,
1908
+ "step": 7625
1909
+ },
1910
+ {
1911
+ "epoch": 4.66,
1912
+ "learning_rate": 5.071724137931035e-06,
1913
+ "loss": 0.0963,
1914
+ "step": 7650
1915
+ },
1916
+ {
1917
+ "epoch": 4.67,
1918
+ "learning_rate": 5.0544827586206905e-06,
1919
+ "loss": 0.0857,
1920
+ "step": 7675
1921
+ },
1922
+ {
1923
+ "epoch": 4.69,
1924
+ "learning_rate": 5.0372413793103445e-06,
1925
+ "loss": 0.0909,
1926
+ "step": 7700
1927
+ },
1928
+ {
1929
+ "epoch": 4.7,
1930
+ "learning_rate": 5.02e-06,
1931
+ "loss": 0.0942,
1932
+ "step": 7725
1933
+ },
1934
+ {
1935
+ "epoch": 4.72,
1936
+ "learning_rate": 5.002758620689656e-06,
1937
+ "loss": 0.0883,
1938
+ "step": 7750
1939
+ },
1940
+ {
1941
+ "epoch": 4.73,
1942
+ "learning_rate": 4.985517241379311e-06,
1943
+ "loss": 0.0953,
1944
+ "step": 7775
1945
+ },
1946
+ {
1947
+ "epoch": 4.75,
1948
+ "learning_rate": 4.968275862068966e-06,
1949
+ "loss": 0.0956,
1950
+ "step": 7800
1951
+ },
1952
+ {
1953
+ "epoch": 4.76,
1954
+ "learning_rate": 4.951034482758621e-06,
1955
+ "loss": 0.0951,
1956
+ "step": 7825
1957
+ },
1958
+ {
1959
+ "epoch": 4.78,
1960
+ "learning_rate": 4.933793103448276e-06,
1961
+ "loss": 0.0867,
1962
+ "step": 7850
1963
+ },
1964
+ {
1965
+ "epoch": 4.79,
1966
+ "learning_rate": 4.916551724137931e-06,
1967
+ "loss": 0.0994,
1968
+ "step": 7875
1969
+ },
1970
+ {
1971
+ "epoch": 4.81,
1972
+ "learning_rate": 4.899310344827586e-06,
1973
+ "loss": 0.0939,
1974
+ "step": 7900
1975
+ },
1976
+ {
1977
+ "epoch": 4.82,
1978
+ "learning_rate": 4.882068965517242e-06,
1979
+ "loss": 0.0935,
1980
+ "step": 7925
1981
+ },
1982
+ {
1983
+ "epoch": 4.84,
1984
+ "learning_rate": 4.8648275862068974e-06,
1985
+ "loss": 0.0908,
1986
+ "step": 7950
1987
+ },
1988
+ {
1989
+ "epoch": 4.85,
1990
+ "learning_rate": 4.847586206896552e-06,
1991
+ "loss": 0.096,
1992
+ "step": 7975
1993
+ },
1994
+ {
1995
+ "epoch": 4.87,
1996
+ "learning_rate": 4.830344827586207e-06,
1997
+ "loss": 0.0902,
1998
+ "step": 8000
1999
+ },
2000
+ {
2001
+ "epoch": 4.87,
2002
+ "eval_cer": 11.231932886358276,
2003
+ "eval_loss": 0.3060995638370514,
2004
+ "eval_runtime": 732.5317,
2005
+ "eval_samples_per_second": 2.575,
2006
+ "eval_steps_per_second": 0.081,
2007
+ "eval_wer": 32.64693030369237,
2008
+ "step": 8000
2009
+ },
2010
+ {
2011
+ "epoch": 4.88,
2012
+ "learning_rate": 4.813103448275863e-06,
2013
+ "loss": 0.0986,
2014
+ "step": 8025
2015
+ },
2016
+ {
2017
+ "epoch": 4.9,
2018
+ "learning_rate": 4.795862068965518e-06,
2019
+ "loss": 0.0899,
2020
+ "step": 8050
2021
+ },
2022
+ {
2023
+ "epoch": 4.91,
2024
+ "learning_rate": 4.778620689655173e-06,
2025
+ "loss": 0.0878,
2026
+ "step": 8075
2027
+ },
2028
+ {
2029
+ "epoch": 4.93,
2030
+ "learning_rate": 4.761379310344828e-06,
2031
+ "loss": 0.0945,
2032
+ "step": 8100
2033
+ },
2034
+ {
2035
+ "epoch": 4.95,
2036
+ "learning_rate": 4.744137931034483e-06,
2037
+ "loss": 0.0928,
2038
+ "step": 8125
2039
+ },
2040
+ {
2041
+ "epoch": 4.96,
2042
+ "learning_rate": 4.726896551724138e-06,
2043
+ "loss": 0.0929,
2044
+ "step": 8150
2045
+ },
2046
+ {
2047
+ "epoch": 4.98,
2048
+ "learning_rate": 4.709655172413794e-06,
2049
+ "loss": 0.0896,
2050
+ "step": 8175
2051
+ },
2052
+ {
2053
+ "epoch": 4.99,
2054
+ "learning_rate": 4.692413793103449e-06,
2055
+ "loss": 0.0932,
2056
+ "step": 8200
2057
+ },
2058
+ {
2059
+ "epoch": 5.01,
2060
+ "learning_rate": 4.6751724137931035e-06,
2061
+ "loss": 0.0806,
2062
+ "step": 8225
2063
+ },
2064
+ {
2065
+ "epoch": 5.02,
2066
+ "learning_rate": 4.657931034482759e-06,
2067
+ "loss": 0.065,
2068
+ "step": 8250
2069
+ },
2070
+ {
2071
+ "epoch": 5.04,
2072
+ "learning_rate": 4.640689655172414e-06,
2073
+ "loss": 0.0608,
2074
+ "step": 8275
2075
+ },
2076
+ {
2077
+ "epoch": 5.05,
2078
+ "learning_rate": 4.623448275862069e-06,
2079
+ "loss": 0.0645,
2080
+ "step": 8300
2081
+ },
2082
+ {
2083
+ "epoch": 5.07,
2084
+ "learning_rate": 4.606206896551724e-06,
2085
+ "loss": 0.0658,
2086
+ "step": 8325
2087
+ },
2088
+ {
2089
+ "epoch": 5.08,
2090
+ "learning_rate": 4.58896551724138e-06,
2091
+ "loss": 0.0611,
2092
+ "step": 8350
2093
+ },
2094
+ {
2095
+ "epoch": 5.1,
2096
+ "learning_rate": 4.571724137931035e-06,
2097
+ "loss": 0.0624,
2098
+ "step": 8375
2099
+ },
2100
+ {
2101
+ "epoch": 5.11,
2102
+ "learning_rate": 4.55448275862069e-06,
2103
+ "loss": 0.0635,
2104
+ "step": 8400
2105
+ },
2106
+ {
2107
+ "epoch": 5.13,
2108
+ "learning_rate": 4.537241379310345e-06,
2109
+ "loss": 0.0654,
2110
+ "step": 8425
2111
+ },
2112
+ {
2113
+ "epoch": 5.14,
2114
+ "learning_rate": 4.520000000000001e-06,
2115
+ "loss": 0.0616,
2116
+ "step": 8450
2117
+ },
2118
+ {
2119
+ "epoch": 5.16,
2120
+ "learning_rate": 4.502758620689656e-06,
2121
+ "loss": 0.0651,
2122
+ "step": 8475
2123
+ },
2124
+ {
2125
+ "epoch": 5.17,
2126
+ "learning_rate": 4.4855172413793105e-06,
2127
+ "loss": 0.0611,
2128
+ "step": 8500
2129
+ },
2130
+ {
2131
+ "epoch": 5.19,
2132
+ "learning_rate": 4.468275862068966e-06,
2133
+ "loss": 0.0618,
2134
+ "step": 8525
2135
+ },
2136
+ {
2137
+ "epoch": 5.2,
2138
+ "learning_rate": 4.451034482758621e-06,
2139
+ "loss": 0.0623,
2140
+ "step": 8550
2141
+ },
2142
+ {
2143
+ "epoch": 5.22,
2144
+ "learning_rate": 4.433793103448276e-06,
2145
+ "loss": 0.065,
2146
+ "step": 8575
2147
+ },
2148
+ {
2149
+ "epoch": 5.23,
2150
+ "learning_rate": 4.416551724137932e-06,
2151
+ "loss": 0.0644,
2152
+ "step": 8600
2153
+ },
2154
+ {
2155
+ "epoch": 5.25,
2156
+ "learning_rate": 4.3993103448275866e-06,
2157
+ "loss": 0.0655,
2158
+ "step": 8625
2159
+ },
2160
+ {
2161
+ "epoch": 5.26,
2162
+ "learning_rate": 4.3820689655172414e-06,
2163
+ "loss": 0.0666,
2164
+ "step": 8650
2165
+ },
2166
+ {
2167
+ "epoch": 5.28,
2168
+ "learning_rate": 4.364827586206897e-06,
2169
+ "loss": 0.0629,
2170
+ "step": 8675
2171
+ },
2172
+ {
2173
+ "epoch": 5.3,
2174
+ "learning_rate": 4.347586206896552e-06,
2175
+ "loss": 0.0641,
2176
+ "step": 8700
2177
+ },
2178
+ {
2179
+ "epoch": 5.31,
2180
+ "learning_rate": 4.330344827586207e-06,
2181
+ "loss": 0.0638,
2182
+ "step": 8725
2183
+ },
2184
+ {
2185
+ "epoch": 5.33,
2186
+ "learning_rate": 4.313103448275863e-06,
2187
+ "loss": 0.0632,
2188
+ "step": 8750
2189
+ },
2190
+ {
2191
+ "epoch": 5.34,
2192
+ "learning_rate": 4.2958620689655175e-06,
2193
+ "loss": 0.0637,
2194
+ "step": 8775
2195
+ },
2196
+ {
2197
+ "epoch": 5.36,
2198
+ "learning_rate": 4.278620689655173e-06,
2199
+ "loss": 0.0628,
2200
+ "step": 8800
2201
+ },
2202
+ {
2203
+ "epoch": 5.37,
2204
+ "learning_rate": 4.261379310344828e-06,
2205
+ "loss": 0.0703,
2206
+ "step": 8825
2207
+ },
2208
+ {
2209
+ "epoch": 5.39,
2210
+ "learning_rate": 4.244137931034483e-06,
2211
+ "loss": 0.0639,
2212
+ "step": 8850
2213
+ },
2214
+ {
2215
+ "epoch": 5.4,
2216
+ "learning_rate": 4.226896551724139e-06,
2217
+ "loss": 0.0645,
2218
+ "step": 8875
2219
+ },
2220
+ {
2221
+ "epoch": 5.42,
2222
+ "learning_rate": 4.2096551724137935e-06,
2223
+ "loss": 0.0664,
2224
+ "step": 8900
2225
+ },
2226
+ {
2227
+ "epoch": 5.43,
2228
+ "learning_rate": 4.192413793103448e-06,
2229
+ "loss": 0.0612,
2230
+ "step": 8925
2231
+ },
2232
+ {
2233
+ "epoch": 5.45,
2234
+ "learning_rate": 4.175172413793104e-06,
2235
+ "loss": 0.0656,
2236
+ "step": 8950
2237
+ },
2238
+ {
2239
+ "epoch": 5.46,
2240
+ "learning_rate": 4.157931034482759e-06,
2241
+ "loss": 0.068,
2242
+ "step": 8975
2243
+ },
2244
+ {
2245
+ "epoch": 5.48,
2246
+ "learning_rate": 4.140689655172414e-06,
2247
+ "loss": 0.065,
2248
+ "step": 9000
2249
+ },
2250
+ {
2251
+ "epoch": 5.48,
2252
+ "eval_cer": 11.159495973855329,
2253
+ "eval_loss": 0.32331350445747375,
2254
+ "eval_runtime": 731.9683,
2255
+ "eval_samples_per_second": 2.577,
2256
+ "eval_steps_per_second": 0.081,
2257
+ "eval_wer": 32.81625518898842,
2258
+ "step": 9000
2259
+ },
2260
+ {
2261
+ "epoch": 5.49,
2262
+ "learning_rate": 4.1234482758620696e-06,
2263
+ "loss": 0.0643,
2264
+ "step": 9025
2265
+ },
2266
+ {
2267
+ "epoch": 5.51,
2268
+ "learning_rate": 4.1062068965517244e-06,
2269
+ "loss": 0.0689,
2270
+ "step": 9050
2271
+ },
2272
+ {
2273
+ "epoch": 5.52,
2274
+ "learning_rate": 4.088965517241379e-06,
2275
+ "loss": 0.0644,
2276
+ "step": 9075
2277
+ },
2278
+ {
2279
+ "epoch": 5.54,
2280
+ "learning_rate": 4.071724137931035e-06,
2281
+ "loss": 0.0633,
2282
+ "step": 9100
2283
+ },
2284
+ {
2285
+ "epoch": 5.55,
2286
+ "learning_rate": 4.05448275862069e-06,
2287
+ "loss": 0.0683,
2288
+ "step": 9125
2289
+ },
2290
+ {
2291
+ "epoch": 5.57,
2292
+ "learning_rate": 4.037241379310346e-06,
2293
+ "loss": 0.0639,
2294
+ "step": 9150
2295
+ },
2296
+ {
2297
+ "epoch": 5.58,
2298
+ "learning_rate": 4.0200000000000005e-06,
2299
+ "loss": 0.063,
2300
+ "step": 9175
2301
+ },
2302
+ {
2303
+ "epoch": 5.6,
2304
+ "learning_rate": 4.003448275862069e-06,
2305
+ "loss": 0.0667,
2306
+ "step": 9200
2307
+ },
2308
+ {
2309
+ "epoch": 5.61,
2310
+ "learning_rate": 3.986206896551724e-06,
2311
+ "loss": 0.07,
2312
+ "step": 9225
2313
+ },
2314
+ {
2315
+ "epoch": 5.63,
2316
+ "learning_rate": 3.96896551724138e-06,
2317
+ "loss": 0.0683,
2318
+ "step": 9250
2319
+ },
2320
+ {
2321
+ "epoch": 5.65,
2322
+ "learning_rate": 3.951724137931035e-06,
2323
+ "loss": 0.0665,
2324
+ "step": 9275
2325
+ },
2326
+ {
2327
+ "epoch": 5.66,
2328
+ "learning_rate": 3.93448275862069e-06,
2329
+ "loss": 0.0598,
2330
+ "step": 9300
2331
+ },
2332
+ {
2333
+ "epoch": 5.68,
2334
+ "learning_rate": 3.917241379310345e-06,
2335
+ "loss": 0.0649,
2336
+ "step": 9325
2337
+ },
2338
+ {
2339
+ "epoch": 5.69,
2340
+ "learning_rate": 3.900000000000001e-06,
2341
+ "loss": 0.067,
2342
+ "step": 9350
2343
+ },
2344
+ {
2345
+ "epoch": 5.71,
2346
+ "learning_rate": 3.882758620689656e-06,
2347
+ "loss": 0.0652,
2348
+ "step": 9375
2349
+ },
2350
+ {
2351
+ "epoch": 5.72,
2352
+ "learning_rate": 3.8655172413793105e-06,
2353
+ "loss": 0.067,
2354
+ "step": 9400
2355
+ },
2356
+ {
2357
+ "epoch": 5.74,
2358
+ "learning_rate": 3.848275862068966e-06,
2359
+ "loss": 0.0667,
2360
+ "step": 9425
2361
+ },
2362
+ {
2363
+ "epoch": 5.75,
2364
+ "learning_rate": 3.831034482758621e-06,
2365
+ "loss": 0.0679,
2366
+ "step": 9450
2367
+ },
2368
+ {
2369
+ "epoch": 5.77,
2370
+ "learning_rate": 3.813793103448276e-06,
2371
+ "loss": 0.0653,
2372
+ "step": 9475
2373
+ },
2374
+ {
2375
+ "epoch": 5.78,
2376
+ "learning_rate": 3.7965517241379313e-06,
2377
+ "loss": 0.0661,
2378
+ "step": 9500
2379
+ },
2380
+ {
2381
+ "epoch": 5.8,
2382
+ "learning_rate": 3.7793103448275866e-06,
2383
+ "loss": 0.0695,
2384
+ "step": 9525
2385
+ },
2386
+ {
2387
+ "epoch": 5.81,
2388
+ "learning_rate": 3.7620689655172414e-06,
2389
+ "loss": 0.065,
2390
+ "step": 9550
2391
+ },
2392
+ {
2393
+ "epoch": 5.83,
2394
+ "learning_rate": 3.7448275862068967e-06,
2395
+ "loss": 0.0625,
2396
+ "step": 9575
2397
+ },
2398
+ {
2399
+ "epoch": 5.84,
2400
+ "learning_rate": 3.727586206896552e-06,
2401
+ "loss": 0.0669,
2402
+ "step": 9600
2403
+ },
2404
+ {
2405
+ "epoch": 5.86,
2406
+ "learning_rate": 3.710344827586207e-06,
2407
+ "loss": 0.0687,
2408
+ "step": 9625
2409
+ },
2410
+ {
2411
+ "epoch": 5.87,
2412
+ "learning_rate": 3.6931034482758626e-06,
2413
+ "loss": 0.0698,
2414
+ "step": 9650
2415
+ },
2416
+ {
2417
+ "epoch": 5.89,
2418
+ "learning_rate": 3.675862068965518e-06,
2419
+ "loss": 0.0624,
2420
+ "step": 9675
2421
+ },
2422
+ {
2423
+ "epoch": 5.9,
2424
+ "learning_rate": 3.6586206896551728e-06,
2425
+ "loss": 0.0649,
2426
+ "step": 9700
2427
+ },
2428
+ {
2429
+ "epoch": 5.92,
2430
+ "learning_rate": 3.641379310344828e-06,
2431
+ "loss": 0.0654,
2432
+ "step": 9725
2433
+ },
2434
+ {
2435
+ "epoch": 5.93,
2436
+ "learning_rate": 3.6241379310344834e-06,
2437
+ "loss": 0.0653,
2438
+ "step": 9750
2439
+ },
2440
+ {
2441
+ "epoch": 5.95,
2442
+ "learning_rate": 3.6068965517241382e-06,
2443
+ "loss": 0.0671,
2444
+ "step": 9775
2445
+ },
2446
+ {
2447
+ "epoch": 5.96,
2448
+ "learning_rate": 3.5896551724137935e-06,
2449
+ "loss": 0.0656,
2450
+ "step": 9800
2451
+ },
2452
+ {
2453
+ "epoch": 5.98,
2454
+ "learning_rate": 3.5724137931034484e-06,
2455
+ "loss": 0.0693,
2456
+ "step": 9825
2457
+ },
2458
+ {
2459
+ "epoch": 6.0,
2460
+ "learning_rate": 3.5551724137931037e-06,
2461
+ "loss": 0.0669,
2462
+ "step": 9850
2463
+ },
2464
+ {
2465
+ "epoch": 6.01,
2466
+ "learning_rate": 3.537931034482759e-06,
2467
+ "loss": 0.053,
2468
+ "step": 9875
2469
+ },
2470
+ {
2471
+ "epoch": 6.03,
2472
+ "learning_rate": 3.520689655172414e-06,
2473
+ "loss": 0.0443,
2474
+ "step": 9900
2475
+ },
2476
+ {
2477
+ "epoch": 6.04,
2478
+ "learning_rate": 3.503448275862069e-06,
2479
+ "loss": 0.043,
2480
+ "step": 9925
2481
+ },
2482
+ {
2483
+ "epoch": 6.06,
2484
+ "learning_rate": 3.4862068965517244e-06,
2485
+ "loss": 0.042,
2486
+ "step": 9950
2487
+ },
2488
+ {
2489
+ "epoch": 6.07,
2490
+ "learning_rate": 3.4689655172413793e-06,
2491
+ "loss": 0.043,
2492
+ "step": 9975
2493
+ },
2494
+ {
2495
+ "epoch": 6.09,
2496
+ "learning_rate": 3.4517241379310346e-06,
2497
+ "loss": 0.0436,
2498
+ "step": 10000
2499
+ },
2500
+ {
2501
+ "epoch": 6.09,
2502
+ "eval_cer": 11.138438731848657,
2503
+ "eval_loss": 0.33723652362823486,
2504
+ "eval_runtime": 732.6587,
2505
+ "eval_samples_per_second": 2.574,
2506
+ "eval_steps_per_second": 0.081,
2507
+ "eval_wer": 32.68516495521084,
2508
+ "step": 10000
2509
+ },
2510
+ {
2511
+ "epoch": 6.1,
2512
+ "learning_rate": 3.43448275862069e-06,
2513
+ "loss": 0.0404,
2514
+ "step": 10025
2515
+ },
2516
+ {
2517
+ "epoch": 6.12,
2518
+ "learning_rate": 3.4172413793103448e-06,
2519
+ "loss": 0.0456,
2520
+ "step": 10050
2521
+ },
2522
+ {
2523
+ "epoch": 6.13,
2524
+ "learning_rate": 3.4000000000000005e-06,
2525
+ "loss": 0.0448,
2526
+ "step": 10075
2527
+ },
2528
+ {
2529
+ "epoch": 6.15,
2530
+ "learning_rate": 3.3827586206896558e-06,
2531
+ "loss": 0.0441,
2532
+ "step": 10100
2533
+ },
2534
+ {
2535
+ "epoch": 6.16,
2536
+ "learning_rate": 3.3655172413793106e-06,
2537
+ "loss": 0.0439,
2538
+ "step": 10125
2539
+ },
2540
+ {
2541
+ "epoch": 6.18,
2542
+ "learning_rate": 3.348275862068966e-06,
2543
+ "loss": 0.0486,
2544
+ "step": 10150
2545
+ },
2546
+ {
2547
+ "epoch": 6.19,
2548
+ "learning_rate": 3.3310344827586212e-06,
2549
+ "loss": 0.0457,
2550
+ "step": 10175
2551
+ },
2552
+ {
2553
+ "epoch": 6.21,
2554
+ "learning_rate": 3.313793103448276e-06,
2555
+ "loss": 0.0446,
2556
+ "step": 10200
2557
+ },
2558
+ {
2559
+ "epoch": 6.22,
2560
+ "learning_rate": 3.2965517241379314e-06,
2561
+ "loss": 0.0463,
2562
+ "step": 10225
2563
+ },
2564
+ {
2565
+ "epoch": 6.24,
2566
+ "learning_rate": 3.2793103448275863e-06,
2567
+ "loss": 0.0434,
2568
+ "step": 10250
2569
+ },
2570
+ {
2571
+ "epoch": 6.25,
2572
+ "learning_rate": 3.2620689655172416e-06,
2573
+ "loss": 0.0424,
2574
+ "step": 10275
2575
+ },
2576
+ {
2577
+ "epoch": 6.27,
2578
+ "learning_rate": 3.244827586206897e-06,
2579
+ "loss": 0.0409,
2580
+ "step": 10300
2581
+ },
2582
+ {
2583
+ "epoch": 6.28,
2584
+ "learning_rate": 3.2275862068965517e-06,
2585
+ "loss": 0.0409,
2586
+ "step": 10325
2587
+ },
2588
+ {
2589
+ "epoch": 6.3,
2590
+ "learning_rate": 3.210344827586207e-06,
2591
+ "loss": 0.0473,
2592
+ "step": 10350
2593
+ },
2594
+ {
2595
+ "epoch": 6.31,
2596
+ "learning_rate": 3.1931034482758623e-06,
2597
+ "loss": 0.0431,
2598
+ "step": 10375
2599
+ },
2600
+ {
2601
+ "epoch": 6.33,
2602
+ "learning_rate": 3.175862068965517e-06,
2603
+ "loss": 0.045,
2604
+ "step": 10400
2605
+ },
2606
+ {
2607
+ "epoch": 6.35,
2608
+ "learning_rate": 3.1586206896551725e-06,
2609
+ "loss": 0.0465,
2610
+ "step": 10425
2611
+ },
2612
+ {
2613
+ "epoch": 6.36,
2614
+ "learning_rate": 3.1413793103448278e-06,
2615
+ "loss": 0.0437,
2616
+ "step": 10450
2617
+ },
2618
+ {
2619
+ "epoch": 6.38,
2620
+ "learning_rate": 3.124137931034483e-06,
2621
+ "loss": 0.0459,
2622
+ "step": 10475
2623
+ },
2624
+ {
2625
+ "epoch": 6.39,
2626
+ "learning_rate": 3.1068965517241384e-06,
2627
+ "loss": 0.045,
2628
+ "step": 10500
2629
+ },
2630
+ {
2631
+ "epoch": 6.41,
2632
+ "learning_rate": 3.0896551724137937e-06,
2633
+ "loss": 0.0455,
2634
+ "step": 10525
2635
+ },
2636
+ {
2637
+ "epoch": 6.42,
2638
+ "learning_rate": 3.0724137931034485e-06,
2639
+ "loss": 0.0442,
2640
+ "step": 10550
2641
+ },
2642
+ {
2643
+ "epoch": 6.44,
2644
+ "learning_rate": 3.055172413793104e-06,
2645
+ "loss": 0.0453,
2646
+ "step": 10575
2647
+ },
2648
+ {
2649
+ "epoch": 6.45,
2650
+ "learning_rate": 3.037931034482759e-06,
2651
+ "loss": 0.0452,
2652
+ "step": 10600
2653
+ },
2654
+ {
2655
+ "epoch": 6.47,
2656
+ "learning_rate": 3.020689655172414e-06,
2657
+ "loss": 0.043,
2658
+ "step": 10625
2659
+ },
2660
+ {
2661
+ "epoch": 6.48,
2662
+ "learning_rate": 3.0034482758620693e-06,
2663
+ "loss": 0.045,
2664
+ "step": 10650
2665
+ },
2666
+ {
2667
+ "epoch": 6.5,
2668
+ "learning_rate": 2.9862068965517246e-06,
2669
+ "loss": 0.0434,
2670
+ "step": 10675
2671
+ },
2672
+ {
2673
+ "epoch": 6.51,
2674
+ "learning_rate": 2.9689655172413794e-06,
2675
+ "loss": 0.0452,
2676
+ "step": 10700
2677
+ },
2678
+ {
2679
+ "epoch": 6.53,
2680
+ "learning_rate": 2.9517241379310347e-06,
2681
+ "loss": 0.0441,
2682
+ "step": 10725
2683
+ },
2684
+ {
2685
+ "epoch": 6.54,
2686
+ "learning_rate": 2.9344827586206896e-06,
2687
+ "loss": 0.0468,
2688
+ "step": 10750
2689
+ },
2690
+ {
2691
+ "epoch": 6.56,
2692
+ "learning_rate": 2.917241379310345e-06,
2693
+ "loss": 0.0459,
2694
+ "step": 10775
2695
+ },
2696
+ {
2697
+ "epoch": 6.57,
2698
+ "learning_rate": 2.900689655172414e-06,
2699
+ "loss": 0.0443,
2700
+ "step": 10800
2701
+ },
2702
+ {
2703
+ "epoch": 6.59,
2704
+ "learning_rate": 2.883448275862069e-06,
2705
+ "loss": 0.0439,
2706
+ "step": 10825
2707
+ },
2708
+ {
2709
+ "epoch": 6.6,
2710
+ "learning_rate": 2.8662068965517244e-06,
2711
+ "loss": 0.0443,
2712
+ "step": 10850
2713
+ },
2714
+ {
2715
+ "epoch": 6.62,
2716
+ "learning_rate": 2.8489655172413793e-06,
2717
+ "loss": 0.046,
2718
+ "step": 10875
2719
+ },
2720
+ {
2721
+ "epoch": 6.63,
2722
+ "learning_rate": 2.8317241379310346e-06,
2723
+ "loss": 0.0439,
2724
+ "step": 10900
2725
+ },
2726
+ {
2727
+ "epoch": 6.65,
2728
+ "learning_rate": 2.8144827586206895e-06,
2729
+ "loss": 0.0448,
2730
+ "step": 10925
2731
+ },
2732
+ {
2733
+ "epoch": 6.66,
2734
+ "learning_rate": 2.7972413793103448e-06,
2735
+ "loss": 0.0462,
2736
+ "step": 10950
2737
+ },
2738
+ {
2739
+ "epoch": 6.68,
2740
+ "learning_rate": 2.7800000000000005e-06,
2741
+ "loss": 0.0432,
2742
+ "step": 10975
2743
+ },
2744
+ {
2745
+ "epoch": 6.7,
2746
+ "learning_rate": 2.7627586206896558e-06,
2747
+ "loss": 0.0469,
2748
+ "step": 11000
2749
+ },
2750
+ {
2751
+ "epoch": 6.7,
2752
+ "eval_cer": 11.286681715575622,
2753
+ "eval_loss": 0.3481425344944,
2754
+ "eval_runtime": 729.7831,
2755
+ "eval_samples_per_second": 2.584,
2756
+ "eval_steps_per_second": 0.081,
2757
+ "eval_wer": 32.82717937513655,
2758
+ "step": 11000
2759
+ },
2760
+ {
2761
+ "epoch": 6.71,
2762
+ "learning_rate": 2.7455172413793107e-06,
2763
+ "loss": 0.0441,
2764
+ "step": 11025
2765
+ },
2766
+ {
2767
+ "epoch": 6.73,
2768
+ "learning_rate": 2.728275862068966e-06,
2769
+ "loss": 0.0434,
2770
+ "step": 11050
2771
+ },
2772
+ {
2773
+ "epoch": 6.74,
2774
+ "learning_rate": 2.711034482758621e-06,
2775
+ "loss": 0.0425,
2776
+ "step": 11075
2777
+ },
2778
+ {
2779
+ "epoch": 6.76,
2780
+ "learning_rate": 2.693793103448276e-06,
2781
+ "loss": 0.0467,
2782
+ "step": 11100
2783
+ },
2784
+ {
2785
+ "epoch": 6.77,
2786
+ "learning_rate": 2.6765517241379314e-06,
2787
+ "loss": 0.045,
2788
+ "step": 11125
2789
+ },
2790
+ {
2791
+ "epoch": 6.79,
2792
+ "learning_rate": 2.6593103448275863e-06,
2793
+ "loss": 0.0445,
2794
+ "step": 11150
2795
+ },
2796
+ {
2797
+ "epoch": 6.8,
2798
+ "learning_rate": 2.6420689655172416e-06,
2799
+ "loss": 0.0444,
2800
+ "step": 11175
2801
+ },
2802
+ {
2803
+ "epoch": 6.82,
2804
+ "learning_rate": 2.624827586206897e-06,
2805
+ "loss": 0.0446,
2806
+ "step": 11200
2807
+ },
2808
+ {
2809
+ "epoch": 6.83,
2810
+ "learning_rate": 2.6075862068965517e-06,
2811
+ "loss": 0.0455,
2812
+ "step": 11225
2813
+ },
2814
+ {
2815
+ "epoch": 6.85,
2816
+ "learning_rate": 2.590344827586207e-06,
2817
+ "loss": 0.0458,
2818
+ "step": 11250
2819
+ },
2820
+ {
2821
+ "epoch": 6.86,
2822
+ "learning_rate": 2.5731034482758623e-06,
2823
+ "loss": 0.0442,
2824
+ "step": 11275
2825
+ },
2826
+ {
2827
+ "epoch": 6.88,
2828
+ "learning_rate": 2.555862068965517e-06,
2829
+ "loss": 0.0427,
2830
+ "step": 11300
2831
+ },
2832
+ {
2833
+ "epoch": 6.89,
2834
+ "learning_rate": 2.5386206896551725e-06,
2835
+ "loss": 0.044,
2836
+ "step": 11325
2837
+ },
2838
+ {
2839
+ "epoch": 6.91,
2840
+ "learning_rate": 2.5213793103448274e-06,
2841
+ "loss": 0.0401,
2842
+ "step": 11350
2843
+ },
2844
+ {
2845
+ "epoch": 6.92,
2846
+ "learning_rate": 2.504137931034483e-06,
2847
+ "loss": 0.0465,
2848
+ "step": 11375
2849
+ },
2850
+ {
2851
+ "epoch": 6.94,
2852
+ "learning_rate": 2.486896551724138e-06,
2853
+ "loss": 0.0424,
2854
+ "step": 11400
2855
+ },
2856
+ {
2857
+ "epoch": 6.95,
2858
+ "learning_rate": 2.4696551724137932e-06,
2859
+ "loss": 0.0422,
2860
+ "step": 11425
2861
+ },
2862
+ {
2863
+ "epoch": 6.97,
2864
+ "learning_rate": 2.4524137931034485e-06,
2865
+ "loss": 0.0463,
2866
+ "step": 11450
2867
+ },
2868
+ {
2869
+ "epoch": 6.98,
2870
+ "learning_rate": 2.435172413793104e-06,
2871
+ "loss": 0.0445,
2872
+ "step": 11475
2873
+ },
2874
+ {
2875
+ "epoch": 7.0,
2876
+ "learning_rate": 2.4179310344827587e-06,
2877
+ "loss": 0.0448,
2878
+ "step": 11500
2879
+ },
2880
+ {
2881
+ "epoch": 7.01,
2882
+ "learning_rate": 2.400689655172414e-06,
2883
+ "loss": 0.0331,
2884
+ "step": 11525
2885
+ },
2886
+ {
2887
+ "epoch": 7.03,
2888
+ "learning_rate": 2.3834482758620693e-06,
2889
+ "loss": 0.028,
2890
+ "step": 11550
2891
+ },
2892
+ {
2893
+ "epoch": 7.05,
2894
+ "learning_rate": 2.366206896551724e-06,
2895
+ "loss": 0.0318,
2896
+ "step": 11575
2897
+ },
2898
+ {
2899
+ "epoch": 7.06,
2900
+ "learning_rate": 2.3489655172413794e-06,
2901
+ "loss": 0.0306,
2902
+ "step": 11600
2903
+ },
2904
+ {
2905
+ "epoch": 7.08,
2906
+ "learning_rate": 2.3317241379310347e-06,
2907
+ "loss": 0.0293,
2908
+ "step": 11625
2909
+ },
2910
+ {
2911
+ "epoch": 7.09,
2912
+ "learning_rate": 2.3144827586206896e-06,
2913
+ "loss": 0.0292,
2914
+ "step": 11650
2915
+ },
2916
+ {
2917
+ "epoch": 7.11,
2918
+ "learning_rate": 2.2972413793103453e-06,
2919
+ "loss": 0.0304,
2920
+ "step": 11675
2921
+ },
2922
+ {
2923
+ "epoch": 7.12,
2924
+ "learning_rate": 2.28e-06,
2925
+ "loss": 0.0312,
2926
+ "step": 11700
2927
+ },
2928
+ {
2929
+ "epoch": 7.14,
2930
+ "learning_rate": 2.2627586206896555e-06,
2931
+ "loss": 0.0276,
2932
+ "step": 11725
2933
+ },
2934
+ {
2935
+ "epoch": 7.15,
2936
+ "learning_rate": 2.2455172413793104e-06,
2937
+ "loss": 0.0286,
2938
+ "step": 11750
2939
+ },
2940
+ {
2941
+ "epoch": 7.17,
2942
+ "learning_rate": 2.2282758620689657e-06,
2943
+ "loss": 0.0294,
2944
+ "step": 11775
2945
+ },
2946
+ {
2947
+ "epoch": 7.18,
2948
+ "learning_rate": 2.211034482758621e-06,
2949
+ "loss": 0.028,
2950
+ "step": 11800
2951
+ },
2952
+ {
2953
+ "epoch": 7.2,
2954
+ "learning_rate": 2.193793103448276e-06,
2955
+ "loss": 0.0291,
2956
+ "step": 11825
2957
+ },
2958
+ {
2959
+ "epoch": 7.21,
2960
+ "learning_rate": 2.176551724137931e-06,
2961
+ "loss": 0.0303,
2962
+ "step": 11850
2963
+ },
2964
+ {
2965
+ "epoch": 7.23,
2966
+ "learning_rate": 2.1593103448275864e-06,
2967
+ "loss": 0.0298,
2968
+ "step": 11875
2969
+ },
2970
+ {
2971
+ "epoch": 7.24,
2972
+ "learning_rate": 2.1420689655172417e-06,
2973
+ "loss": 0.0297,
2974
+ "step": 11900
2975
+ },
2976
+ {
2977
+ "epoch": 7.26,
2978
+ "learning_rate": 2.1248275862068966e-06,
2979
+ "loss": 0.0272,
2980
+ "step": 11925
2981
+ },
2982
+ {
2983
+ "epoch": 7.27,
2984
+ "learning_rate": 2.107586206896552e-06,
2985
+ "loss": 0.0301,
2986
+ "step": 11950
2987
+ },
2988
+ {
2989
+ "epoch": 7.29,
2990
+ "learning_rate": 2.090344827586207e-06,
2991
+ "loss": 0.0279,
2992
+ "step": 11975
2993
+ },
2994
+ {
2995
+ "epoch": 7.3,
2996
+ "learning_rate": 2.073103448275862e-06,
2997
+ "loss": 0.0292,
2998
+ "step": 12000
2999
+ },
3000
+ {
3001
+ "epoch": 7.3,
3002
+ "eval_cer": 11.378491290724705,
3003
+ "eval_loss": 0.36427363753318787,
3004
+ "eval_runtime": 729.5889,
3005
+ "eval_samples_per_second": 2.585,
3006
+ "eval_steps_per_second": 0.081,
3007
+ "eval_wer": 33.07843565654359,
3008
+ "step": 12000
3009
+ },
3010
+ {
3011
+ "epoch": 7.32,
3012
+ "learning_rate": 2.0558620689655173e-06,
3013
+ "loss": 0.0279,
3014
+ "step": 12025
3015
+ },
3016
+ {
3017
+ "epoch": 7.33,
3018
+ "learning_rate": 2.0386206896551726e-06,
3019
+ "loss": 0.0291,
3020
+ "step": 12050
3021
+ },
3022
+ {
3023
+ "epoch": 7.35,
3024
+ "learning_rate": 2.021379310344828e-06,
3025
+ "loss": 0.028,
3026
+ "step": 12075
3027
+ },
3028
+ {
3029
+ "epoch": 7.36,
3030
+ "learning_rate": 2.004137931034483e-06,
3031
+ "loss": 0.0316,
3032
+ "step": 12100
3033
+ },
3034
+ {
3035
+ "epoch": 7.38,
3036
+ "learning_rate": 1.986896551724138e-06,
3037
+ "loss": 0.0263,
3038
+ "step": 12125
3039
+ },
3040
+ {
3041
+ "epoch": 7.4,
3042
+ "learning_rate": 1.9696551724137934e-06,
3043
+ "loss": 0.0299,
3044
+ "step": 12150
3045
+ },
3046
+ {
3047
+ "epoch": 7.41,
3048
+ "learning_rate": 1.9524137931034482e-06,
3049
+ "loss": 0.0282,
3050
+ "step": 12175
3051
+ },
3052
+ {
3053
+ "epoch": 7.43,
3054
+ "learning_rate": 1.9351724137931035e-06,
3055
+ "loss": 0.0331,
3056
+ "step": 12200
3057
+ },
3058
+ {
3059
+ "epoch": 7.44,
3060
+ "learning_rate": 1.917931034482759e-06,
3061
+ "loss": 0.0289,
3062
+ "step": 12225
3063
+ },
3064
+ {
3065
+ "epoch": 7.46,
3066
+ "learning_rate": 1.900689655172414e-06,
3067
+ "loss": 0.0294,
3068
+ "step": 12250
3069
+ },
3070
+ {
3071
+ "epoch": 7.47,
3072
+ "learning_rate": 1.8834482758620692e-06,
3073
+ "loss": 0.0315,
3074
+ "step": 12275
3075
+ },
3076
+ {
3077
+ "epoch": 7.49,
3078
+ "learning_rate": 1.8662068965517243e-06,
3079
+ "loss": 0.0312,
3080
+ "step": 12300
3081
+ },
3082
+ {
3083
+ "epoch": 7.5,
3084
+ "learning_rate": 1.8489655172413796e-06,
3085
+ "loss": 0.0277,
3086
+ "step": 12325
3087
+ },
3088
+ {
3089
+ "epoch": 7.52,
3090
+ "learning_rate": 1.8317241379310347e-06,
3091
+ "loss": 0.0296,
3092
+ "step": 12350
3093
+ },
3094
+ {
3095
+ "epoch": 7.53,
3096
+ "learning_rate": 1.8144827586206897e-06,
3097
+ "loss": 0.0305,
3098
+ "step": 12375
3099
+ },
3100
+ {
3101
+ "epoch": 7.55,
3102
+ "learning_rate": 1.797241379310345e-06,
3103
+ "loss": 0.0296,
3104
+ "step": 12400
3105
+ },
3106
+ {
3107
+ "epoch": 7.56,
3108
+ "learning_rate": 1.7800000000000001e-06,
3109
+ "loss": 0.0275,
3110
+ "step": 12425
3111
+ },
3112
+ {
3113
+ "epoch": 7.58,
3114
+ "learning_rate": 1.7627586206896552e-06,
3115
+ "loss": 0.0301,
3116
+ "step": 12450
3117
+ },
3118
+ {
3119
+ "epoch": 7.59,
3120
+ "learning_rate": 1.7455172413793107e-06,
3121
+ "loss": 0.0289,
3122
+ "step": 12475
3123
+ },
3124
+ {
3125
+ "epoch": 7.61,
3126
+ "learning_rate": 1.7282758620689658e-06,
3127
+ "loss": 0.0301,
3128
+ "step": 12500
3129
+ },
3130
+ {
3131
+ "epoch": 7.62,
3132
+ "learning_rate": 1.7110344827586209e-06,
3133
+ "loss": 0.0282,
3134
+ "step": 12525
3135
+ },
3136
+ {
3137
+ "epoch": 7.64,
3138
+ "learning_rate": 1.693793103448276e-06,
3139
+ "loss": 0.0316,
3140
+ "step": 12550
3141
+ },
3142
+ {
3143
+ "epoch": 7.65,
3144
+ "learning_rate": 1.6765517241379312e-06,
3145
+ "loss": 0.0292,
3146
+ "step": 12575
3147
+ },
3148
+ {
3149
+ "epoch": 7.67,
3150
+ "learning_rate": 1.6593103448275863e-06,
3151
+ "loss": 0.0295,
3152
+ "step": 12600
3153
+ },
3154
+ {
3155
+ "epoch": 7.68,
3156
+ "learning_rate": 1.6420689655172414e-06,
3157
+ "loss": 0.0311,
3158
+ "step": 12625
3159
+ },
3160
+ {
3161
+ "epoch": 7.7,
3162
+ "learning_rate": 1.6248275862068965e-06,
3163
+ "loss": 0.0304,
3164
+ "step": 12650
3165
+ },
3166
+ {
3167
+ "epoch": 7.71,
3168
+ "learning_rate": 1.607586206896552e-06,
3169
+ "loss": 0.0265,
3170
+ "step": 12675
3171
+ },
3172
+ {
3173
+ "epoch": 7.73,
3174
+ "learning_rate": 1.590344827586207e-06,
3175
+ "loss": 0.0297,
3176
+ "step": 12700
3177
+ },
3178
+ {
3179
+ "epoch": 7.74,
3180
+ "learning_rate": 1.5731034482758622e-06,
3181
+ "loss": 0.0294,
3182
+ "step": 12725
3183
+ },
3184
+ {
3185
+ "epoch": 7.76,
3186
+ "learning_rate": 1.5558620689655174e-06,
3187
+ "loss": 0.0296,
3188
+ "step": 12750
3189
+ },
3190
+ {
3191
+ "epoch": 7.78,
3192
+ "learning_rate": 1.5386206896551725e-06,
3193
+ "loss": 0.0298,
3194
+ "step": 12775
3195
+ },
3196
+ {
3197
+ "epoch": 7.79,
3198
+ "learning_rate": 1.5213793103448276e-06,
3199
+ "loss": 0.0288,
3200
+ "step": 12800
3201
+ },
3202
+ {
3203
+ "epoch": 7.81,
3204
+ "learning_rate": 1.504137931034483e-06,
3205
+ "loss": 0.0292,
3206
+ "step": 12825
3207
+ },
3208
+ {
3209
+ "epoch": 7.82,
3210
+ "learning_rate": 1.486896551724138e-06,
3211
+ "loss": 0.0302,
3212
+ "step": 12850
3213
+ },
3214
+ {
3215
+ "epoch": 7.84,
3216
+ "learning_rate": 1.4696551724137933e-06,
3217
+ "loss": 0.0298,
3218
+ "step": 12875
3219
+ },
3220
+ {
3221
+ "epoch": 7.85,
3222
+ "learning_rate": 1.4524137931034486e-06,
3223
+ "loss": 0.0309,
3224
+ "step": 12900
3225
+ },
3226
+ {
3227
+ "epoch": 7.87,
3228
+ "learning_rate": 1.4351724137931037e-06,
3229
+ "loss": 0.0297,
3230
+ "step": 12925
3231
+ },
3232
+ {
3233
+ "epoch": 7.88,
3234
+ "learning_rate": 1.4179310344827587e-06,
3235
+ "loss": 0.0281,
3236
+ "step": 12950
3237
+ },
3238
+ {
3239
+ "epoch": 7.9,
3240
+ "learning_rate": 1.4006896551724138e-06,
3241
+ "loss": 0.0291,
3242
+ "step": 12975
3243
+ },
3244
+ {
3245
+ "epoch": 7.91,
3246
+ "learning_rate": 1.3834482758620691e-06,
3247
+ "loss": 0.0277,
3248
+ "step": 13000
3249
+ },
3250
+ {
3251
+ "epoch": 7.91,
3252
+ "eval_cer": 11.359960917758835,
3253
+ "eval_loss": 0.3699686527252197,
3254
+ "eval_runtime": 727.275,
3255
+ "eval_samples_per_second": 2.593,
3256
+ "eval_steps_per_second": 0.081,
3257
+ "eval_wer": 33.187677518024906,
3258
+ "step": 13000
3259
+ },
3260
+ {
3261
+ "epoch": 7.93,
3262
+ "learning_rate": 1.3662068965517242e-06,
3263
+ "loss": 0.0288,
3264
+ "step": 13025
3265
+ },
3266
+ {
3267
+ "epoch": 7.94,
3268
+ "learning_rate": 1.3489655172413793e-06,
3269
+ "loss": 0.0306,
3270
+ "step": 13050
3271
+ },
3272
+ {
3273
+ "epoch": 7.96,
3274
+ "learning_rate": 1.3317241379310348e-06,
3275
+ "loss": 0.0286,
3276
+ "step": 13075
3277
+ },
3278
+ {
3279
+ "epoch": 7.97,
3280
+ "learning_rate": 1.3144827586206899e-06,
3281
+ "loss": 0.031,
3282
+ "step": 13100
3283
+ },
3284
+ {
3285
+ "epoch": 7.99,
3286
+ "learning_rate": 1.297241379310345e-06,
3287
+ "loss": 0.0304,
3288
+ "step": 13125
3289
+ },
3290
+ {
3291
+ "epoch": 8.0,
3292
+ "learning_rate": 1.28e-06,
3293
+ "loss": 0.0293,
3294
+ "step": 13150
3295
+ },
3296
+ {
3297
+ "epoch": 8.02,
3298
+ "learning_rate": 1.2627586206896553e-06,
3299
+ "loss": 0.0195,
3300
+ "step": 13175
3301
+ },
3302
+ {
3303
+ "epoch": 8.03,
3304
+ "learning_rate": 1.2455172413793104e-06,
3305
+ "loss": 0.0218,
3306
+ "step": 13200
3307
+ },
3308
+ {
3309
+ "epoch": 8.05,
3310
+ "learning_rate": 1.2282758620689657e-06,
3311
+ "loss": 0.0215,
3312
+ "step": 13225
3313
+ },
3314
+ {
3315
+ "epoch": 8.06,
3316
+ "learning_rate": 1.2110344827586208e-06,
3317
+ "loss": 0.0212,
3318
+ "step": 13250
3319
+ },
3320
+ {
3321
+ "epoch": 8.08,
3322
+ "learning_rate": 1.1937931034482759e-06,
3323
+ "loss": 0.0202,
3324
+ "step": 13275
3325
+ },
3326
+ {
3327
+ "epoch": 8.09,
3328
+ "learning_rate": 1.1765517241379312e-06,
3329
+ "loss": 0.0199,
3330
+ "step": 13300
3331
+ },
3332
+ {
3333
+ "epoch": 8.11,
3334
+ "learning_rate": 1.1593103448275864e-06,
3335
+ "loss": 0.0196,
3336
+ "step": 13325
3337
+ },
3338
+ {
3339
+ "epoch": 8.13,
3340
+ "learning_rate": 1.1420689655172415e-06,
3341
+ "loss": 0.0205,
3342
+ "step": 13350
3343
+ },
3344
+ {
3345
+ "epoch": 8.14,
3346
+ "learning_rate": 1.1248275862068966e-06,
3347
+ "loss": 0.0202,
3348
+ "step": 13375
3349
+ },
3350
+ {
3351
+ "epoch": 8.16,
3352
+ "learning_rate": 1.1075862068965517e-06,
3353
+ "loss": 0.0198,
3354
+ "step": 13400
3355
+ },
3356
+ {
3357
+ "epoch": 8.17,
3358
+ "learning_rate": 1.090344827586207e-06,
3359
+ "loss": 0.0201,
3360
+ "step": 13425
3361
+ },
3362
+ {
3363
+ "epoch": 8.19,
3364
+ "learning_rate": 1.0731034482758623e-06,
3365
+ "loss": 0.0202,
3366
+ "step": 13450
3367
+ },
3368
+ {
3369
+ "epoch": 8.2,
3370
+ "learning_rate": 1.0558620689655174e-06,
3371
+ "loss": 0.0215,
3372
+ "step": 13475
3373
+ },
3374
+ {
3375
+ "epoch": 8.22,
3376
+ "learning_rate": 1.0386206896551724e-06,
3377
+ "loss": 0.0211,
3378
+ "step": 13500
3379
+ },
3380
+ {
3381
+ "epoch": 8.23,
3382
+ "learning_rate": 1.0213793103448277e-06,
3383
+ "loss": 0.0195,
3384
+ "step": 13525
3385
+ },
3386
+ {
3387
+ "epoch": 8.25,
3388
+ "learning_rate": 1.0041379310344828e-06,
3389
+ "loss": 0.0186,
3390
+ "step": 13550
3391
+ },
3392
+ {
3393
+ "epoch": 8.26,
3394
+ "learning_rate": 9.868965517241381e-07,
3395
+ "loss": 0.0208,
3396
+ "step": 13575
3397
+ },
3398
+ {
3399
+ "epoch": 8.28,
3400
+ "learning_rate": 9.696551724137932e-07,
3401
+ "loss": 0.0199,
3402
+ "step": 13600
3403
+ },
3404
+ {
3405
+ "epoch": 8.29,
3406
+ "learning_rate": 9.524137931034484e-07,
3407
+ "loss": 0.0201,
3408
+ "step": 13625
3409
+ },
3410
+ {
3411
+ "epoch": 8.31,
3412
+ "learning_rate": 9.351724137931036e-07,
3413
+ "loss": 0.0201,
3414
+ "step": 13650
3415
+ },
3416
+ {
3417
+ "epoch": 8.32,
3418
+ "learning_rate": 9.179310344827587e-07,
3419
+ "loss": 0.021,
3420
+ "step": 13675
3421
+ },
3422
+ {
3423
+ "epoch": 8.34,
3424
+ "learning_rate": 9.006896551724138e-07,
3425
+ "loss": 0.0194,
3426
+ "step": 13700
3427
+ },
3428
+ {
3429
+ "epoch": 8.35,
3430
+ "learning_rate": 8.834482758620691e-07,
3431
+ "loss": 0.0212,
3432
+ "step": 13725
3433
+ },
3434
+ {
3435
+ "epoch": 8.37,
3436
+ "learning_rate": 8.662068965517242e-07,
3437
+ "loss": 0.0194,
3438
+ "step": 13750
3439
+ },
3440
+ {
3441
+ "epoch": 8.38,
3442
+ "learning_rate": 8.489655172413794e-07,
3443
+ "loss": 0.0189,
3444
+ "step": 13775
3445
+ },
3446
+ {
3447
+ "epoch": 8.4,
3448
+ "learning_rate": 8.317241379310345e-07,
3449
+ "loss": 0.0205,
3450
+ "step": 13800
3451
+ },
3452
+ {
3453
+ "epoch": 8.41,
3454
+ "learning_rate": 8.144827586206898e-07,
3455
+ "loss": 0.021,
3456
+ "step": 13825
3457
+ },
3458
+ {
3459
+ "epoch": 8.43,
3460
+ "learning_rate": 7.97241379310345e-07,
3461
+ "loss": 0.0195,
3462
+ "step": 13850
3463
+ },
3464
+ {
3465
+ "epoch": 8.44,
3466
+ "learning_rate": 7.8e-07,
3467
+ "loss": 0.0186,
3468
+ "step": 13875
3469
+ },
3470
+ {
3471
+ "epoch": 8.46,
3472
+ "learning_rate": 7.627586206896552e-07,
3473
+ "loss": 0.0211,
3474
+ "step": 13900
3475
+ },
3476
+ {
3477
+ "epoch": 8.48,
3478
+ "learning_rate": 7.455172413793104e-07,
3479
+ "loss": 0.0198,
3480
+ "step": 13925
3481
+ },
3482
+ {
3483
+ "epoch": 8.49,
3484
+ "learning_rate": 7.282758620689656e-07,
3485
+ "loss": 0.0214,
3486
+ "step": 13950
3487
+ },
3488
+ {
3489
+ "epoch": 8.51,
3490
+ "learning_rate": 7.110344827586208e-07,
3491
+ "loss": 0.0202,
3492
+ "step": 13975
3493
+ },
3494
+ {
3495
+ "epoch": 8.52,
3496
+ "learning_rate": 6.937931034482759e-07,
3497
+ "loss": 0.0196,
3498
+ "step": 14000
3499
+ },
3500
+ {
3501
+ "epoch": 8.52,
3502
+ "eval_cer": 11.427344092180181,
3503
+ "eval_loss": 0.3806290626525879,
3504
+ "eval_runtime": 728.6082,
3505
+ "eval_samples_per_second": 2.588,
3506
+ "eval_steps_per_second": 0.081,
3507
+ "eval_wer": 33.37338868254315,
3508
+ "step": 14000
3509
+ },
3510
+ {
3511
+ "epoch": 8.54,
3512
+ "learning_rate": 6.765517241379311e-07,
3513
+ "loss": 0.0221,
3514
+ "step": 14025
3515
+ },
3516
+ {
3517
+ "epoch": 8.55,
3518
+ "learning_rate": 6.593103448275863e-07,
3519
+ "loss": 0.0204,
3520
+ "step": 14050
3521
+ },
3522
+ {
3523
+ "epoch": 8.57,
3524
+ "learning_rate": 6.420689655172414e-07,
3525
+ "loss": 0.0189,
3526
+ "step": 14075
3527
+ },
3528
+ {
3529
+ "epoch": 8.58,
3530
+ "learning_rate": 6.248275862068965e-07,
3531
+ "loss": 0.0187,
3532
+ "step": 14100
3533
+ },
3534
+ {
3535
+ "epoch": 8.6,
3536
+ "learning_rate": 6.075862068965518e-07,
3537
+ "loss": 0.02,
3538
+ "step": 14125
3539
+ },
3540
+ {
3541
+ "epoch": 8.61,
3542
+ "learning_rate": 5.903448275862069e-07,
3543
+ "loss": 0.0194,
3544
+ "step": 14150
3545
+ },
3546
+ {
3547
+ "epoch": 8.63,
3548
+ "learning_rate": 5.731034482758621e-07,
3549
+ "loss": 0.0184,
3550
+ "step": 14175
3551
+ },
3552
+ {
3553
+ "epoch": 8.64,
3554
+ "learning_rate": 5.558620689655173e-07,
3555
+ "loss": 0.0194,
3556
+ "step": 14200
3557
+ },
3558
+ {
3559
+ "epoch": 8.66,
3560
+ "learning_rate": 5.386206896551725e-07,
3561
+ "loss": 0.0196,
3562
+ "step": 14225
3563
+ },
3564
+ {
3565
+ "epoch": 8.67,
3566
+ "learning_rate": 5.213793103448275e-07,
3567
+ "loss": 0.0211,
3568
+ "step": 14250
3569
+ },
3570
+ {
3571
+ "epoch": 8.69,
3572
+ "learning_rate": 5.041379310344828e-07,
3573
+ "loss": 0.0205,
3574
+ "step": 14275
3575
+ },
3576
+ {
3577
+ "epoch": 8.7,
3578
+ "learning_rate": 4.868965517241379e-07,
3579
+ "loss": 0.0204,
3580
+ "step": 14300
3581
+ },
3582
+ {
3583
+ "epoch": 8.72,
3584
+ "learning_rate": 4.6965517241379317e-07,
3585
+ "loss": 0.019,
3586
+ "step": 14325
3587
+ },
3588
+ {
3589
+ "epoch": 8.73,
3590
+ "learning_rate": 4.524137931034483e-07,
3591
+ "loss": 0.0198,
3592
+ "step": 14350
3593
+ },
3594
+ {
3595
+ "epoch": 8.75,
3596
+ "learning_rate": 4.351724137931035e-07,
3597
+ "loss": 0.0181,
3598
+ "step": 14375
3599
+ },
3600
+ {
3601
+ "epoch": 8.76,
3602
+ "learning_rate": 4.179310344827586e-07,
3603
+ "loss": 0.0211,
3604
+ "step": 14400
3605
+ },
3606
+ {
3607
+ "epoch": 8.78,
3608
+ "learning_rate": 4.006896551724138e-07,
3609
+ "loss": 0.0203,
3610
+ "step": 14425
3611
+ },
3612
+ {
3613
+ "epoch": 8.79,
3614
+ "learning_rate": 3.8344827586206895e-07,
3615
+ "loss": 0.0188,
3616
+ "step": 14450
3617
+ },
3618
+ {
3619
+ "epoch": 8.81,
3620
+ "learning_rate": 3.662068965517242e-07,
3621
+ "loss": 0.0209,
3622
+ "step": 14475
3623
+ },
3624
+ {
3625
+ "epoch": 8.83,
3626
+ "learning_rate": 3.489655172413793e-07,
3627
+ "loss": 0.0197,
3628
+ "step": 14500
3629
+ },
3630
+ {
3631
+ "epoch": 8.84,
3632
+ "learning_rate": 3.317241379310345e-07,
3633
+ "loss": 0.0177,
3634
+ "step": 14525
3635
+ },
3636
+ {
3637
+ "epoch": 8.86,
3638
+ "learning_rate": 3.1448275862068964e-07,
3639
+ "loss": 0.0201,
3640
+ "step": 14550
3641
+ },
3642
+ {
3643
+ "epoch": 8.87,
3644
+ "learning_rate": 2.9724137931034483e-07,
3645
+ "loss": 0.0203,
3646
+ "step": 14575
3647
+ },
3648
+ {
3649
+ "epoch": 8.89,
3650
+ "learning_rate": 2.8e-07,
3651
+ "loss": 0.0221,
3652
+ "step": 14600
3653
+ },
3654
+ {
3655
+ "epoch": 8.9,
3656
+ "learning_rate": 2.627586206896552e-07,
3657
+ "loss": 0.0191,
3658
+ "step": 14625
3659
+ },
3660
+ {
3661
+ "epoch": 8.92,
3662
+ "learning_rate": 2.455172413793104e-07,
3663
+ "loss": 0.0191,
3664
+ "step": 14650
3665
+ },
3666
+ {
3667
+ "epoch": 8.93,
3668
+ "learning_rate": 2.2827586206896553e-07,
3669
+ "loss": 0.0198,
3670
+ "step": 14675
3671
+ },
3672
+ {
3673
+ "epoch": 8.95,
3674
+ "learning_rate": 2.1103448275862072e-07,
3675
+ "loss": 0.0178,
3676
+ "step": 14700
3677
+ },
3678
+ {
3679
+ "epoch": 8.96,
3680
+ "learning_rate": 1.9379310344827588e-07,
3681
+ "loss": 0.0202,
3682
+ "step": 14725
3683
+ },
3684
+ {
3685
+ "epoch": 8.98,
3686
+ "learning_rate": 1.7655172413793107e-07,
3687
+ "loss": 0.0204,
3688
+ "step": 14750
3689
+ },
3690
+ {
3691
+ "epoch": 8.99,
3692
+ "learning_rate": 1.5931034482758623e-07,
3693
+ "loss": 0.0204,
3694
+ "step": 14775
3695
+ },
3696
+ {
3697
+ "epoch": 9.01,
3698
+ "learning_rate": 1.420689655172414e-07,
3699
+ "loss": 0.0164,
3700
+ "step": 14800
3701
+ },
3702
+ {
3703
+ "epoch": 9.02,
3704
+ "learning_rate": 1.2482758620689658e-07,
3705
+ "loss": 0.0167,
3706
+ "step": 14825
3707
+ },
3708
+ {
3709
+ "epoch": 9.04,
3710
+ "learning_rate": 1.0758620689655174e-07,
3711
+ "loss": 0.0161,
3712
+ "step": 14850
3713
+ },
3714
+ {
3715
+ "epoch": 9.05,
3716
+ "learning_rate": 9.034482758620691e-08,
3717
+ "loss": 0.0158,
3718
+ "step": 14875
3719
+ },
3720
+ {
3721
+ "epoch": 9.07,
3722
+ "learning_rate": 7.310344827586207e-08,
3723
+ "loss": 0.0164,
3724
+ "step": 14900
3725
+ },
3726
+ {
3727
+ "epoch": 9.08,
3728
+ "learning_rate": 5.586206896551725e-08,
3729
+ "loss": 0.0174,
3730
+ "step": 14925
3731
+ },
3732
+ {
3733
+ "epoch": 9.1,
3734
+ "learning_rate": 3.8620689655172417e-08,
3735
+ "loss": 0.0156,
3736
+ "step": 14950
3737
+ },
3738
+ {
3739
+ "epoch": 9.11,
3740
+ "learning_rate": 2.1379310344827588e-08,
3741
+ "loss": 0.0165,
3742
+ "step": 14975
3743
+ },
3744
+ {
3745
+ "epoch": 9.13,
3746
+ "learning_rate": 4.137931034482759e-09,
3747
+ "loss": 0.016,
3748
+ "step": 15000
3749
+ },
3750
+ {
3751
+ "epoch": 9.13,
3752
+ "eval_cer": 11.424817223139382,
3753
+ "eval_loss": 0.38436850905418396,
3754
+ "eval_runtime": 729.2219,
3755
+ "eval_samples_per_second": 2.586,
3756
+ "eval_steps_per_second": 0.081,
3757
+ "eval_wer": 33.31876775180249,
3758
+ "step": 15000
3759
+ },
3760
+ {
3761
+ "epoch": 9.13,
3762
+ "step": 15000,
3763
+ "total_flos": 1.3847683858735104e+20,
3764
+ "train_loss": 0.16232306808829308,
3765
+ "train_runtime": 44672.5765,
3766
+ "train_samples_per_second": 10.745,
3767
+ "train_steps_per_second": 0.336
3768
+ },
3769
+ {
3770
+ "epoch": 9.13,
3771
+ "eval_cer": 11.231932886358276,
3772
+ "eval_loss": 0.3060995638370514,
3773
+ "eval_runtime": 730.9925,
3774
+ "eval_samples_per_second": 2.58,
3775
+ "eval_steps_per_second": 0.081,
3776
+ "eval_wer": 32.64693030369237,
3777
+ "step": 15000
3778
+ }
3779
+ ],
3780
+ "max_steps": 15000,
3781
+ "num_train_epochs": 10,
3782
+ "total_flos": 1.3847683858735104e+20,
3783
+ "trial_name": null,
3784
+ "trial_params": null
3785
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff