Oblivion208 commited on
Commit
6683fe2
1 Parent(s): 202e4bc

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": {
3
+ "base_model_class": "WhisperForConditionalGeneration",
4
+ "parent_library": "transformers.models.whisper.modeling_whisper"
5
+ },
6
+ "base_model_name_or_path": "openai/whisper-large-v2",
7
+ "bias": "none",
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layers_pattern": null,
12
+ "layers_to_transform": null,
13
+ "lora_alpha": 64,
14
+ "lora_dropout": 0.05,
15
+ "modules_to_save": null,
16
+ "peft_type": "LORA",
17
+ "r": 32,
18
+ "revision": null,
19
+ "target_modules": [
20
+ "q_proj",
21
+ "v_proj"
22
+ ],
23
+ "task_type": null
24
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06059cf530897e198c421d636f64750f51999ba838d643119a307c7e34366dc7
3
+ size 63056269
added_tokens.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|en|>": 50259,
21
+ "<|es|>": 50262,
22
+ "<|et|>": 50307,
23
+ "<|eu|>": 50310,
24
+ "<|fa|>": 50300,
25
+ "<|fi|>": 50277,
26
+ "<|fo|>": 50338,
27
+ "<|fr|>": 50265,
28
+ "<|gl|>": 50319,
29
+ "<|gu|>": 50333,
30
+ "<|haw|>": 50352,
31
+ "<|ha|>": 50354,
32
+ "<|he|>": 50279,
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
+ "<|ja|>": 50266,
42
+ "<|jw|>": 50356,
43
+ "<|ka|>": 50329,
44
+ "<|kk|>": 50316,
45
+ "<|km|>": 50323,
46
+ "<|kn|>": 50306,
47
+ "<|ko|>": 50264,
48
+ "<|la|>": 50294,
49
+ "<|lb|>": 50345,
50
+ "<|ln|>": 50353,
51
+ "<|lo|>": 50336,
52
+ "<|lt|>": 50293,
53
+ "<|lv|>": 50301,
54
+ "<|mg|>": 50349,
55
+ "<|mi|>": 50295,
56
+ "<|mk|>": 50308,
57
+ "<|ml|>": 50296,
58
+ "<|mn|>": 50314,
59
+ "<|mr|>": 50320,
60
+ "<|ms|>": 50282,
61
+ "<|mt|>": 50343,
62
+ "<|my|>": 50346,
63
+ "<|ne|>": 50313,
64
+ "<|nl|>": 50271,
65
+ "<|nn|>": 50342,
66
+ "<|nocaptions|>": 50362,
67
+ "<|notimestamps|>": 50363,
68
+ "<|no|>": 50288,
69
+ "<|oc|>": 50328,
70
+ "<|pa|>": 50321,
71
+ "<|pl|>": 50269,
72
+ "<|ps|>": 50340,
73
+ "<|pt|>": 50267,
74
+ "<|ro|>": 50284,
75
+ "<|ru|>": 50263,
76
+ "<|sa|>": 50344,
77
+ "<|sd|>": 50332,
78
+ "<|si|>": 50322,
79
+ "<|sk|>": 50298,
80
+ "<|sl|>": 50305,
81
+ "<|sn|>": 50324,
82
+ "<|so|>": 50326,
83
+ "<|sq|>": 50317,
84
+ "<|sr|>": 50303,
85
+ "<|startoflm|>": 50360,
86
+ "<|startofprev|>": 50361,
87
+ "<|startoftranscript|>": 50258,
88
+ "<|su|>": 50357,
89
+ "<|sv|>": 50273,
90
+ "<|sw|>": 50318,
91
+ "<|ta|>": 50287,
92
+ "<|te|>": 50299,
93
+ "<|tg|>": 50331,
94
+ "<|th|>": 50289,
95
+ "<|tk|>": 50341,
96
+ "<|tl|>": 50348,
97
+ "<|transcribe|>": 50359,
98
+ "<|translate|>": 50358,
99
+ "<|tr|>": 50268,
100
+ "<|tt|>": 50351,
101
+ "<|uk|>": 50280,
102
+ "<|ur|>": 50290,
103
+ "<|uz|>": 50337,
104
+ "<|vi|>": 50278,
105
+ "<|yi|>": 50335,
106
+ "<|yo|>": 50325,
107
+ "<|zh|>": 50260
108
+ }
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
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80bf0c21d3eab7941fe7314c29eeeac12913c38b542a8fedb4da1d0f056faafe
3
+ size 84100933
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "feature_extractor_type": "WhisperFeatureExtractor",
4
+ "feature_size": 80,
5
+ "hop_length": 160,
6
+ "n_fft": 400,
7
+ "n_samples": 480000,
8
+ "nb_max_frames": 3000,
9
+ "padding_side": "right",
10
+ "padding_value": 0.0,
11
+ "processor_class": "WhisperProcessor",
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdcf9c7dcea9de8c29967818f021a91aa91ee835ee7ca440b1ea6ad30733f642
3
+ size 14575
runs/Aug27_03-13-31_615941b6b2ea/events.out.tfevents.1693106012.615941b6b2ea.19292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b203cbb5787380cc40c618d37d7ceaab2f2bf0480f9c207ae70e08d3cee28d5
3
+ size 82096
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2617a48fb1a488d3c2368280591e193a65cd03e034d208f75cc3247ca52caca5
3
+ size 627
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
+ "<|he|>",
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": "<|endoftext|>",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false
132
+ }
133
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1024,
23
+ "pad_token": null,
24
+ "processor_class": "WhisperProcessor",
25
+ "return_attention_mask": false,
26
+ "tokenizer_class": "WhisperTokenizer",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
trainer_state.json ADDED
@@ -0,0 +1,2819 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.1165,
5
+ "eval_steps": 200,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 5e-05,
14
+ "loss": 2.492,
15
+ "step": 25
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.0001,
20
+ "loss": 1.5737,
21
+ "step": 50
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.00015,
26
+ "loss": 0.8096,
27
+ "step": 75
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.0002,
32
+ "loss": 0.1818,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 0.00025,
38
+ "loss": 0.1383,
39
+ "step": 125
40
+ },
41
+ {
42
+ "epoch": 0.01,
43
+ "learning_rate": 0.0003,
44
+ "loss": 0.1267,
45
+ "step": 150
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.00035,
50
+ "loss": 0.1119,
51
+ "step": 175
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 0.0004,
56
+ "loss": 0.1193,
57
+ "step": 200
58
+ },
59
+ {
60
+ "epoch": 0.02,
61
+ "eval_loss": 0.5211273431777954,
62
+ "eval_runtime": 222.3408,
63
+ "eval_samples_per_second": 4.498,
64
+ "eval_steps_per_second": 0.283,
65
+ "step": 200
66
+ },
67
+ {
68
+ "epoch": 0.02,
69
+ "learning_rate": 0.00045000000000000004,
70
+ "loss": 0.1103,
71
+ "step": 225
72
+ },
73
+ {
74
+ "epoch": 0.03,
75
+ "learning_rate": 0.0005,
76
+ "loss": 0.1132,
77
+ "step": 250
78
+ },
79
+ {
80
+ "epoch": 0.03,
81
+ "learning_rate": 0.00055,
82
+ "loss": 0.1192,
83
+ "step": 275
84
+ },
85
+ {
86
+ "epoch": 0.03,
87
+ "learning_rate": 0.0006,
88
+ "loss": 0.0996,
89
+ "step": 300
90
+ },
91
+ {
92
+ "epoch": 0.03,
93
+ "learning_rate": 0.0006500000000000001,
94
+ "loss": 0.1094,
95
+ "step": 325
96
+ },
97
+ {
98
+ "epoch": 0.04,
99
+ "learning_rate": 0.0007,
100
+ "loss": 0.1099,
101
+ "step": 350
102
+ },
103
+ {
104
+ "epoch": 0.04,
105
+ "learning_rate": 0.00075,
106
+ "loss": 0.1044,
107
+ "step": 375
108
+ },
109
+ {
110
+ "epoch": 0.04,
111
+ "learning_rate": 0.0008,
112
+ "loss": 0.1153,
113
+ "step": 400
114
+ },
115
+ {
116
+ "epoch": 0.04,
117
+ "eval_loss": 0.5528811812400818,
118
+ "eval_runtime": 215.4309,
119
+ "eval_samples_per_second": 4.642,
120
+ "eval_steps_per_second": 0.292,
121
+ "step": 400
122
+ },
123
+ {
124
+ "epoch": 0.04,
125
+ "learning_rate": 0.00085,
126
+ "loss": 0.1142,
127
+ "step": 425
128
+ },
129
+ {
130
+ "epoch": 0.04,
131
+ "learning_rate": 0.0009000000000000001,
132
+ "loss": 0.1265,
133
+ "step": 450
134
+ },
135
+ {
136
+ "epoch": 0.05,
137
+ "learning_rate": 0.00095,
138
+ "loss": 0.1238,
139
+ "step": 475
140
+ },
141
+ {
142
+ "epoch": 0.05,
143
+ "learning_rate": 0.001,
144
+ "loss": 0.1515,
145
+ "step": 500
146
+ },
147
+ {
148
+ "epoch": 0.05,
149
+ "learning_rate": 0.0009973684210526316,
150
+ "loss": 0.1554,
151
+ "step": 525
152
+ },
153
+ {
154
+ "epoch": 0.06,
155
+ "learning_rate": 0.000994842105263158,
156
+ "loss": 0.1472,
157
+ "step": 550
158
+ },
159
+ {
160
+ "epoch": 0.06,
161
+ "learning_rate": 0.0009922105263157894,
162
+ "loss": 0.1346,
163
+ "step": 575
164
+ },
165
+ {
166
+ "epoch": 0.06,
167
+ "learning_rate": 0.000989578947368421,
168
+ "loss": 0.1307,
169
+ "step": 600
170
+ },
171
+ {
172
+ "epoch": 0.06,
173
+ "eval_loss": 0.6507117748260498,
174
+ "eval_runtime": 230.1411,
175
+ "eval_samples_per_second": 4.345,
176
+ "eval_steps_per_second": 0.274,
177
+ "step": 600
178
+ },
179
+ {
180
+ "epoch": 0.06,
181
+ "learning_rate": 0.0009869473684210527,
182
+ "loss": 0.1318,
183
+ "step": 625
184
+ },
185
+ {
186
+ "epoch": 0.07,
187
+ "learning_rate": 0.0009843157894736843,
188
+ "loss": 0.1296,
189
+ "step": 650
190
+ },
191
+ {
192
+ "epoch": 0.07,
193
+ "learning_rate": 0.0009816842105263158,
194
+ "loss": 0.1215,
195
+ "step": 675
196
+ },
197
+ {
198
+ "epoch": 0.07,
199
+ "learning_rate": 0.0009790526315789473,
200
+ "loss": 0.1209,
201
+ "step": 700
202
+ },
203
+ {
204
+ "epoch": 0.07,
205
+ "learning_rate": 0.000976421052631579,
206
+ "loss": 0.1117,
207
+ "step": 725
208
+ },
209
+ {
210
+ "epoch": 0.07,
211
+ "learning_rate": 0.0009737894736842105,
212
+ "loss": 0.1156,
213
+ "step": 750
214
+ },
215
+ {
216
+ "epoch": 0.08,
217
+ "learning_rate": 0.0009711578947368422,
218
+ "loss": 0.1223,
219
+ "step": 775
220
+ },
221
+ {
222
+ "epoch": 0.08,
223
+ "learning_rate": 0.0009685263157894737,
224
+ "loss": 0.1195,
225
+ "step": 800
226
+ },
227
+ {
228
+ "epoch": 0.08,
229
+ "eval_loss": 0.6224600672721863,
230
+ "eval_runtime": 224.4686,
231
+ "eval_samples_per_second": 4.455,
232
+ "eval_steps_per_second": 0.281,
233
+ "step": 800
234
+ },
235
+ {
236
+ "epoch": 0.08,
237
+ "learning_rate": 0.0009658947368421053,
238
+ "loss": 0.1256,
239
+ "step": 825
240
+ },
241
+ {
242
+ "epoch": 0.09,
243
+ "learning_rate": 0.0009632631578947368,
244
+ "loss": 0.127,
245
+ "step": 850
246
+ },
247
+ {
248
+ "epoch": 0.09,
249
+ "learning_rate": 0.0009606315789473684,
250
+ "loss": 0.1131,
251
+ "step": 875
252
+ },
253
+ {
254
+ "epoch": 0.09,
255
+ "learning_rate": 0.000958,
256
+ "loss": 0.1266,
257
+ "step": 900
258
+ },
259
+ {
260
+ "epoch": 0.09,
261
+ "learning_rate": 0.0009553684210526315,
262
+ "loss": 0.1223,
263
+ "step": 925
264
+ },
265
+ {
266
+ "epoch": 0.1,
267
+ "learning_rate": 0.0009527368421052632,
268
+ "loss": 0.1247,
269
+ "step": 950
270
+ },
271
+ {
272
+ "epoch": 0.1,
273
+ "learning_rate": 0.0009501052631578948,
274
+ "loss": 0.126,
275
+ "step": 975
276
+ },
277
+ {
278
+ "epoch": 0.1,
279
+ "learning_rate": 0.0009474736842105263,
280
+ "loss": 0.1271,
281
+ "step": 1000
282
+ },
283
+ {
284
+ "epoch": 0.1,
285
+ "eval_loss": 0.6543993353843689,
286
+ "eval_runtime": 224.6223,
287
+ "eval_samples_per_second": 4.452,
288
+ "eval_steps_per_second": 0.28,
289
+ "step": 1000
290
+ },
291
+ {
292
+ "epoch": 0.1,
293
+ "learning_rate": 0.000944842105263158,
294
+ "loss": 0.1111,
295
+ "step": 1025
296
+ },
297
+ {
298
+ "epoch": 0.1,
299
+ "learning_rate": 0.0009422105263157895,
300
+ "loss": 0.1174,
301
+ "step": 1050
302
+ },
303
+ {
304
+ "epoch": 0.11,
305
+ "learning_rate": 0.0009395789473684211,
306
+ "loss": 0.1234,
307
+ "step": 1075
308
+ },
309
+ {
310
+ "epoch": 0.11,
311
+ "learning_rate": 0.0009369473684210527,
312
+ "loss": 0.1176,
313
+ "step": 1100
314
+ },
315
+ {
316
+ "epoch": 0.11,
317
+ "learning_rate": 0.0009343157894736842,
318
+ "loss": 0.1154,
319
+ "step": 1125
320
+ },
321
+ {
322
+ "epoch": 0.12,
323
+ "learning_rate": 0.0009316842105263158,
324
+ "loss": 0.1096,
325
+ "step": 1150
326
+ },
327
+ {
328
+ "epoch": 0.12,
329
+ "learning_rate": 0.0009290526315789473,
330
+ "loss": 0.1202,
331
+ "step": 1175
332
+ },
333
+ {
334
+ "epoch": 0.12,
335
+ "learning_rate": 0.000926421052631579,
336
+ "loss": 0.1153,
337
+ "step": 1200
338
+ },
339
+ {
340
+ "epoch": 0.12,
341
+ "eval_loss": 0.6334092020988464,
342
+ "eval_runtime": 231.0686,
343
+ "eval_samples_per_second": 4.328,
344
+ "eval_steps_per_second": 0.273,
345
+ "step": 1200
346
+ },
347
+ {
348
+ "epoch": 0.12,
349
+ "learning_rate": 0.0009237894736842105,
350
+ "loss": 0.1045,
351
+ "step": 1225
352
+ },
353
+ {
354
+ "epoch": 0.12,
355
+ "learning_rate": 0.000921157894736842,
356
+ "loss": 0.1181,
357
+ "step": 1250
358
+ },
359
+ {
360
+ "epoch": 0.13,
361
+ "learning_rate": 0.0009185263157894737,
362
+ "loss": 0.1149,
363
+ "step": 1275
364
+ },
365
+ {
366
+ "epoch": 0.13,
367
+ "learning_rate": 0.0009158947368421053,
368
+ "loss": 0.1108,
369
+ "step": 1300
370
+ },
371
+ {
372
+ "epoch": 0.13,
373
+ "learning_rate": 0.0009132631578947369,
374
+ "loss": 0.1154,
375
+ "step": 1325
376
+ },
377
+ {
378
+ "epoch": 0.14,
379
+ "learning_rate": 0.0009106315789473685,
380
+ "loss": 0.1137,
381
+ "step": 1350
382
+ },
383
+ {
384
+ "epoch": 0.14,
385
+ "learning_rate": 0.0009080000000000001,
386
+ "loss": 0.1165,
387
+ "step": 1375
388
+ },
389
+ {
390
+ "epoch": 0.14,
391
+ "learning_rate": 0.0009053684210526316,
392
+ "loss": 0.1157,
393
+ "step": 1400
394
+ },
395
+ {
396
+ "epoch": 0.14,
397
+ "eval_loss": 0.6377915740013123,
398
+ "eval_runtime": 234.7043,
399
+ "eval_samples_per_second": 4.261,
400
+ "eval_steps_per_second": 0.268,
401
+ "step": 1400
402
+ },
403
+ {
404
+ "epoch": 0.14,
405
+ "learning_rate": 0.0009027368421052631,
406
+ "loss": 0.1047,
407
+ "step": 1425
408
+ },
409
+ {
410
+ "epoch": 0.14,
411
+ "learning_rate": 0.0009001052631578948,
412
+ "loss": 0.1164,
413
+ "step": 1450
414
+ },
415
+ {
416
+ "epoch": 0.15,
417
+ "learning_rate": 0.0008974736842105263,
418
+ "loss": 0.1643,
419
+ "step": 1475
420
+ },
421
+ {
422
+ "epoch": 0.15,
423
+ "learning_rate": 0.0008948421052631579,
424
+ "loss": 0.3201,
425
+ "step": 1500
426
+ },
427
+ {
428
+ "epoch": 0.15,
429
+ "learning_rate": 0.0008922105263157895,
430
+ "loss": 0.3339,
431
+ "step": 1525
432
+ },
433
+ {
434
+ "epoch": 0.15,
435
+ "learning_rate": 0.000889578947368421,
436
+ "loss": 0.3632,
437
+ "step": 1550
438
+ },
439
+ {
440
+ "epoch": 0.16,
441
+ "learning_rate": 0.0008869473684210526,
442
+ "loss": 0.3388,
443
+ "step": 1575
444
+ },
445
+ {
446
+ "epoch": 0.16,
447
+ "learning_rate": 0.0008843157894736842,
448
+ "loss": 0.3302,
449
+ "step": 1600
450
+ },
451
+ {
452
+ "epoch": 0.16,
453
+ "eval_loss": 0.3262811303138733,
454
+ "eval_runtime": 238.2184,
455
+ "eval_samples_per_second": 4.198,
456
+ "eval_steps_per_second": 0.264,
457
+ "step": 1600
458
+ },
459
+ {
460
+ "epoch": 0.16,
461
+ "learning_rate": 0.0008816842105263158,
462
+ "loss": 0.3697,
463
+ "step": 1625
464
+ },
465
+ {
466
+ "epoch": 0.17,
467
+ "learning_rate": 0.0008790526315789474,
468
+ "loss": 0.3009,
469
+ "step": 1650
470
+ },
471
+ {
472
+ "epoch": 0.17,
473
+ "learning_rate": 0.0008764210526315791,
474
+ "loss": 0.2743,
475
+ "step": 1675
476
+ },
477
+ {
478
+ "epoch": 0.17,
479
+ "learning_rate": 0.000874,
480
+ "loss": 0.2846,
481
+ "step": 1700
482
+ },
483
+ {
484
+ "epoch": 0.17,
485
+ "learning_rate": 0.0008714736842105263,
486
+ "loss": 0.2532,
487
+ "step": 1725
488
+ },
489
+ {
490
+ "epoch": 0.17,
491
+ "learning_rate": 0.0008688421052631579,
492
+ "loss": 0.2461,
493
+ "step": 1750
494
+ },
495
+ {
496
+ "epoch": 1.0,
497
+ "learning_rate": 0.0008662105263157894,
498
+ "loss": 0.2367,
499
+ "step": 1775
500
+ },
501
+ {
502
+ "epoch": 1.0,
503
+ "learning_rate": 0.0008635789473684211,
504
+ "loss": 0.1269,
505
+ "step": 1800
506
+ },
507
+ {
508
+ "epoch": 1.0,
509
+ "eval_loss": 0.3383277654647827,
510
+ "eval_runtime": 259.2781,
511
+ "eval_samples_per_second": 3.857,
512
+ "eval_steps_per_second": 0.243,
513
+ "step": 1800
514
+ },
515
+ {
516
+ "epoch": 1.01,
517
+ "learning_rate": 0.0008609473684210527,
518
+ "loss": 0.1188,
519
+ "step": 1825
520
+ },
521
+ {
522
+ "epoch": 1.01,
523
+ "learning_rate": 0.0008583157894736842,
524
+ "loss": 0.1173,
525
+ "step": 1850
526
+ },
527
+ {
528
+ "epoch": 1.01,
529
+ "learning_rate": 0.0008556842105263159,
530
+ "loss": 0.1257,
531
+ "step": 1875
532
+ },
533
+ {
534
+ "epoch": 1.01,
535
+ "learning_rate": 0.0008530526315789474,
536
+ "loss": 0.1197,
537
+ "step": 1900
538
+ },
539
+ {
540
+ "epoch": 1.02,
541
+ "learning_rate": 0.000850421052631579,
542
+ "loss": 0.1109,
543
+ "step": 1925
544
+ },
545
+ {
546
+ "epoch": 1.02,
547
+ "learning_rate": 0.0008477894736842105,
548
+ "loss": 0.1041,
549
+ "step": 1950
550
+ },
551
+ {
552
+ "epoch": 1.02,
553
+ "learning_rate": 0.0008451578947368422,
554
+ "loss": 0.101,
555
+ "step": 1975
556
+ },
557
+ {
558
+ "epoch": 1.02,
559
+ "learning_rate": 0.0008425263157894737,
560
+ "loss": 0.1006,
561
+ "step": 2000
562
+ },
563
+ {
564
+ "epoch": 1.02,
565
+ "eval_loss": 0.3684940040111542,
566
+ "eval_runtime": 255.8865,
567
+ "eval_samples_per_second": 3.908,
568
+ "eval_steps_per_second": 0.246,
569
+ "step": 2000
570
+ },
571
+ {
572
+ "epoch": 1.03,
573
+ "learning_rate": 0.0008398947368421052,
574
+ "loss": 0.1051,
575
+ "step": 2025
576
+ },
577
+ {
578
+ "epoch": 1.03,
579
+ "learning_rate": 0.0008372631578947369,
580
+ "loss": 0.1029,
581
+ "step": 2050
582
+ },
583
+ {
584
+ "epoch": 1.03,
585
+ "learning_rate": 0.0008346315789473684,
586
+ "loss": 0.0923,
587
+ "step": 2075
588
+ },
589
+ {
590
+ "epoch": 1.03,
591
+ "learning_rate": 0.000832,
592
+ "loss": 0.0983,
593
+ "step": 2100
594
+ },
595
+ {
596
+ "epoch": 1.04,
597
+ "learning_rate": 0.0008293684210526316,
598
+ "loss": 0.09,
599
+ "step": 2125
600
+ },
601
+ {
602
+ "epoch": 1.04,
603
+ "learning_rate": 0.0008267368421052631,
604
+ "loss": 0.0906,
605
+ "step": 2150
606
+ },
607
+ {
608
+ "epoch": 1.04,
609
+ "learning_rate": 0.0008241052631578948,
610
+ "loss": 0.0899,
611
+ "step": 2175
612
+ },
613
+ {
614
+ "epoch": 1.04,
615
+ "learning_rate": 0.0008214736842105264,
616
+ "loss": 0.0876,
617
+ "step": 2200
618
+ },
619
+ {
620
+ "epoch": 1.04,
621
+ "eval_loss": 0.3948498070240021,
622
+ "eval_runtime": 239.7929,
623
+ "eval_samples_per_second": 4.17,
624
+ "eval_steps_per_second": 0.263,
625
+ "step": 2200
626
+ },
627
+ {
628
+ "epoch": 1.05,
629
+ "learning_rate": 0.000818842105263158,
630
+ "loss": 0.0845,
631
+ "step": 2225
632
+ },
633
+ {
634
+ "epoch": 1.05,
635
+ "learning_rate": 0.0008162105263157895,
636
+ "loss": 0.0799,
637
+ "step": 2250
638
+ },
639
+ {
640
+ "epoch": 1.05,
641
+ "learning_rate": 0.000813578947368421,
642
+ "loss": 0.0898,
643
+ "step": 2275
644
+ },
645
+ {
646
+ "epoch": 1.05,
647
+ "learning_rate": 0.0008109473684210527,
648
+ "loss": 0.0818,
649
+ "step": 2300
650
+ },
651
+ {
652
+ "epoch": 1.06,
653
+ "learning_rate": 0.0008083157894736842,
654
+ "loss": 0.0914,
655
+ "step": 2325
656
+ },
657
+ {
658
+ "epoch": 1.06,
659
+ "learning_rate": 0.0008056842105263158,
660
+ "loss": 0.0844,
661
+ "step": 2350
662
+ },
663
+ {
664
+ "epoch": 1.06,
665
+ "learning_rate": 0.0008030526315789474,
666
+ "loss": 0.0845,
667
+ "step": 2375
668
+ },
669
+ {
670
+ "epoch": 1.06,
671
+ "learning_rate": 0.0008004210526315789,
672
+ "loss": 0.0815,
673
+ "step": 2400
674
+ },
675
+ {
676
+ "epoch": 1.06,
677
+ "eval_loss": 0.40161755681037903,
678
+ "eval_runtime": 239.5377,
679
+ "eval_samples_per_second": 4.175,
680
+ "eval_steps_per_second": 0.263,
681
+ "step": 2400
682
+ },
683
+ {
684
+ "epoch": 1.07,
685
+ "learning_rate": 0.0007977894736842105,
686
+ "loss": 0.0806,
687
+ "step": 2425
688
+ },
689
+ {
690
+ "epoch": 1.07,
691
+ "learning_rate": 0.0007951578947368421,
692
+ "loss": 0.0783,
693
+ "step": 2450
694
+ },
695
+ {
696
+ "epoch": 1.07,
697
+ "learning_rate": 0.0007925263157894737,
698
+ "loss": 0.0746,
699
+ "step": 2475
700
+ },
701
+ {
702
+ "epoch": 1.07,
703
+ "learning_rate": 0.0007898947368421053,
704
+ "loss": 0.0748,
705
+ "step": 2500
706
+ },
707
+ {
708
+ "epoch": 1.08,
709
+ "learning_rate": 0.0007872631578947369,
710
+ "loss": 0.079,
711
+ "step": 2525
712
+ },
713
+ {
714
+ "epoch": 1.08,
715
+ "learning_rate": 0.0007846315789473685,
716
+ "loss": 0.0729,
717
+ "step": 2550
718
+ },
719
+ {
720
+ "epoch": 1.08,
721
+ "learning_rate": 0.000782,
722
+ "loss": 0.0745,
723
+ "step": 2575
724
+ },
725
+ {
726
+ "epoch": 1.08,
727
+ "learning_rate": 0.0007793684210526316,
728
+ "loss": 0.0821,
729
+ "step": 2600
730
+ },
731
+ {
732
+ "epoch": 1.08,
733
+ "eval_loss": 0.4262455105781555,
734
+ "eval_runtime": 240.4602,
735
+ "eval_samples_per_second": 4.159,
736
+ "eval_steps_per_second": 0.262,
737
+ "step": 2600
738
+ },
739
+ {
740
+ "epoch": 1.09,
741
+ "learning_rate": 0.0007767368421052632,
742
+ "loss": 0.074,
743
+ "step": 2625
744
+ },
745
+ {
746
+ "epoch": 1.09,
747
+ "learning_rate": 0.0007741052631578948,
748
+ "loss": 0.0692,
749
+ "step": 2650
750
+ },
751
+ {
752
+ "epoch": 1.09,
753
+ "learning_rate": 0.0007714736842105263,
754
+ "loss": 0.0779,
755
+ "step": 2675
756
+ },
757
+ {
758
+ "epoch": 1.09,
759
+ "learning_rate": 0.0007688421052631579,
760
+ "loss": 0.0678,
761
+ "step": 2700
762
+ },
763
+ {
764
+ "epoch": 1.1,
765
+ "learning_rate": 0.0007662105263157895,
766
+ "loss": 0.079,
767
+ "step": 2725
768
+ },
769
+ {
770
+ "epoch": 1.1,
771
+ "learning_rate": 0.000763578947368421,
772
+ "loss": 0.0689,
773
+ "step": 2750
774
+ },
775
+ {
776
+ "epoch": 1.1,
777
+ "learning_rate": 0.0007609473684210527,
778
+ "loss": 0.0761,
779
+ "step": 2775
780
+ },
781
+ {
782
+ "epoch": 1.1,
783
+ "learning_rate": 0.0007583157894736842,
784
+ "loss": 0.0758,
785
+ "step": 2800
786
+ },
787
+ {
788
+ "epoch": 1.1,
789
+ "eval_loss": 0.4292161166667938,
790
+ "eval_runtime": 229.938,
791
+ "eval_samples_per_second": 4.349,
792
+ "eval_steps_per_second": 0.274,
793
+ "step": 2800
794
+ },
795
+ {
796
+ "epoch": 1.11,
797
+ "learning_rate": 0.0007556842105263157,
798
+ "loss": 0.0652,
799
+ "step": 2825
800
+ },
801
+ {
802
+ "epoch": 1.11,
803
+ "learning_rate": 0.0007530526315789474,
804
+ "loss": 0.0722,
805
+ "step": 2850
806
+ },
807
+ {
808
+ "epoch": 1.11,
809
+ "learning_rate": 0.000750421052631579,
810
+ "loss": 0.0703,
811
+ "step": 2875
812
+ },
813
+ {
814
+ "epoch": 1.11,
815
+ "learning_rate": 0.0007477894736842106,
816
+ "loss": 0.0698,
817
+ "step": 2900
818
+ },
819
+ {
820
+ "epoch": 1.12,
821
+ "learning_rate": 0.0007451578947368421,
822
+ "loss": 0.0675,
823
+ "step": 2925
824
+ },
825
+ {
826
+ "epoch": 1.12,
827
+ "learning_rate": 0.0007425263157894738,
828
+ "loss": 0.0717,
829
+ "step": 2950
830
+ },
831
+ {
832
+ "epoch": 1.12,
833
+ "learning_rate": 0.0007398947368421053,
834
+ "loss": 0.0711,
835
+ "step": 2975
836
+ },
837
+ {
838
+ "epoch": 1.12,
839
+ "learning_rate": 0.0007372631578947368,
840
+ "loss": 0.0689,
841
+ "step": 3000
842
+ },
843
+ {
844
+ "epoch": 1.12,
845
+ "eval_loss": 0.4249730110168457,
846
+ "eval_runtime": 233.7088,
847
+ "eval_samples_per_second": 4.279,
848
+ "eval_steps_per_second": 0.27,
849
+ "step": 3000
850
+ },
851
+ {
852
+ "epoch": 1.13,
853
+ "learning_rate": 0.0007346315789473685,
854
+ "loss": 0.0697,
855
+ "step": 3025
856
+ },
857
+ {
858
+ "epoch": 1.13,
859
+ "learning_rate": 0.000732,
860
+ "loss": 0.0719,
861
+ "step": 3050
862
+ },
863
+ {
864
+ "epoch": 1.13,
865
+ "learning_rate": 0.0007293684210526315,
866
+ "loss": 0.0717,
867
+ "step": 3075
868
+ },
869
+ {
870
+ "epoch": 1.13,
871
+ "learning_rate": 0.0007267368421052631,
872
+ "loss": 0.0739,
873
+ "step": 3100
874
+ },
875
+ {
876
+ "epoch": 1.14,
877
+ "learning_rate": 0.0007241052631578947,
878
+ "loss": 0.0653,
879
+ "step": 3125
880
+ },
881
+ {
882
+ "epoch": 1.14,
883
+ "learning_rate": 0.0007214736842105263,
884
+ "loss": 0.0679,
885
+ "step": 3150
886
+ },
887
+ {
888
+ "epoch": 1.14,
889
+ "learning_rate": 0.0007188421052631579,
890
+ "loss": 0.0697,
891
+ "step": 3175
892
+ },
893
+ {
894
+ "epoch": 1.14,
895
+ "learning_rate": 0.0007162105263157896,
896
+ "loss": 0.0612,
897
+ "step": 3200
898
+ },
899
+ {
900
+ "epoch": 1.14,
901
+ "eval_loss": 0.4456619620323181,
902
+ "eval_runtime": 283.5688,
903
+ "eval_samples_per_second": 3.526,
904
+ "eval_steps_per_second": 0.222,
905
+ "step": 3200
906
+ },
907
+ {
908
+ "epoch": 1.15,
909
+ "learning_rate": 0.0007135789473684211,
910
+ "loss": 0.071,
911
+ "step": 3225
912
+ },
913
+ {
914
+ "epoch": 1.15,
915
+ "learning_rate": 0.0007109473684210526,
916
+ "loss": 0.1414,
917
+ "step": 3250
918
+ },
919
+ {
920
+ "epoch": 1.15,
921
+ "learning_rate": 0.0007083157894736843,
922
+ "loss": 0.2082,
923
+ "step": 3275
924
+ },
925
+ {
926
+ "epoch": 1.15,
927
+ "learning_rate": 0.0007056842105263158,
928
+ "loss": 0.2392,
929
+ "step": 3300
930
+ },
931
+ {
932
+ "epoch": 1.16,
933
+ "learning_rate": 0.0007030526315789474,
934
+ "loss": 0.2313,
935
+ "step": 3325
936
+ },
937
+ {
938
+ "epoch": 1.16,
939
+ "learning_rate": 0.000700421052631579,
940
+ "loss": 0.2382,
941
+ "step": 3350
942
+ },
943
+ {
944
+ "epoch": 1.16,
945
+ "learning_rate": 0.0006977894736842105,
946
+ "loss": 0.2509,
947
+ "step": 3375
948
+ },
949
+ {
950
+ "epoch": 1.16,
951
+ "learning_rate": 0.0006951578947368421,
952
+ "loss": 0.2347,
953
+ "step": 3400
954
+ },
955
+ {
956
+ "epoch": 1.16,
957
+ "eval_loss": 0.2735106348991394,
958
+ "eval_runtime": 256.6563,
959
+ "eval_samples_per_second": 3.896,
960
+ "eval_steps_per_second": 0.245,
961
+ "step": 3400
962
+ },
963
+ {
964
+ "epoch": 1.17,
965
+ "learning_rate": 0.0006925263157894736,
966
+ "loss": 0.215,
967
+ "step": 3425
968
+ },
969
+ {
970
+ "epoch": 1.17,
971
+ "learning_rate": 0.0006898947368421053,
972
+ "loss": 0.1968,
973
+ "step": 3450
974
+ },
975
+ {
976
+ "epoch": 1.17,
977
+ "learning_rate": 0.0006872631578947368,
978
+ "loss": 0.1947,
979
+ "step": 3475
980
+ },
981
+ {
982
+ "epoch": 1.17,
983
+ "learning_rate": 0.0006846315789473683,
984
+ "loss": 0.1786,
985
+ "step": 3500
986
+ },
987
+ {
988
+ "epoch": 1.18,
989
+ "learning_rate": 0.0006820000000000001,
990
+ "loss": 0.1816,
991
+ "step": 3525
992
+ },
993
+ {
994
+ "epoch": 2.0,
995
+ "learning_rate": 0.0006793684210526316,
996
+ "loss": 0.1258,
997
+ "step": 3550
998
+ },
999
+ {
1000
+ "epoch": 2.0,
1001
+ "learning_rate": 0.0006767368421052632,
1002
+ "loss": 0.076,
1003
+ "step": 3575
1004
+ },
1005
+ {
1006
+ "epoch": 2.01,
1007
+ "learning_rate": 0.0006741052631578948,
1008
+ "loss": 0.0723,
1009
+ "step": 3600
1010
+ },
1011
+ {
1012
+ "epoch": 2.01,
1013
+ "eval_loss": 0.3416486084461212,
1014
+ "eval_runtime": 264.4251,
1015
+ "eval_samples_per_second": 3.782,
1016
+ "eval_steps_per_second": 0.238,
1017
+ "step": 3600
1018
+ },
1019
+ {
1020
+ "epoch": 2.01,
1021
+ "learning_rate": 0.0006714736842105264,
1022
+ "loss": 0.0754,
1023
+ "step": 3625
1024
+ },
1025
+ {
1026
+ "epoch": 2.01,
1027
+ "learning_rate": 0.0006688421052631579,
1028
+ "loss": 0.0775,
1029
+ "step": 3650
1030
+ },
1031
+ {
1032
+ "epoch": 2.01,
1033
+ "learning_rate": 0.0006662105263157895,
1034
+ "loss": 0.0781,
1035
+ "step": 3675
1036
+ },
1037
+ {
1038
+ "epoch": 2.02,
1039
+ "learning_rate": 0.0006635789473684211,
1040
+ "loss": 0.0684,
1041
+ "step": 3700
1042
+ },
1043
+ {
1044
+ "epoch": 2.02,
1045
+ "learning_rate": 0.0006609473684210526,
1046
+ "loss": 0.0682,
1047
+ "step": 3725
1048
+ },
1049
+ {
1050
+ "epoch": 2.02,
1051
+ "learning_rate": 0.0006583157894736842,
1052
+ "loss": 0.0624,
1053
+ "step": 3750
1054
+ },
1055
+ {
1056
+ "epoch": 2.02,
1057
+ "learning_rate": 0.0006556842105263158,
1058
+ "loss": 0.07,
1059
+ "step": 3775
1060
+ },
1061
+ {
1062
+ "epoch": 2.03,
1063
+ "learning_rate": 0.0006530526315789473,
1064
+ "loss": 0.0728,
1065
+ "step": 3800
1066
+ },
1067
+ {
1068
+ "epoch": 2.03,
1069
+ "eval_loss": 0.3479284644126892,
1070
+ "eval_runtime": 292.143,
1071
+ "eval_samples_per_second": 3.423,
1072
+ "eval_steps_per_second": 0.216,
1073
+ "step": 3800
1074
+ },
1075
+ {
1076
+ "epoch": 2.03,
1077
+ "learning_rate": 0.0006504210526315789,
1078
+ "loss": 0.0762,
1079
+ "step": 3825
1080
+ },
1081
+ {
1082
+ "epoch": 2.03,
1083
+ "learning_rate": 0.0006477894736842106,
1084
+ "loss": 0.0714,
1085
+ "step": 3850
1086
+ },
1087
+ {
1088
+ "epoch": 2.03,
1089
+ "learning_rate": 0.0006451578947368422,
1090
+ "loss": 0.0753,
1091
+ "step": 3875
1092
+ },
1093
+ {
1094
+ "epoch": 2.04,
1095
+ "learning_rate": 0.0006425263157894737,
1096
+ "loss": 0.0653,
1097
+ "step": 3900
1098
+ },
1099
+ {
1100
+ "epoch": 2.04,
1101
+ "learning_rate": 0.0006398947368421054,
1102
+ "loss": 0.0711,
1103
+ "step": 3925
1104
+ },
1105
+ {
1106
+ "epoch": 2.04,
1107
+ "learning_rate": 0.0006372631578947369,
1108
+ "loss": 0.0664,
1109
+ "step": 3950
1110
+ },
1111
+ {
1112
+ "epoch": 2.04,
1113
+ "learning_rate": 0.0006346315789473684,
1114
+ "loss": 0.0608,
1115
+ "step": 3975
1116
+ },
1117
+ {
1118
+ "epoch": 2.05,
1119
+ "learning_rate": 0.000632,
1120
+ "loss": 0.0592,
1121
+ "step": 4000
1122
+ },
1123
+ {
1124
+ "epoch": 2.05,
1125
+ "eval_loss": 0.37529394030570984,
1126
+ "eval_runtime": 235.8642,
1127
+ "eval_samples_per_second": 4.24,
1128
+ "eval_steps_per_second": 0.267,
1129
+ "step": 4000
1130
+ },
1131
+ {
1132
+ "epoch": 2.05,
1133
+ "learning_rate": 0.0006293684210526316,
1134
+ "loss": 0.0588,
1135
+ "step": 4025
1136
+ },
1137
+ {
1138
+ "epoch": 2.05,
1139
+ "learning_rate": 0.0006267368421052632,
1140
+ "loss": 0.0612,
1141
+ "step": 4050
1142
+ },
1143
+ {
1144
+ "epoch": 2.05,
1145
+ "learning_rate": 0.0006241052631578947,
1146
+ "loss": 0.0603,
1147
+ "step": 4075
1148
+ },
1149
+ {
1150
+ "epoch": 2.06,
1151
+ "learning_rate": 0.0006214736842105263,
1152
+ "loss": 0.0727,
1153
+ "step": 4100
1154
+ },
1155
+ {
1156
+ "epoch": 2.06,
1157
+ "learning_rate": 0.0006188421052631579,
1158
+ "loss": 0.0625,
1159
+ "step": 4125
1160
+ },
1161
+ {
1162
+ "epoch": 2.06,
1163
+ "learning_rate": 0.0006162105263157894,
1164
+ "loss": 0.0617,
1165
+ "step": 4150
1166
+ },
1167
+ {
1168
+ "epoch": 2.06,
1169
+ "learning_rate": 0.0006135789473684211,
1170
+ "loss": 0.0642,
1171
+ "step": 4175
1172
+ },
1173
+ {
1174
+ "epoch": 2.07,
1175
+ "learning_rate": 0.0006109473684210527,
1176
+ "loss": 0.0601,
1177
+ "step": 4200
1178
+ },
1179
+ {
1180
+ "epoch": 2.07,
1181
+ "eval_loss": 0.39785417914390564,
1182
+ "eval_runtime": 249.2887,
1183
+ "eval_samples_per_second": 4.011,
1184
+ "eval_steps_per_second": 0.253,
1185
+ "step": 4200
1186
+ },
1187
+ {
1188
+ "epoch": 2.07,
1189
+ "learning_rate": 0.0006083157894736842,
1190
+ "loss": 0.0603,
1191
+ "step": 4225
1192
+ },
1193
+ {
1194
+ "epoch": 2.07,
1195
+ "learning_rate": 0.0006056842105263159,
1196
+ "loss": 0.0555,
1197
+ "step": 4250
1198
+ },
1199
+ {
1200
+ "epoch": 2.07,
1201
+ "learning_rate": 0.0006030526315789474,
1202
+ "loss": 0.0486,
1203
+ "step": 4275
1204
+ },
1205
+ {
1206
+ "epoch": 2.08,
1207
+ "learning_rate": 0.000600421052631579,
1208
+ "loss": 0.0605,
1209
+ "step": 4300
1210
+ },
1211
+ {
1212
+ "epoch": 2.08,
1213
+ "learning_rate": 0.0005977894736842105,
1214
+ "loss": 0.0507,
1215
+ "step": 4325
1216
+ },
1217
+ {
1218
+ "epoch": 2.08,
1219
+ "learning_rate": 0.0005951578947368421,
1220
+ "loss": 0.0524,
1221
+ "step": 4350
1222
+ },
1223
+ {
1224
+ "epoch": 2.08,
1225
+ "learning_rate": 0.0005925263157894737,
1226
+ "loss": 0.0572,
1227
+ "step": 4375
1228
+ },
1229
+ {
1230
+ "epoch": 2.09,
1231
+ "learning_rate": 0.0005898947368421052,
1232
+ "loss": 0.0484,
1233
+ "step": 4400
1234
+ },
1235
+ {
1236
+ "epoch": 2.09,
1237
+ "eval_loss": 0.3840053975582123,
1238
+ "eval_runtime": 233.7153,
1239
+ "eval_samples_per_second": 4.279,
1240
+ "eval_steps_per_second": 0.27,
1241
+ "step": 4400
1242
+ },
1243
+ {
1244
+ "epoch": 2.09,
1245
+ "learning_rate": 0.0005872631578947369,
1246
+ "loss": 0.0532,
1247
+ "step": 4425
1248
+ },
1249
+ {
1250
+ "epoch": 2.09,
1251
+ "learning_rate": 0.0005846315789473684,
1252
+ "loss": 0.0532,
1253
+ "step": 4450
1254
+ },
1255
+ {
1256
+ "epoch": 2.09,
1257
+ "learning_rate": 0.0005819999999999999,
1258
+ "loss": 0.0455,
1259
+ "step": 4475
1260
+ },
1261
+ {
1262
+ "epoch": 2.1,
1263
+ "learning_rate": 0.0005793684210526316,
1264
+ "loss": 0.0506,
1265
+ "step": 4500
1266
+ },
1267
+ {
1268
+ "epoch": 2.1,
1269
+ "learning_rate": 0.0005767368421052631,
1270
+ "loss": 0.046,
1271
+ "step": 4525
1272
+ },
1273
+ {
1274
+ "epoch": 2.1,
1275
+ "learning_rate": 0.0005741052631578948,
1276
+ "loss": 0.0523,
1277
+ "step": 4550
1278
+ },
1279
+ {
1280
+ "epoch": 2.1,
1281
+ "learning_rate": 0.0005714736842105264,
1282
+ "loss": 0.0456,
1283
+ "step": 4575
1284
+ },
1285
+ {
1286
+ "epoch": 2.11,
1287
+ "learning_rate": 0.000568842105263158,
1288
+ "loss": 0.0457,
1289
+ "step": 4600
1290
+ },
1291
+ {
1292
+ "epoch": 2.11,
1293
+ "eval_loss": 0.4161207675933838,
1294
+ "eval_runtime": 226.1145,
1295
+ "eval_samples_per_second": 4.423,
1296
+ "eval_steps_per_second": 0.279,
1297
+ "step": 4600
1298
+ },
1299
+ {
1300
+ "epoch": 2.11,
1301
+ "learning_rate": 0.0005662105263157895,
1302
+ "loss": 0.0454,
1303
+ "step": 4625
1304
+ },
1305
+ {
1306
+ "epoch": 2.11,
1307
+ "learning_rate": 0.000563578947368421,
1308
+ "loss": 0.0461,
1309
+ "step": 4650
1310
+ },
1311
+ {
1312
+ "epoch": 2.11,
1313
+ "learning_rate": 0.0005609473684210527,
1314
+ "loss": 0.0438,
1315
+ "step": 4675
1316
+ },
1317
+ {
1318
+ "epoch": 2.12,
1319
+ "learning_rate": 0.0005583157894736842,
1320
+ "loss": 0.0444,
1321
+ "step": 4700
1322
+ },
1323
+ {
1324
+ "epoch": 2.12,
1325
+ "learning_rate": 0.0005556842105263158,
1326
+ "loss": 0.0457,
1327
+ "step": 4725
1328
+ },
1329
+ {
1330
+ "epoch": 2.12,
1331
+ "learning_rate": 0.0005530526315789474,
1332
+ "loss": 0.0432,
1333
+ "step": 4750
1334
+ },
1335
+ {
1336
+ "epoch": 2.12,
1337
+ "learning_rate": 0.0005504210526315789,
1338
+ "loss": 0.0424,
1339
+ "step": 4775
1340
+ },
1341
+ {
1342
+ "epoch": 2.13,
1343
+ "learning_rate": 0.0005477894736842105,
1344
+ "loss": 0.0472,
1345
+ "step": 4800
1346
+ },
1347
+ {
1348
+ "epoch": 2.13,
1349
+ "eval_loss": 0.3975374102592468,
1350
+ "eval_runtime": 233.7801,
1351
+ "eval_samples_per_second": 4.278,
1352
+ "eval_steps_per_second": 0.269,
1353
+ "step": 4800
1354
+ },
1355
+ {
1356
+ "epoch": 2.13,
1357
+ "learning_rate": 0.0005451578947368421,
1358
+ "loss": 0.0418,
1359
+ "step": 4825
1360
+ },
1361
+ {
1362
+ "epoch": 2.13,
1363
+ "learning_rate": 0.0005425263157894737,
1364
+ "loss": 0.0435,
1365
+ "step": 4850
1366
+ },
1367
+ {
1368
+ "epoch": 2.13,
1369
+ "learning_rate": 0.0005398947368421053,
1370
+ "loss": 0.0459,
1371
+ "step": 4875
1372
+ },
1373
+ {
1374
+ "epoch": 2.14,
1375
+ "learning_rate": 0.0005372631578947368,
1376
+ "loss": 0.0457,
1377
+ "step": 4900
1378
+ },
1379
+ {
1380
+ "epoch": 2.14,
1381
+ "learning_rate": 0.0005346315789473685,
1382
+ "loss": 0.0429,
1383
+ "step": 4925
1384
+ },
1385
+ {
1386
+ "epoch": 2.14,
1387
+ "learning_rate": 0.000532,
1388
+ "loss": 0.0426,
1389
+ "step": 4950
1390
+ },
1391
+ {
1392
+ "epoch": 2.14,
1393
+ "learning_rate": 0.0005293684210526316,
1394
+ "loss": 0.0387,
1395
+ "step": 4975
1396
+ },
1397
+ {
1398
+ "epoch": 2.15,
1399
+ "learning_rate": 0.0005267368421052632,
1400
+ "loss": 0.0371,
1401
+ "step": 5000
1402
+ },
1403
+ {
1404
+ "epoch": 2.15,
1405
+ "eval_loss": 0.38193443417549133,
1406
+ "eval_runtime": 235.0403,
1407
+ "eval_samples_per_second": 4.255,
1408
+ "eval_steps_per_second": 0.268,
1409
+ "step": 5000
1410
+ },
1411
+ {
1412
+ "epoch": 2.15,
1413
+ "learning_rate": 0.0005241052631578948,
1414
+ "loss": 0.1203,
1415
+ "step": 5025
1416
+ },
1417
+ {
1418
+ "epoch": 2.15,
1419
+ "learning_rate": 0.0005214736842105263,
1420
+ "loss": 0.1324,
1421
+ "step": 5050
1422
+ },
1423
+ {
1424
+ "epoch": 2.15,
1425
+ "learning_rate": 0.0005188421052631579,
1426
+ "loss": 0.1544,
1427
+ "step": 5075
1428
+ },
1429
+ {
1430
+ "epoch": 2.16,
1431
+ "learning_rate": 0.0005162105263157895,
1432
+ "loss": 0.1441,
1433
+ "step": 5100
1434
+ },
1435
+ {
1436
+ "epoch": 2.16,
1437
+ "learning_rate": 0.000513578947368421,
1438
+ "loss": 0.1528,
1439
+ "step": 5125
1440
+ },
1441
+ {
1442
+ "epoch": 2.16,
1443
+ "learning_rate": 0.0005109473684210527,
1444
+ "loss": 0.176,
1445
+ "step": 5150
1446
+ },
1447
+ {
1448
+ "epoch": 2.16,
1449
+ "learning_rate": 0.0005083157894736842,
1450
+ "loss": 0.1425,
1451
+ "step": 5175
1452
+ },
1453
+ {
1454
+ "epoch": 2.17,
1455
+ "learning_rate": 0.0005056842105263157,
1456
+ "loss": 0.1266,
1457
+ "step": 5200
1458
+ },
1459
+ {
1460
+ "epoch": 2.17,
1461
+ "eval_loss": 0.2390679568052292,
1462
+ "eval_runtime": 228.9049,
1463
+ "eval_samples_per_second": 4.369,
1464
+ "eval_steps_per_second": 0.275,
1465
+ "step": 5200
1466
+ },
1467
+ {
1468
+ "epoch": 2.17,
1469
+ "learning_rate": 0.0005030526315789474,
1470
+ "loss": 0.1253,
1471
+ "step": 5225
1472
+ },
1473
+ {
1474
+ "epoch": 2.17,
1475
+ "learning_rate": 0.000500421052631579,
1476
+ "loss": 0.1176,
1477
+ "step": 5250
1478
+ },
1479
+ {
1480
+ "epoch": 2.17,
1481
+ "learning_rate": 0.0004977894736842106,
1482
+ "loss": 0.1122,
1483
+ "step": 5275
1484
+ },
1485
+ {
1486
+ "epoch": 2.18,
1487
+ "learning_rate": 0.0004951578947368421,
1488
+ "loss": 0.1195,
1489
+ "step": 5300
1490
+ },
1491
+ {
1492
+ "epoch": 3.0,
1493
+ "learning_rate": 0.0004925263157894737,
1494
+ "loss": 0.0519,
1495
+ "step": 5325
1496
+ },
1497
+ {
1498
+ "epoch": 3.0,
1499
+ "learning_rate": 0.0004898947368421053,
1500
+ "loss": 0.0397,
1501
+ "step": 5350
1502
+ },
1503
+ {
1504
+ "epoch": 3.01,
1505
+ "learning_rate": 0.0004872631578947369,
1506
+ "loss": 0.0439,
1507
+ "step": 5375
1508
+ },
1509
+ {
1510
+ "epoch": 3.01,
1511
+ "learning_rate": 0.0004846315789473684,
1512
+ "loss": 0.0467,
1513
+ "step": 5400
1514
+ },
1515
+ {
1516
+ "epoch": 3.01,
1517
+ "eval_loss": 0.3231227993965149,
1518
+ "eval_runtime": 236.2617,
1519
+ "eval_samples_per_second": 4.233,
1520
+ "eval_steps_per_second": 0.267,
1521
+ "step": 5400
1522
+ },
1523
+ {
1524
+ "epoch": 3.01,
1525
+ "learning_rate": 0.000482,
1526
+ "loss": 0.047,
1527
+ "step": 5425
1528
+ },
1529
+ {
1530
+ "epoch": 3.01,
1531
+ "learning_rate": 0.00047936842105263154,
1532
+ "loss": 0.0416,
1533
+ "step": 5450
1534
+ },
1535
+ {
1536
+ "epoch": 3.02,
1537
+ "learning_rate": 0.0004767368421052632,
1538
+ "loss": 0.0344,
1539
+ "step": 5475
1540
+ },
1541
+ {
1542
+ "epoch": 3.02,
1543
+ "learning_rate": 0.0004741052631578948,
1544
+ "loss": 0.0369,
1545
+ "step": 5500
1546
+ },
1547
+ {
1548
+ "epoch": 3.02,
1549
+ "learning_rate": 0.0004714736842105263,
1550
+ "loss": 0.0344,
1551
+ "step": 5525
1552
+ },
1553
+ {
1554
+ "epoch": 3.02,
1555
+ "learning_rate": 0.0004688421052631579,
1556
+ "loss": 0.0358,
1557
+ "step": 5550
1558
+ },
1559
+ {
1560
+ "epoch": 3.03,
1561
+ "learning_rate": 0.00046621052631578945,
1562
+ "loss": 0.0385,
1563
+ "step": 5575
1564
+ },
1565
+ {
1566
+ "epoch": 3.03,
1567
+ "learning_rate": 0.00046357894736842104,
1568
+ "loss": 0.0342,
1569
+ "step": 5600
1570
+ },
1571
+ {
1572
+ "epoch": 3.03,
1573
+ "eval_loss": 0.31728434562683105,
1574
+ "eval_runtime": 231.7415,
1575
+ "eval_samples_per_second": 4.315,
1576
+ "eval_steps_per_second": 0.272,
1577
+ "step": 5600
1578
+ },
1579
+ {
1580
+ "epoch": 3.03,
1581
+ "learning_rate": 0.00046094736842105263,
1582
+ "loss": 0.0345,
1583
+ "step": 5625
1584
+ },
1585
+ {
1586
+ "epoch": 3.03,
1587
+ "learning_rate": 0.0004583157894736842,
1588
+ "loss": 0.0377,
1589
+ "step": 5650
1590
+ },
1591
+ {
1592
+ "epoch": 3.04,
1593
+ "learning_rate": 0.0004556842105263158,
1594
+ "loss": 0.0313,
1595
+ "step": 5675
1596
+ },
1597
+ {
1598
+ "epoch": 3.04,
1599
+ "learning_rate": 0.00045305263157894736,
1600
+ "loss": 0.0337,
1601
+ "step": 5700
1602
+ },
1603
+ {
1604
+ "epoch": 3.04,
1605
+ "learning_rate": 0.00045042105263157895,
1606
+ "loss": 0.0312,
1607
+ "step": 5725
1608
+ },
1609
+ {
1610
+ "epoch": 3.04,
1611
+ "learning_rate": 0.00044778947368421054,
1612
+ "loss": 0.0349,
1613
+ "step": 5750
1614
+ },
1615
+ {
1616
+ "epoch": 3.05,
1617
+ "learning_rate": 0.0004451578947368421,
1618
+ "loss": 0.03,
1619
+ "step": 5775
1620
+ },
1621
+ {
1622
+ "epoch": 3.05,
1623
+ "learning_rate": 0.00044252631578947367,
1624
+ "loss": 0.0302,
1625
+ "step": 5800
1626
+ },
1627
+ {
1628
+ "epoch": 3.05,
1629
+ "eval_loss": 0.3289109170436859,
1630
+ "eval_runtime": 231.1941,
1631
+ "eval_samples_per_second": 4.325,
1632
+ "eval_steps_per_second": 0.272,
1633
+ "step": 5800
1634
+ },
1635
+ {
1636
+ "epoch": 3.05,
1637
+ "learning_rate": 0.0004398947368421053,
1638
+ "loss": 0.0314,
1639
+ "step": 5825
1640
+ },
1641
+ {
1642
+ "epoch": 3.05,
1643
+ "learning_rate": 0.00043726315789473685,
1644
+ "loss": 0.0298,
1645
+ "step": 5850
1646
+ },
1647
+ {
1648
+ "epoch": 3.06,
1649
+ "learning_rate": 0.00043463157894736845,
1650
+ "loss": 0.0343,
1651
+ "step": 5875
1652
+ },
1653
+ {
1654
+ "epoch": 3.06,
1655
+ "learning_rate": 0.000432,
1656
+ "loss": 0.0279,
1657
+ "step": 5900
1658
+ },
1659
+ {
1660
+ "epoch": 3.06,
1661
+ "learning_rate": 0.0004293684210526316,
1662
+ "loss": 0.029,
1663
+ "step": 5925
1664
+ },
1665
+ {
1666
+ "epoch": 3.06,
1667
+ "learning_rate": 0.00042673684210526317,
1668
+ "loss": 0.0325,
1669
+ "step": 5950
1670
+ },
1671
+ {
1672
+ "epoch": 3.07,
1673
+ "learning_rate": 0.00042410526315789476,
1674
+ "loss": 0.0286,
1675
+ "step": 5975
1676
+ },
1677
+ {
1678
+ "epoch": 3.07,
1679
+ "learning_rate": 0.00042147368421052635,
1680
+ "loss": 0.0288,
1681
+ "step": 6000
1682
+ },
1683
+ {
1684
+ "epoch": 3.07,
1685
+ "eval_loss": 0.33179327845573425,
1686
+ "eval_runtime": 229.5634,
1687
+ "eval_samples_per_second": 4.356,
1688
+ "eval_steps_per_second": 0.274,
1689
+ "step": 6000
1690
+ },
1691
+ {
1692
+ "epoch": 3.07,
1693
+ "learning_rate": 0.0004188421052631579,
1694
+ "loss": 0.0239,
1695
+ "step": 6025
1696
+ },
1697
+ {
1698
+ "epoch": 3.07,
1699
+ "learning_rate": 0.0004162105263157895,
1700
+ "loss": 0.03,
1701
+ "step": 6050
1702
+ },
1703
+ {
1704
+ "epoch": 3.08,
1705
+ "learning_rate": 0.0004135789473684211,
1706
+ "loss": 0.0267,
1707
+ "step": 6075
1708
+ },
1709
+ {
1710
+ "epoch": 3.08,
1711
+ "learning_rate": 0.0004109473684210526,
1712
+ "loss": 0.0243,
1713
+ "step": 6100
1714
+ },
1715
+ {
1716
+ "epoch": 3.08,
1717
+ "learning_rate": 0.0004083157894736842,
1718
+ "loss": 0.0265,
1719
+ "step": 6125
1720
+ },
1721
+ {
1722
+ "epoch": 3.08,
1723
+ "learning_rate": 0.0004056842105263158,
1724
+ "loss": 0.0286,
1725
+ "step": 6150
1726
+ },
1727
+ {
1728
+ "epoch": 3.09,
1729
+ "learning_rate": 0.0004030526315789474,
1730
+ "loss": 0.0229,
1731
+ "step": 6175
1732
+ },
1733
+ {
1734
+ "epoch": 3.09,
1735
+ "learning_rate": 0.000400421052631579,
1736
+ "loss": 0.0236,
1737
+ "step": 6200
1738
+ },
1739
+ {
1740
+ "epoch": 3.09,
1741
+ "eval_loss": 0.3390714228153229,
1742
+ "eval_runtime": 232.9846,
1743
+ "eval_samples_per_second": 4.292,
1744
+ "eval_steps_per_second": 0.27,
1745
+ "step": 6200
1746
+ },
1747
+ {
1748
+ "epoch": 3.09,
1749
+ "learning_rate": 0.0003977894736842105,
1750
+ "loss": 0.0225,
1751
+ "step": 6225
1752
+ },
1753
+ {
1754
+ "epoch": 3.09,
1755
+ "learning_rate": 0.0003951578947368421,
1756
+ "loss": 0.0241,
1757
+ "step": 6250
1758
+ },
1759
+ {
1760
+ "epoch": 3.1,
1761
+ "learning_rate": 0.0003925263157894737,
1762
+ "loss": 0.0253,
1763
+ "step": 6275
1764
+ },
1765
+ {
1766
+ "epoch": 3.1,
1767
+ "learning_rate": 0.00038989473684210524,
1768
+ "loss": 0.0241,
1769
+ "step": 6300
1770
+ },
1771
+ {
1772
+ "epoch": 3.1,
1773
+ "learning_rate": 0.0003872631578947369,
1774
+ "loss": 0.0231,
1775
+ "step": 6325
1776
+ },
1777
+ {
1778
+ "epoch": 3.1,
1779
+ "learning_rate": 0.0003846315789473684,
1780
+ "loss": 0.0212,
1781
+ "step": 6350
1782
+ },
1783
+ {
1784
+ "epoch": 3.11,
1785
+ "learning_rate": 0.000382,
1786
+ "loss": 0.0209,
1787
+ "step": 6375
1788
+ },
1789
+ {
1790
+ "epoch": 3.11,
1791
+ "learning_rate": 0.0003793684210526316,
1792
+ "loss": 0.0223,
1793
+ "step": 6400
1794
+ },
1795
+ {
1796
+ "epoch": 3.11,
1797
+ "eval_loss": 0.35378792881965637,
1798
+ "eval_runtime": 234.1666,
1799
+ "eval_samples_per_second": 4.27,
1800
+ "eval_steps_per_second": 0.269,
1801
+ "step": 6400
1802
+ },
1803
+ {
1804
+ "epoch": 3.11,
1805
+ "learning_rate": 0.00037673684210526315,
1806
+ "loss": 0.0241,
1807
+ "step": 6425
1808
+ },
1809
+ {
1810
+ "epoch": 3.11,
1811
+ "learning_rate": 0.00037410526315789474,
1812
+ "loss": 0.0206,
1813
+ "step": 6450
1814
+ },
1815
+ {
1816
+ "epoch": 3.12,
1817
+ "learning_rate": 0.0003714736842105263,
1818
+ "loss": 0.0206,
1819
+ "step": 6475
1820
+ },
1821
+ {
1822
+ "epoch": 3.12,
1823
+ "learning_rate": 0.0003688421052631579,
1824
+ "loss": 0.0234,
1825
+ "step": 6500
1826
+ },
1827
+ {
1828
+ "epoch": 3.12,
1829
+ "learning_rate": 0.0003662105263157895,
1830
+ "loss": 0.0185,
1831
+ "step": 6525
1832
+ },
1833
+ {
1834
+ "epoch": 3.12,
1835
+ "learning_rate": 0.00036357894736842105,
1836
+ "loss": 0.0205,
1837
+ "step": 6550
1838
+ },
1839
+ {
1840
+ "epoch": 3.13,
1841
+ "learning_rate": 0.00036094736842105264,
1842
+ "loss": 0.0217,
1843
+ "step": 6575
1844
+ },
1845
+ {
1846
+ "epoch": 3.13,
1847
+ "learning_rate": 0.0003583157894736842,
1848
+ "loss": 0.023,
1849
+ "step": 6600
1850
+ },
1851
+ {
1852
+ "epoch": 3.13,
1853
+ "eval_loss": 0.3395112156867981,
1854
+ "eval_runtime": 232.7288,
1855
+ "eval_samples_per_second": 4.297,
1856
+ "eval_steps_per_second": 0.271,
1857
+ "step": 6600
1858
+ },
1859
+ {
1860
+ "epoch": 3.13,
1861
+ "learning_rate": 0.00035568421052631577,
1862
+ "loss": 0.0209,
1863
+ "step": 6625
1864
+ },
1865
+ {
1866
+ "epoch": 3.13,
1867
+ "learning_rate": 0.0003530526315789474,
1868
+ "loss": 0.0195,
1869
+ "step": 6650
1870
+ },
1871
+ {
1872
+ "epoch": 3.14,
1873
+ "learning_rate": 0.00035042105263157896,
1874
+ "loss": 0.0223,
1875
+ "step": 6675
1876
+ },
1877
+ {
1878
+ "epoch": 3.14,
1879
+ "learning_rate": 0.00034778947368421055,
1880
+ "loss": 0.0231,
1881
+ "step": 6700
1882
+ },
1883
+ {
1884
+ "epoch": 3.14,
1885
+ "learning_rate": 0.00034515789473684214,
1886
+ "loss": 0.021,
1887
+ "step": 6725
1888
+ },
1889
+ {
1890
+ "epoch": 3.14,
1891
+ "learning_rate": 0.0003425263157894737,
1892
+ "loss": 0.0234,
1893
+ "step": 6750
1894
+ },
1895
+ {
1896
+ "epoch": 3.15,
1897
+ "learning_rate": 0.00033989473684210527,
1898
+ "loss": 0.0281,
1899
+ "step": 6775
1900
+ },
1901
+ {
1902
+ "epoch": 3.15,
1903
+ "learning_rate": 0.0003372631578947368,
1904
+ "loss": 0.0652,
1905
+ "step": 6800
1906
+ },
1907
+ {
1908
+ "epoch": 3.15,
1909
+ "eval_loss": 0.2487945556640625,
1910
+ "eval_runtime": 234.5765,
1911
+ "eval_samples_per_second": 4.263,
1912
+ "eval_steps_per_second": 0.269,
1913
+ "step": 6800
1914
+ },
1915
+ {
1916
+ "epoch": 3.15,
1917
+ "learning_rate": 0.00033463157894736845,
1918
+ "loss": 0.069,
1919
+ "step": 6825
1920
+ },
1921
+ {
1922
+ "epoch": 3.15,
1923
+ "learning_rate": 0.00033200000000000005,
1924
+ "loss": 0.0776,
1925
+ "step": 6850
1926
+ },
1927
+ {
1928
+ "epoch": 3.16,
1929
+ "learning_rate": 0.0003293684210526316,
1930
+ "loss": 0.0736,
1931
+ "step": 6875
1932
+ },
1933
+ {
1934
+ "epoch": 3.16,
1935
+ "learning_rate": 0.0003267368421052632,
1936
+ "loss": 0.0746,
1937
+ "step": 6900
1938
+ },
1939
+ {
1940
+ "epoch": 3.16,
1941
+ "learning_rate": 0.0003241052631578947,
1942
+ "loss": 0.0903,
1943
+ "step": 6925
1944
+ },
1945
+ {
1946
+ "epoch": 3.16,
1947
+ "learning_rate": 0.0003214736842105263,
1948
+ "loss": 0.073,
1949
+ "step": 6950
1950
+ },
1951
+ {
1952
+ "epoch": 3.17,
1953
+ "learning_rate": 0.0003188421052631579,
1954
+ "loss": 0.0624,
1955
+ "step": 6975
1956
+ },
1957
+ {
1958
+ "epoch": 3.17,
1959
+ "learning_rate": 0.0003162105263157895,
1960
+ "loss": 0.0585,
1961
+ "step": 7000
1962
+ },
1963
+ {
1964
+ "epoch": 3.17,
1965
+ "eval_loss": 0.23527191579341888,
1966
+ "eval_runtime": 232.506,
1967
+ "eval_samples_per_second": 4.301,
1968
+ "eval_steps_per_second": 0.271,
1969
+ "step": 7000
1970
+ },
1971
+ {
1972
+ "epoch": 3.17,
1973
+ "learning_rate": 0.0003135789473684211,
1974
+ "loss": 0.055,
1975
+ "step": 7025
1976
+ },
1977
+ {
1978
+ "epoch": 3.17,
1979
+ "learning_rate": 0.0003109473684210526,
1980
+ "loss": 0.0531,
1981
+ "step": 7050
1982
+ },
1983
+ {
1984
+ "epoch": 4.0,
1985
+ "learning_rate": 0.0003083157894736842,
1986
+ "loss": 0.05,
1987
+ "step": 7075
1988
+ },
1989
+ {
1990
+ "epoch": 4.0,
1991
+ "learning_rate": 0.0003056842105263158,
1992
+ "loss": 0.0237,
1993
+ "step": 7100
1994
+ },
1995
+ {
1996
+ "epoch": 4.01,
1997
+ "learning_rate": 0.00030305263157894734,
1998
+ "loss": 0.0206,
1999
+ "step": 7125
2000
+ },
2001
+ {
2002
+ "epoch": 4.01,
2003
+ "learning_rate": 0.00030042105263157893,
2004
+ "loss": 0.0197,
2005
+ "step": 7150
2006
+ },
2007
+ {
2008
+ "epoch": 4.01,
2009
+ "learning_rate": 0.0002977894736842106,
2010
+ "loss": 0.0209,
2011
+ "step": 7175
2012
+ },
2013
+ {
2014
+ "epoch": 4.01,
2015
+ "learning_rate": 0.0002951578947368421,
2016
+ "loss": 0.0219,
2017
+ "step": 7200
2018
+ },
2019
+ {
2020
+ "epoch": 4.01,
2021
+ "eval_loss": 0.29737773537635803,
2022
+ "eval_runtime": 231.2741,
2023
+ "eval_samples_per_second": 4.324,
2024
+ "eval_steps_per_second": 0.272,
2025
+ "step": 7200
2026
+ },
2027
+ {
2028
+ "epoch": 4.02,
2029
+ "learning_rate": 0.0002925263157894737,
2030
+ "loss": 0.02,
2031
+ "step": 7225
2032
+ },
2033
+ {
2034
+ "epoch": 4.02,
2035
+ "learning_rate": 0.00028989473684210525,
2036
+ "loss": 0.0158,
2037
+ "step": 7250
2038
+ },
2039
+ {
2040
+ "epoch": 4.02,
2041
+ "learning_rate": 0.00028726315789473684,
2042
+ "loss": 0.0175,
2043
+ "step": 7275
2044
+ },
2045
+ {
2046
+ "epoch": 4.02,
2047
+ "learning_rate": 0.00028463157894736843,
2048
+ "loss": 0.0152,
2049
+ "step": 7300
2050
+ },
2051
+ {
2052
+ "epoch": 4.03,
2053
+ "learning_rate": 0.00028199999999999997,
2054
+ "loss": 0.0176,
2055
+ "step": 7325
2056
+ },
2057
+ {
2058
+ "epoch": 4.03,
2059
+ "learning_rate": 0.0002793684210526316,
2060
+ "loss": 0.0146,
2061
+ "step": 7350
2062
+ },
2063
+ {
2064
+ "epoch": 4.03,
2065
+ "learning_rate": 0.00027673684210526315,
2066
+ "loss": 0.0141,
2067
+ "step": 7375
2068
+ },
2069
+ {
2070
+ "epoch": 4.03,
2071
+ "learning_rate": 0.00027410526315789475,
2072
+ "loss": 0.0171,
2073
+ "step": 7400
2074
+ },
2075
+ {
2076
+ "epoch": 4.03,
2077
+ "eval_loss": 0.3058754801750183,
2078
+ "eval_runtime": 236.0616,
2079
+ "eval_samples_per_second": 4.236,
2080
+ "eval_steps_per_second": 0.267,
2081
+ "step": 7400
2082
+ },
2083
+ {
2084
+ "epoch": 4.04,
2085
+ "learning_rate": 0.00027147368421052634,
2086
+ "loss": 0.0159,
2087
+ "step": 7425
2088
+ },
2089
+ {
2090
+ "epoch": 4.04,
2091
+ "learning_rate": 0.0002688421052631579,
2092
+ "loss": 0.0155,
2093
+ "step": 7450
2094
+ },
2095
+ {
2096
+ "epoch": 4.04,
2097
+ "learning_rate": 0.00026621052631578947,
2098
+ "loss": 0.014,
2099
+ "step": 7475
2100
+ },
2101
+ {
2102
+ "epoch": 4.04,
2103
+ "learning_rate": 0.00026357894736842106,
2104
+ "loss": 0.0141,
2105
+ "step": 7500
2106
+ },
2107
+ {
2108
+ "epoch": 4.05,
2109
+ "learning_rate": 0.00026094736842105265,
2110
+ "loss": 0.0157,
2111
+ "step": 7525
2112
+ },
2113
+ {
2114
+ "epoch": 4.05,
2115
+ "learning_rate": 0.00025831578947368424,
2116
+ "loss": 0.0128,
2117
+ "step": 7550
2118
+ },
2119
+ {
2120
+ "epoch": 4.05,
2121
+ "learning_rate": 0.0002556842105263158,
2122
+ "loss": 0.0152,
2123
+ "step": 7575
2124
+ },
2125
+ {
2126
+ "epoch": 4.05,
2127
+ "learning_rate": 0.0002530526315789474,
2128
+ "loss": 0.0146,
2129
+ "step": 7600
2130
+ },
2131
+ {
2132
+ "epoch": 4.05,
2133
+ "eval_loss": 0.30549487471580505,
2134
+ "eval_runtime": 230.3772,
2135
+ "eval_samples_per_second": 4.341,
2136
+ "eval_steps_per_second": 0.273,
2137
+ "step": 7600
2138
+ },
2139
+ {
2140
+ "epoch": 4.06,
2141
+ "learning_rate": 0.0002504210526315789,
2142
+ "loss": 0.0168,
2143
+ "step": 7625
2144
+ },
2145
+ {
2146
+ "epoch": 4.06,
2147
+ "learning_rate": 0.00024778947368421056,
2148
+ "loss": 0.0149,
2149
+ "step": 7650
2150
+ },
2151
+ {
2152
+ "epoch": 4.06,
2153
+ "learning_rate": 0.0002451578947368421,
2154
+ "loss": 0.0136,
2155
+ "step": 7675
2156
+ },
2157
+ {
2158
+ "epoch": 4.06,
2159
+ "learning_rate": 0.0002425263157894737,
2160
+ "loss": 0.0131,
2161
+ "step": 7700
2162
+ },
2163
+ {
2164
+ "epoch": 4.07,
2165
+ "learning_rate": 0.00023989473684210528,
2166
+ "loss": 0.0138,
2167
+ "step": 7725
2168
+ },
2169
+ {
2170
+ "epoch": 4.07,
2171
+ "learning_rate": 0.00023726315789473684,
2172
+ "loss": 0.0128,
2173
+ "step": 7750
2174
+ },
2175
+ {
2176
+ "epoch": 4.07,
2177
+ "learning_rate": 0.0002346315789473684,
2178
+ "loss": 0.0129,
2179
+ "step": 7775
2180
+ },
2181
+ {
2182
+ "epoch": 4.07,
2183
+ "learning_rate": 0.00023200000000000003,
2184
+ "loss": 0.0123,
2185
+ "step": 7800
2186
+ },
2187
+ {
2188
+ "epoch": 4.07,
2189
+ "eval_loss": 0.3095347583293915,
2190
+ "eval_runtime": 230.2124,
2191
+ "eval_samples_per_second": 4.344,
2192
+ "eval_steps_per_second": 0.274,
2193
+ "step": 7800
2194
+ },
2195
+ {
2196
+ "epoch": 4.08,
2197
+ "learning_rate": 0.0002293684210526316,
2198
+ "loss": 0.0123,
2199
+ "step": 7825
2200
+ },
2201
+ {
2202
+ "epoch": 4.08,
2203
+ "learning_rate": 0.00022673684210526316,
2204
+ "loss": 0.0109,
2205
+ "step": 7850
2206
+ },
2207
+ {
2208
+ "epoch": 4.08,
2209
+ "learning_rate": 0.00022410526315789472,
2210
+ "loss": 0.0124,
2211
+ "step": 7875
2212
+ },
2213
+ {
2214
+ "epoch": 4.08,
2215
+ "learning_rate": 0.00022147368421052632,
2216
+ "loss": 0.0123,
2217
+ "step": 7900
2218
+ },
2219
+ {
2220
+ "epoch": 4.09,
2221
+ "learning_rate": 0.0002188421052631579,
2222
+ "loss": 0.011,
2223
+ "step": 7925
2224
+ },
2225
+ {
2226
+ "epoch": 4.09,
2227
+ "learning_rate": 0.00021621052631578947,
2228
+ "loss": 0.0109,
2229
+ "step": 7950
2230
+ },
2231
+ {
2232
+ "epoch": 4.09,
2233
+ "learning_rate": 0.00021357894736842106,
2234
+ "loss": 0.0113,
2235
+ "step": 7975
2236
+ },
2237
+ {
2238
+ "epoch": 4.09,
2239
+ "learning_rate": 0.00021094736842105263,
2240
+ "loss": 0.0102,
2241
+ "step": 8000
2242
+ },
2243
+ {
2244
+ "epoch": 4.09,
2245
+ "eval_loss": 0.3172641098499298,
2246
+ "eval_runtime": 232.1001,
2247
+ "eval_samples_per_second": 4.308,
2248
+ "eval_steps_per_second": 0.271,
2249
+ "step": 8000
2250
+ },
2251
+ {
2252
+ "epoch": 4.1,
2253
+ "learning_rate": 0.00020831578947368422,
2254
+ "loss": 0.0126,
2255
+ "step": 8025
2256
+ },
2257
+ {
2258
+ "epoch": 4.1,
2259
+ "learning_rate": 0.0002056842105263158,
2260
+ "loss": 0.0105,
2261
+ "step": 8050
2262
+ },
2263
+ {
2264
+ "epoch": 4.1,
2265
+ "learning_rate": 0.00020305263157894738,
2266
+ "loss": 0.0113,
2267
+ "step": 8075
2268
+ },
2269
+ {
2270
+ "epoch": 4.1,
2271
+ "learning_rate": 0.00020042105263157894,
2272
+ "loss": 0.0108,
2273
+ "step": 8100
2274
+ },
2275
+ {
2276
+ "epoch": 4.11,
2277
+ "learning_rate": 0.0001977894736842105,
2278
+ "loss": 0.0097,
2279
+ "step": 8125
2280
+ },
2281
+ {
2282
+ "epoch": 4.11,
2283
+ "learning_rate": 0.00019515789473684213,
2284
+ "loss": 0.0112,
2285
+ "step": 8150
2286
+ },
2287
+ {
2288
+ "epoch": 4.11,
2289
+ "learning_rate": 0.0001925263157894737,
2290
+ "loss": 0.0103,
2291
+ "step": 8175
2292
+ },
2293
+ {
2294
+ "epoch": 4.11,
2295
+ "learning_rate": 0.00018989473684210526,
2296
+ "loss": 0.0106,
2297
+ "step": 8200
2298
+ },
2299
+ {
2300
+ "epoch": 4.11,
2301
+ "eval_loss": 0.31945887207984924,
2302
+ "eval_runtime": 268.0042,
2303
+ "eval_samples_per_second": 3.731,
2304
+ "eval_steps_per_second": 0.235,
2305
+ "step": 8200
2306
+ },
2307
+ {
2308
+ "epoch": 4.12,
2309
+ "learning_rate": 0.00018726315789473685,
2310
+ "loss": 0.0094,
2311
+ "step": 8225
2312
+ },
2313
+ {
2314
+ "epoch": 4.12,
2315
+ "learning_rate": 0.00018463157894736844,
2316
+ "loss": 0.0099,
2317
+ "step": 8250
2318
+ },
2319
+ {
2320
+ "epoch": 4.12,
2321
+ "learning_rate": 0.000182,
2322
+ "loss": 0.0103,
2323
+ "step": 8275
2324
+ },
2325
+ {
2326
+ "epoch": 4.12,
2327
+ "learning_rate": 0.00017936842105263157,
2328
+ "loss": 0.0091,
2329
+ "step": 8300
2330
+ },
2331
+ {
2332
+ "epoch": 4.13,
2333
+ "learning_rate": 0.00017673684210526316,
2334
+ "loss": 0.0083,
2335
+ "step": 8325
2336
+ },
2337
+ {
2338
+ "epoch": 4.13,
2339
+ "learning_rate": 0.00017410526315789473,
2340
+ "loss": 0.0091,
2341
+ "step": 8350
2342
+ },
2343
+ {
2344
+ "epoch": 4.13,
2345
+ "learning_rate": 0.00017147368421052632,
2346
+ "loss": 0.0093,
2347
+ "step": 8375
2348
+ },
2349
+ {
2350
+ "epoch": 4.13,
2351
+ "learning_rate": 0.0001688421052631579,
2352
+ "loss": 0.0093,
2353
+ "step": 8400
2354
+ },
2355
+ {
2356
+ "epoch": 4.13,
2357
+ "eval_loss": 0.3215804398059845,
2358
+ "eval_runtime": 237.5836,
2359
+ "eval_samples_per_second": 4.209,
2360
+ "eval_steps_per_second": 0.265,
2361
+ "step": 8400
2362
+ },
2363
+ {
2364
+ "epoch": 4.14,
2365
+ "learning_rate": 0.00016621052631578948,
2366
+ "loss": 0.0095,
2367
+ "step": 8425
2368
+ },
2369
+ {
2370
+ "epoch": 4.14,
2371
+ "learning_rate": 0.00016357894736842104,
2372
+ "loss": 0.0104,
2373
+ "step": 8450
2374
+ },
2375
+ {
2376
+ "epoch": 4.14,
2377
+ "learning_rate": 0.00016094736842105266,
2378
+ "loss": 0.0091,
2379
+ "step": 8475
2380
+ },
2381
+ {
2382
+ "epoch": 4.14,
2383
+ "learning_rate": 0.00015831578947368423,
2384
+ "loss": 0.0083,
2385
+ "step": 8500
2386
+ },
2387
+ {
2388
+ "epoch": 4.15,
2389
+ "learning_rate": 0.0001556842105263158,
2390
+ "loss": 0.0087,
2391
+ "step": 8525
2392
+ },
2393
+ {
2394
+ "epoch": 4.15,
2395
+ "learning_rate": 0.00015305263157894736,
2396
+ "loss": 0.0158,
2397
+ "step": 8550
2398
+ },
2399
+ {
2400
+ "epoch": 4.15,
2401
+ "learning_rate": 0.00015042105263157895,
2402
+ "loss": 0.0306,
2403
+ "step": 8575
2404
+ },
2405
+ {
2406
+ "epoch": 4.15,
2407
+ "learning_rate": 0.00014778947368421054,
2408
+ "loss": 0.0323,
2409
+ "step": 8600
2410
+ },
2411
+ {
2412
+ "epoch": 4.15,
2413
+ "eval_loss": 0.244441956281662,
2414
+ "eval_runtime": 237.4283,
2415
+ "eval_samples_per_second": 4.212,
2416
+ "eval_steps_per_second": 0.265,
2417
+ "step": 8600
2418
+ },
2419
+ {
2420
+ "epoch": 4.16,
2421
+ "learning_rate": 0.0001451578947368421,
2422
+ "loss": 0.0321,
2423
+ "step": 8625
2424
+ },
2425
+ {
2426
+ "epoch": 4.16,
2427
+ "learning_rate": 0.0001425263157894737,
2428
+ "loss": 0.0313,
2429
+ "step": 8650
2430
+ },
2431
+ {
2432
+ "epoch": 4.16,
2433
+ "learning_rate": 0.00013989473684210526,
2434
+ "loss": 0.0363,
2435
+ "step": 8675
2436
+ },
2437
+ {
2438
+ "epoch": 4.16,
2439
+ "learning_rate": 0.00013726315789473685,
2440
+ "loss": 0.0329,
2441
+ "step": 8700
2442
+ },
2443
+ {
2444
+ "epoch": 4.17,
2445
+ "learning_rate": 0.00013463157894736842,
2446
+ "loss": 0.0294,
2447
+ "step": 8725
2448
+ },
2449
+ {
2450
+ "epoch": 4.17,
2451
+ "learning_rate": 0.000132,
2452
+ "loss": 0.0255,
2453
+ "step": 8750
2454
+ },
2455
+ {
2456
+ "epoch": 4.17,
2457
+ "learning_rate": 0.00012936842105263158,
2458
+ "loss": 0.0213,
2459
+ "step": 8775
2460
+ },
2461
+ {
2462
+ "epoch": 4.17,
2463
+ "learning_rate": 0.00012673684210526314,
2464
+ "loss": 0.023,
2465
+ "step": 8800
2466
+ },
2467
+ {
2468
+ "epoch": 4.17,
2469
+ "eval_loss": 0.2333984673023224,
2470
+ "eval_runtime": 235.211,
2471
+ "eval_samples_per_second": 4.252,
2472
+ "eval_steps_per_second": 0.268,
2473
+ "step": 8800
2474
+ },
2475
+ {
2476
+ "epoch": 4.18,
2477
+ "learning_rate": 0.00012410526315789473,
2478
+ "loss": 0.0227,
2479
+ "step": 8825
2480
+ },
2481
+ {
2482
+ "epoch": 5.0,
2483
+ "learning_rate": 0.00012147368421052632,
2484
+ "loss": 0.0157,
2485
+ "step": 8850
2486
+ },
2487
+ {
2488
+ "epoch": 5.0,
2489
+ "learning_rate": 0.00011884210526315789,
2490
+ "loss": 0.0108,
2491
+ "step": 8875
2492
+ },
2493
+ {
2494
+ "epoch": 5.01,
2495
+ "learning_rate": 0.00011621052631578948,
2496
+ "loss": 0.01,
2497
+ "step": 8900
2498
+ },
2499
+ {
2500
+ "epoch": 5.01,
2501
+ "learning_rate": 0.00011357894736842106,
2502
+ "loss": 0.0092,
2503
+ "step": 8925
2504
+ },
2505
+ {
2506
+ "epoch": 5.01,
2507
+ "learning_rate": 0.00011094736842105262,
2508
+ "loss": 0.0093,
2509
+ "step": 8950
2510
+ },
2511
+ {
2512
+ "epoch": 5.01,
2513
+ "learning_rate": 0.00010831578947368422,
2514
+ "loss": 0.0112,
2515
+ "step": 8975
2516
+ },
2517
+ {
2518
+ "epoch": 5.02,
2519
+ "learning_rate": 0.00010568421052631578,
2520
+ "loss": 0.0082,
2521
+ "step": 9000
2522
+ },
2523
+ {
2524
+ "epoch": 5.02,
2525
+ "eval_loss": 0.2606710195541382,
2526
+ "eval_runtime": 238.1871,
2527
+ "eval_samples_per_second": 4.198,
2528
+ "eval_steps_per_second": 0.264,
2529
+ "step": 9000
2530
+ },
2531
+ {
2532
+ "epoch": 5.02,
2533
+ "learning_rate": 0.00010305263157894737,
2534
+ "loss": 0.0078,
2535
+ "step": 9025
2536
+ },
2537
+ {
2538
+ "epoch": 5.02,
2539
+ "learning_rate": 0.00010042105263157895,
2540
+ "loss": 0.0084,
2541
+ "step": 9050
2542
+ },
2543
+ {
2544
+ "epoch": 5.02,
2545
+ "learning_rate": 9.778947368421053e-05,
2546
+ "loss": 0.0069,
2547
+ "step": 9075
2548
+ },
2549
+ {
2550
+ "epoch": 5.03,
2551
+ "learning_rate": 9.515789473684211e-05,
2552
+ "loss": 0.0071,
2553
+ "step": 9100
2554
+ },
2555
+ {
2556
+ "epoch": 5.03,
2557
+ "learning_rate": 9.252631578947369e-05,
2558
+ "loss": 0.0068,
2559
+ "step": 9125
2560
+ },
2561
+ {
2562
+ "epoch": 5.03,
2563
+ "learning_rate": 8.989473684210527e-05,
2564
+ "loss": 0.0069,
2565
+ "step": 9150
2566
+ },
2567
+ {
2568
+ "epoch": 5.03,
2569
+ "learning_rate": 8.726315789473684e-05,
2570
+ "loss": 0.0081,
2571
+ "step": 9175
2572
+ },
2573
+ {
2574
+ "epoch": 5.04,
2575
+ "learning_rate": 8.463157894736842e-05,
2576
+ "loss": 0.0069,
2577
+ "step": 9200
2578
+ },
2579
+ {
2580
+ "epoch": 5.04,
2581
+ "eval_loss": 0.26959776878356934,
2582
+ "eval_runtime": 236.0274,
2583
+ "eval_samples_per_second": 4.237,
2584
+ "eval_steps_per_second": 0.267,
2585
+ "step": 9200
2586
+ },
2587
+ {
2588
+ "epoch": 5.04,
2589
+ "learning_rate": 8.2e-05,
2590
+ "loss": 0.0073,
2591
+ "step": 9225
2592
+ },
2593
+ {
2594
+ "epoch": 5.04,
2595
+ "learning_rate": 7.936842105263158e-05,
2596
+ "loss": 0.0065,
2597
+ "step": 9250
2598
+ },
2599
+ {
2600
+ "epoch": 5.04,
2601
+ "learning_rate": 7.673684210526316e-05,
2602
+ "loss": 0.0067,
2603
+ "step": 9275
2604
+ },
2605
+ {
2606
+ "epoch": 5.05,
2607
+ "learning_rate": 7.410526315789475e-05,
2608
+ "loss": 0.0067,
2609
+ "step": 9300
2610
+ },
2611
+ {
2612
+ "epoch": 5.05,
2613
+ "learning_rate": 7.147368421052631e-05,
2614
+ "loss": 0.0058,
2615
+ "step": 9325
2616
+ },
2617
+ {
2618
+ "epoch": 5.05,
2619
+ "learning_rate": 6.884210526315791e-05,
2620
+ "loss": 0.0078,
2621
+ "step": 9350
2622
+ },
2623
+ {
2624
+ "epoch": 5.05,
2625
+ "learning_rate": 6.621052631578947e-05,
2626
+ "loss": 0.0068,
2627
+ "step": 9375
2628
+ },
2629
+ {
2630
+ "epoch": 5.06,
2631
+ "learning_rate": 6.357894736842105e-05,
2632
+ "loss": 0.008,
2633
+ "step": 9400
2634
+ },
2635
+ {
2636
+ "epoch": 5.06,
2637
+ "eval_loss": 0.2715131342411041,
2638
+ "eval_runtime": 235.3933,
2639
+ "eval_samples_per_second": 4.248,
2640
+ "eval_steps_per_second": 0.268,
2641
+ "step": 9400
2642
+ },
2643
+ {
2644
+ "epoch": 5.06,
2645
+ "learning_rate": 6.0947368421052635e-05,
2646
+ "loss": 0.0065,
2647
+ "step": 9425
2648
+ },
2649
+ {
2650
+ "epoch": 5.06,
2651
+ "learning_rate": 5.8315789473684214e-05,
2652
+ "loss": 0.0065,
2653
+ "step": 9450
2654
+ },
2655
+ {
2656
+ "epoch": 5.06,
2657
+ "learning_rate": 5.5684210526315786e-05,
2658
+ "loss": 0.0072,
2659
+ "step": 9475
2660
+ },
2661
+ {
2662
+ "epoch": 5.07,
2663
+ "learning_rate": 5.3052631578947364e-05,
2664
+ "loss": 0.0055,
2665
+ "step": 9500
2666
+ },
2667
+ {
2668
+ "epoch": 5.07,
2669
+ "learning_rate": 5.042105263157895e-05,
2670
+ "loss": 0.0069,
2671
+ "step": 9525
2672
+ },
2673
+ {
2674
+ "epoch": 5.07,
2675
+ "learning_rate": 4.778947368421053e-05,
2676
+ "loss": 0.0074,
2677
+ "step": 9550
2678
+ },
2679
+ {
2680
+ "epoch": 5.07,
2681
+ "learning_rate": 4.5157894736842106e-05,
2682
+ "loss": 0.006,
2683
+ "step": 9575
2684
+ },
2685
+ {
2686
+ "epoch": 5.08,
2687
+ "learning_rate": 4.2526315789473685e-05,
2688
+ "loss": 0.0068,
2689
+ "step": 9600
2690
+ },
2691
+ {
2692
+ "epoch": 5.08,
2693
+ "eval_loss": 0.27589207887649536,
2694
+ "eval_runtime": 232.1651,
2695
+ "eval_samples_per_second": 4.307,
2696
+ "eval_steps_per_second": 0.271,
2697
+ "step": 9600
2698
+ },
2699
+ {
2700
+ "epoch": 5.08,
2701
+ "learning_rate": 3.989473684210526e-05,
2702
+ "loss": 0.0057,
2703
+ "step": 9625
2704
+ },
2705
+ {
2706
+ "epoch": 5.08,
2707
+ "learning_rate": 3.726315789473685e-05,
2708
+ "loss": 0.0061,
2709
+ "step": 9650
2710
+ },
2711
+ {
2712
+ "epoch": 5.08,
2713
+ "learning_rate": 3.463157894736843e-05,
2714
+ "loss": 0.0056,
2715
+ "step": 9675
2716
+ },
2717
+ {
2718
+ "epoch": 5.09,
2719
+ "learning_rate": 3.2e-05,
2720
+ "loss": 0.0056,
2721
+ "step": 9700
2722
+ },
2723
+ {
2724
+ "epoch": 5.09,
2725
+ "learning_rate": 2.936842105263158e-05,
2726
+ "loss": 0.0056,
2727
+ "step": 9725
2728
+ },
2729
+ {
2730
+ "epoch": 5.09,
2731
+ "learning_rate": 2.673684210526316e-05,
2732
+ "loss": 0.0064,
2733
+ "step": 9750
2734
+ },
2735
+ {
2736
+ "epoch": 5.09,
2737
+ "learning_rate": 2.4105263157894737e-05,
2738
+ "loss": 0.0057,
2739
+ "step": 9775
2740
+ },
2741
+ {
2742
+ "epoch": 5.1,
2743
+ "learning_rate": 2.1473684210526316e-05,
2744
+ "loss": 0.0061,
2745
+ "step": 9800
2746
+ },
2747
+ {
2748
+ "epoch": 5.1,
2749
+ "eval_loss": 0.27701282501220703,
2750
+ "eval_runtime": 227.6759,
2751
+ "eval_samples_per_second": 4.392,
2752
+ "eval_steps_per_second": 0.277,
2753
+ "step": 9800
2754
+ },
2755
+ {
2756
+ "epoch": 5.1,
2757
+ "learning_rate": 1.8842105263157898e-05,
2758
+ "loss": 0.0055,
2759
+ "step": 9825
2760
+ },
2761
+ {
2762
+ "epoch": 5.1,
2763
+ "learning_rate": 1.6210526315789473e-05,
2764
+ "loss": 0.0059,
2765
+ "step": 9850
2766
+ },
2767
+ {
2768
+ "epoch": 5.1,
2769
+ "learning_rate": 1.3578947368421053e-05,
2770
+ "loss": 0.0054,
2771
+ "step": 9875
2772
+ },
2773
+ {
2774
+ "epoch": 5.11,
2775
+ "learning_rate": 1.0947368421052631e-05,
2776
+ "loss": 0.005,
2777
+ "step": 9900
2778
+ },
2779
+ {
2780
+ "epoch": 5.11,
2781
+ "learning_rate": 8.31578947368421e-06,
2782
+ "loss": 0.0054,
2783
+ "step": 9925
2784
+ },
2785
+ {
2786
+ "epoch": 5.11,
2787
+ "learning_rate": 5.68421052631579e-06,
2788
+ "loss": 0.0055,
2789
+ "step": 9950
2790
+ },
2791
+ {
2792
+ "epoch": 5.11,
2793
+ "learning_rate": 3.0526315789473684e-06,
2794
+ "loss": 0.0048,
2795
+ "step": 9975
2796
+ },
2797
+ {
2798
+ "epoch": 5.12,
2799
+ "learning_rate": 4.210526315789474e-07,
2800
+ "loss": 0.0046,
2801
+ "step": 10000
2802
+ },
2803
+ {
2804
+ "epoch": 5.12,
2805
+ "eval_loss": 0.2767942547798157,
2806
+ "eval_runtime": 226.6824,
2807
+ "eval_samples_per_second": 4.411,
2808
+ "eval_steps_per_second": 0.278,
2809
+ "step": 10000
2810
+ }
2811
+ ],
2812
+ "logging_steps": 25,
2813
+ "max_steps": 10000,
2814
+ "num_train_epochs": 9223372036854775807,
2815
+ "save_steps": 400,
2816
+ "total_flos": 1.029789873027072e+21,
2817
+ "trial_name": null,
2818
+ "trial_params": null
2819
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6aeab43e4432e1a5e411a7171c22dfc5bd21699fe719c2b5523f4c9fac7430
3
+ size 4219
vocab.json ADDED
The diff for this file is too large to render. See raw diff