Hugging Face's logo

flair
/
upos-multi-fast

Token Classification Flair PyTorch
12 languages sequence-tagger-model
Model card Files Community
1
alanakbik commited on
Commit
055fe96
•
1 Parent(s): 448a84f

initial model commit

Browse files
Files changed (4) hide show
  1. README.md +189 -0
  2. loss.tsv +151 -0
  3. pytorch_model.bin +3 -0
  4. training.log +0 -0
README.md ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - flair
4
+ - token-classification
5
+ - sequence-tagger-model
6
+ language:
7
+ - en
8
+ - de
9
+ - fr
10
+ - it
11
+ - nl
12
+ - pl
13
+ - es
14
+ - sv
15
+ - da
16
+ - no
17
+ - fi
18
+ - cs
19
+ datasets:
20
+ - ontonotes
21
+ inference: false
22
+ ---
23
+
24
+ ## Multilingual Universal Part-of-Speech Tagging in Flair (fast model)
25
+
26
+ This is the fast multilingual universal part-of-speech tagging model that ships with [Flair](https://github.com/flairNLP/flair/).
27
+
28
+ F1-Score: **92,88** (12 UD Treebanks covering English, German, French, Italian, Dutch, Polish, Spanish, Swedish, Danish, Norwegian, Finnish and Czech)
29
+
30
+ Predicts universal POS tags:
31
+
32
+ | **tag** | **meaning** |
33
+ |---------------------------------|-----------|
34
+ |ADJ | adjective |
35
+ | ADP | adposition |
36
+ | ADV | adverb |
37
+ | AUX | auxiliary |
38
+ | CCONJ | coordinating conjunction |
39
+ | DET | determiner |
40
+ | INTJ | interjection |
41
+ | NOUN | noun |
42
+ | NUM | numeral |
43
+ | PART | particle |
44
+ | PRON | pronoun |
45
+ | PROPN | proper noun |
46
+ | PUNCT | punctuation |
47
+ | SCONJ | subordinating conjunction |
48
+ | SYM | symbol |
49
+ | VERB | verb |
50
+ | X | other |
51
+
52
+
53
+
54
+ Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF.
55
+
56
+ ---
57
+
58
+ ### Demo: How to use in Flair
59
+
60
+ Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
61
+
62
+ ```python
63
+ from flair.data import Sentence
64
+ from flair.models import SequenceTagger
65
+
66
+ # load tagger
67
+ tagger = SequenceTagger.load("flair/upos-multi-fast")
68
+
69
+ # make example sentence
70
+ sentence = Sentence("Ich liebe Berlin, as they say. ")
71
+
72
+ # predict NER tags
73
+ tagger.predict(sentence)
74
+
75
+ # print sentence
76
+ print(sentence)
77
+
78
+ # print predicted NER spans
79
+ print('The following NER tags are found:')
80
+ # iterate over entities and print
81
+ for entity in sentence.get_spans('pos'):
82
+ print(entity)
83
+ ```
84
+
85
+ This yields the following output:
86
+ ```
87
+ Span [1]: "Ich" [− Labels: PRON (0.9999)]
88
+ Span [2]: "liebe" [− Labels: VERB (0.9999)]
89
+ Span [3]: "Berlin" [− Labels: PROPN (0.9997)]
90
+ Span [4]: "," [− Labels: PUNCT (1.0)]
91
+ Span [5]: "as" [− Labels: SCONJ (0.9991)]
92
+ Span [6]: "they" [− Labels: PRON (0.9998)]
93
+ Span [7]: "say" [− Labels: VERB (0.9998)]
94
+ Span [8]: "." [− Labels: PUNCT (1.0)]
95
+ ```
96
+
97
+ So, the words "*Ich*" and "*they*" are labeled as **pronouns** (PRON), while "*liebe*" and "*say*" are labeled as **verbs** (VERB) in the multilingual sentence "*Ich liebe Berlin, as they say*".
98
+
99
+
100
+ ---
101
+
102
+ ### Training: Script to train this model
103
+
104
+ The following Flair script was used to train this model:
105
+
106
+ ```python
107
+ from flair.data import MultiCorpus
108
+ from flair.datasets import UD_ENGLISH, UD_GERMAN, UD_FRENCH, UD_ITALIAN, UD_POLISH, UD_DUTCH, UD_CZECH, \
109
+ UD_DANISH, UD_SPANISH, UD_SWEDISH, UD_NORWEGIAN, UD_FINNISH
110
+ from flair.embeddings import StackedEmbeddings, FlairEmbeddings
111
+
112
+ # 1. make a multi corpus consisting of 12 UD treebanks (in_memory=False here because this corpus becomes large)
113
+ corpus = MultiCorpus([
114
+ UD_ENGLISH(in_memory=False),
115
+ UD_GERMAN(in_memory=False),
116
+ UD_DUTCH(in_memory=False),
117
+ UD_FRENCH(in_memory=False),
118
+ UD_ITALIAN(in_memory=False),
119
+ UD_SPANISH(in_memory=False),
120
+ UD_POLISH(in_memory=False),
121
+ UD_CZECH(in_memory=False),
122
+ UD_DANISH(in_memory=False),
123
+ UD_SWEDISH(in_memory=False),
124
+ UD_NORWEGIAN(in_memory=False),
125
+ UD_FINNISH(in_memory=False),
126
+ ])
127
+
128
+ # 2. what tag do we want to predict?
129
+ tag_type = 'upos'
130
+
131
+ # 3. make the tag dictionary from the corpus
132
+ tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
133
+
134
+ # 4. initialize each embedding we use
135
+ embedding_types = [
136
+
137
+ # contextual string embeddings, forward
138
+ FlairEmbeddings('multi-forward-fast'),
139
+
140
+ # contextual string embeddings, backward
141
+ FlairEmbeddings('multi-backward-fast'),
142
+ ]
143
+
144
+ # embedding stack consists of Flair and GloVe embeddings
145
+ embeddings = StackedEmbeddings(embeddings=embedding_types)
146
+
147
+ # 5. initialize sequence tagger
148
+ from flair.models import SequenceTagger
149
+
150
+ tagger = SequenceTagger(hidden_size=256,
151
+ embeddings=embeddings,
152
+ tag_dictionary=tag_dictionary,
153
+ tag_type=tag_type,
154
+ use_crf=False)
155
+
156
+ # 6. initialize trainer
157
+ from flair.trainers import ModelTrainer
158
+
159
+ trainer = ModelTrainer(tagger, corpus)
160
+
161
+ # 7. run training
162
+ trainer.train('resources/taggers/upos-multi-fast',
163
+ train_with_dev=True,
164
+ max_epochs=150)
165
+ ```
166
+
167
+
168
+
169
+ ---
170
+
171
+ ### Cite
172
+
173
+ Please cite the following paper when using this model.
174
+
175
+ ```
176
+ @inproceedings{akbik2018coling,
177
+ title={Contextual String Embeddings for Sequence Labeling},
178
+ author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
179
+ booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
180
+ pages = {1638--1649},
181
+ year = {2018}
182
+ }
183
+ ```
184
+
185
+ ---
186
+
187
+ ### Issues?
188
+
189
+ The Flair issue tracker is available [here](https://github.com/flairNLP/flair/issues/).
loss.tsv ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP BAD_EPOCHS LEARNING_RATE TRAIN_LOSS TRAIN_PRECISION TRAIN_RECALL TRAIN_ACCURACY TRAIN_F-SCORE DEV_LOSS DEV_PRECISION DEV_RECALL DEV_ACCURACY DEV_F-SCORE TEST_LOSS TEST_PRECISION TEST_RECALL TEST_ACCURACY TEST_F-SCORE
2
+ 0 17:20:53 0 0.1000 0.9190797222630016 _ _ _ _ _ _ _ _ _ _ 0.777 0.777 0.777 0.777
3
+ 1 17:24:38 0 0.1000 0.6716432737287085 _ _ _ _ _ _ _ _ _ _ 0.8233 0.8233 0.8233 0.8233
4
+ 2 17:28:26 0 0.1000 0.5960667036171194 _ _ _ _ _ _ _ _ _ _ 0.8401 0.8401 0.8401 0.8401
5
+ 3 17:32:07 0 0.1000 0.5517474701099455 _ _ _ _ _ _ _ _ _ _ 0.8553 0.8553 0.8553 0.8553
6
+ 4 17:35:50 0 0.1000 0.5247127810490859 _ _ _ _ _ _ _ _ _ _ 0.8654 0.8654 0.8654 0.8654
7
+ 5 17:39:48 0 0.1000 0.5020367544745151 _ _ _ _ _ _ _ _ _ _ 0.8735 0.8735 0.8735 0.8735
8
+ 6 17:43:32 0 0.1000 0.48632956523237236 _ _ _ _ _ _ _ _ _ _ 0.8774 0.8774 0.8774 0.8774
9
+ 7 17:47:14 0 0.1000 0.47448061674651854 _ _ _ _ _ _ _ _ _ _ 0.8797 0.8797 0.8797 0.8797
10
+ 8 17:50:58 0 0.1000 0.4657747268559462 _ _ _ _ _ _ _ _ _ _ 0.8845 0.8845 0.8845 0.8845
11
+ 9 17:54:40 0 0.1000 0.4548023839797725 _ _ _ _ _ _ _ _ _ _ 0.8892 0.8892 0.8892 0.8892
12
+ 10 17:58:22 0 0.1000 0.4479015595216538 _ _ _ _ _ _ _ _ _ _ 0.888 0.888 0.888 0.888
13
+ 11 18:02:05 0 0.1000 0.4417490141883859 _ _ _ _ _ _ _ _ _ _ 0.8913 0.8913 0.8913 0.8913
14
+ 12 18:05:47 0 0.1000 0.4353397585937434 _ _ _ _ _ _ _ _ _ _ 0.8957 0.8957 0.8957 0.8957
15
+ 13 18:09:45 0 0.1000 0.4300186406485238 _ _ _ _ _ _ _ _ _ _ 0.8971 0.8971 0.8971 0.8971
16
+ 14 18:13:33 0 0.1000 0.42514593633532055 _ _ _ _ _ _ _ _ _ _ 0.8986 0.8986 0.8986 0.8986
17
+ 15 18:17:16 0 0.1000 0.4217662339969708 _ _ _ _ _ _ _ _ _ _ 0.899 0.899 0.899 0.899
18
+ 16 18:21:19 0 0.1000 0.4185326483417642 _ _ _ _ _ _ _ _ _ _ 0.8996 0.8996 0.8996 0.8996
19
+ 17 18:25:02 0 0.1000 0.41529573476239035 _ _ _ _ _ _ _ _ _ _ 0.9021 0.9021 0.9021 0.9021
20
+ 18 18:28:44 0 0.1000 0.41164514654259365 _ _ _ _ _ _ _ _ _ _ 0.9014 0.9014 0.9014 0.9014
21
+ 19 18:32:27 0 0.1000 0.40819807794557744 _ _ _ _ _ _ _ _ _ _ 0.9026 0.9026 0.9026 0.9026
22
+ 20 18:36:09 0 0.1000 0.4072363424415511 _ _ _ _ _ _ _ _ _ _ 0.904 0.904 0.904 0.904
23
+ 21 18:39:47 0 0.1000 0.40504910720195475 _ _ _ _ _ _ _ _ _ _ 0.905 0.905 0.905 0.905
24
+ 22 18:43:34 0 0.1000 0.40202132739125 _ _ _ _ _ _ _ _ _ _ 0.9047 0.9047 0.9047 0.9047
25
+ 23 18:47:11 0 0.1000 0.4016447351458934 _ _ _ _ _ _ _ _ _ _ 0.9048 0.9048 0.9048 0.9048
26
+ 24 18:50:53 0 0.1000 0.3990221622819437 _ _ _ _ _ _ _ _ _ _ 0.9057 0.9057 0.9057 0.9057
27
+ 25 18:54:29 0 0.1000 0.39748555323960455 _ _ _ _ _ _ _ _ _ _ 0.9066 0.9066 0.9066 0.9066
28
+ 26 18:58:06 0 0.1000 0.39510030264373813 _ _ _ _ _ _ _ _ _ _ 0.9074 0.9074 0.9074 0.9074
29
+ 27 19:01:41 0 0.1000 0.3918911876917555 _ _ _ _ _ _ _ _ _ _ 0.9092 0.9092 0.9092 0.9092
30
+ 28 19:05:16 0 0.1000 0.3908691110859825 _ _ _ _ _ _ _ _ _ _ 0.909 0.909 0.909 0.909
31
+ 29 19:08:51 0 0.1000 0.39194263081204284 _ _ _ _ _ _ _ _ _ _ 0.9083 0.9083 0.9083 0.9083
32
+ 30 19:12:54 1 0.1000 0.390020066672355 _ _ _ _ _ _ _ _ _ _ 0.9101 0.9101 0.9101 0.9101
33
+ 31 19:16:30 0 0.1000 0.3874159374133058 _ _ _ _ _ _ _ _ _ _ 0.9101 0.9101 0.9101 0.9101
34
+ 32 19:20:07 0 0.1000 0.38671515579703375 _ _ _ _ _ _ _ _ _ _ 0.9102 0.9102 0.9102 0.9102
35
+ 33 19:23:42 0 0.1000 0.38522100101608026 _ _ _ _ _ _ _ _ _ _ 0.91 0.91 0.91 0.91
36
+ 34 19:27:18 0 0.1000 0.38452733974479464 _ _ _ _ _ _ _ _ _ _ 0.9115 0.9115 0.9115 0.9115
37
+ 35 19:30:53 0 0.1000 0.38427426408016185 _ _ _ _ _ _ _ _ _ _ 0.9109 0.9109 0.9109 0.9109
38
+ 36 19:34:29 0 0.1000 0.38305842953409763 _ _ _ _ _ _ _ _ _ _ 0.9124 0.9124 0.9124 0.9124
39
+ 37 19:38:04 0 0.1000 0.38233189722553446 _ _ _ _ _ _ _ _ _ _ 0.9114 0.9114 0.9114 0.9114
40
+ 38 19:41:47 0 0.1000 0.38083049013437587 _ _ _ _ _ _ _ _ _ _ 0.9125 0.9125 0.9125 0.9125
41
+ 39 19:45:25 0 0.1000 0.38015748730049487 _ _ _ _ _ _ _ _ _ _ 0.9127 0.9127 0.9127 0.9127
42
+ 40 19:49:03 0 0.1000 0.37948072639638775 _ _ _ _ _ _ _ _ _ _ 0.9123 0.9123 0.9123 0.9123
43
+ 41 19:52:39 0 0.1000 0.3794758443748531 _ _ _ _ _ _ _ _ _ _ 0.9126 0.9126 0.9126 0.9126
44
+ 42 19:56:13 1 0.1000 0.377902250212404 _ _ _ _ _ _ _ _ _ _ 0.9135 0.9135 0.9135 0.9135
45
+ 43 19:59:47 0 0.1000 0.3766043377062385 _ _ _ _ _ _ _ _ _ _ 0.9133 0.9133 0.9133 0.9133
46
+ 44 20:03:19 0 0.1000 0.37573553599806514 _ _ _ _ _ _ _ _ _ _ 0.9137 0.9137 0.9137 0.9137
47
+ 45 20:06:50 0 0.1000 0.3748471322266952 _ _ _ _ _ _ _ _ _ _ 0.9135 0.9135 0.9135 0.9135
48
+ 46 20:10:19 0 0.1000 0.3744547664734294 _ _ _ _ _ _ _ _ _ _ 0.9132 0.9132 0.9132 0.9132
49
+ 47 20:13:52 0 0.1000 0.37502166761711847 _ _ _ _ _ _ _ _ _ _ 0.9143 0.9143 0.9143 0.9143
50
+ 48 20:17:41 1 0.1000 0.3721831904085566 _ _ _ _ _ _ _ _ _ _ 0.9145 0.9145 0.9145 0.9145
51
+ 49 20:21:08 0 0.1000 0.3714427081547894 _ _ _ _ _ _ _ _ _ _ 0.9148 0.9148 0.9148 0.9148
52
+ 50 20:24:37 0 0.1000 0.37246603286469393 _ _ _ _ _ _ _ _ _ _ 0.9145 0.9145 0.9145 0.9145
53
+ 51 20:28:05 1 0.1000 0.3704952007998493 _ _ _ _ _ _ _ _ _ _ 0.9144 0.9144 0.9144 0.9144
54
+ 52 20:31:34 0 0.1000 0.3703908653195547 _ _ _ _ _ _ _ _ _ _ 0.9143 0.9143 0.9143 0.9143
55
+ 53 20:35:03 0 0.1000 0.37107703269995407 _ _ _ _ _ _ _ _ _ _ 0.916 0.916 0.916 0.916
56
+ 54 20:38:32 1 0.1000 0.37049108522393775 _ _ _ _ _ _ _ _ _ _ 0.9153 0.9153 0.9153 0.9153
57
+ 55 20:42:02 2 0.1000 0.37020046933146 _ _ _ _ _ _ _ _ _ _ 0.9152 0.9152 0.9152 0.9152
58
+ 56 20:45:33 0 0.1000 0.36912775061910197 _ _ _ _ _ _ _ _ _ _ 0.9159 0.9159 0.9159 0.9159
59
+ 57 20:49:02 0 0.1000 0.3671512951590983 _ _ _ _ _ _ _ _ _ _ 0.9151 0.9151 0.9151 0.9151
60
+ 58 20:52:30 0 0.1000 0.3668931041249558 _ _ _ _ _ _ _ _ _ _ 0.9154 0.9154 0.9154 0.9154
61
+ 59 20:55:59 0 0.1000 0.36706147675945966 _ _ _ _ _ _ _ _ _ _ 0.9172 0.9172 0.9172 0.9172
62
+ 60 20:59:28 1 0.1000 0.3657434461712214 _ _ _ _ _ _ _ _ _ _ 0.9168 0.9168 0.9168 0.9168
63
+ 61 21:02:58 0 0.1000 0.3659182143304713 _ _ _ _ _ _ _ _ _ _ 0.916 0.916 0.916 0.916
64
+ 62 21:06:27 1 0.1000 0.3662726061567449 _ _ _ _ _ _ _ _ _ _ 0.9156 0.9156 0.9156 0.9156
65
+ 63 21:09:56 2 0.1000 0.3638134179826793 _ _ _ _ _ _ _ _ _ _ 0.9163 0.9163 0.9163 0.9163
66
+ 64 21:13:27 0 0.1000 0.3639648409197477 _ _ _ _ _ _ _ _ _ _ 0.9176 0.9176 0.9176 0.9176
67
+ 65 21:16:56 1 0.1000 0.3648721676257142 _ _ _ _ _ _ _ _ _ _ 0.9168 0.9168 0.9168 0.9168
68
+ 66 21:20:25 2 0.1000 0.3633504617117189 _ _ _ _ _ _ _ _ _ _ 0.917 0.917 0.917 0.917
69
+ 67 21:23:53 0 0.1000 0.3645101590239933 _ _ _ _ _ _ _ _ _ _ 0.9171 0.9171 0.9171 0.9171
70
+ 68 21:27:23 1 0.1000 0.3630188812231188 _ _ _ _ _ _ _ _ _ _ 0.916 0.916 0.916 0.916
71
+ 69 21:30:52 0 0.1000 0.3636482348753987 _ _ _ _ _ _ _ _ _ _ 0.9167 0.9167 0.9167 0.9167
72
+ 70 21:34:20 1 0.1000 0.3639552533385855 _ _ _ _ _ _ _ _ _ _ 0.9173 0.9173 0.9173 0.9173
73
+ 71 21:37:48 2 0.1000 0.3624460829547383 _ _ _ _ _ _ _ _ _ _ 0.9162 0.9162 0.9162 0.9162
74
+ 72 21:41:17 0 0.1000 0.36187481353822637 _ _ _ _ _ _ _ _ _ _ 0.9167 0.9167 0.9167 0.9167
75
+ 73 21:44:48 0 0.1000 0.3638685102028578 _ _ _ _ _ _ _ _ _ _ 0.9178 0.9178 0.9178 0.9178
76
+ 74 21:48:20 1 0.1000 0.3608434076808494 _ _ _ _ _ _ _ _ _ _ 0.9167 0.9167 0.9167 0.9167
77
+ 75 21:51:49 0 0.1000 0.3602308806752747 _ _ _ _ _ _ _ _ _ _ 0.9172 0.9172 0.9172 0.9172
78
+ 76 21:55:23 0 0.1000 0.3598624867144525 _ _ _ _ _ _ _ _ _ _ 0.9182 0.9182 0.9182 0.9182
79
+ 77 21:58:51 0 0.1000 0.36065239670790644 _ _ _ _ _ _ _ _ _ _ 0.9181 0.9181 0.9181 0.9181
80
+ 78 22:02:19 1 0.1000 0.360412118996118 _ _ _ _ _ _ _ _ _ _ 0.9175 0.9175 0.9175 0.9175
81
+ 79 22:05:47 2 0.1000 0.3591554729788417 _ _ _ _ _ _ _ _ _ _ 0.9181 0.9181 0.9181 0.9181
82
+ 80 22:09:15 0 0.1000 0.358690284100161 _ _ _ _ _ _ _ _ _ _ 0.9186 0.9186 0.9186 0.9186
83
+ 81 22:13:04 0 0.1000 0.35836367092432064 _ _ _ _ _ _ _ _ _ _ 0.9179 0.9179 0.9179 0.9179
84
+ 82 22:16:35 0 0.1000 0.3590073234306779 _ _ _ _ _ _ _ _ _ _ 0.9173 0.9173 0.9173 0.9173
85
+ 83 22:20:03 1 0.1000 0.35931719463767836 _ _ _ _ _ _ _ _ _ _ 0.9173 0.9173 0.9173 0.9173
86
+ 84 22:23:32 2 0.1000 0.35991999209495307 _ _ _ _ _ _ _ _ _ _ 0.9167 0.9167 0.9167 0.9167
87
+ 85 22:27:00 3 0.1000 0.3583576700660675 _ _ _ _ _ _ _ _ _ _ 0.9182 0.9182 0.9182 0.9182
88
+ 86 22:30:28 0 0.0500 0.3383489196435348 _ _ _ _ _ _ _ _ _ _ 0.9214 0.9214 0.9214 0.9214
89
+ 87 22:33:56 0 0.0500 0.3332596721458173 _ _ _ _ _ _ _ _ _ _ 0.922 0.922 0.922 0.922
90
+ 88 22:37:27 0 0.0500 0.3287687047201385 _ _ _ _ _ _ _ _ _ _ 0.9229 0.9229 0.9229 0.9229
91
+ 89 22:40:56 0 0.0500 0.3285579723036529 _ _ _ _ _ _ _ _ _ _ 0.9225 0.9225 0.9225 0.9225
92
+ 90 22:44:25 0 0.0500 0.3249955790471447 _ _ _ _ _ _ _ _ _ _ 0.923 0.923 0.923 0.923
93
+ 91 22:47:56 0 0.0500 0.32664729893809913 _ _ _ _ _ _ _ _ _ _ 0.9227 0.9227 0.9227 0.9227
94
+ 92 22:51:31 1 0.0500 0.32461294523941386 _ _ _ _ _ _ _ _ _ _ 0.9229 0.9229 0.9229 0.9229
95
+ 93 22:55:00 0 0.0500 0.32429037422202617 _ _ _ _ _ _ _ _ _ _ 0.9236 0.9236 0.9236 0.9236
96
+ 94 22:58:32 0 0.0500 0.3235636986328555 _ _ _ _ _ _ _ _ _ _ 0.923 0.923 0.923 0.923
97
+ 95 23:02:00 0 0.0500 0.3222244535159027 _ _ _ _ _ _ _ _ _ _ 0.9238 0.9238 0.9238 0.9238
98
+ 96 23:05:29 0 0.0500 0.32155113324754814 _ _ _ _ _ _ _ _ _ _ 0.9235 0.9235 0.9235 0.9235
99
+ 97 23:09:01 0 0.0500 0.321625706469336 _ _ _ _ _ _ _ _ _ _ 0.924 0.924 0.924 0.924
100
+ 98 23:12:30 1 0.0500 0.32150654914675636 _ _ _ _ _ _ _ _ _ _ 0.9236 0.9236 0.9236 0.9236
101
+ 99 23:16:06 0 0.0500 0.32067421640541527 _ _ _ _ _ _ _ _ _ _ 0.9238 0.9238 0.9238 0.9238
102
+ 100 23:19:38 0 0.0500 0.3206731891157032 _ _ _ _ _ _ _ _ _ _ 0.9246 0.9246 0.9246 0.9246
103
+ 101 23:23:06 1 0.0500 0.319841820813021 _ _ _ _ _ _ _ _ _ _ 0.9242 0.9242 0.9242 0.9242
104
+ 102 23:26:33 0 0.0500 0.3191204305807779 _ _ _ _ _ _ _ _ _ _ 0.9239 0.9239 0.9239 0.9239
105
+ 103 23:30:01 0 0.0500 0.3174570998350242 _ _ _ _ _ _ _ _ _ _ 0.9241 0.9241 0.9241 0.9241
106
+ 104 23:33:29 0 0.0500 0.3191340444096926 _ _ _ _ _ _ _ _ _ _ 0.9243 0.9243 0.9243 0.9243
107
+ 105 23:36:57 1 0.0500 0.31770479497054654 _ _ _ _ _ _ _ _ _ _ 0.9241 0.9241 0.9241 0.9241
108
+ 106 23:40:26 2 0.0500 0.3172146900209962 _ _ _ _ _ _ _ _ _ _ 0.9239 0.9239 0.9239 0.9239
109
+ 107 23:43:54 0 0.0500 0.3160222761159336 _ _ _ _ _ _ _ _ _ _ 0.924 0.924 0.924 0.924
110
+ 108 23:47:24 0 0.0500 0.31664770050950836 _ _ _ _ _ _ _ _ _ _ 0.9244 0.9244 0.9244 0.9244
111
+ 109 23:50:54 1 0.0500 0.3151855416235648 _ _ _ _ _ _ _ _ _ _ 0.9243 0.9243 0.9243 0.9243
112
+ 110 23:54:22 0 0.0500 0.3156811461111346 _ _ _ _ _ _ _ _ _ _ 0.924 0.924 0.924 0.924
113
+ 111 23:57:54 1 0.0500 0.3161979560382085 _ _ _ _ _ _ _ _ _ _ 0.9246 0.9246 0.9246 0.9246
114
+ 112 00:01:23 2 0.0500 0.31593882176664106 _ _ _ _ _ _ _ _ _ _ 0.925 0.925 0.925 0.925
115
+ 113 00:05:18 3 0.0500 0.3152490947733476 _ _ _ _ _ _ _ _ _ _ 0.9246 0.9246 0.9246 0.9246
116
+ 114 00:08:47 0 0.0250 0.3063757599452114 _ _ _ _ _ _ _ _ _ _ 0.926 0.926 0.926 0.926
117
+ 115 00:12:17 0 0.0250 0.3037663424432667 _ _ _ _ _ _ _ _ _ _ 0.9264 0.9264 0.9264 0.9264
118
+ 116 00:15:50 0 0.0250 0.3026768150561347 _ _ _ _ _ _ _ _ _ _ 0.9262 0.9262 0.9262 0.9262
119
+ 117 00:19:23 0 0.0250 0.301911720552316 _ _ _ _ _ _ _ _ _ _ 0.9262 0.9262 0.9262 0.9262
120
+ 118 00:22:54 0 0.0250 0.30135701154769623 _ _ _ _ _ _ _ _ _ _ 0.9265 0.9265 0.9265 0.9265
121
+ 119 00:26:28 0 0.0250 0.30062567218434066 _ _ _ _ _ _ _ _ _ _ 0.9267 0.9267 0.9267 0.9267
122
+ 120 00:30:04 0 0.0250 0.30065195452518656 _ _ _ _ _ _ _ _ _ _ 0.9267 0.9267 0.9267 0.9267
123
+ 121 00:33:34 1 0.0250 0.29976059630590474 _ _ _ _ _ _ _ _ _ _ 0.9268 0.9268 0.9268 0.9268
124
+ 122 00:37:02 0 0.0250 0.2985034517248484 _ _ _ _ _ _ _ _ _ _ 0.9269 0.9269 0.9269 0.9269
125
+ 123 00:40:31 0 0.0250 0.2982299711554555 _ _ _ _ _ _ _ _ _ _ 0.9272 0.9272 0.9272 0.9272
126
+ 124 00:44:00 0 0.0250 0.2981091206836624 _ _ _ _ _ _ _ _ _ _ 0.927 0.927 0.927 0.927
127
+ 125 00:47:28 0 0.0250 0.2959095034530295 _ _ _ _ _ _ _ _ _ _ 0.9271 0.9271 0.9271 0.9271
128
+ 126 00:51:01 0 0.0250 0.29701172573023016 _ _ _ _ _ _ _ _ _ _ 0.9268 0.9268 0.9268 0.9268
129
+ 127 00:54:29 1 0.0250 0.2971695579327705 _ _ _ _ _ _ _ _ _ _ 0.9272 0.9272 0.9272 0.9272
130
+ 128 00:57:58 2 0.0250 0.2969908203507443 _ _ _ _ _ _ _ _ _ _ 0.9272 0.9272 0.9272 0.9272
131
+ 129 01:01:27 3 0.0250 0.2980158057176761 _ _ _ _ _ _ _ _ _ _ 0.9273 0.9273 0.9273 0.9273
132
+ 130 01:04:56 0 0.0125 0.2920450986249077 _ _ _ _ _ _ _ _ _ _ 0.9273 0.9273 0.9273 0.9273
133
+ 131 01:08:31 0 0.0125 0.29132962870162377 _ _ _ _ _ _ _ _ _ _ 0.9278 0.9278 0.9278 0.9278
134
+ 132 01:11:59 0 0.0125 0.29008412956788265 _ _ _ _ _ _ _ _ _ _ 0.9277 0.9277 0.9277 0.9277
135
+ 133 01:15:27 0 0.0125 0.29002047444153295 _ _ _ _ _ _ _ _ _ _ 0.9279 0.9279 0.9279 0.9279
136
+ 134 01:18:56 0 0.0125 0.2895771512047742 _ _ _ _ _ _ _ _ _ _ 0.928 0.928 0.928 0.928
137
+ 135 01:22:29 0 0.0125 0.2890135376831141 _ _ _ _ _ _ _ _ _ _ 0.9281 0.9281 0.9281 0.9281
138
+ 136 01:25:58 0 0.0125 0.28820534214831617 _ _ _ _ _ _ _ _ _ _ 0.928 0.928 0.928 0.928
139
+ 137 01:29:27 0 0.0125 0.2886223816855515 _ _ _ _ _ _ _ _ _ _ 0.9282 0.9282 0.9282 0.9282
140
+ 138 01:32:55 1 0.0125 0.28920243310231414 _ _ _ _ _ _ _ _ _ _ 0.9281 0.9281 0.9281 0.9281
141
+ 139 01:36:23 2 0.0125 0.28792437217338346 _ _ _ _ _ _ _ _ _ _ 0.9279 0.9279 0.9279 0.9279
142
+ 140 01:39:52 0 0.0125 0.28707431522855614 _ _ _ _ _ _ _ _ _ _ 0.9281 0.9281 0.9281 0.9281
143
+ 141 01:43:20 0 0.0125 0.28832379478522974 _ _ _ _ _ _ _ _ _ _ 0.9283 0.9283 0.9283 0.9283
144
+ 142 01:46:48 1 0.0125 0.28975775159598055 _ _ _ _ _ _ _ _ _ _ 0.9282 0.9282 0.9282 0.9282
145
+ 143 01:50:16 2 0.0125 0.2880531497794666 _ _ _ _ _ _ _ _ _ _ 0.928 0.928 0.928 0.928
146
+ 144 01:53:49 3 0.0125 0.287825567466029 _ _ _ _ _ _ _ _ _ _ 0.9285 0.9285 0.9285 0.9285
147
+ 145 01:57:18 0 0.0063 0.28631645248738896 _ _ _ _ _ _ _ _ _ _ 0.9286 0.9286 0.9286 0.9286
148
+ 146 02:01:13 0 0.0063 0.28486480532279373 _ _ _ _ _ _ _ _ _ _ 0.9286 0.9286 0.9286 0.9286
149
+ 147 02:04:41 0 0.0063 0.2841264129166399 _ _ _ _ _ _ _ _ _ _ 0.9287 0.9287 0.9287 0.9287
150
+ 148 02:08:10 0 0.0063 0.28465119782251286 _ _ _ _ _ _ _ _ _ _ 0.9288 0.9288 0.9288 0.9288
151
+ 149 02:11:38 1 0.0063 0.28372669010548646 _ _ _ _ _ _ _ _ _ _ 0.9288 0.9288 0.9288 0.9288
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb8d2732935a24eb64a73891e8ae3f12b37a5cf8ca1e3d8d22059e21a32ec912
3
+ size 72105507
training.log ADDED
The diff for this file is too large to render. See raw diff