alanakbik commited on
Commit
a5e34eb
1 Parent(s): db0a3e8

initial model commit

Browse files
Files changed (4) hide show
  1. README.md +166 -0
  2. loss.tsv +151 -0
  3. pytorch_model.bin +3 -0
  4. training.log +0 -0
README.md ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - flair
4
+ - token-classification
5
+ - sequence-tagger-model
6
+ language: en de fr it nl pl es sw da no fi cz
7
+ datasets:
8
+ - ontonotes
9
+ inference: false
10
+ ---
11
+
12
+ ## Multilingual Universal Part-of-Speech Tagging in Flair (default model)
13
+
14
+ This is the default multilingual universal part-of-speech tagging model that ships with [Flair](https://github.com/flairNLP/flair/).
15
+
16
+ F1-Score: **98,47** (12 UD Treebanks covering English, German, French, Italian, Dutch, Polish, Spanish, Swedish, Danish, Norwegian, Finnish and Czech)
17
+
18
+ Predicts universal POS tags:
19
+
20
+ | **tag** | **meaning** |
21
+ |---------------------------------|-----------|
22
+ |ADJ | adjective |
23
+ | ADP | adposition |
24
+ | ADV | adverb |
25
+ | AUX | auxiliary |
26
+ | CCONJ | coordinating conjunction |
27
+ | DET | determiner |
28
+ | INTJ | interjection |
29
+ | NOUN | noun |
30
+ | NUM | numeral |
31
+ | PART | particle |
32
+ | PRON | pronoun |
33
+ | PROPN | proper noun |
34
+ | PUNCT | punctuation |
35
+ | SCONJ | subordinating conjunction |
36
+ | SYM | symbol |
37
+ | VERB | verb |
38
+ | X | other |
39
+
40
+
41
+
42
+ Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF.
43
+
44
+ ---
45
+
46
+ ### Demo: How to use in Flair
47
+
48
+ Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
49
+
50
+ ```python
51
+ from flair.data import Sentence
52
+ from flair.models import SequenceTagger
53
+
54
+ # load tagger
55
+ tagger = SequenceTagger.load("flair/upos-multi")
56
+
57
+ # make example sentence
58
+ sentence = Sentence("Ich liebe Berlin, as they say. ")
59
+
60
+ # predict NER tags
61
+ tagger.predict(sentence)
62
+
63
+ # print sentence
64
+ print(sentence)
65
+
66
+ # print predicted NER spans
67
+ print('The following NER tags are found:')
68
+ # iterate over entities and print
69
+ for entity in sentence.get_spans('pos'):
70
+ print(entity)
71
+ ```
72
+
73
+ This yields the following output:
74
+ ```
75
+ Span [1]: "Ich" [− Labels: PRON (0.9999)]
76
+ Span [2]: "liebe" [− Labels: VERB (0.9999)]
77
+ Span [3]: "Berlin" [− Labels: PROPN (0.9997)]
78
+ Span [4]: "," [− Labels: PUNCT (1.0)]
79
+ Span [5]: "as" [− Labels: SCONJ (0.9991)]
80
+ Span [6]: "they" [− Labels: PRON (0.9998)]
81
+ Span [7]: "say" [− Labels: VERB (0.9998)]
82
+ Span [8]: "." [− Labels: PUNCT (1.0)]
83
+ ```
84
+
85
+ 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*".
86
+
87
+
88
+ ---
89
+
90
+ ### Training: Script to train this model
91
+
92
+ The following Flair script was used to train this model:
93
+
94
+ ```python
95
+ from flair.data import Corpus
96
+ from flair.datasets import ColumnCorpus
97
+ from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings
98
+
99
+ # 1. load the corpus (Ontonotes does not ship with Flair, you need to download and reformat into a column format yourself)
100
+ corpus: Corpus = ColumnCorpus(
101
+ "resources/tasks/onto-ner",
102
+ column_format={0: "text", 1: "pos", 2: "upos", 3: "ner"},
103
+ tag_to_bioes="ner",
104
+ )
105
+
106
+ # 2. what tag do we want to predict?
107
+ tag_type = 'upos'
108
+
109
+ # 3. make the tag dictionary from the corpus
110
+ tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
111
+
112
+ # 4. initialize each embedding we use
113
+ embedding_types = [
114
+
115
+ # contextual string embeddings, forward
116
+ FlairEmbeddings('multi-forward'),
117
+
118
+ # contextual string embeddings, backward
119
+ FlairEmbeddings('multi-backward'),
120
+ ]
121
+
122
+ # embedding stack consists of Flair and GloVe embeddings
123
+ embeddings = StackedEmbeddings(embeddings=embedding_types)
124
+
125
+ # 5. initialize sequence tagger
126
+ from flair.models import SequenceTagger
127
+
128
+ tagger = SequenceTagger(hidden_size=256,
129
+ embeddings=embeddings,
130
+ tag_dictionary=tag_dictionary,
131
+ tag_type=tag_type)
132
+
133
+ # 6. initialize trainer
134
+ from flair.trainers import ModelTrainer
135
+
136
+ trainer = ModelTrainer(tagger, corpus)
137
+
138
+ # 7. run training
139
+ trainer.train('resources/taggers/upos-english-fast',
140
+ train_with_dev=True,
141
+ max_epochs=150)
142
+ ```
143
+
144
+
145
+
146
+ ---
147
+
148
+ ### Cite
149
+
150
+ Please cite the following paper when using this model.
151
+
152
+ ```
153
+ @inproceedings{akbik2018coling,
154
+ title={Contextual String Embeddings for Sequence Labeling},
155
+ author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
156
+ booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
157
+ pages = {1638--1649},
158
+ year = {2018}
159
+ }
160
+ ```
161
+
162
+ ---
163
+
164
+ ### Issues?
165
+
166
+ 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 11:12:55 0 0.1000 0.7210021345162283 _ _ _ _ _ _ _ _ _ _ 0.8481 0.8481 0.8481 0.8481
3
+ 1 11:36:23 0 0.1000 0.4978160696237081 _ _ _ _ _ _ _ _ _ _ 0.878 0.878 0.878 0.878
4
+ 2 11:59:52 0 0.1000 0.43429711483610006 _ _ _ _ _ _ _ _ _ _ 0.8967 0.8967 0.8967 0.8967
5
+ 3 12:23:17 0 0.1000 0.39905918871464724 _ _ _ _ _ _ _ _ _ _ 0.904 0.904 0.904 0.904
6
+ 4 12:46:45 0 0.1000 0.3742375968457236 _ _ _ _ _ _ _ _ _ _ 0.9095 0.9095 0.9095 0.9095
7
+ 5 13:10:21 0 0.1000 0.35342702350133975 _ _ _ _ _ _ _ _ _ _ 0.9169 0.9169 0.9169 0.9169
8
+ 6 13:33:49 0 0.1000 0.33980307603623794 _ _ _ _ _ _ _ _ _ _ 0.9202 0.9202 0.9202 0.9202
9
+ 7 13:57:21 0 0.1000 0.32579335047085706 _ _ _ _ _ _ _ _ _ _ 0.9232 0.9232 0.9232 0.9232
10
+ 8 14:20:44 0 0.1000 0.31598528568207496 _ _ _ _ _ _ _ _ _ _ 0.9276 0.9276 0.9276 0.9276
11
+ 9 14:44:11 0 0.1000 0.30771679594818646 _ _ _ _ _ _ _ _ _ _ 0.9303 0.9303 0.9303 0.9303
12
+ 10 15:07:37 0 0.1000 0.29935787006847003 _ _ _ _ _ _ _ _ _ _ 0.933 0.933 0.933 0.933
13
+ 11 15:31:00 0 0.1000 0.2921474775313901 _ _ _ _ _ _ _ _ _ _ 0.9343 0.9343 0.9343 0.9343
14
+ 12 15:54:34 0 0.1000 0.2871364236691731 _ _ _ _ _ _ _ _ _ _ 0.9354 0.9354 0.9354 0.9354
15
+ 13 16:17:59 0 0.1000 0.28096626128222385 _ _ _ _ _ _ _ _ _ _ 0.9367 0.9367 0.9367 0.9367
16
+ 14 16:41:22 0 0.1000 0.2746626851626277 _ _ _ _ _ _ _ _ _ _ 0.9388 0.9388 0.9388 0.9388
17
+ 15 17:04:53 0 0.1000 0.2702156779567315 _ _ _ _ _ _ _ _ _ _ 0.939 0.939 0.939 0.939
18
+ 16 17:28:14 0 0.1000 0.2677499098394409 _ _ _ _ _ _ _ _ _ _ 0.94 0.94 0.94 0.94
19
+ 17 17:51:41 0 0.1000 0.26327742492058104 _ _ _ _ _ _ _ _ _ _ 0.9414 0.9414 0.9414 0.9414
20
+ 18 18:15:15 0 0.1000 0.25877575904336814 _ _ _ _ _ _ _ _ _ _ 0.9432 0.9432 0.9432 0.9432
21
+ 19 18:38:40 0 0.1000 0.2537475148621729 _ _ _ _ _ _ _ _ _ _ 0.9429 0.9429 0.9429 0.9429
22
+ 20 19:02:06 0 0.1000 0.2526139328870411 _ _ _ _ _ _ _ _ _ _ 0.9433 0.9433 0.9433 0.9433
23
+ 21 19:25:36 0 0.1000 0.25058489056542393 _ _ _ _ _ _ _ _ _ _ 0.9454 0.9454 0.9454 0.9454
24
+ 22 19:49:01 0 0.1000 0.24793850796675693 _ _ _ _ _ _ _ _ _ _ 0.9459 0.9459 0.9459 0.9459
25
+ 23 20:12:32 0 0.1000 0.24369133532522563 _ _ _ _ _ _ _ _ _ _ 0.9458 0.9458 0.9458 0.9458
26
+ 24 20:35:57 0 0.1000 0.24157939653927565 _ _ _ _ _ _ _ _ _ _ 0.9464 0.9464 0.9464 0.9464
27
+ 25 20:59:37 0 0.1000 0.23970980893528734 _ _ _ _ _ _ _ _ _ _ 0.9477 0.9477 0.9477 0.9477
28
+ 26 21:23:02 0 0.1000 0.23712054908323255 _ _ _ _ _ _ _ _ _ _ 0.9474 0.9474 0.9474 0.9474
29
+ 27 21:46:26 0 0.1000 0.2367942676861768 _ _ _ _ _ _ _ _ _ _ 0.9464 0.9464 0.9464 0.9464
30
+ 28 22:09:57 0 0.1000 0.2333034627188289 _ _ _ _ _ _ _ _ _ _ 0.9481 0.9481 0.9481 0.9481
31
+ 29 22:33:23 0 0.1000 0.23126234505920054 _ _ _ _ _ _ _ _ _ _ 0.949 0.949 0.949 0.949
32
+ 30 22:56:56 0 0.1000 0.22932123181550282 _ _ _ _ _ _ _ _ _ _ 0.9484 0.9484 0.9484 0.9484
33
+ 31 23:20:45 0 0.1000 0.2273743192486796 _ _ _ _ _ _ _ _ _ _ 0.9492 0.9492 0.9492 0.9492
34
+ 32 23:44:10 0 0.1000 0.2255119944040062 _ _ _ _ _ _ _ _ _ _ 0.9485 0.9485 0.9485 0.9485
35
+ 33 00:07:34 0 0.1000 0.22409818432363 _ _ _ _ _ _ _ _ _ _ 0.95 0.95 0.95 0.95
36
+ 34 00:30:57 0 0.1000 0.22151199458546297 _ _ _ _ _ _ _ _ _ _ 0.9506 0.9506 0.9506 0.9506
37
+ 35 00:54:24 0 0.1000 0.22155024732969722 _ _ _ _ _ _ _ _ _ _ 0.9512 0.9512 0.9512 0.9512
38
+ 36 01:17:51 1 0.1000 0.2205742845282017 _ _ _ _ _ _ _ _ _ _ 0.9511 0.9511 0.9511 0.9511
39
+ 37 01:41:20 0 0.1000 0.21852846494206418 _ _ _ _ _ _ _ _ _ _ 0.9511 0.9511 0.9511 0.9511
40
+ 38 02:04:56 0 0.1000 0.21719484818274226 _ _ _ _ _ _ _ _ _ _ 0.9519 0.9519 0.9519 0.9519
41
+ 39 02:28:19 0 0.1000 0.21682299653427595 _ _ _ _ _ _ _ _ _ _ 0.9509 0.9509 0.9509 0.9509
42
+ 40 02:51:41 0 0.1000 0.21704343444362736 _ _ _ _ _ _ _ _ _ _ 0.9524 0.9524 0.9524 0.9524
43
+ 41 03:15:08 1 0.1000 0.21260865162828568 _ _ _ _ _ _ _ _ _ _ 0.9526 0.9526 0.9526 0.9526
44
+ 42 03:38:43 0 0.1000 0.21280285771466917 _ _ _ _ _ _ _ _ _ _ 0.9525 0.9525 0.9525 0.9525
45
+ 43 04:02:11 1 0.1000 0.21139400303602057 _ _ _ _ _ _ _ _ _ _ 0.9532 0.9532 0.9532 0.9532
46
+ 44 04:25:50 0 0.1000 0.2103025148200453 _ _ _ _ _ _ _ _ _ _ 0.9534 0.9534 0.9534 0.9534
47
+ 45 04:49:17 0 0.1000 0.21047394277326975 _ _ _ _ _ _ _ _ _ _ 0.954 0.954 0.954 0.954
48
+ 46 05:12:43 1 0.1000 0.20889954569228175 _ _ _ _ _ _ _ _ _ _ 0.9538 0.9538 0.9538 0.9538
49
+ 47 05:36:11 0 0.1000 0.2081116257508449 _ _ _ _ _ _ _ _ _ _ 0.9534 0.9534 0.9534 0.9534
50
+ 48 05:59:47 0 0.1000 0.20735290020180713 _ _ _ _ _ _ _ _ _ _ 0.9544 0.9544 0.9544 0.9544
51
+ 49 06:23:19 0 0.1000 0.2051314154268594 _ _ _ _ _ _ _ _ _ _ 0.9545 0.9545 0.9545 0.9545
52
+ 50 06:46:47 0 0.1000 0.20549383197211374 _ _ _ _ _ _ _ _ _ _ 0.9542 0.9542 0.9542 0.9542
53
+ 51 07:10:30 1 0.1000 0.20552540715422096 _ _ _ _ _ _ _ _ _ _ 0.9541 0.9541 0.9541 0.9541
54
+ 52 07:34:01 2 0.1000 0.2022382171174598 _ _ _ _ _ _ _ _ _ _ 0.9545 0.9545 0.9545 0.9545
55
+ 53 07:57:33 0 0.1000 0.2034686032817135 _ _ _ _ _ _ _ _ _ _ 0.955 0.955 0.955 0.955
56
+ 54 08:20:55 1 0.1000 0.2022125936710602 _ _ _ _ _ _ _ _ _ _ 0.9547 0.9547 0.9547 0.9547
57
+ 55 08:44:21 0 0.1000 0.20195547892638116 _ _ _ _ _ _ _ _ _ _ 0.9548 0.9548 0.9548 0.9548
58
+ 56 09:07:58 0 0.1000 0.2010047433371816 _ _ _ _ _ _ _ _ _ _ 0.9549 0.9549 0.9549 0.9549
59
+ 57 09:31:27 0 0.1000 0.20029620328622608 _ _ _ _ _ _ _ _ _ _ 0.9554 0.9554 0.9554 0.9554
60
+ 58 09:55:07 0 0.1000 0.200410623315139 _ _ _ _ _ _ _ _ _ _ 0.9555 0.9555 0.9555 0.9555
61
+ 59 10:18:35 1 0.1000 0.19885549961224236 _ _ _ _ _ _ _ _ _ _ 0.9559 0.9559 0.9559 0.9559
62
+ 60 10:42:00 0 0.1000 0.1969310509000975 _ _ _ _ _ _ _ _ _ _ 0.9562 0.9562 0.9562 0.9562
63
+ 61 11:05:28 0 0.1000 0.19752888845380348 _ _ _ _ _ _ _ _ _ _ 0.956 0.956 0.956 0.956
64
+ 62 11:28:57 1 0.1000 0.19763092688816444 _ _ _ _ _ _ _ _ _ _ 0.9562 0.9562 0.9562 0.9562
65
+ 63 11:52:29 2 0.1000 0.19646054708820582 _ _ _ _ _ _ _ _ _ _ 0.9561 0.9561 0.9561 0.9561
66
+ 64 12:16:10 0 0.1000 0.19479624992381397 _ _ _ _ _ _ _ _ _ _ 0.9568 0.9568 0.9568 0.9568
67
+ 65 12:39:43 0 0.1000 0.19464160452930918 _ _ _ _ _ _ _ _ _ _ 0.9566 0.9566 0.9566 0.9566
68
+ 66 13:03:14 0 0.1000 0.19548884070323036 _ _ _ _ _ _ _ _ _ _ 0.9568 0.9568 0.9568 0.9568
69
+ 67 13:26:40 1 0.1000 0.19475973537225158 _ _ _ _ _ _ _ _ _ _ 0.9569 0.9569 0.9569 0.9569
70
+ 68 13:50:07 2 0.1000 0.19439746426108423 _ _ _ _ _ _ _ _ _ _ 0.9563 0.9563 0.9563 0.9563
71
+ 69 14:13:32 0 0.1000 0.19370671081686655 _ _ _ _ _ _ _ _ _ _ 0.9564 0.9564 0.9564 0.9564
72
+ 70 14:36:59 0 0.1000 0.19183528371686911 _ _ _ _ _ _ _ _ _ _ 0.9576 0.9576 0.9576 0.9576
73
+ 71 15:00:41 0 0.1000 0.19287951452775143 _ _ _ _ _ _ _ _ _ _ 0.9572 0.9572 0.9572 0.9572
74
+ 72 15:24:07 1 0.1000 0.19141927684724075 _ _ _ _ _ _ _ _ _ _ 0.9576 0.9576 0.9576 0.9576
75
+ 73 15:47:38 0 0.1000 0.19037402588275787 _ _ _ _ _ _ _ _ _ _ 0.957 0.957 0.957 0.957
76
+ 74 16:11:07 0 0.1000 0.19046012064034978 _ _ _ _ _ _ _ _ _ _ 0.9571 0.9571 0.9571 0.9571
77
+ 75 16:34:34 1 0.1000 0.1903303293783702 _ _ _ _ _ _ _ _ _ _ 0.9572 0.9572 0.9572 0.9572
78
+ 76 16:58:12 0 0.1000 0.19066792594619927 _ _ _ _ _ _ _ _ _ _ 0.9573 0.9573 0.9573 0.9573
79
+ 77 17:22:06 1 0.1000 0.18952273385669854 _ _ _ _ _ _ _ _ _ _ 0.9573 0.9573 0.9573 0.9573
80
+ 78 17:45:42 0 0.1000 0.18825725826713122 _ _ _ _ _ _ _ _ _ _ 0.9579 0.9579 0.9579 0.9579
81
+ 79 18:09:17 0 0.1000 0.18935545475904278 _ _ _ _ _ _ _ _ _ _ 0.958 0.958 0.958 0.958
82
+ 80 18:32:52 1 0.1000 0.1879875679614127 _ _ _ _ _ _ _ _ _ _ 0.958 0.958 0.958 0.958
83
+ 81 18:56:27 0 0.1000 0.18778680214824128 _ _ _ _ _ _ _ _ _ _ 0.9584 0.9584 0.9584 0.9584
84
+ 82 19:20:01 0 0.1000 0.18746448831188942 _ _ _ _ _ _ _ _ _ _ 0.9585 0.9585 0.9585 0.9585
85
+ 83 19:43:32 0 0.1000 0.18597292849562683 _ _ _ _ _ _ _ _ _ _ 0.9578 0.9578 0.9578 0.9578
86
+ 84 20:07:22 0 0.1000 0.1860005068718633 _ _ _ _ _ _ _ _ _ _ 0.9582 0.9582 0.9582 0.9582
87
+ 85 20:30:58 1 0.1000 0.18633582194462925 _ _ _ _ _ _ _ _ _ _ 0.9583 0.9583 0.9583 0.9583
88
+ 86 20:54:31 2 0.1000 0.18582389025507537 _ _ _ _ _ _ _ _ _ _ 0.9584 0.9584 0.9584 0.9584
89
+ 87 21:18:02 0 0.1000 0.18583678361469438 _ _ _ _ _ _ _ _ _ _ 0.9584 0.9584 0.9584 0.9584
90
+ 88 21:41:34 1 0.1000 0.18316908685788577 _ _ _ _ _ _ _ _ _ _ 0.9586 0.9586 0.9586 0.9586
91
+ 89 22:05:12 0 0.1000 0.18534635613074252 _ _ _ _ _ _ _ _ _ _ 0.958 0.958 0.958 0.958
92
+ 90 22:28:54 1 0.1000 0.18384256521973166 _ _ _ _ _ _ _ _ _ _ 0.9587 0.9587 0.9587 0.9587
93
+ 91 22:52:27 2 0.1000 0.18405010121052887 _ _ _ _ _ _ _ _ _ _ 0.9588 0.9588 0.9588 0.9588
94
+ 92 23:15:59 0 0.0500 0.17556561555019948 _ _ _ _ _ _ _ _ _ _ 0.9603 0.9603 0.9603 0.9603
95
+ 93 23:39:32 0 0.0500 0.16994592318872956 _ _ _ _ _ _ _ _ _ _ 0.9603 0.9603 0.9603 0.9603
96
+ 94 00:03:02 0 0.0500 0.16775754866871675 _ _ _ _ _ _ _ _ _ _ 0.9605 0.9605 0.9605 0.9605
97
+ 95 00:26:30 0 0.0500 0.167797892421305 _ _ _ _ _ _ _ _ _ _ 0.9608 0.9608 0.9608 0.9608
98
+ 96 00:50:08 1 0.0500 0.1654042344597402 _ _ _ _ _ _ _ _ _ _ 0.961 0.961 0.961 0.961
99
+ 97 01:13:54 0 0.0500 0.1638417892170097 _ _ _ _ _ _ _ _ _ _ 0.9611 0.9611 0.9611 0.9611
100
+ 98 01:37:21 0 0.0500 0.1628716704711418 _ _ _ _ _ _ _ _ _ _ 0.9615 0.9615 0.9615 0.9615
101
+ 99 02:00:54 0 0.0500 0.16135923191805748 _ _ _ _ _ _ _ _ _ _ 0.9614 0.9614 0.9614 0.9614
102
+ 100 02:24:23 0 0.0500 0.16102960881517717 _ _ _ _ _ _ _ _ _ _ 0.9614 0.9614 0.9614 0.9614
103
+ 101 02:47:58 0 0.0500 0.1597511584858509 _ _ _ _ _ _ _ _ _ _ 0.9612 0.9612 0.9612 0.9612
104
+ 102 03:11:33 0 0.0500 0.158750009230552 _ _ _ _ _ _ _ _ _ _ 0.9613 0.9613 0.9613 0.9613
105
+ 103 03:35:16 0 0.0500 0.1598144823844623 _ _ _ _ _ _ _ _ _ _ 0.9617 0.9617 0.9617 0.9617
106
+ 104 03:58:47 1 0.0500 0.15843389315256012 _ _ _ _ _ _ _ _ _ _ 0.962 0.962 0.962 0.962
107
+ 105 04:22:18 0 0.0500 0.1582850175641563 _ _ _ _ _ _ _ _ _ _ 0.9619 0.9619 0.9619 0.9619
108
+ 106 04:45:55 0 0.0500 0.15683828063503616 _ _ _ _ _ _ _ _ _ _ 0.9619 0.9619 0.9619 0.9619
109
+ 107 05:09:22 0 0.0500 0.15554793214376686 _ _ _ _ _ _ _ _ _ _ 0.962 0.962 0.962 0.962
110
+ 108 05:32:50 0 0.0500 0.15559760241105475 _ _ _ _ _ _ _ _ _ _ 0.9618 0.9618 0.9618 0.9618
111
+ 109 05:56:18 1 0.0500 0.15592738710675413 _ _ _ _ _ _ _ _ _ _ 0.9619 0.9619 0.9619 0.9619
112
+ 110 06:19:57 2 0.0500 0.1559649915345551 _ _ _ _ _ _ _ _ _ _ 0.9625 0.9625 0.9625 0.9625
113
+ 111 06:43:28 0 0.0250 0.15047709863006958 _ _ _ _ _ _ _ _ _ _ 0.9626 0.9626 0.9626 0.9626
114
+ 112 07:06:53 0 0.0250 0.14901342020445227 _ _ _ _ _ _ _ _ _ _ 0.9626 0.9626 0.9626 0.9626
115
+ 113 07:30:23 0 0.0250 0.14785490136836343 _ _ _ _ _ _ _ _ _ _ 0.9629 0.9629 0.9629 0.9629
116
+ 114 07:53:54 0 0.0250 0.14793952625254247 _ _ _ _ _ _ _ _ _ _ 0.963 0.963 0.963 0.963
117
+ 115 08:17:22 1 0.0250 0.14614440136844034 _ _ _ _ _ _ _ _ _ _ 0.9629 0.9629 0.9629 0.9629
118
+ 116 08:41:03 0 0.0250 0.14456831456853306 _ _ _ _ _ _ _ _ _ _ 0.9631 0.9631 0.9631 0.9631
119
+ 117 09:04:35 0 0.0250 0.1456362626140971 _ _ _ _ _ _ _ _ _ _ 0.9631 0.9631 0.9631 0.9631
120
+ 118 09:28:00 1 0.0250 0.1439011391959644 _ _ _ _ _ _ _ _ _ _ 0.9631 0.9631 0.9631 0.9631
121
+ 119 09:51:25 0 0.0250 0.14387666936879415 _ _ _ _ _ _ _ _ _ _ 0.9632 0.9632 0.9632 0.9632
122
+ 120 10:14:51 0 0.0250 0.14368277304316643 _ _ _ _ _ _ _ _ _ _ 0.9633 0.9633 0.9633 0.9633
123
+ 121 10:38:15 0 0.0250 0.14401180188408505 _ _ _ _ _ _ _ _ _ _ 0.9632 0.9632 0.9632 0.9632
124
+ 122 11:01:45 1 0.0250 0.14190384826544228 _ _ _ _ _ _ _ _ _ _ 0.9632 0.9632 0.9632 0.9632
125
+ 123 11:25:31 0 0.0250 0.14156404113846752 _ _ _ _ _ _ _ _ _ _ 0.9633 0.9633 0.9633 0.9633
126
+ 124 11:49:02 0 0.0250 0.14334506448280024 _ _ _ _ _ _ _ _ _ _ 0.9635 0.9635 0.9635 0.9635
127
+ 125 12:12:31 1 0.0250 0.1419388082834431 _ _ _ _ _ _ _ _ _ _ 0.9634 0.9634 0.9634 0.9634
128
+ 126 12:36:00 2 0.0250 0.14170677811496898 _ _ _ _ _ _ _ _ _ _ 0.9636 0.9636 0.9636 0.9636
129
+ 127 12:59:27 0 0.0125 0.13874942668664622 _ _ _ _ _ _ _ _ _ _ 0.9638 0.9638 0.9638 0.9638
130
+ 128 13:22:56 0 0.0125 0.13761071341297706 _ _ _ _ _ _ _ _ _ _ 0.9639 0.9639 0.9639 0.9639
131
+ 129 13:46:24 0 0.0125 0.13801613958699138 _ _ _ _ _ _ _ _ _ _ 0.9639 0.9639 0.9639 0.9639
132
+ 130 14:10:12 1 0.0125 0.13691942280057715 _ _ _ _ _ _ _ _ _ _ 0.964 0.964 0.964 0.964
133
+ 131 14:33:48 0 0.0125 0.13759175252124392 _ _ _ _ _ _ _ _ _ _ 0.964 0.964 0.964 0.964
134
+ 132 14:57:26 1 0.0125 0.13605770421426944 _ _ _ _ _ _ _ _ _ _ 0.964 0.964 0.964 0.964
135
+ 133 15:20:56 0 0.0125 0.13757905333765666 _ _ _ _ _ _ _ _ _ _ 0.9641 0.9641 0.9641 0.9641
136
+ 134 15:44:27 1 0.0125 0.13585668101601625 _ _ _ _ _ _ _ _ _ _ 0.964 0.964 0.964 0.964
137
+ 135 16:07:57 0 0.0125 0.1359525140283796 _ _ _ _ _ _ _ _ _ _ 0.9641 0.9641 0.9641 0.9641
138
+ 136 16:31:41 1 0.0125 0.1353510881129821 _ _ _ _ _ _ _ _ _ _ 0.9642 0.9642 0.9642 0.9642
139
+ 137 16:55:09 0 0.0125 0.13588478053671538 _ _ _ _ _ _ _ _ _ _ 0.9641 0.9641 0.9641 0.9641
140
+ 138 17:18:45 1 0.0125 0.13547475301437173 _ _ _ _ _ _ _ _ _ _ 0.9642 0.9642 0.9642 0.9642
141
+ 139 17:42:22 2 0.0125 0.13502782606054411 _ _ _ _ _ _ _ _ _ _ 0.9642 0.9642 0.9642 0.9642
142
+ 140 18:05:53 0 0.0125 0.13481195497481782 _ _ _ _ _ _ _ _ _ _ 0.9641 0.9641 0.9641 0.9641
143
+ 141 18:29:30 0 0.0125 0.13416481617924972 _ _ _ _ _ _ _ _ _ _ 0.9645 0.9645 0.9645 0.9645
144
+ 142 18:53:03 0 0.0125 0.13502357041225113 _ _ _ _ _ _ _ _ _ _ 0.9643 0.9643 0.9643 0.9643
145
+ 143 19:16:51 1 0.0125 0.1348685677112196 _ _ _ _ _ _ _ _ _ _ 0.9643 0.9643 0.9643 0.9643
146
+ 144 19:40:23 2 0.0125 0.13317074967193576 _ _ _ _ _ _ _ _ _ _ 0.9645 0.9645 0.9645 0.9645
147
+ 145 20:03:53 0 0.0125 0.13302220075108664 _ _ _ _ _ _ _ _ _ _ 0.9644 0.9644 0.9644 0.9644
148
+ 146 20:27:21 0 0.0125 0.13223227358080888 _ _ _ _ _ _ _ _ _ _ 0.9644 0.9644 0.9644 0.9644
149
+ 147 20:50:55 0 0.0125 0.13367648299557353 _ _ _ _ _ _ _ _ _ _ 0.9644 0.9644 0.9644 0.9644
150
+ 148 21:14:30 1 0.0125 0.13366286128920055 _ _ _ _ _ _ _ _ _ _ 0.9644 0.9644 0.9644 0.9644
151
+ 149 21:38:15 2 0.0125 0.13307078396670677 _ _ _ _ _ _ _ _ _ _ 0.9641 0.9641 0.9641 0.9641
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3402226c5babc6cd0b34fc0a16d05528603634255fec03d455621f6898a9433c
3
+ size 314055714
training.log ADDED
The diff for this file is too large to render. See raw diff