Hugging Face's logo

flair
/
ner-multi-fast

Token Classification
Flair
PyTorch
sequence-tagger-model
Model card Files Community
1
alanakbik commited on
Commit
25200da
•
1 Parent(s): 3453a2e

initial model commit

Browse files
Files changed (4) hide show
  1. README.md +148 -0
  2. loss.tsv +151 -0
  3. pytorch_model.bin +3 -0
  4. training.log +0 -0
README.md ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - flair
4
+ - token-classification
5
+ - sequence-tagger-model
6
+ language: en de nl es
7
+ datasets:
8
+ - conll2003
9
+ inference: false
10
+ ---
11
+
12
+ ## 4-Language NER in Flair (English, German, Dutch and Spanish)
13
+
14
+ This is the standard 4-class NER model for 4 CoNLL-03 languages that ships with [Flair](https://github.com/flairNLP/flair/). Also kind of works for related languages like French.
15
+
16
+ F1-Score: **92,16** (CoNLL-03 English), **87,33** (CoNLL-03 German revised), **88,96** (CoNLL-03 Dutch), **86,65** (CoNLL-03 Spanish)
17
+
18
+
19
+ Predicts 4 tags:
20
+
21
+ | **tag** | **meaning** |
22
+ |---------------------------------|-----------|
23
+ | PER | person name |
24
+ | LOC | location name |
25
+ | ORG | organization name |
26
+ | MISC | other name |
27
+
28
+ Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF.
29
+
30
+ ---
31
+
32
+ ### Demo: How to use in Flair
33
+
34
+ Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
35
+
36
+ ```python
37
+ from flair.data import Sentence
38
+ from flair.models import SequenceTagger
39
+
40
+ # load tagger
41
+ tagger = SequenceTagger.load("flair/ner-multi")
42
+
43
+ # make example sentence in any of the four languages
44
+ sentence = Sentence("George Washington ging nach Washington")
45
+
46
+ # predict NER tags
47
+ tagger.predict(sentence)
48
+
49
+ # print sentence
50
+ print(sentence)
51
+
52
+ # print predicted NER spans
53
+ print('The following NER tags are found:')
54
+ # iterate over entities and print
55
+ for entity in sentence.get_spans('ner'):
56
+ print(entity)
57
+
58
+ ```
59
+
60
+ This yields the following output:
61
+ ```
62
+ Span [1,2]: "George Washington" [− Labels: PER (0.9977)]
63
+ Span [5]: "Washington" [− Labels: LOC (0.9895)]
64
+ ```
65
+
66
+ So, the entities "*George Washington*" (labeled as a **person**) and "*Washington*" (labeled as a **location**) are found in the sentence "*George Washington ging nach Washington*".
67
+
68
+
69
+ ---
70
+
71
+ ### Training: Script to train this model
72
+
73
+ The following Flair script was used to train this model:
74
+
75
+ ```python
76
+ from flair.data import Corpus
77
+ from flair.datasets import CONLL_03, CONLL_03_GERMAN, CONLL_03_DUTCH, CONLL_03_SPANISH
78
+ from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings
79
+
80
+ # 1. get the multi-language corpus
81
+ corpus: Corpus = MultiCorpus([
82
+ CONLL_03(), # English corpus
83
+ CONLL_03_GERMAN(), # German corpus
84
+ CONLL_03_DUTCH(), # Dutch corpus
85
+ CONLL_03_SPANISH(), # Spanish corpus
86
+ ])
87
+
88
+ # 2. what tag do we want to predict?
89
+ tag_type = 'ner'
90
+
91
+ # 3. make the tag dictionary from the corpus
92
+ tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
93
+
94
+ # 4. initialize each embedding we use
95
+ embedding_types = [
96
+
97
+ # GloVe embeddings
98
+ WordEmbeddings('glove'),
99
+
100
+ # FastText embeddings
101
+ WordEmbeddings('de'),
102
+
103
+ # contextual string embeddings, forward
104
+ FlairEmbeddings('multi-forward'),
105
+
106
+ # contextual string embeddings, backward
107
+ FlairEmbeddings('multi-backward'),
108
+ ]
109
+
110
+ # embedding stack consists of Flair and GloVe embeddings
111
+ embeddings = StackedEmbeddings(embeddings=embedding_types)
112
+
113
+ # 5. initialize sequence tagger
114
+ from flair.models import SequenceTagger
115
+
116
+ tagger = SequenceTagger(hidden_size=256,
117
+ embeddings=embeddings,
118
+ tag_dictionary=tag_dictionary,
119
+ tag_type=tag_type)
120
+
121
+ # 6. initialize trainer
122
+ from flair.trainers import ModelTrainer
123
+
124
+ trainer = ModelTrainer(tagger, corpus)
125
+
126
+ # 7. run training
127
+ trainer.train('resources/taggers/ner-multi',
128
+ train_with_dev=True,
129
+ max_epochs=150)
130
+ ```
131
+
132
+
133
+
134
+ ---
135
+
136
+ ### Cite
137
+
138
+ Please cite the following paper when using this model.
139
+
140
+ ```
141
+ @inproceedings{akbik2018coling,
142
+ title={Contextual String Embeddings for Sequence Labeling},
143
+ author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
144
+ booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
145
+ pages = {1638--1649},
146
+ year = {2018}
147
+ }
148
+ ```
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 10:59:00 0 0.1000 2.953475790447307 _ _ _ _ _ _ _ _ _ _ 0.7908 0.7848 0.7878 0.7878
3
+ 1 11:03:26 0 0.1000 1.5613928847477874 _ _ _ _ _ _ _ _ _ _ 0.8328 0.7913 0.8115 0.8115
4
+ 2 11:07:47 0 0.1000 1.3328234553044571 _ _ _ _ _ _ _ _ _ _ 0.8269 0.8103 0.8185 0.8185
5
+ 3 11:12:10 0 0.1000 1.1894718631716301 _ _ _ _ _ _ _ _ _ _ 0.8479 0.8346 0.8412 0.8412
6
+ 4 11:16:31 0 0.1000 1.1186298550029252 _ _ _ _ _ _ _ _ _ _ 0.8536 0.828 0.8406 0.8406
7
+ 5 11:20:59 0 0.1000 1.0496702689508508 _ _ _ _ _ _ _ _ _ _ 0.8618 0.8418 0.8517 0.8517
8
+ 6 11:25:22 0 0.1000 0.9990235921427482 _ _ _ _ _ _ _ _ _ _ 0.854 0.852 0.853 0.853
9
+ 7 11:29:41 0 0.1000 0.961911206602871 _ _ _ _ _ _ _ _ _ _ 0.8673 0.8407 0.8538 0.8538
10
+ 8 11:34:05 0 0.1000 0.9181876736129632 _ _ _ _ _ _ _ _ _ _ 0.8708 0.8539 0.8623 0.8623
11
+ 9 11:38:30 0 0.1000 0.907997776430991 _ _ _ _ _ _ _ _ _ _ 0.8633 0.8567 0.86 0.86
12
+ 10 11:42:57 0 0.1000 0.8613800380307894 _ _ _ _ _ _ _ _ _ _ 0.8679 0.8518 0.8598 0.8598
13
+ 11 11:47:27 0 0.1000 0.849987226690182 _ _ _ _ _ _ _ _ _ _ 0.8631 0.8565 0.8598 0.8598
14
+ 12 11:51:48 0 0.1000 0.830854225634283 _ _ _ _ _ _ _ _ _ _ 0.873 0.8513 0.862 0.862
15
+ 13 11:56:08 0 0.1000 0.8218251601785131 _ _ _ _ _ _ _ _ _ _ 0.8759 0.8565 0.8661 0.8661
16
+ 14 12:00:32 0 0.1000 0.8054646737349248 _ _ _ _ _ _ _ _ _ _ 0.8756 0.8589 0.8672 0.8672
17
+ 15 12:04:53 0 0.1000 0.7794681299046988 _ _ _ _ _ _ _ _ _ _ 0.8746 0.8583 0.8663 0.8664
18
+ 16 12:09:13 0 0.1000 0.7848604690242548 _ _ _ _ _ _ _ _ _ _ 0.8802 0.8594 0.8697 0.8697
19
+ 17 12:13:34 1 0.1000 0.7637730026230019 _ _ _ _ _ _ _ _ _ _ 0.8732 0.8601 0.8666 0.8666
20
+ 18 12:17:54 0 0.1000 0.7584837641142651 _ _ _ _ _ _ _ _ _ _ 0.8809 0.8626 0.8716 0.8717
21
+ 19 12:22:14 0 0.1000 0.7435564011696313 _ _ _ _ _ _ _ _ _ _ 0.8783 0.8606 0.8694 0.8694
22
+ 20 12:26:37 0 0.1000 0.7319077155977514 _ _ _ _ _ _ _ _ _ _ 0.8839 0.8621 0.8728 0.8729
23
+ 21 12:30:57 0 0.1000 0.7107181243636796 _ _ _ _ _ _ _ _ _ _ 0.8647 0.8614 0.863 0.863
24
+ 22 12:35:17 0 0.1000 0.7171132942111534 _ _ _ _ _ _ _ _ _ _ 0.8764 0.8651 0.8707 0.8707
25
+ 23 12:39:40 1 0.1000 0.7009657600265137 _ _ _ _ _ _ _ _ _ _ 0.8738 0.8665 0.8701 0.8701
26
+ 24 12:44:00 0 0.1000 0.6989209016579343 _ _ _ _ _ _ _ _ _ _ 0.8829 0.8594 0.871 0.871
27
+ 25 12:48:21 0 0.1000 0.6951734939474944 _ _ _ _ _ _ _ _ _ _ 0.8827 0.8569 0.8696 0.8696
28
+ 26 12:52:43 0 0.1000 0.6822735162280682 _ _ _ _ _ _ _ _ _ _ 0.8842 0.857 0.8704 0.8704
29
+ 27 12:57:07 0 0.1000 0.6838434803809537 _ _ _ _ _ _ _ _ _ _ 0.8753 0.8681 0.8717 0.8717
30
+ 28 13:01:31 1 0.1000 0.6716522983858122 _ _ _ _ _ _ _ _ _ _ 0.8788 0.861 0.8698 0.8698
31
+ 29 13:05:47 0 0.1000 0.6634576296755379 _ _ _ _ _ _ _ _ _ _ 0.877 0.8626 0.8697 0.8697
32
+ 30 13:10:06 0 0.1000 0.6633003305447108 _ _ _ _ _ _ _ _ _ _ 0.8754 0.8626 0.869 0.869
33
+ 31 13:14:26 0 0.1000 0.6601696083931253 _ _ _ _ _ _ _ _ _ _ 0.8841 0.8606 0.8722 0.8722
34
+ 32 13:18:44 0 0.1000 0.6539714311143616 _ _ _ _ _ _ _ _ _ _ 0.8754 0.8662 0.8707 0.8708
35
+ 33 13:23:01 0 0.1000 0.6405916364668743 _ _ _ _ _ _ _ _ _ _ 0.8819 0.8654 0.8736 0.8736
36
+ 34 13:27:21 0 0.1000 0.642544928475003 _ _ _ _ _ _ _ _ _ _ 0.882 0.864 0.8729 0.8729
37
+ 35 13:31:45 1 0.1000 0.641501997323611 _ _ _ _ _ _ _ _ _ _ 0.8767 0.8663 0.8715 0.8715
38
+ 36 13:36:09 2 0.1000 0.635029950176255 _ _ _ _ _ _ _ _ _ _ 0.877 0.8708 0.8739 0.8739
39
+ 37 13:40:36 0 0.1000 0.6317766632252801 _ _ _ _ _ _ _ _ _ _ 0.8828 0.8678 0.8752 0.8752
40
+ 38 13:44:55 0 0.1000 0.6303625095185952 _ _ _ _ _ _ _ _ _ _ 0.8761 0.8667 0.8714 0.8714
41
+ 39 13:49:12 0 0.1000 0.6248182013889186 _ _ _ _ _ _ _ _ _ _ 0.8877 0.8609 0.8741 0.8741
42
+ 40 13:53:34 0 0.1000 0.6206092986888428 _ _ _ _ _ _ _ _ _ _ 0.8792 0.8651 0.8721 0.8721
43
+ 41 13:57:59 0 0.1000 0.6217844312872125 _ _ _ _ _ _ _ _ _ _ 0.8822 0.8692 0.8756 0.8757
44
+ 42 14:02:20 1 0.1000 0.6284974648759417 _ _ _ _ _ _ _ _ _ _ 0.8747 0.8647 0.8696 0.8697
45
+ 43 14:06:42 2 0.1000 0.613935504287663 _ _ _ _ _ _ _ _ _ _ 0.8793 0.8622 0.8707 0.8707
46
+ 44 14:10:58 0 0.1000 0.6208729479739985 _ _ _ _ _ _ _ _ _ _ 0.8809 0.8699 0.8754 0.8754
47
+ 45 14:15:26 1 0.1000 0.61270951145969 _ _ _ _ _ _ _ _ _ _ 0.8794 0.8614 0.8703 0.8703
48
+ 46 14:19:48 0 0.1000 0.6128666626890906 _ _ _ _ _ _ _ _ _ _ 0.8793 0.8676 0.8734 0.8734
49
+ 47 14:24:18 1 0.1000 0.6043824241760176 _ _ _ _ _ _ _ _ _ _ 0.8854 0.862 0.8736 0.8735
50
+ 48 14:28:40 0 0.1000 0.5973783223691089 _ _ _ _ _ _ _ _ _ _ 0.8801 0.8669 0.8735 0.8735
51
+ 49 14:32:56 0 0.1000 0.6026040092081145 _ _ _ _ _ _ _ _ _ _ 0.8817 0.8623 0.8719 0.8719
52
+ 50 14:37:26 1 0.1000 0.5987746510701575 _ _ _ _ _ _ _ _ _ _ 0.8747 0.868 0.8713 0.8713
53
+ 51 14:41:50 2 0.1000 0.5947843462103743 _ _ _ _ _ _ _ _ _ _ 0.8775 0.8675 0.8724 0.8725
54
+ 52 14:46:16 0 0.1000 0.5919834629086921 _ _ _ _ _ _ _ _ _ _ 0.8813 0.8647 0.8729 0.8729
55
+ 53 14:50:34 0 0.1000 0.5937702719695134 _ _ _ _ _ _ _ _ _ _ 0.8823 0.8702 0.8762 0.8762
56
+ 54 14:54:55 1 0.1000 0.5917879479803156 _ _ _ _ _ _ _ _ _ _ 0.8805 0.8622 0.8713 0.8713
57
+ 55 14:59:18 0 0.1000 0.5933259962781406 _ _ _ _ _ _ _ _ _ _ 0.8819 0.8626 0.8721 0.8721
58
+ 56 15:03:37 1 0.1000 0.5928614687883759 _ _ _ _ _ _ _ _ _ _ 0.8779 0.8681 0.873 0.873
59
+ 57 15:07:55 2 0.1000 0.5851544519694847 _ _ _ _ _ _ _ _ _ _ 0.882 0.8651 0.8735 0.8735
60
+ 58 15:12:12 0 0.1000 0.5841915451073357 _ _ _ _ _ _ _ _ _ _ 0.8788 0.8674 0.8731 0.8731
61
+ 59 15:16:31 0 0.1000 0.59194735543873 _ _ _ _ _ _ _ _ _ _ 0.8793 0.8678 0.8735 0.8735
62
+ 60 15:20:51 1 0.1000 0.5790510222227323 _ _ _ _ _ _ _ _ _ _ 0.8737 0.8687 0.8712 0.8712
63
+ 61 15:25:10 0 0.1000 0.5804060975380279 _ _ _ _ _ _ _ _ _ _ 0.8782 0.8652 0.8717 0.8717
64
+ 62 15:29:39 1 0.1000 0.585388834950364 _ _ _ _ _ _ _ _ _ _ 0.8735 0.867 0.8702 0.8702
65
+ 63 15:33:56 2 0.1000 0.5736780315191722 _ _ _ _ _ _ _ _ _ _ 0.8826 0.8628 0.8726 0.8726
66
+ 64 15:38:19 0 0.1000 0.5671733145606986 _ _ _ _ _ _ _ _ _ _ 0.8769 0.8624 0.8696 0.8696
67
+ 65 15:42:45 0 0.1000 0.5727116274737428 _ _ _ _ _ _ _ _ _ _ 0.8822 0.8609 0.8714 0.8714
68
+ 66 15:47:18 1 0.1000 0.5807550209185521 _ _ _ _ _ _ _ _ _ _ 0.8807 0.8672 0.8739 0.8739
69
+ 67 15:51:42 2 0.1000 0.5776320083779413 _ _ _ _ _ _ _ _ _ _ 0.8787 0.8712 0.875 0.8749
70
+ 68 15:56:01 3 0.1000 0.5778845083474792 _ _ _ _ _ _ _ _ _ _ 0.8781 0.8673 0.8726 0.8727
71
+ 69 16:00:29 0 0.0500 0.5233265276618764 _ _ _ _ _ _ _ _ _ _ 0.881 0.8682 0.8746 0.8746
72
+ 70 16:04:55 0 0.0500 0.5091402300838657 _ _ _ _ _ _ _ _ _ _ 0.8804 0.8699 0.8751 0.8751
73
+ 71 16:09:22 0 0.0500 0.48569875567842435 _ _ _ _ _ _ _ _ _ _ 0.8841 0.869 0.8765 0.8765
74
+ 72 16:13:42 0 0.0500 0.47439900001701624 _ _ _ _ _ _ _ _ _ _ 0.8834 0.8712 0.8773 0.8773
75
+ 73 16:17:59 0 0.0500 0.46478448706398684 _ _ _ _ _ _ _ _ _ _ 0.8816 0.8712 0.8764 0.8764
76
+ 74 16:22:18 0 0.0500 0.4667157404082863 _ _ _ _ _ _ _ _ _ _ 0.8767 0.8718 0.8742 0.8742
77
+ 75 16:26:39 1 0.0500 0.4609185567276217 _ _ _ _ _ _ _ _ _ _ 0.8858 0.8714 0.8785 0.8785
78
+ 76 16:31:02 0 0.0500 0.4479405909302511 _ _ _ _ _ _ _ _ _ _ 0.8851 0.8672 0.8761 0.8761
79
+ 77 16:35:21 0 0.0500 0.4526363062460368 _ _ _ _ _ _ _ _ _ _ 0.8813 0.87 0.8756 0.8756
80
+ 78 16:39:40 1 0.0500 0.4462794515947487 _ _ _ _ _ _ _ _ _ _ 0.8783 0.8696 0.8739 0.8739
81
+ 79 16:44:05 0 0.0500 0.43589636060524034 _ _ _ _ _ _ _ _ _ _ 0.8823 0.8707 0.8765 0.8765
82
+ 80 16:48:24 0 0.0500 0.4365409203967733 _ _ _ _ _ _ _ _ _ _ 0.8838 0.8702 0.877 0.8769
83
+ 81 16:52:43 1 0.0500 0.43502475776572713 _ _ _ _ _ _ _ _ _ _ 0.8792 0.8733 0.8762 0.8762
84
+ 82 16:57:03 0 0.0500 0.4373334978176562 _ _ _ _ _ _ _ _ _ _ 0.882 0.8707 0.8763 0.8763
85
+ 83 17:01:26 1 0.0500 0.4334466782543237 _ _ _ _ _ _ _ _ _ _ 0.8808 0.8683 0.8745 0.8745
86
+ 84 17:05:54 0 0.0500 0.4254087798321586 _ _ _ _ _ _ _ _ _ _ 0.8839 0.87 0.8769 0.8769
87
+ 85 17:10:19 0 0.0500 0.4255044488190453 _ _ _ _ _ _ _ _ _ _ 0.8822 0.8675 0.8748 0.8748
88
+ 86 17:14:47 1 0.0500 0.4202859611302876 _ _ _ _ _ _ _ _ _ _ 0.8817 0.872 0.8768 0.8768
89
+ 87 17:19:05 0 0.0500 0.41523468196793106 _ _ _ _ _ _ _ _ _ _ 0.8786 0.8695 0.874 0.874
90
+ 88 17:23:25 0 0.0500 0.4162545773211675 _ _ _ _ _ _ _ _ _ _ 0.8803 0.8712 0.8757 0.8757
91
+ 89 17:27:55 1 0.0500 0.4111110245408652 _ _ _ _ _ _ _ _ _ _ 0.8788 0.8717 0.8753 0.8752
92
+ 90 17:32:31 0 0.0500 0.4167104086720782 _ _ _ _ _ _ _ _ _ _ 0.8783 0.8687 0.8735 0.8735
93
+ 91 17:37:03 1 0.0500 0.41473309594586694 _ _ _ _ _ _ _ _ _ _ 0.88 0.8707 0.8753 0.8753
94
+ 92 17:41:27 2 0.0500 0.41171511629929425 _ _ _ _ _ _ _ _ _ _ 0.8839 0.8683 0.8761 0.876
95
+ 93 17:45:59 3 0.0500 0.4053407998584393 _ _ _ _ _ _ _ _ _ _ 0.8832 0.8707 0.8769 0.8769
96
+ 94 17:50:21 0 0.0500 0.4051551429164539 _ _ _ _ _ _ _ _ _ _ 0.8825 0.871 0.8767 0.8767
97
+ 95 17:54:42 0 0.0500 0.40289974819591906 _ _ _ _ _ _ _ _ _ _ 0.8832 0.8712 0.8771 0.8772
98
+ 96 17:59:04 0 0.0500 0.3960453512888854 _ _ _ _ _ _ _ _ _ _ 0.881 0.8744 0.8777 0.8777
99
+ 97 18:03:37 0 0.0500 0.4043394380894219 _ _ _ _ _ _ _ _ _ _ 0.8784 0.8728 0.8756 0.8756
100
+ 98 18:07:59 1 0.0500 0.40074241869638155 _ _ _ _ _ _ _ _ _ _ 0.8811 0.8704 0.8757 0.8757
101
+ 99 18:12:20 2 0.0500 0.4009374214579409 _ _ _ _ _ _ _ _ _ _ 0.8828 0.8684 0.8755 0.8755
102
+ 100 18:16:44 3 0.0500 0.39415279716963364 _ _ _ _ _ _ _ _ _ _ 0.8837 0.8751 0.8794 0.8794
103
+ 101 18:21:07 0 0.0500 0.39470267033507134 _ _ _ _ _ _ _ _ _ _ 0.8786 0.8718 0.8752 0.8752
104
+ 102 18:25:27 1 0.0500 0.3907430959372549 _ _ _ _ _ _ _ _ _ _ 0.8818 0.8725 0.8771 0.8771
105
+ 103 18:29:48 0 0.0500 0.3938351009347457 _ _ _ _ _ _ _ _ _ _ 0.8817 0.8707 0.8762 0.8762
106
+ 104 18:34:16 1 0.0500 0.38270939616572686 _ _ _ _ _ _ _ _ _ _ 0.8821 0.8677 0.8749 0.8748
107
+ 105 18:38:37 0 0.0500 0.3885159160635453 _ _ _ _ _ _ _ _ _ _ 0.883 0.8727 0.8778 0.8778
108
+ 106 18:43:10 1 0.0500 0.3883291266625618 _ _ _ _ _ _ _ _ _ _ 0.886 0.8705 0.8782 0.8782
109
+ 107 18:47:40 2 0.0500 0.38669439267632816 _ _ _ _ _ _ _ _ _ _ 0.8839 0.8701 0.8769 0.8769
110
+ 108 18:52:10 3 0.0500 0.38662982775500127 _ _ _ _ _ _ _ _ _ _ 0.8825 0.8705 0.8765 0.8765
111
+ 109 18:56:31 0 0.0250 0.3666808893379931 _ _ _ _ _ _ _ _ _ _ 0.8832 0.8721 0.8776 0.8776
112
+ 110 19:00:55 0 0.0250 0.3527461102972647 _ _ _ _ _ _ _ _ _ _ 0.8798 0.8733 0.8766 0.8765
113
+ 111 19:05:19 0 0.0250 0.3453178777930988 _ _ _ _ _ _ _ _ _ _ 0.8846 0.8704 0.8774 0.8774
114
+ 112 19:09:39 0 0.0250 0.3501398392813719 _ _ _ _ _ _ _ _ _ _ 0.8822 0.873 0.8776 0.8776
115
+ 113 19:14:09 1 0.0250 0.3436550526062968 _ _ _ _ _ _ _ _ _ _ 0.8858 0.8725 0.8791 0.8791
116
+ 114 19:18:46 0 0.0250 0.3465682747716397 _ _ _ _ _ _ _ _ _ _ 0.8839 0.873 0.8784 0.8784
117
+ 115 19:23:17 1 0.0250 0.3389248694715256 _ _ _ _ _ _ _ _ _ _ 0.8843 0.8736 0.8789 0.8789
118
+ 116 19:27:41 0 0.0250 0.3388266236616183 _ _ _ _ _ _ _ _ _ _ 0.8823 0.8742 0.8782 0.8782
119
+ 117 19:32:02 0 0.0250 0.3426530549034204 _ _ _ _ _ _ _ _ _ _ 0.8824 0.8717 0.877 0.877
120
+ 118 19:36:36 1 0.0250 0.33444241207663017 _ _ _ _ _ _ _ _ _ _ 0.8824 0.8726 0.8775 0.8775
121
+ 119 19:41:13 0 0.0250 0.3356248891977349 _ _ _ _ _ _ _ _ _ _ 0.8833 0.8704 0.8768 0.8768
122
+ 120 19:45:40 1 0.0250 0.3277514071869546 _ _ _ _ _ _ _ _ _ _ 0.8822 0.8754 0.8788 0.8788
123
+ 121 19:50:00 0 0.0250 0.3324392681232043 _ _ _ _ _ _ _ _ _ _ 0.8829 0.8739 0.8784 0.8784
124
+ 122 19:54:18 1 0.0250 0.32520957710642356 _ _ _ _ _ _ _ _ _ _ 0.8853 0.874 0.8796 0.8796
125
+ 123 19:58:38 0 0.0250 0.3207463735829413 _ _ _ _ _ _ _ _ _ _ 0.8826 0.8746 0.8786 0.8786
126
+ 124 20:02:57 0 0.0250 0.32199384285757643 _ _ _ _ _ _ _ _ _ _ 0.8843 0.8738 0.879 0.879
127
+ 125 20:07:22 1 0.0250 0.32214300781759714 _ _ _ _ _ _ _ _ _ _ 0.8851 0.8716 0.8783 0.8783
128
+ 126 20:11:41 2 0.0250 0.3181642439872496 _ _ _ _ _ _ _ _ _ _ 0.8848 0.873 0.8788 0.8789
129
+ 127 20:15:58 0 0.0250 0.31885623830727194 _ _ _ _ _ _ _ _ _ _ 0.8833 0.8725 0.8779 0.8779
130
+ 128 20:20:16 1 0.0250 0.31512833852472777 _ _ _ _ _ _ _ _ _ _ 0.8824 0.8718 0.8771 0.8771
131
+ 129 20:24:36 0 0.0250 0.3152116099719734 _ _ _ _ _ _ _ _ _ _ 0.8867 0.873 0.8798 0.8798
132
+ 130 20:28:55 1 0.0250 0.32019182619040343 _ _ _ _ _ _ _ _ _ _ 0.8847 0.8711 0.8779 0.8778
133
+ 131 20:33:19 2 0.0250 0.3163907725520554 _ _ _ _ _ _ _ _ _ _ 0.8819 0.8723 0.877 0.8771
134
+ 132 20:37:36 3 0.0250 0.3078251098573024 _ _ _ _ _ _ _ _ _ _ 0.8842 0.8717 0.8779 0.8779
135
+ 133 20:42:02 0 0.0250 0.3111053387984559 _ _ _ _ _ _ _ _ _ _ 0.8839 0.8725 0.8781 0.8782
136
+ 134 20:46:23 1 0.0250 0.3092448969837757 _ _ _ _ _ _ _ _ _ _ 0.8845 0.8732 0.8788 0.8788
137
+ 135 20:50:44 2 0.0250 0.3134185765273288 _ _ _ _ _ _ _ _ _ _ 0.8838 0.8734 0.8785 0.8786
138
+ 136 20:55:02 3 0.0250 0.3033614675062414 _ _ _ _ _ _ _ _ _ _ 0.8824 0.8723 0.8773 0.8773
139
+ 137 20:59:22 0 0.0250 0.3163979164883878 _ _ _ _ _ _ _ _ _ _ 0.882 0.8731 0.8776 0.8775
140
+ 138 21:03:39 1 0.0250 0.30996306355280934 _ _ _ _ _ _ _ _ _ _ 0.8818 0.8724 0.8771 0.8771
141
+ 139 21:07:56 2 0.0250 0.30494013050054886 _ _ _ _ _ _ _ _ _ _ 0.8838 0.8712 0.8775 0.8775
142
+ 140 21:12:21 3 0.0250 0.3057546090411619 _ _ _ _ _ _ _ _ _ _ 0.8857 0.8717 0.8787 0.8786
143
+ 141 21:16:41 0 0.0125 0.2974806412130884 _ _ _ _ _ _ _ _ _ _ 0.8852 0.8742 0.8796 0.8797
144
+ 142 21:21:00 0 0.0125 0.2924100736045671 _ _ _ _ _ _ _ _ _ _ 0.8826 0.8733 0.8779 0.8779
145
+ 143 21:25:17 0 0.0125 0.28917630017535056 _ _ _ _ _ _ _ _ _ _ 0.8841 0.8744 0.8792 0.8792
146
+ 144 21:29:37 0 0.0125 0.2891165876694287 _ _ _ _ _ _ _ _ _ _ 0.8855 0.8749 0.8801 0.8802
147
+ 145 21:33:56 0 0.0125 0.2874728485910039 _ _ _ _ _ _ _ _ _ _ 0.884 0.8732 0.8786 0.8786
148
+ 146 21:38:13 0 0.0125 0.28690377793817484 _ _ _ _ _ _ _ _ _ _ 0.8847 0.8717 0.8782 0.8782
149
+ 147 21:42:38 0 0.0125 0.2853494226248391 _ _ _ _ _ _ _ _ _ _ 0.8851 0.874 0.8795 0.8795
150
+ 148 21:47:06 0 0.0125 0.282234717166538 _ _ _ _ _ _ _ _ _ _ 0.8853 0.8744 0.8798 0.8798
151
+ 149 21:51:23 0 0.0125 0.278328151237858 _ _ _ _ _ _ _ _ _ _ 0.8849 0.8734 0.8791 0.8791
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d81cca5b24f295c7a09b36c37353c55d528960fb6218ccb5d6b71c0bc98dfd0e
3
+ size 1512864032
training.log ADDED
The diff for this file is too large to render. See raw diff