Hugging Face's logo

flair
/
ner-german-large

Token Classification Flair PyTorch
German sequence-tagger-model
Model card Files Community
1
alanakbik commited on
Commit
99581cd
•
1 Parent(s): 03af702

initial commit

Browse files
Files changed (4) hide show
  1. README.md +158 -0
  2. loss.tsv +21 -0
  3. pytorch_model.bin +3 -0
  4. training.log +892 -0
README.md ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - flair
4
+ - token-classification
5
+ - sequence-tagger-model
6
+ language: de
7
+ datasets:
8
+ - conll2003
9
+ inference: false
10
+ ---
11
+
12
+ ## German NER in Flair (large model)
13
+
14
+ This is the large 4-class NER model for German that ships with [Flair](https://github.com/flairNLP/flair/).
15
+
16
+ F1-Score: **94,36** (CoNLL-03)
17
+
18
+ **! This model only works with Flair version 0.8 (will be released in the next few days) !**
19
+
20
+ Predicts 4 tags:
21
+
22
+ | **tag** | **meaning** |
23
+ |---------------------------------|-----------|
24
+ | PER | person name |
25
+ | LOC | location name |
26
+ | ORG | organization name |
27
+ | MISC | other name |
28
+
29
+ Based on [document-level XLM-R embeddings](https://www.aclweb.org/anthology/C18-1139/).
30
+
31
+ ---
32
+
33
+ ### Demo: How to use in Flair
34
+
35
+ Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
36
+
37
+ ```python
38
+ from flair.data import Sentence
39
+ from flair.models import SequenceTagger
40
+
41
+ # load tagger
42
+ tagger = SequenceTagger.load("flair/ner-german-large")
43
+
44
+ # make example sentence
45
+ sentence = Sentence("George Washington went to Washington")
46
+
47
+ # predict NER tags
48
+ tagger.predict(sentence)
49
+
50
+ # print sentence
51
+ print(sentence)
52
+
53
+ # print predicted NER spans
54
+ print('The following NER tags are found:')
55
+ # iterate over entities and print
56
+ for entity in sentence.get_spans('ner'):
57
+ print(entity)
58
+
59
+ ```
60
+
61
+ This yields the following output:
62
+ ```
63
+ Span [1,2]: "George Washington" [− Labels: PER (1.0)]
64
+ Span [5]: "Washington" [− Labels: LOC (1.0)]
65
+ ```
66
+
67
+ So, the entities "*George Washington*" (labeled as a **person**) and "*Washington*" (labeled as a **location**) are found in the sentence "*George Washington went to Washington*".
68
+
69
+
70
+ ---
71
+
72
+ ### Training: Script to train this model
73
+
74
+ The following Flair script was used to train this model:
75
+
76
+ ```python
77
+ import torch
78
+
79
+ # 1. get the corpus
80
+ from flair.datasets import CONLL_03_GERMAN
81
+
82
+ corpus = CONLL_03_GERMAN()
83
+
84
+ # 2. what tag do we want to predict?
85
+ tag_type = 'ner'
86
+
87
+ # 3. make the tag dictionary from the corpus
88
+ tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
89
+
90
+ # 4. initialize fine-tuneable transformer embeddings WITH document context
91
+ from flair.embeddings import TransformerWordEmbeddings
92
+
93
+ embeddings = TransformerWordEmbeddings(
94
+ model='xlm-roberta-large',
95
+ layers="-1",
96
+ subtoken_pooling="first",
97
+ fine_tune=True,
98
+ use_context=True,
99
+ )
100
+
101
+ # 5. initialize bare-bones sequence tagger (no CRF, no RNN, no reprojection)
102
+ from flair.models import SequenceTagger
103
+
104
+ tagger = SequenceTagger(
105
+ hidden_size=256,
106
+ embeddings=embeddings,
107
+ tag_dictionary=tag_dictionary,
108
+ tag_type='ner',
109
+ use_crf=False,
110
+ use_rnn=False,
111
+ reproject_embeddings=False,
112
+ )
113
+
114
+ # 6. initialize trainer with AdamW optimizer
115
+ from flair.trainers import ModelTrainer
116
+
117
+ trainer = ModelTrainer(tagger, corpus, optimizer=torch.optim.AdamW)
118
+
119
+ # 7. run training with XLM parameters (20 epochs, small LR)
120
+ from torch.optim.lr_scheduler import OneCycleLR
121
+
122
+ trainer.train('resources/taggers/ner-german-large',
123
+ learning_rate=5.0e-6,
124
+ mini_batch_size=4,
125
+ mini_batch_chunk_size=1,
126
+ max_epochs=20,
127
+ scheduler=OneCycleLR,
128
+ embeddings_storage_mode='none',
129
+ weight_decay=0.,
130
+ )
131
+
132
+ )
133
+ ```
134
+
135
+
136
+
137
+ ---
138
+
139
+ ### Cite
140
+
141
+ Please cite the following paper when using this model.
142
+
143
+ ```
144
+ @misc{schweter2020flert,
145
+ title={FLERT: Document-Level Features for Named Entity Recognition},
146
+ author={Stefan Schweter and Alan Akbik},
147
+ year={2020},
148
+ eprint={2011.06993},
149
+ archivePrefix={arXiv},
150
+ primaryClass={cs.CL}
151
+ }
152
+ ```
153
+
154
+ ---
155
+
156
+ ### Issues?
157
+
158
+ The Flair issue tracker is available [here](https://github.com/flairNLP/flair/issues/).
loss.tsv ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP BAD_EPOCHS LEARNING_RATE TRAIN_LOSS
2
+ 1 16:51:59 4 0.0000 0.2866137816264941
3
+ 2 17:16:36 4 0.0000 0.19963635197194995
4
+ 3 17:41:09 4 0.0000 0.19381841593759824
5
+ 4 18:05:44 4 0.0000 0.16904323373543453
6
+ 5 18:30:18 4 0.0000 0.17083178105798114
7
+ 6 18:54:35 4 0.0000 0.16211920515636655
8
+ 7 19:18:47 4 0.0000 0.16189787430929792
9
+ 8 19:42:57 4 0.0000 0.15914436206804433
10
+ 9 20:07:08 4 0.0000 0.1469039810866205
11
+ 10 20:31:16 4 0.0000 0.1492166711907655
12
+ 11 20:55:24 4 0.0000 0.15147419168516288
13
+ 12 21:19:32 4 0.0000 0.13647247537528812
14
+ 13 21:43:54 4 0.0000 0.14614263093116467
15
+ 14 22:08:30 4 0.0000 0.13674926033805127
16
+ 15 22:33:01 4 0.0000 0.1387276056972103
17
+ 16 22:57:29 4 0.0000 0.13758350506155864
18
+ 17 23:21:41 4 0.0000 0.13729583443464166
19
+ 18 23:45:55 4 0.0000 0.13997356167795372
20
+ 19 00:10:06 4 0.0000 0.13157929521994233
21
+ 20 00:34:21 4 0.0000 0.1353108691912222
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf4313719a9b40a2daa419d066fa1fae405827bc126bde5ecd283b068b34790
3
+ size 2239866697
training.log ADDED
@@ -0,0 +1,892 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-01-15 16:27:19,924 ----------------------------------------------------------------------------------------------------
2
+ 2021-01-15 16:27:19,927 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): XLMRobertaModel(
5
+ (embeddings): RobertaEmbeddings(
6
+ (word_embeddings): Embedding(250002, 1024, padding_idx=1)
7
+ (position_embeddings): Embedding(514, 1024, padding_idx=1)
8
+ (token_type_embeddings): Embedding(1, 1024)
9
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): RobertaEncoder(
13
+ (layer): ModuleList(
14
+ (0): RobertaLayer(
15
+ (attention): RobertaAttention(
16
+ (self): RobertaSelfAttention(
17
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
18
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
19
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): RobertaSelfOutput(
23
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
24
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): RobertaIntermediate(
29
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
30
+ )
31
+ (output): RobertaOutput(
32
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
33
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
34
+ (dropout): Dropout(p=0.1, inplace=False)
35
+ )
36
+ )
37
+ (1): RobertaLayer(
38
+ (attention): RobertaAttention(
39
+ (self): RobertaSelfAttention(
40
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
41
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
42
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
43
+ (dropout): Dropout(p=0.1, inplace=False)
44
+ )
45
+ (output): RobertaSelfOutput(
46
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
47
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
48
+ (dropout): Dropout(p=0.1, inplace=False)
49
+ )
50
+ )
51
+ (intermediate): RobertaIntermediate(
52
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
53
+ )
54
+ (output): RobertaOutput(
55
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
56
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
57
+ (dropout): Dropout(p=0.1, inplace=False)
58
+ )
59
+ )
60
+ (2): RobertaLayer(
61
+ (attention): RobertaAttention(
62
+ (self): RobertaSelfAttention(
63
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
64
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
65
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
66
+ (dropout): Dropout(p=0.1, inplace=False)
67
+ )
68
+ (output): RobertaSelfOutput(
69
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
70
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
71
+ (dropout): Dropout(p=0.1, inplace=False)
72
+ )
73
+ )
74
+ (intermediate): RobertaIntermediate(
75
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
76
+ )
77
+ (output): RobertaOutput(
78
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
79
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
80
+ (dropout): Dropout(p=0.1, inplace=False)
81
+ )
82
+ )
83
+ (3): RobertaLayer(
84
+ (attention): RobertaAttention(
85
+ (self): RobertaSelfAttention(
86
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
87
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
88
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
89
+ (dropout): Dropout(p=0.1, inplace=False)
90
+ )
91
+ (output): RobertaSelfOutput(
92
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
93
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
94
+ (dropout): Dropout(p=0.1, inplace=False)
95
+ )
96
+ )
97
+ (intermediate): RobertaIntermediate(
98
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
99
+ )
100
+ (output): RobertaOutput(
101
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
102
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
103
+ (dropout): Dropout(p=0.1, inplace=False)
104
+ )
105
+ )
106
+ (4): RobertaLayer(
107
+ (attention): RobertaAttention(
108
+ (self): RobertaSelfAttention(
109
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
110
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
111
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
112
+ (dropout): Dropout(p=0.1, inplace=False)
113
+ )
114
+ (output): RobertaSelfOutput(
115
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
116
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
117
+ (dropout): Dropout(p=0.1, inplace=False)
118
+ )
119
+ )
120
+ (intermediate): RobertaIntermediate(
121
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
122
+ )
123
+ (output): RobertaOutput(
124
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
125
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
126
+ (dropout): Dropout(p=0.1, inplace=False)
127
+ )
128
+ )
129
+ (5): RobertaLayer(
130
+ (attention): RobertaAttention(
131
+ (self): RobertaSelfAttention(
132
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
133
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
134
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
135
+ (dropout): Dropout(p=0.1, inplace=False)
136
+ )
137
+ (output): RobertaSelfOutput(
138
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
139
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
140
+ (dropout): Dropout(p=0.1, inplace=False)
141
+ )
142
+ )
143
+ (intermediate): RobertaIntermediate(
144
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
145
+ )
146
+ (output): RobertaOutput(
147
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
148
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
149
+ (dropout): Dropout(p=0.1, inplace=False)
150
+ )
151
+ )
152
+ (6): RobertaLayer(
153
+ (attention): RobertaAttention(
154
+ (self): RobertaSelfAttention(
155
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
156
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
157
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
158
+ (dropout): Dropout(p=0.1, inplace=False)
159
+ )
160
+ (output): RobertaSelfOutput(
161
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
162
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
163
+ (dropout): Dropout(p=0.1, inplace=False)
164
+ )
165
+ )
166
+ (intermediate): RobertaIntermediate(
167
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
168
+ )
169
+ (output): RobertaOutput(
170
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
171
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
172
+ (dropout): Dropout(p=0.1, inplace=False)
173
+ )
174
+ )
175
+ (7): RobertaLayer(
176
+ (attention): RobertaAttention(
177
+ (self): RobertaSelfAttention(
178
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
179
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
180
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
181
+ (dropout): Dropout(p=0.1, inplace=False)
182
+ )
183
+ (output): RobertaSelfOutput(
184
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
185
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
186
+ (dropout): Dropout(p=0.1, inplace=False)
187
+ )
188
+ )
189
+ (intermediate): RobertaIntermediate(
190
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
191
+ )
192
+ (output): RobertaOutput(
193
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
194
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
195
+ (dropout): Dropout(p=0.1, inplace=False)
196
+ )
197
+ )
198
+ (8): RobertaLayer(
199
+ (attention): RobertaAttention(
200
+ (self): RobertaSelfAttention(
201
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
202
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
203
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
204
+ (dropout): Dropout(p=0.1, inplace=False)
205
+ )
206
+ (output): RobertaSelfOutput(
207
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
208
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
209
+ (dropout): Dropout(p=0.1, inplace=False)
210
+ )
211
+ )
212
+ (intermediate): RobertaIntermediate(
213
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
214
+ )
215
+ (output): RobertaOutput(
216
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
217
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
218
+ (dropout): Dropout(p=0.1, inplace=False)
219
+ )
220
+ )
221
+ (9): RobertaLayer(
222
+ (attention): RobertaAttention(
223
+ (self): RobertaSelfAttention(
224
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
225
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
226
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
227
+ (dropout): Dropout(p=0.1, inplace=False)
228
+ )
229
+ (output): RobertaSelfOutput(
230
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
231
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
232
+ (dropout): Dropout(p=0.1, inplace=False)
233
+ )
234
+ )
235
+ (intermediate): RobertaIntermediate(
236
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
237
+ )
238
+ (output): RobertaOutput(
239
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
240
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
241
+ (dropout): Dropout(p=0.1, inplace=False)
242
+ )
243
+ )
244
+ (10): RobertaLayer(
245
+ (attention): RobertaAttention(
246
+ (self): RobertaSelfAttention(
247
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
248
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
249
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
250
+ (dropout): Dropout(p=0.1, inplace=False)
251
+ )
252
+ (output): RobertaSelfOutput(
253
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
254
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
255
+ (dropout): Dropout(p=0.1, inplace=False)
256
+ )
257
+ )
258
+ (intermediate): RobertaIntermediate(
259
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
260
+ )
261
+ (output): RobertaOutput(
262
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
263
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
264
+ (dropout): Dropout(p=0.1, inplace=False)
265
+ )
266
+ )
267
+ (11): RobertaLayer(
268
+ (attention): RobertaAttention(
269
+ (self): RobertaSelfAttention(
270
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
271
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
272
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
273
+ (dropout): Dropout(p=0.1, inplace=False)
274
+ )
275
+ (output): RobertaSelfOutput(
276
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
277
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
278
+ (dropout): Dropout(p=0.1, inplace=False)
279
+ )
280
+ )
281
+ (intermediate): RobertaIntermediate(
282
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
283
+ )
284
+ (output): RobertaOutput(
285
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
286
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
287
+ (dropout): Dropout(p=0.1, inplace=False)
288
+ )
289
+ )
290
+ (12): RobertaLayer(
291
+ (attention): RobertaAttention(
292
+ (self): RobertaSelfAttention(
293
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
294
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
295
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
296
+ (dropout): Dropout(p=0.1, inplace=False)
297
+ )
298
+ (output): RobertaSelfOutput(
299
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
300
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
301
+ (dropout): Dropout(p=0.1, inplace=False)
302
+ )
303
+ )
304
+ (intermediate): RobertaIntermediate(
305
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
306
+ )
307
+ (output): RobertaOutput(
308
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
309
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
310
+ (dropout): Dropout(p=0.1, inplace=False)
311
+ )
312
+ )
313
+ (13): RobertaLayer(
314
+ (attention): RobertaAttention(
315
+ (self): RobertaSelfAttention(
316
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
317
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
318
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
319
+ (dropout): Dropout(p=0.1, inplace=False)
320
+ )
321
+ (output): RobertaSelfOutput(
322
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
323
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
324
+ (dropout): Dropout(p=0.1, inplace=False)
325
+ )
326
+ )
327
+ (intermediate): RobertaIntermediate(
328
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
329
+ )
330
+ (output): RobertaOutput(
331
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
332
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
333
+ (dropout): Dropout(p=0.1, inplace=False)
334
+ )
335
+ )
336
+ (14): RobertaLayer(
337
+ (attention): RobertaAttention(
338
+ (self): RobertaSelfAttention(
339
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
340
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
341
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
342
+ (dropout): Dropout(p=0.1, inplace=False)
343
+ )
344
+ (output): RobertaSelfOutput(
345
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
346
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
347
+ (dropout): Dropout(p=0.1, inplace=False)
348
+ )
349
+ )
350
+ (intermediate): RobertaIntermediate(
351
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
352
+ )
353
+ (output): RobertaOutput(
354
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
355
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
356
+ (dropout): Dropout(p=0.1, inplace=False)
357
+ )
358
+ )
359
+ (15): RobertaLayer(
360
+ (attention): RobertaAttention(
361
+ (self): RobertaSelfAttention(
362
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
363
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
364
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
365
+ (dropout): Dropout(p=0.1, inplace=False)
366
+ )
367
+ (output): RobertaSelfOutput(
368
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
369
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
370
+ (dropout): Dropout(p=0.1, inplace=False)
371
+ )
372
+ )
373
+ (intermediate): RobertaIntermediate(
374
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
375
+ )
376
+ (output): RobertaOutput(
377
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
378
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
379
+ (dropout): Dropout(p=0.1, inplace=False)
380
+ )
381
+ )
382
+ (16): RobertaLayer(
383
+ (attention): RobertaAttention(
384
+ (self): RobertaSelfAttention(
385
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
386
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
387
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
388
+ (dropout): Dropout(p=0.1, inplace=False)
389
+ )
390
+ (output): RobertaSelfOutput(
391
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
392
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
393
+ (dropout): Dropout(p=0.1, inplace=False)
394
+ )
395
+ )
396
+ (intermediate): RobertaIntermediate(
397
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
398
+ )
399
+ (output): RobertaOutput(
400
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
401
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
402
+ (dropout): Dropout(p=0.1, inplace=False)
403
+ )
404
+ )
405
+ (17): RobertaLayer(
406
+ (attention): RobertaAttention(
407
+ (self): RobertaSelfAttention(
408
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
409
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
410
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
411
+ (dropout): Dropout(p=0.1, inplace=False)
412
+ )
413
+ (output): RobertaSelfOutput(
414
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
415
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
416
+ (dropout): Dropout(p=0.1, inplace=False)
417
+ )
418
+ )
419
+ (intermediate): RobertaIntermediate(
420
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
421
+ )
422
+ (output): RobertaOutput(
423
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
424
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
425
+ (dropout): Dropout(p=0.1, inplace=False)
426
+ )
427
+ )
428
+ (18): RobertaLayer(
429
+ (attention): RobertaAttention(
430
+ (self): RobertaSelfAttention(
431
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
432
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
433
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
434
+ (dropout): Dropout(p=0.1, inplace=False)
435
+ )
436
+ (output): RobertaSelfOutput(
437
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
438
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
439
+ (dropout): Dropout(p=0.1, inplace=False)
440
+ )
441
+ )
442
+ (intermediate): RobertaIntermediate(
443
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
444
+ )
445
+ (output): RobertaOutput(
446
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
447
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
448
+ (dropout): Dropout(p=0.1, inplace=False)
449
+ )
450
+ )
451
+ (19): RobertaLayer(
452
+ (attention): RobertaAttention(
453
+ (self): RobertaSelfAttention(
454
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
455
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
456
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
457
+ (dropout): Dropout(p=0.1, inplace=False)
458
+ )
459
+ (output): RobertaSelfOutput(
460
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
461
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
462
+ (dropout): Dropout(p=0.1, inplace=False)
463
+ )
464
+ )
465
+ (intermediate): RobertaIntermediate(
466
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
467
+ )
468
+ (output): RobertaOutput(
469
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
470
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
471
+ (dropout): Dropout(p=0.1, inplace=False)
472
+ )
473
+ )
474
+ (20): RobertaLayer(
475
+ (attention): RobertaAttention(
476
+ (self): RobertaSelfAttention(
477
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
478
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
479
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
480
+ (dropout): Dropout(p=0.1, inplace=False)
481
+ )
482
+ (output): RobertaSelfOutput(
483
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
484
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
485
+ (dropout): Dropout(p=0.1, inplace=False)
486
+ )
487
+ )
488
+ (intermediate): RobertaIntermediate(
489
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
490
+ )
491
+ (output): RobertaOutput(
492
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
493
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
494
+ (dropout): Dropout(p=0.1, inplace=False)
495
+ )
496
+ )
497
+ (21): RobertaLayer(
498
+ (attention): RobertaAttention(
499
+ (self): RobertaSelfAttention(
500
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
501
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
502
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
503
+ (dropout): Dropout(p=0.1, inplace=False)
504
+ )
505
+ (output): RobertaSelfOutput(
506
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
507
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
508
+ (dropout): Dropout(p=0.1, inplace=False)
509
+ )
510
+ )
511
+ (intermediate): RobertaIntermediate(
512
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
513
+ )
514
+ (output): RobertaOutput(
515
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
516
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
517
+ (dropout): Dropout(p=0.1, inplace=False)
518
+ )
519
+ )
520
+ (22): RobertaLayer(
521
+ (attention): RobertaAttention(
522
+ (self): RobertaSelfAttention(
523
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
524
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
525
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
526
+ (dropout): Dropout(p=0.1, inplace=False)
527
+ )
528
+ (output): RobertaSelfOutput(
529
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
530
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
531
+ (dropout): Dropout(p=0.1, inplace=False)
532
+ )
533
+ )
534
+ (intermediate): RobertaIntermediate(
535
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
536
+ )
537
+ (output): RobertaOutput(
538
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
539
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
540
+ (dropout): Dropout(p=0.1, inplace=False)
541
+ )
542
+ )
543
+ (23): RobertaLayer(
544
+ (attention): RobertaAttention(
545
+ (self): RobertaSelfAttention(
546
+ (query): Linear(in_features=1024, out_features=1024, bias=True)
547
+ (key): Linear(in_features=1024, out_features=1024, bias=True)
548
+ (value): Linear(in_features=1024, out_features=1024, bias=True)
549
+ (dropout): Dropout(p=0.1, inplace=False)
550
+ )
551
+ (output): RobertaSelfOutput(
552
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
553
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
554
+ (dropout): Dropout(p=0.1, inplace=False)
555
+ )
556
+ )
557
+ (intermediate): RobertaIntermediate(
558
+ (dense): Linear(in_features=1024, out_features=4096, bias=True)
559
+ )
560
+ (output): RobertaOutput(
561
+ (dense): Linear(in_features=4096, out_features=1024, bias=True)
562
+ (LayerNorm): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
563
+ (dropout): Dropout(p=0.1, inplace=False)
564
+ )
565
+ )
566
+ )
567
+ )
568
+ (pooler): RobertaPooler(
569
+ (dense): Linear(in_features=1024, out_features=1024, bias=True)
570
+ (activation): Tanh()
571
+ )
572
+ )
573
+ )
574
+ (word_dropout): WordDropout(p=0.05)
575
+ (locked_dropout): LockedDropout(p=0.5)
576
+ (linear): Linear(in_features=1024, out_features=20, bias=True)
577
+ (beta): 1.0
578
+ (weights): None
579
+ (weight_tensor) None
580
+ )"
581
+ 2021-01-15 16:27:19,928 ----------------------------------------------------------------------------------------------------
582
+ 2021-01-15 16:27:19,928 Corpus: "Corpus: 12705 train + 3068 dev + 3160 test sentences"
583
+ 2021-01-15 16:27:19,928 ----------------------------------------------------------------------------------------------------
584
+ 2021-01-15 16:27:19,928 Parameters:
585
+ 2021-01-15 16:27:19,928 - learning_rate: "5e-06"
586
+ 2021-01-15 16:27:19,928 - mini_batch_size: "4"
587
+ 2021-01-15 16:27:19,928 - patience: "3"
588
+ 2021-01-15 16:27:19,928 - anneal_factor: "0.5"
589
+ 2021-01-15 16:27:19,928 - max_epochs: "20"
590
+ 2021-01-15 16:27:19,928 - shuffle: "True"
591
+ 2021-01-15 16:27:19,928 - train_with_dev: "True"
592
+ 2021-01-15 16:27:19,928 - batch_growth_annealing: "False"
593
+ 2021-01-15 16:27:19,928 ----------------------------------------------------------------------------------------------------
594
+ 2021-01-15 16:27:19,928 Model training base path: "resources/contextdrop/flert-de-ft+dev-xlm-roberta-large-context+drop-64-True-42"
595
+ 2021-01-15 16:27:19,928 ----------------------------------------------------------------------------------------------------
596
+ 2021-01-15 16:27:19,929 Device: cuda:2
597
+ 2021-01-15 16:27:19,929 ----------------------------------------------------------------------------------------------------
598
+ 2021-01-15 16:27:19,929 Embeddings storage mode: none
599
+ 2021-01-15 16:27:19,939 ----------------------------------------------------------------------------------------------------
600
+ 2021-01-15 16:29:48,177 epoch 1 - iter 394/3944 - loss 0.58149384 - samples/sec: 10.63 - lr: 0.000005
601
+ 2021-01-15 16:32:16,470 epoch 1 - iter 788/3944 - loss 0.43146001 - samples/sec: 10.63 - lr: 0.000005
602
+ 2021-01-15 16:34:43,836 epoch 1 - iter 1182/3944 - loss 0.38010955 - samples/sec: 10.70 - lr: 0.000005
603
+ 2021-01-15 16:37:11,698 epoch 1 - iter 1576/3944 - loss 0.34431028 - samples/sec: 10.66 - lr: 0.000005
604
+ 2021-01-15 16:39:39,747 epoch 1 - iter 1970/3944 - loss 0.32744939 - samples/sec: 10.65 - lr: 0.000005
605
+ 2021-01-15 16:42:07,631 epoch 1 - iter 2364/3944 - loss 0.31857823 - samples/sec: 10.66 - lr: 0.000005
606
+ 2021-01-15 16:44:34,485 epoch 1 - iter 2758/3944 - loss 0.30456838 - samples/sec: 10.73 - lr: 0.000005
607
+ 2021-01-15 16:47:02,394 epoch 1 - iter 3152/3944 - loss 0.29905511 - samples/sec: 10.66 - lr: 0.000005
608
+ 2021-01-15 16:49:29,868 epoch 1 - iter 3546/3944 - loss 0.29295683 - samples/sec: 10.69 - lr: 0.000005
609
+ 2021-01-15 16:51:58,152 epoch 1 - iter 3940/3944 - loss 0.28678117 - samples/sec: 10.63 - lr: 0.000005
610
+ 2021-01-15 16:51:59,459 ----------------------------------------------------------------------------------------------------
611
+ 2021-01-15 16:51:59,459 EPOCH 1 done: loss 0.2866 - lr 0.0000050
612
+ 2021-01-15 16:51:59,459 BAD EPOCHS (no improvement): 4
613
+ 2021-01-15 16:51:59,462 ----------------------------------------------------------------------------------------------------
614
+ 2021-01-15 16:54:27,337 epoch 2 - iter 394/3944 - loss 0.23763366 - samples/sec: 10.66 - lr: 0.000005
615
+ 2021-01-15 16:56:55,082 epoch 2 - iter 788/3944 - loss 0.20691177 - samples/sec: 10.67 - lr: 0.000005
616
+ 2021-01-15 16:59:22,869 epoch 2 - iter 1182/3944 - loss 0.21072023 - samples/sec: 10.66 - lr: 0.000005
617
+ 2021-01-15 17:01:50,770 epoch 2 - iter 1576/3944 - loss 0.20705774 - samples/sec: 10.66 - lr: 0.000005
618
+ 2021-01-15 17:04:18,029 epoch 2 - iter 1970/3944 - loss 0.20345128 - samples/sec: 10.70 - lr: 0.000005
619
+ 2021-01-15 17:06:45,050 epoch 2 - iter 2364/3944 - loss 0.19762390 - samples/sec: 10.72 - lr: 0.000005
620
+ 2021-01-15 17:09:11,995 epoch 2 - iter 2758/3944 - loss 0.20206661 - samples/sec: 10.73 - lr: 0.000005
621
+ 2021-01-15 17:11:39,892 epoch 2 - iter 3152/3944 - loss 0.19768991 - samples/sec: 10.66 - lr: 0.000005
622
+ 2021-01-15 17:14:07,315 epoch 2 - iter 3546/3944 - loss 0.20115805 - samples/sec: 10.69 - lr: 0.000005
623
+ 2021-01-15 17:16:34,784 epoch 2 - iter 3940/3944 - loss 0.19983876 - samples/sec: 10.69 - lr: 0.000005
624
+ 2021-01-15 17:16:36,073 ----------------------------------------------------------------------------------------------------
625
+ 2021-01-15 17:16:36,074 EPOCH 2 done: loss 0.1996 - lr 0.0000049
626
+ 2021-01-15 17:16:36,074 BAD EPOCHS (no improvement): 4
627
+ 2021-01-15 17:16:36,077 ----------------------------------------------------------------------------------------------------
628
+ 2021-01-15 17:19:03,268 epoch 3 - iter 394/3944 - loss 0.16475767 - samples/sec: 10.71 - lr: 0.000005
629
+ 2021-01-15 17:21:30,430 epoch 3 - iter 788/3944 - loss 0.16467943 - samples/sec: 10.71 - lr: 0.000005
630
+ 2021-01-15 17:23:57,785 epoch 3 - iter 1182/3944 - loss 0.16820842 - samples/sec: 10.70 - lr: 0.000005
631
+ 2021-01-15 17:26:25,077 epoch 3 - iter 1576/3944 - loss 0.17111347 - samples/sec: 10.70 - lr: 0.000005
632
+ 2021-01-15 17:28:51,818 epoch 3 - iter 1970/3944 - loss 0.17649180 - samples/sec: 10.74 - lr: 0.000005
633
+ 2021-01-15 17:31:18,679 epoch 3 - iter 2364/3944 - loss 0.18734800 - samples/sec: 10.73 - lr: 0.000005
634
+ 2021-01-15 17:33:45,680 epoch 3 - iter 2758/3944 - loss 0.18971106 - samples/sec: 10.72 - lr: 0.000005
635
+ 2021-01-15 17:36:13,246 epoch 3 - iter 3152/3944 - loss 0.18746164 - samples/sec: 10.68 - lr: 0.000005
636
+ 2021-01-15 17:38:40,672 epoch 3 - iter 3546/3944 - loss 0.19218287 - samples/sec: 10.69 - lr: 0.000005
637
+ 2021-01-15 17:41:07,957 epoch 3 - iter 3940/3944 - loss 0.19381799 - samples/sec: 10.70 - lr: 0.000005
638
+ 2021-01-15 17:41:09,257 ----------------------------------------------------------------------------------------------------
639
+ 2021-01-15 17:41:09,257 EPOCH 3 done: loss 0.1938 - lr 0.0000047
640
+ 2021-01-15 17:41:09,257 BAD EPOCHS (no improvement): 4
641
+ 2021-01-15 17:41:09,260 ----------------------------------------------------------------------------------------------------
642
+ 2021-01-15 17:43:36,593 epoch 4 - iter 394/3944 - loss 0.16488209 - samples/sec: 10.70 - lr: 0.000005
643
+ 2021-01-15 17:46:04,133 epoch 4 - iter 788/3944 - loss 0.17473605 - samples/sec: 10.68 - lr: 0.000005
644
+ 2021-01-15 17:48:31,440 epoch 4 - iter 1182/3944 - loss 0.16738039 - samples/sec: 10.70 - lr: 0.000005
645
+ 2021-01-15 17:50:58,858 epoch 4 - iter 1576/3944 - loss 0.16596805 - samples/sec: 10.69 - lr: 0.000005
646
+ 2021-01-15 17:53:26,260 epoch 4 - iter 1970/3944 - loss 0.16483490 - samples/sec: 10.69 - lr: 0.000005
647
+ 2021-01-15 17:55:53,072 epoch 4 - iter 2364/3944 - loss 0.16752558 - samples/sec: 10.74 - lr: 0.000005
648
+ 2021-01-15 17:58:19,944 epoch 4 - iter 2758/3944 - loss 0.16537132 - samples/sec: 10.73 - lr: 0.000005
649
+ 2021-01-15 18:00:47,459 epoch 4 - iter 3152/3944 - loss 0.16501133 - samples/sec: 10.68 - lr: 0.000005
650
+ 2021-01-15 18:03:15,474 epoch 4 - iter 3546/3944 - loss 0.16726116 - samples/sec: 10.65 - lr: 0.000005
651
+ 2021-01-15 18:05:43,265 epoch 4 - iter 3940/3944 - loss 0.16914137 - samples/sec: 10.66 - lr: 0.000005
652
+ 2021-01-15 18:05:44,543 ----------------------------------------------------------------------------------------------------
653
+ 2021-01-15 18:05:44,543 EPOCH 4 done: loss 0.1690 - lr 0.0000045
654
+ 2021-01-15 18:05:44,543 BAD EPOCHS (no improvement): 4
655
+ 2021-01-15 18:05:44,547 ----------------------------------------------------------------------------------------------------
656
+ 2021-01-15 18:08:12,011 epoch 5 - iter 394/3944 - loss 0.15833616 - samples/sec: 10.69 - lr: 0.000004
657
+ 2021-01-15 18:10:38,832 epoch 5 - iter 788/3944 - loss 0.16551527 - samples/sec: 10.74 - lr: 0.000004
658
+ 2021-01-15 18:13:06,451 epoch 5 - iter 1182/3944 - loss 0.17177677 - samples/sec: 10.68 - lr: 0.000004
659
+ 2021-01-15 18:15:34,493 epoch 5 - iter 1576/3944 - loss 0.17301128 - samples/sec: 10.65 - lr: 0.000004
660
+ 2021-01-15 18:18:03,239 epoch 5 - iter 1970/3944 - loss 0.17650116 - samples/sec: 10.60 - lr: 0.000004
661
+ 2021-01-15 18:20:32,247 epoch 5 - iter 2364/3944 - loss 0.17631064 - samples/sec: 10.58 - lr: 0.000004
662
+ 2021-01-15 18:22:59,227 epoch 5 - iter 2758/3944 - loss 0.17537379 - samples/sec: 10.72 - lr: 0.000004
663
+ 2021-01-15 18:25:24,556 epoch 5 - iter 3152/3944 - loss 0.17617518 - samples/sec: 10.85 - lr: 0.000004
664
+ 2021-01-15 18:27:50,096 epoch 5 - iter 3546/3944 - loss 0.17367857 - samples/sec: 10.83 - lr: 0.000004
665
+ 2021-01-15 18:30:16,704 epoch 5 - iter 3940/3944 - loss 0.17093901 - samples/sec: 10.75 - lr: 0.000004
666
+ 2021-01-15 18:30:18,004 ----------------------------------------------------------------------------------------------------
667
+ 2021-01-15 18:30:18,004 EPOCH 5 done: loss 0.1708 - lr 0.0000043
668
+ 2021-01-15 18:30:18,004 BAD EPOCHS (no improvement): 4
669
+ 2021-01-15 18:30:18,007 ----------------------------------------------------------------------------------------------------
670
+ 2021-01-15 18:32:42,968 epoch 6 - iter 394/3944 - loss 0.17698825 - samples/sec: 10.87 - lr: 0.000004
671
+ 2021-01-15 18:35:08,371 epoch 6 - iter 788/3944 - loss 0.16713416 - samples/sec: 10.84 - lr: 0.000004
672
+ 2021-01-15 18:37:34,014 epoch 6 - iter 1182/3944 - loss 0.16902562 - samples/sec: 10.82 - lr: 0.000004
673
+ 2021-01-15 18:40:00,144 epoch 6 - iter 1576/3944 - loss 0.16574844 - samples/sec: 10.79 - lr: 0.000004
674
+ 2021-01-15 18:42:26,534 epoch 6 - iter 1970/3944 - loss 0.16657012 - samples/sec: 10.77 - lr: 0.000004
675
+ 2021-01-15 18:44:52,613 epoch 6 - iter 2364/3944 - loss 0.16641916 - samples/sec: 10.79 - lr: 0.000004
676
+ 2021-01-15 18:47:17,983 epoch 6 - iter 2758/3944 - loss 0.16274268 - samples/sec: 10.84 - lr: 0.000004
677
+ 2021-01-15 18:49:43,878 epoch 6 - iter 3152/3944 - loss 0.16172776 - samples/sec: 10.80 - lr: 0.000004
678
+ 2021-01-15 18:52:09,331 epoch 6 - iter 3546/3944 - loss 0.16291188 - samples/sec: 10.84 - lr: 0.000004
679
+ 2021-01-15 18:54:34,272 epoch 6 - iter 3940/3944 - loss 0.16208591 - samples/sec: 10.87 - lr: 0.000004
680
+ 2021-01-15 18:54:35,553 ----------------------------------------------------------------------------------------------------
681
+ 2021-01-15 18:54:35,553 EPOCH 6 done: loss 0.1621 - lr 0.0000040
682
+ 2021-01-15 18:54:35,553 BAD EPOCHS (no improvement): 4
683
+ 2021-01-15 18:54:35,556 ----------------------------------------------------------------------------------------------------
684
+ 2021-01-15 18:57:00,031 epoch 7 - iter 394/3944 - loss 0.15674837 - samples/sec: 10.91 - lr: 0.000004
685
+ 2021-01-15 18:59:25,217 epoch 7 - iter 788/3944 - loss 0.16222971 - samples/sec: 10.86 - lr: 0.000004
686
+ 2021-01-15 19:01:50,483 epoch 7 - iter 1182/3944 - loss 0.17608659 - samples/sec: 10.85 - lr: 0.000004
687
+ 2021-01-15 19:04:15,644 epoch 7 - iter 1576/3944 - loss 0.17042676 - samples/sec: 10.86 - lr: 0.000004
688
+ 2021-01-15 19:06:40,626 epoch 7 - iter 1970/3944 - loss 0.16835536 - samples/sec: 10.87 - lr: 0.000004
689
+ 2021-01-15 19:09:06,269 epoch 7 - iter 2364/3944 - loss 0.17005717 - samples/sec: 10.82 - lr: 0.000004
690
+ 2021-01-15 19:11:30,455 epoch 7 - iter 2758/3944 - loss 0.16986731 - samples/sec: 10.93 - lr: 0.000004
691
+ 2021-01-15 19:13:55,363 epoch 7 - iter 3152/3944 - loss 0.16607768 - samples/sec: 10.88 - lr: 0.000004
692
+ 2021-01-15 19:16:20,669 epoch 7 - iter 3546/3944 - loss 0.16408475 - samples/sec: 10.85 - lr: 0.000004
693
+ 2021-01-15 19:18:46,350 epoch 7 - iter 3940/3944 - loss 0.16187247 - samples/sec: 10.82 - lr: 0.000004
694
+ 2021-01-15 19:18:47,632 ----------------------------------------------------------------------------------------------------
695
+ 2021-01-15 19:18:47,632 EPOCH 7 done: loss 0.1619 - lr 0.0000036
696
+ 2021-01-15 19:18:47,632 BAD EPOCHS (no improvement): 4
697
+ 2021-01-15 19:18:47,635 ----------------------------------------------------------------------------------------------------
698
+ 2021-01-15 19:21:13,232 epoch 8 - iter 394/3944 - loss 0.15860862 - samples/sec: 10.83 - lr: 0.000004
699
+ 2021-01-15 19:23:37,769 epoch 8 - iter 788/3944 - loss 0.16488914 - samples/sec: 10.90 - lr: 0.000004
700
+ 2021-01-15 19:26:03,243 epoch 8 - iter 1182/3944 - loss 0.16503533 - samples/sec: 10.83 - lr: 0.000004
701
+ 2021-01-15 19:28:28,171 epoch 8 - iter 1576/3944 - loss 0.16139434 - samples/sec: 10.88 - lr: 0.000003
702
+ 2021-01-15 19:30:53,669 epoch 8 - iter 1970/3944 - loss 0.15723985 - samples/sec: 10.83 - lr: 0.000003
703
+ 2021-01-15 19:33:18,230 epoch 8 - iter 2364/3944 - loss 0.15695920 - samples/sec: 10.90 - lr: 0.000003
704
+ 2021-01-15 19:35:43,271 epoch 8 - iter 2758/3944 - loss 0.15942351 - samples/sec: 10.87 - lr: 0.000003
705
+ 2021-01-15 19:38:07,861 epoch 8 - iter 3152/3944 - loss 0.16047035 - samples/sec: 10.90 - lr: 0.000003
706
+ 2021-01-15 19:40:31,578 epoch 8 - iter 3546/3944 - loss 0.15915561 - samples/sec: 10.97 - lr: 0.000003
707
+ 2021-01-15 19:42:56,291 epoch 8 - iter 3940/3944 - loss 0.15889894 - samples/sec: 10.89 - lr: 0.000003
708
+ 2021-01-15 19:42:57,531 ----------------------------------------------------------------------------------------------------
709
+ 2021-01-15 19:42:57,531 EPOCH 8 done: loss 0.1591 - lr 0.0000033
710
+ 2021-01-15 19:42:57,531 BAD EPOCHS (no improvement): 4
711
+ 2021-01-15 19:42:57,534 ----------------------------------------------------------------------------------------------------
712
+ 2021-01-15 19:45:22,077 epoch 9 - iter 394/3944 - loss 0.15628960 - samples/sec: 10.90 - lr: 0.000003
713
+ 2021-01-15 19:47:46,787 epoch 9 - iter 788/3944 - loss 0.15383703 - samples/sec: 10.89 - lr: 0.000003
714
+ 2021-01-15 19:50:11,703 epoch 9 - iter 1182/3944 - loss 0.14587839 - samples/sec: 10.88 - lr: 0.000003
715
+ 2021-01-15 19:52:36,604 epoch 9 - iter 1576/3944 - loss 0.14536078 - samples/sec: 10.88 - lr: 0.000003
716
+ 2021-01-15 19:55:01,857 epoch 9 - iter 1970/3944 - loss 0.14842223 - samples/sec: 10.85 - lr: 0.000003
717
+ 2021-01-15 19:57:26,976 epoch 9 - iter 2364/3944 - loss 0.14781136 - samples/sec: 10.86 - lr: 0.000003
718
+ 2021-01-15 19:59:52,570 epoch 9 - iter 2758/3944 - loss 0.14980740 - samples/sec: 10.83 - lr: 0.000003
719
+ 2021-01-15 20:02:16,766 epoch 9 - iter 3152/3944 - loss 0.15147019 - samples/sec: 10.93 - lr: 0.000003
720
+ 2021-01-15 20:04:41,587 epoch 9 - iter 3546/3944 - loss 0.14992780 - samples/sec: 10.88 - lr: 0.000003
721
+ 2021-01-15 20:07:07,065 epoch 9 - iter 3940/3944 - loss 0.14688711 - samples/sec: 10.83 - lr: 0.000003
722
+ 2021-01-15 20:07:08,315 ----------------------------------------------------------------------------------------------------
723
+ 2021-01-15 20:07:08,315 EPOCH 9 done: loss 0.1469 - lr 0.0000029
724
+ 2021-01-15 20:07:08,315 BAD EPOCHS (no improvement): 4
725
+ 2021-01-15 20:07:08,318 ----------------------------------------------------------------------------------------------------
726
+ 2021-01-15 20:09:33,307 epoch 10 - iter 394/3944 - loss 0.15646665 - samples/sec: 10.87 - lr: 0.000003
727
+ 2021-01-15 20:11:57,958 epoch 10 - iter 788/3944 - loss 0.15117971 - samples/sec: 10.90 - lr: 0.000003
728
+ 2021-01-15 20:14:23,257 epoch 10 - iter 1182/3944 - loss 0.15319049 - samples/sec: 10.85 - lr: 0.000003
729
+ 2021-01-15 20:16:47,405 epoch 10 - iter 1576/3944 - loss 0.14632406 - samples/sec: 10.93 - lr: 0.000003
730
+ 2021-01-15 20:19:13,077 epoch 10 - iter 1970/3944 - loss 0.14880268 - samples/sec: 10.82 - lr: 0.000003
731
+ 2021-01-15 20:21:37,974 epoch 10 - iter 2364/3944 - loss 0.14738769 - samples/sec: 10.88 - lr: 0.000003
732
+ 2021-01-15 20:24:02,312 epoch 10 - iter 2758/3944 - loss 0.14992138 - samples/sec: 10.92 - lr: 0.000003
733
+ 2021-01-15 20:26:26,416 epoch 10 - iter 3152/3944 - loss 0.14923992 - samples/sec: 10.94 - lr: 0.000003
734
+ 2021-01-15 20:28:50,624 epoch 10 - iter 3546/3944 - loss 0.14988541 - samples/sec: 10.93 - lr: 0.000003
735
+ 2021-01-15 20:31:15,232 epoch 10 - iter 3940/3944 - loss 0.14923823 - samples/sec: 10.90 - lr: 0.000003
736
+ 2021-01-15 20:31:16,444 ----------------------------------------------------------------------------------------------------
737
+ 2021-01-15 20:31:16,445 EPOCH 10 done: loss 0.1492 - lr 0.0000025
738
+ 2021-01-15 20:31:16,445 BAD EPOCHS (no improvement): 4
739
+ 2021-01-15 20:31:16,447 ----------------------------------------------------------------------------------------------------
740
+ 2021-01-15 20:33:41,402 epoch 11 - iter 394/3944 - loss 0.16146740 - samples/sec: 10.87 - lr: 0.000002
741
+ 2021-01-15 20:36:05,837 epoch 11 - iter 788/3944 - loss 0.16349808 - samples/sec: 10.91 - lr: 0.000002
742
+ 2021-01-15 20:38:30,901 epoch 11 - iter 1182/3944 - loss 0.15115769 - samples/sec: 10.87 - lr: 0.000002
743
+ 2021-01-15 20:40:55,438 epoch 11 - iter 1576/3944 - loss 0.14705117 - samples/sec: 10.90 - lr: 0.000002
744
+ 2021-01-15 20:43:20,378 epoch 11 - iter 1970/3944 - loss 0.14991591 - samples/sec: 10.87 - lr: 0.000002
745
+ 2021-01-15 20:45:45,151 epoch 11 - iter 2364/3944 - loss 0.15439655 - samples/sec: 10.89 - lr: 0.000002
746
+ 2021-01-15 20:48:09,941 epoch 11 - iter 2758/3944 - loss 0.15580945 - samples/sec: 10.89 - lr: 0.000002
747
+ 2021-01-15 20:50:34,492 epoch 11 - iter 3152/3944 - loss 0.15253824 - samples/sec: 10.90 - lr: 0.000002
748
+ 2021-01-15 20:52:58,700 epoch 11 - iter 3546/3944 - loss 0.15092320 - samples/sec: 10.93 - lr: 0.000002
749
+ 2021-01-15 20:55:23,174 epoch 11 - iter 3940/3944 - loss 0.15157769 - samples/sec: 10.91 - lr: 0.000002
750
+ 2021-01-15 20:55:24,418 ----------------------------------------------------------------------------------------------------
751
+ 2021-01-15 20:55:24,418 EPOCH 11 done: loss 0.1515 - lr 0.0000021
752
+ 2021-01-15 20:55:24,418 BAD EPOCHS (no improvement): 4
753
+ 2021-01-15 20:55:24,421 ----------------------------------------------------------------------------------------------------
754
+ 2021-01-15 20:57:49,024 epoch 12 - iter 394/3944 - loss 0.13353775 - samples/sec: 10.90 - lr: 0.000002
755
+ 2021-01-15 21:00:13,363 epoch 12 - iter 788/3944 - loss 0.12481125 - samples/sec: 10.92 - lr: 0.000002
756
+ 2021-01-15 21:02:37,921 epoch 12 - iter 1182/3944 - loss 0.13012621 - samples/sec: 10.90 - lr: 0.000002
757
+ 2021-01-15 21:05:02,587 epoch 12 - iter 1576/3944 - loss 0.13179293 - samples/sec: 10.90 - lr: 0.000002
758
+ 2021-01-15 21:07:27,496 epoch 12 - iter 1970/3944 - loss 0.13504151 - samples/sec: 10.88 - lr: 0.000002
759
+ 2021-01-15 21:09:52,384 epoch 12 - iter 2364/3944 - loss 0.13639646 - samples/sec: 10.88 - lr: 0.000002
760
+ 2021-01-15 21:12:16,819 epoch 12 - iter 2758/3944 - loss 0.13538659 - samples/sec: 10.91 - lr: 0.000002
761
+ 2021-01-15 21:14:41,429 epoch 12 - iter 3152/3944 - loss 0.13401163 - samples/sec: 10.90 - lr: 0.000002
762
+ 2021-01-15 21:17:06,129 epoch 12 - iter 3546/3944 - loss 0.13558124 - samples/sec: 10.89 - lr: 0.000002
763
+ 2021-01-15 21:19:30,783 epoch 12 - iter 3940/3944 - loss 0.13632296 - samples/sec: 10.90 - lr: 0.000002
764
+ 2021-01-15 21:19:32,074 ----------------------------------------------------------------------------------------------------
765
+ 2021-01-15 21:19:32,075 EPOCH 12 done: loss 0.1365 - lr 0.0000017
766
+ 2021-01-15 21:19:32,075 BAD EPOCHS (no improvement): 4
767
+ 2021-01-15 21:19:32,086 ----------------------------------------------------------------------------------------------------
768
+ 2021-01-15 21:21:56,456 epoch 13 - iter 394/3944 - loss 0.13665988 - samples/sec: 10.92 - lr: 0.000002
769
+ 2021-01-15 21:24:21,213 epoch 13 - iter 788/3944 - loss 0.13434678 - samples/sec: 10.89 - lr: 0.000002
770
+ 2021-01-15 21:26:45,716 epoch 13 - iter 1182/3944 - loss 0.14362465 - samples/sec: 10.91 - lr: 0.000002
771
+ 2021-01-15 21:29:10,027 epoch 13 - iter 1576/3944 - loss 0.14463862 - samples/sec: 10.92 - lr: 0.000002
772
+ 2021-01-15 21:31:35,804 epoch 13 - iter 1970/3944 - loss 0.14445941 - samples/sec: 10.81 - lr: 0.000002
773
+ 2021-01-15 21:34:02,830 epoch 13 - iter 2364/3944 - loss 0.14383136 - samples/sec: 10.72 - lr: 0.000002
774
+ 2021-01-15 21:36:29,998 epoch 13 - iter 2758/3944 - loss 0.14458719 - samples/sec: 10.71 - lr: 0.000001
775
+ 2021-01-15 21:38:58,765 epoch 13 - iter 3152/3944 - loss 0.14583862 - samples/sec: 10.59 - lr: 0.000001
776
+ 2021-01-15 21:41:27,066 epoch 13 - iter 3546/3944 - loss 0.14570568 - samples/sec: 10.63 - lr: 0.000001
777
+ 2021-01-15 21:43:53,640 epoch 13 - iter 3940/3944 - loss 0.14616666 - samples/sec: 10.75 - lr: 0.000001
778
+ 2021-01-15 21:43:54,933 ----------------------------------------------------------------------------------------------------
779
+ 2021-01-15 21:43:54,933 EPOCH 13 done: loss 0.1461 - lr 0.0000014
780
+ 2021-01-15 21:43:54,933 BAD EPOCHS (no improvement): 4
781
+ 2021-01-15 21:43:54,953 ----------------------------------------------------------------------------------------------------
782
+ 2021-01-15 21:46:22,842 epoch 14 - iter 394/3944 - loss 0.12543846 - samples/sec: 10.66 - lr: 0.000001
783
+ 2021-01-15 21:48:49,756 epoch 14 - iter 788/3944 - loss 0.12854973 - samples/sec: 10.73 - lr: 0.000001
784
+ 2021-01-15 21:51:16,782 epoch 14 - iter 1182/3944 - loss 0.12800828 - samples/sec: 10.72 - lr: 0.000001
785
+ 2021-01-15 21:53:43,875 epoch 14 - iter 1576/3944 - loss 0.13018865 - samples/sec: 10.72 - lr: 0.000001
786
+ 2021-01-15 21:56:11,947 epoch 14 - iter 1970/3944 - loss 0.13230140 - samples/sec: 10.64 - lr: 0.000001
787
+ 2021-01-15 21:58:40,070 epoch 14 - iter 2364/3944 - loss 0.13276864 - samples/sec: 10.64 - lr: 0.000001
788
+ 2021-01-15 22:01:07,197 epoch 14 - iter 2758/3944 - loss 0.13188423 - samples/sec: 10.71 - lr: 0.000001
789
+ 2021-01-15 22:03:33,892 epoch 14 - iter 3152/3944 - loss 0.13622326 - samples/sec: 10.74 - lr: 0.000001
790
+ 2021-01-15 22:06:01,226 epoch 14 - iter 3546/3944 - loss 0.13623591 - samples/sec: 10.70 - lr: 0.000001
791
+ 2021-01-15 22:08:29,247 epoch 14 - iter 3940/3944 - loss 0.13681664 - samples/sec: 10.65 - lr: 0.000001
792
+ 2021-01-15 22:08:30,571 ----------------------------------------------------------------------------------------------------
793
+ 2021-01-15 22:08:30,571 EPOCH 14 done: loss 0.1367 - lr 0.0000010
794
+ 2021-01-15 22:08:30,571 BAD EPOCHS (no improvement): 4
795
+ 2021-01-15 22:08:30,619 ----------------------------------------------------------------------------------------------------
796
+ 2021-01-15 22:10:58,784 epoch 15 - iter 394/3944 - loss 0.14687040 - samples/sec: 10.64 - lr: 0.000001
797
+ 2021-01-15 22:13:25,824 epoch 15 - iter 788/3944 - loss 0.13773561 - samples/sec: 10.72 - lr: 0.000001
798
+ 2021-01-15 22:15:52,774 epoch 15 - iter 1182/3944 - loss 0.13724811 - samples/sec: 10.73 - lr: 0.000001
799
+ 2021-01-15 22:18:19,309 epoch 15 - iter 1576/3944 - loss 0.14105250 - samples/sec: 10.76 - lr: 0.000001
800
+ 2021-01-15 22:20:46,418 epoch 15 - iter 1970/3944 - loss 0.13929364 - samples/sec: 10.71 - lr: 0.000001
801
+ 2021-01-15 22:23:12,930 epoch 15 - iter 2364/3944 - loss 0.13891907 - samples/sec: 10.76 - lr: 0.000001
802
+ 2021-01-15 22:25:40,051 epoch 15 - iter 2758/3944 - loss 0.13941754 - samples/sec: 10.71 - lr: 0.000001
803
+ 2021-01-15 22:28:06,583 epoch 15 - iter 3152/3944 - loss 0.14071295 - samples/sec: 10.76 - lr: 0.000001
804
+ 2021-01-15 22:30:32,954 epoch 15 - iter 3546/3944 - loss 0.13981342 - samples/sec: 10.77 - lr: 0.000001
805
+ 2021-01-15 22:33:00,397 epoch 15 - iter 3940/3944 - loss 0.13880390 - samples/sec: 10.69 - lr: 0.000001
806
+ 2021-01-15 22:33:01,714 ----------------------------------------------------------------------------------------------------
807
+ 2021-01-15 22:33:01,715 EPOCH 15 done: loss 0.1387 - lr 0.0000007
808
+ 2021-01-15 22:33:01,715 BAD EPOCHS (no improvement): 4
809
+ 2021-01-15 22:33:01,718 ----------------------------------------------------------------------------------------------------
810
+ 2021-01-15 22:35:29,035 epoch 16 - iter 394/3944 - loss 0.14291727 - samples/sec: 10.70 - lr: 0.000001
811
+ 2021-01-15 22:37:56,417 epoch 16 - iter 788/3944 - loss 0.13149588 - samples/sec: 10.69 - lr: 0.000001
812
+ 2021-01-15 22:40:23,990 epoch 16 - iter 1182/3944 - loss 0.13203036 - samples/sec: 10.68 - lr: 0.000001
813
+ 2021-01-15 22:42:51,538 epoch 16 - iter 1576/3944 - loss 0.13134927 - samples/sec: 10.68 - lr: 0.000001
814
+ 2021-01-15 22:45:19,113 epoch 16 - iter 1970/3944 - loss 0.13179903 - samples/sec: 10.68 - lr: 0.000001
815
+ 2021-01-15 22:47:46,156 epoch 16 - iter 2364/3944 - loss 0.13354076 - samples/sec: 10.72 - lr: 0.000001
816
+ 2021-01-15 22:50:13,300 epoch 16 - iter 2758/3944 - loss 0.13476940 - samples/sec: 10.71 - lr: 0.000001
817
+ 2021-01-15 22:52:38,377 epoch 16 - iter 3152/3944 - loss 0.13497255 - samples/sec: 10.86 - lr: 0.000001
818
+ 2021-01-15 22:55:03,400 epoch 16 - iter 3546/3944 - loss 0.13634147 - samples/sec: 10.87 - lr: 0.000001
819
+ 2021-01-15 22:57:27,892 epoch 16 - iter 3940/3944 - loss 0.13727031 - samples/sec: 10.91 - lr: 0.000000
820
+ 2021-01-15 22:57:29,178 ----------------------------------------------------------------------------------------------------
821
+ 2021-01-15 22:57:29,178 EPOCH 16 done: loss 0.1376 - lr 0.0000005
822
+ 2021-01-15 22:57:29,178 BAD EPOCHS (no improvement): 4
823
+ 2021-01-15 22:57:29,181 ----------------------------------------------------------------------------------------------------
824
+ 2021-01-15 22:59:53,548 epoch 17 - iter 394/3944 - loss 0.14524632 - samples/sec: 10.92 - lr: 0.000000
825
+ 2021-01-15 23:02:18,357 epoch 17 - iter 788/3944 - loss 0.14652155 - samples/sec: 10.88 - lr: 0.000000
826
+ 2021-01-15 23:04:43,610 epoch 17 - iter 1182/3944 - loss 0.13884438 - samples/sec: 10.85 - lr: 0.000000
827
+ 2021-01-15 23:07:08,806 epoch 17 - iter 1576/3944 - loss 0.13549453 - samples/sec: 10.86 - lr: 0.000000
828
+ 2021-01-15 23:09:34,317 epoch 17 - iter 1970/3944 - loss 0.13560330 - samples/sec: 10.83 - lr: 0.000000
829
+ 2021-01-15 23:11:59,595 epoch 17 - iter 2364/3944 - loss 0.13972037 - samples/sec: 10.85 - lr: 0.000000
830
+ 2021-01-15 23:14:24,656 epoch 17 - iter 2758/3944 - loss 0.14040167 - samples/sec: 10.87 - lr: 0.000000
831
+ 2021-01-15 23:16:49,375 epoch 17 - iter 3152/3944 - loss 0.13946642 - samples/sec: 10.89 - lr: 0.000000
832
+ 2021-01-15 23:19:15,069 epoch 17 - iter 3546/3944 - loss 0.13849877 - samples/sec: 10.82 - lr: 0.000000
833
+ 2021-01-15 23:21:40,239 epoch 17 - iter 3940/3944 - loss 0.13743522 - samples/sec: 10.86 - lr: 0.000000
834
+ 2021-01-15 23:21:41,530 ----------------------------------------------------------------------------------------------------
835
+ 2021-01-15 23:21:41,530 EPOCH 17 done: loss 0.1373 - lr 0.0000003
836
+ 2021-01-15 23:21:41,530 BAD EPOCHS (no improvement): 4
837
+ 2021-01-15 23:21:41,533 ----------------------------------------------------------------------------------------------------
838
+ 2021-01-15 23:24:07,941 epoch 18 - iter 394/3944 - loss 0.13214318 - samples/sec: 10.77 - lr: 0.000000
839
+ 2021-01-15 23:26:34,009 epoch 18 - iter 788/3944 - loss 0.14259440 - samples/sec: 10.79 - lr: 0.000000
840
+ 2021-01-15 23:29:00,116 epoch 18 - iter 1182/3944 - loss 0.13753739 - samples/sec: 10.79 - lr: 0.000000
841
+ 2021-01-15 23:31:25,087 epoch 18 - iter 1576/3944 - loss 0.13957844 - samples/sec: 10.87 - lr: 0.000000
842
+ 2021-01-15 23:33:50,076 epoch 18 - iter 1970/3944 - loss 0.13743370 - samples/sec: 10.87 - lr: 0.000000
843
+ 2021-01-15 23:36:14,776 epoch 18 - iter 2364/3944 - loss 0.13970779 - samples/sec: 10.89 - lr: 0.000000
844
+ 2021-01-15 23:38:38,473 epoch 18 - iter 2758/3944 - loss 0.13932537 - samples/sec: 10.97 - lr: 0.000000
845
+ 2021-01-15 23:41:03,249 epoch 18 - iter 3152/3944 - loss 0.13745278 - samples/sec: 10.89 - lr: 0.000000
846
+ 2021-01-15 23:43:28,499 epoch 18 - iter 3546/3944 - loss 0.13924606 - samples/sec: 10.85 - lr: 0.000000
847
+ 2021-01-15 23:45:53,779 epoch 18 - iter 3940/3944 - loss 0.13920658 - samples/sec: 10.85 - lr: 0.000000
848
+ 2021-01-15 23:45:55,039 ----------------------------------------------------------------------------------------------------
849
+ 2021-01-15 23:45:55,040 EPOCH 18 done: loss 0.1400 - lr 0.0000001
850
+ 2021-01-15 23:45:55,040 BAD EPOCHS (no improvement): 4
851
+ 2021-01-15 23:45:55,060 ----------------------------------------------------------------------------------------------------
852
+ 2021-01-15 23:48:19,848 epoch 19 - iter 394/3944 - loss 0.12011491 - samples/sec: 10.89 - lr: 0.000000
853
+ 2021-01-15 23:50:45,410 epoch 19 - iter 788/3944 - loss 0.12712191 - samples/sec: 10.83 - lr: 0.000000
854
+ 2021-01-15 23:53:10,309 epoch 19 - iter 1182/3944 - loss 0.12601271 - samples/sec: 10.88 - lr: 0.000000
855
+ 2021-01-15 23:55:35,025 epoch 19 - iter 1576/3944 - loss 0.12838937 - samples/sec: 10.89 - lr: 0.000000
856
+ 2021-01-15 23:57:59,862 epoch 19 - iter 1970/3944 - loss 0.13018004 - samples/sec: 10.88 - lr: 0.000000
857
+ 2021-01-16 00:00:24,890 epoch 19 - iter 2364/3944 - loss 0.12867846 - samples/sec: 10.87 - lr: 0.000000
858
+ 2021-01-16 00:02:49,627 epoch 19 - iter 2758/3944 - loss 0.12932283 - samples/sec: 10.89 - lr: 0.000000
859
+ 2021-01-16 00:05:14,400 epoch 19 - iter 3152/3944 - loss 0.12859496 - samples/sec: 10.89 - lr: 0.000000
860
+ 2021-01-16 00:07:39,476 epoch 19 - iter 3546/3944 - loss 0.12980219 - samples/sec: 10.86 - lr: 0.000000
861
+ 2021-01-16 00:10:04,796 epoch 19 - iter 3940/3944 - loss 0.13157911 - samples/sec: 10.85 - lr: 0.000000
862
+ 2021-01-16 00:10:06,033 ----------------------------------------------------------------------------------------------------
863
+ 2021-01-16 00:10:06,033 EPOCH 19 done: loss 0.1316 - lr 0.0000000
864
+ 2021-01-16 00:10:06,033 BAD EPOCHS (no improvement): 4
865
+ 2021-01-16 00:10:06,036 ----------------------------------------------------------------------------------------------------
866
+ 2021-01-16 00:12:31,453 epoch 20 - iter 394/3944 - loss 0.12043092 - samples/sec: 10.84 - lr: 0.000000
867
+ 2021-01-16 00:14:56,680 epoch 20 - iter 788/3944 - loss 0.13192874 - samples/sec: 10.85 - lr: 0.000000
868
+ 2021-01-16 00:17:21,816 epoch 20 - iter 1182/3944 - loss 0.13095020 - samples/sec: 10.86 - lr: 0.000000
869
+ 2021-01-16 00:19:46,815 epoch 20 - iter 1576/3944 - loss 0.13423819 - samples/sec: 10.87 - lr: 0.000000
870
+ 2021-01-16 00:22:12,079 epoch 20 - iter 1970/3944 - loss 0.13458985 - samples/sec: 10.85 - lr: 0.000000
871
+ 2021-01-16 00:24:37,900 epoch 20 - iter 2364/3944 - loss 0.13241959 - samples/sec: 10.81 - lr: 0.000000
872
+ 2021-01-16 00:27:03,059 epoch 20 - iter 2758/3944 - loss 0.13235752 - samples/sec: 10.86 - lr: 0.000000
873
+ 2021-01-16 00:29:28,845 epoch 20 - iter 3152/3944 - loss 0.13390899 - samples/sec: 10.81 - lr: 0.000000
874
+ 2021-01-16 00:31:54,866 epoch 20 - iter 3546/3944 - loss 0.13467390 - samples/sec: 10.79 - lr: 0.000000
875
+ 2021-01-16 00:34:19,750 epoch 20 - iter 3940/3944 - loss 0.13514658 - samples/sec: 10.88 - lr: 0.000000
876
+ 2021-01-16 00:34:21,013 ----------------------------------------------------------------------------------------------------
877
+ 2021-01-16 00:34:21,013 EPOCH 20 done: loss 0.1353 - lr 0.0000000
878
+ 2021-01-16 00:34:21,013 BAD EPOCHS (no improvement): 4
879
+ 2021-01-16 00:34:59,015 ----------------------------------------------------------------------------------------------------
880
+ 2021-01-16 00:34:59,015 Testing using best model ...
881
+ 2021-01-16 00:36:54,780 0.9319 0.9145 0.9231
882
+ 2021-01-16 00:36:54,780
883
+ Results:
884
+ - F1-score (micro) 0.9231
885
+ - F1-score (macro) 0.8691
886
+
887
+ By class:
888
+ LOC tp: 981 - fp: 62 - fn: 70 - precision: 0.9406 - recall: 0.9334 - f1-score: 0.9370
889
+ MISC tp: 128 - fp: 26 - fn: 78 - precision: 0.8312 - recall: 0.6214 - f1-score: 0.7111
890
+ ORG tp: 497 - fp: 87 - fn: 87 - precision: 0.8510 - recall: 0.8510 - f1-score: 0.8510
891
+ PER tp: 1184 - fp: 29 - fn: 26 - precision: 0.9761 - recall: 0.9785 - f1-score: 0.9773
892
+ 2021-01-16 00:36:54,780 ----------------------------------------------------------------------------------------------------