Hugging Face's logo

flair
/
ner-spanish-large

Token Classification
Flair
PyTorch
Spanish
sequence-tagger-model
Model card Files Community
2
alanakbik commited on
Commit
5dbaccf
•
1 Parent(s): a495de0

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: es
7
+ datasets:
8
+ - conll2003
9
+ inference: false
10
+ ---
11
+
12
+ ## Spanish NER in Flair (large model)
13
+
14
+ This is the large 4-class NER model for Spanish that ships with [Flair](https://github.com/flairNLP/flair/).
15
+
16
+ F1-Score: **92,31** (CoNLL-03 German revised)
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-spanish-large")
43
+
44
+ # make example sentence
45
+ sentence = Sentence("George Washington ging nach 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 ging nach 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_SPANISH
81
+
82
+ corpus = CONLL_03_SPANISH()
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-spanish-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 03:42:54 4 0.0000 0.3266703642570718
3
+ 2 03:59:31 4 0.0000 0.2195460225134484
4
+ 3 04:16:13 4 0.0000 0.1933198845743666
5
+ 4 04:32:40 4 0.0000 0.1872510862514337
6
+ 5 04:48:56 4 0.0000 0.17857406046914318
7
+ 6 05:05:14 4 0.0000 0.16921875621090116
8
+ 7 05:21:27 4 0.0000 0.1666596209211079
9
+ 8 05:37:43 4 0.0000 0.16070350912475692
10
+ 9 05:54:08 4 0.0000 0.1624060529415902
11
+ 10 06:10:32 4 0.0000 0.1580145349272955
12
+ 11 06:26:56 4 0.0000 0.1540521664003986
13
+ 12 06:43:17 4 0.0000 0.15517560774918843
14
+ 13 06:59:39 4 0.0000 0.1558255414095817
15
+ 14 07:16:07 4 0.0000 0.14988600317802847
16
+ 15 07:32:36 4 0.0000 0.14841691814629973
17
+ 16 07:49:05 4 0.0000 0.15282003354897164
18
+ 17 08:05:31 4 0.0000 0.15712539515756105
19
+ 18 08:21:54 4 0.0000 0.16291884726042624
20
+ 19 08:38:14 4 0.0000 0.14057681102068115
21
+ 20 08:54:33 4 0.0000 0.14611905722473392
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1da7ebe3bdcc58c91eb9916f7d881791ac2659307f0c383c325361382f2f42
3
+ size 2239866697
training.log ADDED
@@ -0,0 +1,892 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-01-16 03:26:26,142 ----------------------------------------------------------------------------------------------------
2
+ 2021-01-16 03:26:26,146 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
+ 2021-01-16 03:26:26,148 ----------------------------------------------------------------------------------------------------
582
+ 2021-01-16 03:26:26,148 Corpus: "Corpus: 8323 train + 1915 dev + 1517 test sentences"
583
+ 2021-01-16 03:26:26,148 ----------------------------------------------------------------------------------------------------
584
+ 2021-01-16 03:26:26,148 Parameters:
585
+ 2021-01-16 03:26:26,148 - learning_rate: "5e-06"
586
+ 2021-01-16 03:26:26,148 - mini_batch_size: "4"
587
+ 2021-01-16 03:26:26,148 - patience: "3"
588
+ 2021-01-16 03:26:26,148 - anneal_factor: "0.5"
589
+ 2021-01-16 03:26:26,148 - max_epochs: "20"
590
+ 2021-01-16 03:26:26,148 - shuffle: "True"
591
+ 2021-01-16 03:26:26,148 - train_with_dev: "True"
592
+ 2021-01-16 03:26:26,148 - batch_growth_annealing: "False"
593
+ 2021-01-16 03:26:26,149 ----------------------------------------------------------------------------------------------------
594
+ 2021-01-16 03:26:26,149 Model training base path: "resources/contextdrop/flert-es-ft+dev-xlm-roberta-large-context+drop-64-True-258"
595
+ 2021-01-16 03:26:26,149 ----------------------------------------------------------------------------------------------------
596
+ 2021-01-16 03:26:26,149 Device: cuda:3
597
+ 2021-01-16 03:26:26,149 ----------------------------------------------------------------------------------------------------
598
+ 2021-01-16 03:26:26,149 Embeddings storage mode: none
599
+ 2021-01-16 03:26:26,161 ----------------------------------------------------------------------------------------------------
600
+ 2021-01-16 03:28:04,650 epoch 1 - iter 256/2560 - loss 0.87027155 - samples/sec: 10.40 - lr: 0.000005
601
+ 2021-01-16 03:29:42,988 epoch 1 - iter 512/2560 - loss 0.59530026 - samples/sec: 10.41 - lr: 0.000005
602
+ 2021-01-16 03:31:21,817 epoch 1 - iter 768/2560 - loss 0.52507711 - samples/sec: 10.36 - lr: 0.000005
603
+ 2021-01-16 03:33:00,647 epoch 1 - iter 1024/2560 - loss 0.45703199 - samples/sec: 10.36 - lr: 0.000005
604
+ 2021-01-16 03:34:42,020 epoch 1 - iter 1280/2560 - loss 0.41694313 - samples/sec: 10.10 - lr: 0.000005
605
+ 2021-01-16 03:36:21,509 epoch 1 - iter 1536/2560 - loss 0.38192728 - samples/sec: 10.29 - lr: 0.000005
606
+ 2021-01-16 03:38:00,214 epoch 1 - iter 1792/2560 - loss 0.36367874 - samples/sec: 10.38 - lr: 0.000005
607
+ 2021-01-16 03:39:38,871 epoch 1 - iter 2048/2560 - loss 0.34546215 - samples/sec: 10.38 - lr: 0.000005
608
+ 2021-01-16 03:41:16,409 epoch 1 - iter 2304/2560 - loss 0.33346538 - samples/sec: 10.50 - lr: 0.000005
609
+ 2021-01-16 03:42:54,136 epoch 1 - iter 2560/2560 - loss 0.32667036 - samples/sec: 10.48 - lr: 0.000005
610
+ 2021-01-16 03:42:54,138 ----------------------------------------------------------------------------------------------------
611
+ 2021-01-16 03:42:54,138 EPOCH 1 done: loss 0.3267 - lr 0.0000050
612
+ 2021-01-16 03:42:54,138 BAD EPOCHS (no improvement): 4
613
+ 2021-01-16 03:42:54,141 ----------------------------------------------------------------------------------------------------
614
+ 2021-01-16 03:44:32,764 epoch 2 - iter 256/2560 - loss 0.21108762 - samples/sec: 10.38 - lr: 0.000005
615
+ 2021-01-16 03:46:11,253 epoch 2 - iter 512/2560 - loss 0.22128268 - samples/sec: 10.40 - lr: 0.000005
616
+ 2021-01-16 03:47:49,772 epoch 2 - iter 768/2560 - loss 0.22246430 - samples/sec: 10.39 - lr: 0.000005
617
+ 2021-01-16 03:49:28,129 epoch 2 - iter 1024/2560 - loss 0.21358276 - samples/sec: 10.41 - lr: 0.000005
618
+ 2021-01-16 03:51:06,924 epoch 2 - iter 1280/2560 - loss 0.21429265 - samples/sec: 10.37 - lr: 0.000005
619
+ 2021-01-16 03:52:46,984 epoch 2 - iter 1536/2560 - loss 0.21196466 - samples/sec: 10.23 - lr: 0.000005
620
+ 2021-01-16 03:54:29,705 epoch 2 - iter 1792/2560 - loss 0.21758704 - samples/sec: 9.97 - lr: 0.000005
621
+ 2021-01-16 03:56:10,481 epoch 2 - iter 2048/2560 - loss 0.21965157 - samples/sec: 10.16 - lr: 0.000005
622
+ 2021-01-16 03:57:50,615 epoch 2 - iter 2304/2560 - loss 0.21877101 - samples/sec: 10.23 - lr: 0.000005
623
+ 2021-01-16 03:59:31,158 epoch 2 - iter 2560/2560 - loss 0.21954602 - samples/sec: 10.19 - lr: 0.000005
624
+ 2021-01-16 03:59:31,160 ----------------------------------------------------------------------------------------------------
625
+ 2021-01-16 03:59:31,160 EPOCH 2 done: loss 0.2195 - lr 0.0000049
626
+ 2021-01-16 03:59:31,160 BAD EPOCHS (no improvement): 4
627
+ 2021-01-16 03:59:31,163 ----------------------------------------------------------------------------------------------------
628
+ 2021-01-16 04:01:11,656 epoch 3 - iter 256/2560 - loss 0.20612080 - samples/sec: 10.19 - lr: 0.000005
629
+ 2021-01-16 04:02:51,941 epoch 3 - iter 512/2560 - loss 0.19317841 - samples/sec: 10.21 - lr: 0.000005
630
+ 2021-01-16 04:04:32,511 epoch 3 - iter 768/2560 - loss 0.19963626 - samples/sec: 10.18 - lr: 0.000005
631
+ 2021-01-16 04:06:11,909 epoch 3 - iter 1024/2560 - loss 0.19312694 - samples/sec: 10.30 - lr: 0.000005
632
+ 2021-01-16 04:07:53,866 epoch 3 - iter 1280/2560 - loss 0.19674287 - samples/sec: 10.04 - lr: 0.000005
633
+ 2021-01-16 04:09:33,688 epoch 3 - iter 1536/2560 - loss 0.19699039 - samples/sec: 10.26 - lr: 0.000005
634
+ 2021-01-16 04:11:13,497 epoch 3 - iter 1792/2560 - loss 0.19513463 - samples/sec: 10.26 - lr: 0.000005
635
+ 2021-01-16 04:12:53,541 epoch 3 - iter 2048/2560 - loss 0.19334227 - samples/sec: 10.24 - lr: 0.000005
636
+ 2021-01-16 04:14:33,916 epoch 3 - iter 2304/2560 - loss 0.19294838 - samples/sec: 10.20 - lr: 0.000005
637
+ 2021-01-16 04:16:13,001 epoch 3 - iter 2560/2560 - loss 0.19331988 - samples/sec: 10.34 - lr: 0.000005
638
+ 2021-01-16 04:16:13,003 ----------------------------------------------------------------------------------------------------
639
+ 2021-01-16 04:16:13,003 EPOCH 3 done: loss 0.1933 - lr 0.0000047
640
+ 2021-01-16 04:16:13,003 BAD EPOCHS (no improvement): 4
641
+ 2021-01-16 04:16:13,006 ----------------------------------------------------------------------------------------------------
642
+ 2021-01-16 04:17:52,069 epoch 4 - iter 256/2560 - loss 0.16853571 - samples/sec: 10.34 - lr: 0.000005
643
+ 2021-01-16 04:19:31,083 epoch 4 - iter 512/2560 - loss 0.16783710 - samples/sec: 10.34 - lr: 0.000005
644
+ 2021-01-16 04:21:09,860 epoch 4 - iter 768/2560 - loss 0.17852492 - samples/sec: 10.37 - lr: 0.000005
645
+ 2021-01-16 04:22:48,222 epoch 4 - iter 1024/2560 - loss 0.18170671 - samples/sec: 10.41 - lr: 0.000005
646
+ 2021-01-16 04:24:28,304 epoch 4 - iter 1280/2560 - loss 0.17619093 - samples/sec: 10.23 - lr: 0.000005
647
+ 2021-01-16 04:26:06,542 epoch 4 - iter 1536/2560 - loss 0.18313451 - samples/sec: 10.42 - lr: 0.000005
648
+ 2021-01-16 04:27:44,976 epoch 4 - iter 1792/2560 - loss 0.18543083 - samples/sec: 10.40 - lr: 0.000005
649
+ 2021-01-16 04:29:25,900 epoch 4 - iter 2048/2560 - loss 0.18948785 - samples/sec: 10.15 - lr: 0.000005
650
+ 2021-01-16 04:31:03,494 epoch 4 - iter 2304/2560 - loss 0.18818842 - samples/sec: 10.49 - lr: 0.000005
651
+ 2021-01-16 04:32:40,881 epoch 4 - iter 2560/2560 - loss 0.18725109 - samples/sec: 10.52 - lr: 0.000005
652
+ 2021-01-16 04:32:40,883 ----------------------------------------------------------------------------------------------------
653
+ 2021-01-16 04:32:40,884 EPOCH 4 done: loss 0.1873 - lr 0.0000045
654
+ 2021-01-16 04:32:40,884 BAD EPOCHS (no improvement): 4
655
+ 2021-01-16 04:32:40,886 ----------------------------------------------------------------------------------------------------
656
+ 2021-01-16 04:34:18,022 epoch 5 - iter 256/2560 - loss 0.19665239 - samples/sec: 10.54 - lr: 0.000004
657
+ 2021-01-16 04:35:54,846 epoch 5 - iter 512/2560 - loss 0.19948870 - samples/sec: 10.58 - lr: 0.000004
658
+ 2021-01-16 04:37:32,278 epoch 5 - iter 768/2560 - loss 0.19201483 - samples/sec: 10.51 - lr: 0.000004
659
+ 2021-01-16 04:39:11,686 epoch 5 - iter 1024/2560 - loss 0.18716260 - samples/sec: 10.30 - lr: 0.000004
660
+ 2021-01-16 04:40:48,941 epoch 5 - iter 1280/2560 - loss 0.17767008 - samples/sec: 10.53 - lr: 0.000004
661
+ 2021-01-16 04:42:26,151 epoch 5 - iter 1536/2560 - loss 0.17738586 - samples/sec: 10.53 - lr: 0.000004
662
+ 2021-01-16 04:44:03,440 epoch 5 - iter 1792/2560 - loss 0.17437861 - samples/sec: 10.53 - lr: 0.000004
663
+ 2021-01-16 04:45:40,641 epoch 5 - iter 2048/2560 - loss 0.17843058 - samples/sec: 10.54 - lr: 0.000004
664
+ 2021-01-16 04:47:18,726 epoch 5 - iter 2304/2560 - loss 0.17962338 - samples/sec: 10.44 - lr: 0.000004
665
+ 2021-01-16 04:48:56,938 epoch 5 - iter 2560/2560 - loss 0.17857406 - samples/sec: 10.43 - lr: 0.000004
666
+ 2021-01-16 04:48:56,941 ----------------------------------------------------------------------------------------------------
667
+ 2021-01-16 04:48:56,941 EPOCH 5 done: loss 0.1786 - lr 0.0000043
668
+ 2021-01-16 04:48:56,941 BAD EPOCHS (no improvement): 4
669
+ 2021-01-16 04:48:56,944 ----------------------------------------------------------------------------------------------------
670
+ 2021-01-16 04:50:37,578 epoch 6 - iter 256/2560 - loss 0.19558805 - samples/sec: 10.18 - lr: 0.000004
671
+ 2021-01-16 04:52:15,762 epoch 6 - iter 512/2560 - loss 0.17503759 - samples/sec: 10.43 - lr: 0.000004
672
+ 2021-01-16 04:53:52,814 epoch 6 - iter 768/2560 - loss 0.17416353 - samples/sec: 10.55 - lr: 0.000004
673
+ 2021-01-16 04:55:29,984 epoch 6 - iter 1024/2560 - loss 0.16483752 - samples/sec: 10.54 - lr: 0.000004
674
+ 2021-01-16 04:57:07,349 epoch 6 - iter 1280/2560 - loss 0.16624319 - samples/sec: 10.52 - lr: 0.000004
675
+ 2021-01-16 04:58:44,378 epoch 6 - iter 1536/2560 - loss 0.16546115 - samples/sec: 10.55 - lr: 0.000004
676
+ 2021-01-16 05:00:21,884 epoch 6 - iter 1792/2560 - loss 0.16436590 - samples/sec: 10.50 - lr: 0.000004
677
+ 2021-01-16 05:01:58,951 epoch 6 - iter 2048/2560 - loss 0.16724299 - samples/sec: 10.55 - lr: 0.000004
678
+ 2021-01-16 05:03:36,482 epoch 6 - iter 2304/2560 - loss 0.16918433 - samples/sec: 10.50 - lr: 0.000004
679
+ 2021-01-16 05:05:14,584 epoch 6 - iter 2560/2560 - loss 0.16921876 - samples/sec: 10.44 - lr: 0.000004
680
+ 2021-01-16 05:05:14,587 ----------------------------------------------------------------------------------------------------
681
+ 2021-01-16 05:05:14,587 EPOCH 6 done: loss 0.1692 - lr 0.0000040
682
+ 2021-01-16 05:05:14,587 BAD EPOCHS (no improvement): 4
683
+ 2021-01-16 05:05:14,599 ----------------------------------------------------------------------------------------------------
684
+ 2021-01-16 05:06:51,663 epoch 7 - iter 256/2560 - loss 0.18482960 - samples/sec: 10.55 - lr: 0.000004
685
+ 2021-01-16 05:08:28,534 epoch 7 - iter 512/2560 - loss 0.16880554 - samples/sec: 10.57 - lr: 0.000004
686
+ 2021-01-16 05:10:05,876 epoch 7 - iter 768/2560 - loss 0.16822603 - samples/sec: 10.52 - lr: 0.000004
687
+ 2021-01-16 05:11:42,818 epoch 7 - iter 1024/2560 - loss 0.17842509 - samples/sec: 10.56 - lr: 0.000004
688
+ 2021-01-16 05:13:20,349 epoch 7 - iter 1280/2560 - loss 0.16997025 - samples/sec: 10.50 - lr: 0.000004
689
+ 2021-01-16 05:14:57,279 epoch 7 - iter 1536/2560 - loss 0.16850697 - samples/sec: 10.57 - lr: 0.000004
690
+ 2021-01-16 05:16:33,604 epoch 7 - iter 1792/2560 - loss 0.16897440 - samples/sec: 10.63 - lr: 0.000004
691
+ 2021-01-16 05:18:11,130 epoch 7 - iter 2048/2560 - loss 0.16901586 - samples/sec: 10.50 - lr: 0.000004
692
+ 2021-01-16 05:19:48,742 epoch 7 - iter 2304/2560 - loss 0.16746824 - samples/sec: 10.49 - lr: 0.000004
693
+ 2021-01-16 05:21:27,376 epoch 7 - iter 2560/2560 - loss 0.16665962 - samples/sec: 10.38 - lr: 0.000004
694
+ 2021-01-16 05:21:27,378 ----------------------------------------------------------------------------------------------------
695
+ 2021-01-16 05:21:27,378 EPOCH 7 done: loss 0.1667 - lr 0.0000036
696
+ 2021-01-16 05:21:27,378 BAD EPOCHS (no improvement): 4
697
+ 2021-01-16 05:21:27,381 ----------------------------------------------------------------------------------------------------
698
+ 2021-01-16 05:23:04,098 epoch 8 - iter 256/2560 - loss 0.17170512 - samples/sec: 10.59 - lr: 0.000004
699
+ 2021-01-16 05:24:40,963 epoch 8 - iter 512/2560 - loss 0.16578343 - samples/sec: 10.57 - lr: 0.000004
700
+ 2021-01-16 05:26:17,874 epoch 8 - iter 768/2560 - loss 0.15936900 - samples/sec: 10.57 - lr: 0.000004
701
+ 2021-01-16 05:27:54,684 epoch 8 - iter 1024/2560 - loss 0.16254958 - samples/sec: 10.58 - lr: 0.000003
702
+ 2021-01-16 05:29:31,674 epoch 8 - iter 1280/2560 - loss 0.16254652 - samples/sec: 10.56 - lr: 0.000003
703
+ 2021-01-16 05:31:09,021 epoch 8 - iter 1536/2560 - loss 0.16126451 - samples/sec: 10.52 - lr: 0.000003
704
+ 2021-01-16 05:32:48,943 epoch 8 - iter 1792/2560 - loss 0.15960888 - samples/sec: 10.25 - lr: 0.000003
705
+ 2021-01-16 05:34:26,910 epoch 8 - iter 2048/2560 - loss 0.16106515 - samples/sec: 10.45 - lr: 0.000003
706
+ 2021-01-16 05:36:05,072 epoch 8 - iter 2304/2560 - loss 0.15881735 - samples/sec: 10.43 - lr: 0.000003
707
+ 2021-01-16 05:37:43,202 epoch 8 - iter 2560/2560 - loss 0.16070351 - samples/sec: 10.44 - lr: 0.000003
708
+ 2021-01-16 05:37:43,204 ----------------------------------------------------------------------------------------------------
709
+ 2021-01-16 05:37:43,204 EPOCH 8 done: loss 0.1607 - lr 0.0000033
710
+ 2021-01-16 05:37:43,204 BAD EPOCHS (no improvement): 4
711
+ 2021-01-16 05:37:43,207 ----------------------------------------------------------------------------------------------------
712
+ 2021-01-16 05:39:21,420 epoch 9 - iter 256/2560 - loss 0.17227183 - samples/sec: 10.43 - lr: 0.000003
713
+ 2021-01-16 05:40:59,261 epoch 9 - iter 512/2560 - loss 0.17554657 - samples/sec: 10.47 - lr: 0.000003
714
+ 2021-01-16 05:42:38,175 epoch 9 - iter 768/2560 - loss 0.16616659 - samples/sec: 10.35 - lr: 0.000003
715
+ 2021-01-16 05:44:16,618 epoch 9 - iter 1024/2560 - loss 0.16832605 - samples/sec: 10.40 - lr: 0.000003
716
+ 2021-01-16 05:45:57,429 epoch 9 - iter 1280/2560 - loss 0.16394874 - samples/sec: 10.16 - lr: 0.000003
717
+ 2021-01-16 05:47:35,957 epoch 9 - iter 1536/2560 - loss 0.16352007 - samples/sec: 10.39 - lr: 0.000003
718
+ 2021-01-16 05:49:13,705 epoch 9 - iter 1792/2560 - loss 0.16385724 - samples/sec: 10.48 - lr: 0.000003
719
+ 2021-01-16 05:50:52,424 epoch 9 - iter 2048/2560 - loss 0.16055360 - samples/sec: 10.37 - lr: 0.000003
720
+ 2021-01-16 05:52:30,508 epoch 9 - iter 2304/2560 - loss 0.16334559 - samples/sec: 10.44 - lr: 0.000003
721
+ 2021-01-16 05:54:08,468 epoch 9 - iter 2560/2560 - loss 0.16240605 - samples/sec: 10.45 - lr: 0.000003
722
+ 2021-01-16 05:54:08,470 ----------------------------------------------------------------------------------------------------
723
+ 2021-01-16 05:54:08,470 EPOCH 9 done: loss 0.1624 - lr 0.0000029
724
+ 2021-01-16 05:54:08,470 BAD EPOCHS (no improvement): 4
725
+ 2021-01-16 05:54:08,473 ----------------------------------------------------------------------------------------------------
726
+ 2021-01-16 05:55:47,128 epoch 10 - iter 256/2560 - loss 0.16313144 - samples/sec: 10.38 - lr: 0.000003
727
+ 2021-01-16 05:57:25,407 epoch 10 - iter 512/2560 - loss 0.15020732 - samples/sec: 10.42 - lr: 0.000003
728
+ 2021-01-16 05:59:03,413 epoch 10 - iter 768/2560 - loss 0.15983365 - samples/sec: 10.45 - lr: 0.000003
729
+ 2021-01-16 06:00:41,548 epoch 10 - iter 1024/2560 - loss 0.15880243 - samples/sec: 10.44 - lr: 0.000003
730
+ 2021-01-16 06:02:19,846 epoch 10 - iter 1280/2560 - loss 0.15641733 - samples/sec: 10.42 - lr: 0.000003
731
+ 2021-01-16 06:03:57,792 epoch 10 - iter 1536/2560 - loss 0.15979563 - samples/sec: 10.46 - lr: 0.000003
732
+ 2021-01-16 06:05:37,942 epoch 10 - iter 1792/2560 - loss 0.15822496 - samples/sec: 10.23 - lr: 0.000003
733
+ 2021-01-16 06:07:15,923 epoch 10 - iter 2048/2560 - loss 0.15759511 - samples/sec: 10.45 - lr: 0.000003
734
+ 2021-01-16 06:08:53,939 epoch 10 - iter 2304/2560 - loss 0.15693087 - samples/sec: 10.45 - lr: 0.000003
735
+ 2021-01-16 06:10:32,048 epoch 10 - iter 2560/2560 - loss 0.15801453 - samples/sec: 10.44 - lr: 0.000002
736
+ 2021-01-16 06:10:32,051 ----------------------------------------------------------------------------------------------------
737
+ 2021-01-16 06:10:32,051 EPOCH 10 done: loss 0.1580 - lr 0.0000025
738
+ 2021-01-16 06:10:32,051 BAD EPOCHS (no improvement): 4
739
+ 2021-01-16 06:10:32,054 ----------------------------------------------------------------------------------------------------
740
+ 2021-01-16 06:12:10,483 epoch 11 - iter 256/2560 - loss 0.16742767 - samples/sec: 10.40 - lr: 0.000002
741
+ 2021-01-16 06:13:48,782 epoch 11 - iter 512/2560 - loss 0.15327274 - samples/sec: 10.42 - lr: 0.000002
742
+ 2021-01-16 06:15:26,970 epoch 11 - iter 768/2560 - loss 0.15209073 - samples/sec: 10.43 - lr: 0.000002
743
+ 2021-01-16 06:17:05,366 epoch 11 - iter 1024/2560 - loss 0.14838890 - samples/sec: 10.41 - lr: 0.000002
744
+ 2021-01-16 06:18:43,497 epoch 11 - iter 1280/2560 - loss 0.14857876 - samples/sec: 10.44 - lr: 0.000002
745
+ 2021-01-16 06:20:21,564 epoch 11 - iter 1536/2560 - loss 0.14942513 - samples/sec: 10.44 - lr: 0.000002
746
+ 2021-01-16 06:21:59,181 epoch 11 - iter 1792/2560 - loss 0.14977847 - samples/sec: 10.49 - lr: 0.000002
747
+ 2021-01-16 06:23:37,984 epoch 11 - iter 2048/2560 - loss 0.15052564 - samples/sec: 10.37 - lr: 0.000002
748
+ 2021-01-16 06:25:18,744 epoch 11 - iter 2304/2560 - loss 0.15348464 - samples/sec: 10.16 - lr: 0.000002
749
+ 2021-01-16 06:26:56,801 epoch 11 - iter 2560/2560 - loss 0.15405217 - samples/sec: 10.44 - lr: 0.000002
750
+ 2021-01-16 06:26:56,804 ----------------------------------------------------------------------------------------------------
751
+ 2021-01-16 06:26:56,804 EPOCH 11 done: loss 0.1541 - lr 0.0000021
752
+ 2021-01-16 06:26:56,804 BAD EPOCHS (no improvement): 4
753
+ 2021-01-16 06:26:56,806 ----------------------------------------------------------------------------------------------------
754
+ 2021-01-16 06:28:34,919 epoch 12 - iter 256/2560 - loss 0.14515525 - samples/sec: 10.44 - lr: 0.000002
755
+ 2021-01-16 06:30:14,290 epoch 12 - iter 512/2560 - loss 0.16185121 - samples/sec: 10.31 - lr: 0.000002
756
+ 2021-01-16 06:31:51,825 epoch 12 - iter 768/2560 - loss 0.15630178 - samples/sec: 10.50 - lr: 0.000002
757
+ 2021-01-16 06:33:29,645 epoch 12 - iter 1024/2560 - loss 0.16061640 - samples/sec: 10.47 - lr: 0.000002
758
+ 2021-01-16 06:35:07,390 epoch 12 - iter 1280/2560 - loss 0.16106939 - samples/sec: 10.48 - lr: 0.000002
759
+ 2021-01-16 06:36:45,537 epoch 12 - iter 1536/2560 - loss 0.16553326 - samples/sec: 10.43 - lr: 0.000002
760
+ 2021-01-16 06:38:23,976 epoch 12 - iter 1792/2560 - loss 0.16298360 - samples/sec: 10.40 - lr: 0.000002
761
+ 2021-01-16 06:40:01,697 epoch 12 - iter 2048/2560 - loss 0.15791582 - samples/sec: 10.48 - lr: 0.000002
762
+ 2021-01-16 06:41:40,081 epoch 12 - iter 2304/2560 - loss 0.15724189 - samples/sec: 10.41 - lr: 0.000002
763
+ 2021-01-16 06:43:17,722 epoch 12 - iter 2560/2560 - loss 0.15517561 - samples/sec: 10.49 - lr: 0.000002
764
+ 2021-01-16 06:43:17,724 ----------------------------------------------------------------------------------------------------
765
+ 2021-01-16 06:43:17,724 EPOCH 12 done: loss 0.1552 - lr 0.0000017
766
+ 2021-01-16 06:43:17,724 BAD EPOCHS (no improvement): 4
767
+ 2021-01-16 06:43:17,727 ----------------------------------------------------------------------------------------------------
768
+ 2021-01-16 06:44:55,687 epoch 13 - iter 256/2560 - loss 0.15713525 - samples/sec: 10.45 - lr: 0.000002
769
+ 2021-01-16 06:46:36,001 epoch 13 - iter 512/2560 - loss 0.15100717 - samples/sec: 10.21 - lr: 0.000002
770
+ 2021-01-16 06:48:13,819 epoch 13 - iter 768/2560 - loss 0.15847721 - samples/sec: 10.47 - lr: 0.000002
771
+ 2021-01-16 06:49:52,306 epoch 13 - iter 1024/2560 - loss 0.15904259 - samples/sec: 10.40 - lr: 0.000002
772
+ 2021-01-16 06:51:29,891 epoch 13 - iter 1280/2560 - loss 0.15989578 - samples/sec: 10.49 - lr: 0.000002
773
+ 2021-01-16 06:53:08,047 epoch 13 - iter 1536/2560 - loss 0.15584846 - samples/sec: 10.43 - lr: 0.000002
774
+ 2021-01-16 06:54:45,903 epoch 13 - iter 1792/2560 - loss 0.15456669 - samples/sec: 10.47 - lr: 0.000001
775
+ 2021-01-16 06:56:23,958 epoch 13 - iter 2048/2560 - loss 0.15476196 - samples/sec: 10.44 - lr: 0.000001
776
+ 2021-01-16 06:58:01,860 epoch 13 - iter 2304/2560 - loss 0.15554818 - samples/sec: 10.46 - lr: 0.000001
777
+ 2021-01-16 06:59:39,510 epoch 13 - iter 2560/2560 - loss 0.15582554 - samples/sec: 10.49 - lr: 0.000001
778
+ 2021-01-16 06:59:39,513 ----------------------------------------------------------------------------------------------------
779
+ 2021-01-16 06:59:39,513 EPOCH 13 done: loss 0.1558 - lr 0.0000014
780
+ 2021-01-16 06:59:39,513 BAD EPOCHS (no improvement): 4
781
+ 2021-01-16 06:59:39,536 ----------------------------------------------------------------------------------------------------
782
+ 2021-01-16 07:01:17,550 epoch 14 - iter 256/2560 - loss 0.14336771 - samples/sec: 10.45 - lr: 0.000001
783
+ 2021-01-16 07:02:55,149 epoch 14 - iter 512/2560 - loss 0.13420979 - samples/sec: 10.49 - lr: 0.000001
784
+ 2021-01-16 07:04:33,295 epoch 14 - iter 768/2560 - loss 0.14666678 - samples/sec: 10.43 - lr: 0.000001
785
+ 2021-01-16 07:06:11,482 epoch 14 - iter 1024/2560 - loss 0.14107045 - samples/sec: 10.43 - lr: 0.000001
786
+ 2021-01-16 07:07:50,423 epoch 14 - iter 1280/2560 - loss 0.14810884 - samples/sec: 10.35 - lr: 0.000001
787
+ 2021-01-16 07:09:29,149 epoch 14 - iter 1536/2560 - loss 0.15039081 - samples/sec: 10.37 - lr: 0.000001
788
+ 2021-01-16 07:11:08,549 epoch 14 - iter 1792/2560 - loss 0.15404881 - samples/sec: 10.30 - lr: 0.000001
789
+ 2021-01-16 07:12:48,860 epoch 14 - iter 2048/2560 - loss 0.15398198 - samples/sec: 10.21 - lr: 0.000001
790
+ 2021-01-16 07:14:26,993 epoch 14 - iter 2304/2560 - loss 0.15119867 - samples/sec: 10.44 - lr: 0.000001
791
+ 2021-01-16 07:16:07,905 epoch 14 - iter 2560/2560 - loss 0.14988600 - samples/sec: 10.15 - lr: 0.000001
792
+ 2021-01-16 07:16:07,907 ----------------------------------------------------------------------------------------------------
793
+ 2021-01-16 07:16:07,907 EPOCH 14 done: loss 0.1499 - lr 0.0000010
794
+ 2021-01-16 07:16:07,907 BAD EPOCHS (no improvement): 4
795
+ 2021-01-16 07:16:07,910 ----------------------------------------------------------------------------------------------------
796
+ 2021-01-16 07:17:47,163 epoch 15 - iter 256/2560 - loss 0.13211162 - samples/sec: 10.32 - lr: 0.000001
797
+ 2021-01-16 07:19:26,428 epoch 15 - iter 512/2560 - loss 0.14312262 - samples/sec: 10.32 - lr: 0.000001
798
+ 2021-01-16 07:21:04,402 epoch 15 - iter 768/2560 - loss 0.14991927 - samples/sec: 10.45 - lr: 0.000001
799
+ 2021-01-16 07:22:42,083 epoch 15 - iter 1024/2560 - loss 0.15132502 - samples/sec: 10.48 - lr: 0.000001
800
+ 2021-01-16 07:24:23,248 epoch 15 - iter 1280/2560 - loss 0.15012698 - samples/sec: 10.12 - lr: 0.000001
801
+ 2021-01-16 07:26:02,510 epoch 15 - iter 1536/2560 - loss 0.15443282 - samples/sec: 10.32 - lr: 0.000001
802
+ 2021-01-16 07:27:41,227 epoch 15 - iter 1792/2560 - loss 0.15337861 - samples/sec: 10.37 - lr: 0.000001
803
+ 2021-01-16 07:29:19,916 epoch 15 - iter 2048/2560 - loss 0.15342457 - samples/sec: 10.38 - lr: 0.000001
804
+ 2021-01-16 07:30:58,353 epoch 15 - iter 2304/2560 - loss 0.15126241 - samples/sec: 10.40 - lr: 0.000001
805
+ 2021-01-16 07:32:36,692 epoch 15 - iter 2560/2560 - loss 0.14841692 - samples/sec: 10.41 - lr: 0.000001
806
+ 2021-01-16 07:32:36,694 ----------------------------------------------------------------------------------------------------
807
+ 2021-01-16 07:32:36,694 EPOCH 15 done: loss 0.1484 - lr 0.0000007
808
+ 2021-01-16 07:32:36,694 BAD EPOCHS (no improvement): 4
809
+ 2021-01-16 07:32:36,700 ----------------------------------------------------------------------------------------------------
810
+ 2021-01-16 07:34:15,608 epoch 16 - iter 256/2560 - loss 0.14154861 - samples/sec: 10.35 - lr: 0.000001
811
+ 2021-01-16 07:35:54,182 epoch 16 - iter 512/2560 - loss 0.15666068 - samples/sec: 10.39 - lr: 0.000001
812
+ 2021-01-16 07:37:32,436 epoch 16 - iter 768/2560 - loss 0.14965853 - samples/sec: 10.42 - lr: 0.000001
813
+ 2021-01-16 07:39:11,322 epoch 16 - iter 1024/2560 - loss 0.14517837 - samples/sec: 10.36 - lr: 0.000001
814
+ 2021-01-16 07:40:50,070 epoch 16 - iter 1280/2560 - loss 0.15012946 - samples/sec: 10.37 - lr: 0.000001
815
+ 2021-01-16 07:42:28,901 epoch 16 - iter 1536/2560 - loss 0.14944365 - samples/sec: 10.36 - lr: 0.000001
816
+ 2021-01-16 07:44:07,511 epoch 16 - iter 1792/2560 - loss 0.15203691 - samples/sec: 10.39 - lr: 0.000001
817
+ 2021-01-16 07:45:46,097 epoch 16 - iter 2048/2560 - loss 0.15361748 - samples/sec: 10.39 - lr: 0.000001
818
+ 2021-01-16 07:47:24,743 epoch 16 - iter 2304/2560 - loss 0.15600239 - samples/sec: 10.38 - lr: 0.000001
819
+ 2021-01-16 07:49:05,943 epoch 16 - iter 2560/2560 - loss 0.15282003 - samples/sec: 10.12 - lr: 0.000000
820
+ 2021-01-16 07:49:05,945 ----------------------------------------------------------------------------------------------------
821
+ 2021-01-16 07:49:05,945 EPOCH 16 done: loss 0.1528 - lr 0.0000005
822
+ 2021-01-16 07:49:05,945 BAD EPOCHS (no improvement): 4
823
+ 2021-01-16 07:49:05,948 ----------------------------------------------------------------------------------------------------
824
+ 2021-01-16 07:50:44,838 epoch 17 - iter 256/2560 - loss 0.16498748 - samples/sec: 10.36 - lr: 0.000000
825
+ 2021-01-16 07:52:23,007 epoch 17 - iter 512/2560 - loss 0.16360209 - samples/sec: 10.43 - lr: 0.000000
826
+ 2021-01-16 07:54:00,994 epoch 17 - iter 768/2560 - loss 0.15339211 - samples/sec: 10.45 - lr: 0.000000
827
+ 2021-01-16 07:55:39,191 epoch 17 - iter 1024/2560 - loss 0.15505899 - samples/sec: 10.43 - lr: 0.000000
828
+ 2021-01-16 07:57:19,956 epoch 17 - iter 1280/2560 - loss 0.15433689 - samples/sec: 10.16 - lr: 0.000000
829
+ 2021-01-16 07:58:58,357 epoch 17 - iter 1536/2560 - loss 0.15255959 - samples/sec: 10.41 - lr: 0.000000
830
+ 2021-01-16 08:00:36,819 epoch 17 - iter 1792/2560 - loss 0.15399288 - samples/sec: 10.40 - lr: 0.000000
831
+ 2021-01-16 08:02:15,472 epoch 17 - iter 2048/2560 - loss 0.15148049 - samples/sec: 10.38 - lr: 0.000000
832
+ 2021-01-16 08:03:54,072 epoch 17 - iter 2304/2560 - loss 0.15382739 - samples/sec: 10.39 - lr: 0.000000
833
+ 2021-01-16 08:05:31,830 epoch 17 - iter 2560/2560 - loss 0.15712540 - samples/sec: 10.48 - lr: 0.000000
834
+ 2021-01-16 08:05:31,833 ----------------------------------------------------------------------------------------------------
835
+ 2021-01-16 08:05:31,833 EPOCH 17 done: loss 0.1571 - lr 0.0000003
836
+ 2021-01-16 08:05:31,833 BAD EPOCHS (no improvement): 4
837
+ 2021-01-16 08:05:31,841 ----------------------------------------------------------------------------------------------------
838
+ 2021-01-16 08:07:10,239 epoch 18 - iter 256/2560 - loss 0.15978983 - samples/sec: 10.41 - lr: 0.000000
839
+ 2021-01-16 08:08:48,106 epoch 18 - iter 512/2560 - loss 0.14347639 - samples/sec: 10.46 - lr: 0.000000
840
+ 2021-01-16 08:10:26,495 epoch 18 - iter 768/2560 - loss 0.15206254 - samples/sec: 10.41 - lr: 0.000000
841
+ 2021-01-16 08:12:04,438 epoch 18 - iter 1024/2560 - loss 0.16796272 - samples/sec: 10.46 - lr: 0.000000
842
+ 2021-01-16 08:13:42,204 epoch 18 - iter 1280/2560 - loss 0.16531154 - samples/sec: 10.48 - lr: 0.000000
843
+ 2021-01-16 08:15:23,133 epoch 18 - iter 1536/2560 - loss 0.16233384 - samples/sec: 10.15 - lr: 0.000000
844
+ 2021-01-16 08:17:01,293 epoch 18 - iter 1792/2560 - loss 0.16011966 - samples/sec: 10.43 - lr: 0.000000
845
+ 2021-01-16 08:18:39,512 epoch 18 - iter 2048/2560 - loss 0.16087553 - samples/sec: 10.43 - lr: 0.000000
846
+ 2021-01-16 08:20:17,092 epoch 18 - iter 2304/2560 - loss 0.16158800 - samples/sec: 10.50 - lr: 0.000000
847
+ 2021-01-16 08:21:54,438 epoch 18 - iter 2560/2560 - loss 0.16291885 - samples/sec: 10.52 - lr: 0.000000
848
+ 2021-01-16 08:21:54,441 ----------------------------------------------------------------------------------------------------
849
+ 2021-01-16 08:21:54,441 EPOCH 18 done: loss 0.1629 - lr 0.0000001
850
+ 2021-01-16 08:21:54,441 BAD EPOCHS (no improvement): 4
851
+ 2021-01-16 08:21:54,456 ----------------------------------------------------------------------------------------------------
852
+ 2021-01-16 08:23:31,809 epoch 19 - iter 256/2560 - loss 0.13830293 - samples/sec: 10.52 - lr: 0.000000
853
+ 2021-01-16 08:25:09,222 epoch 19 - iter 512/2560 - loss 0.14792782 - samples/sec: 10.51 - lr: 0.000000
854
+ 2021-01-16 08:26:47,079 epoch 19 - iter 768/2560 - loss 0.13707639 - samples/sec: 10.47 - lr: 0.000000
855
+ 2021-01-16 08:28:27,701 epoch 19 - iter 1024/2560 - loss 0.13387744 - samples/sec: 10.18 - lr: 0.000000
856
+ 2021-01-16 08:30:05,328 epoch 19 - iter 1280/2560 - loss 0.13241945 - samples/sec: 10.49 - lr: 0.000000
857
+ 2021-01-16 08:31:43,732 epoch 19 - iter 1536/2560 - loss 0.13879341 - samples/sec: 10.41 - lr: 0.000000
858
+ 2021-01-16 08:33:21,817 epoch 19 - iter 1792/2560 - loss 0.13955545 - samples/sec: 10.44 - lr: 0.000000
859
+ 2021-01-16 08:34:59,377 epoch 19 - iter 2048/2560 - loss 0.13983331 - samples/sec: 10.50 - lr: 0.000000
860
+ 2021-01-16 08:36:36,814 epoch 19 - iter 2304/2560 - loss 0.14005413 - samples/sec: 10.51 - lr: 0.000000
861
+ 2021-01-16 08:38:14,963 epoch 19 - iter 2560/2560 - loss 0.14057681 - samples/sec: 10.43 - lr: 0.000000
862
+ 2021-01-16 08:38:14,965 ----------------------------------------------------------------------------------------------------
863
+ 2021-01-16 08:38:14,965 EPOCH 19 done: loss 0.1406 - lr 0.0000000
864
+ 2021-01-16 08:38:14,965 BAD EPOCHS (no improvement): 4
865
+ 2021-01-16 08:38:14,968 ----------------------------------------------------------------------------------------------------
866
+ 2021-01-16 08:39:54,826 epoch 20 - iter 256/2560 - loss 0.14269958 - samples/sec: 10.26 - lr: 0.000000
867
+ 2021-01-16 08:41:32,343 epoch 20 - iter 512/2560 - loss 0.13295984 - samples/sec: 10.50 - lr: 0.000000
868
+ 2021-01-16 08:43:09,612 epoch 20 - iter 768/2560 - loss 0.13303004 - samples/sec: 10.53 - lr: 0.000000
869
+ 2021-01-16 08:44:46,898 epoch 20 - iter 1024/2560 - loss 0.13511050 - samples/sec: 10.53 - lr: 0.000000
870
+ 2021-01-16 08:46:24,453 epoch 20 - iter 1280/2560 - loss 0.14147167 - samples/sec: 10.50 - lr: 0.000000
871
+ 2021-01-16 08:48:01,998 epoch 20 - iter 1536/2560 - loss 0.14640782 - samples/sec: 10.50 - lr: 0.000000
872
+ 2021-01-16 08:49:39,864 epoch 20 - iter 1792/2560 - loss 0.14698716 - samples/sec: 10.46 - lr: 0.000000
873
+ 2021-01-16 08:51:17,251 epoch 20 - iter 2048/2560 - loss 0.14558654 - samples/sec: 10.52 - lr: 0.000000
874
+ 2021-01-16 08:52:55,347 epoch 20 - iter 2304/2560 - loss 0.14717600 - samples/sec: 10.44 - lr: 0.000000
875
+ 2021-01-16 08:54:33,232 epoch 20 - iter 2560/2560 - loss 0.14611906 - samples/sec: 10.46 - lr: 0.000000
876
+ 2021-01-16 08:54:33,234 ----------------------------------------------------------------------------------------------------
877
+ 2021-01-16 08:54:33,234 EPOCH 20 done: loss 0.1461 - lr 0.0000000
878
+ 2021-01-16 08:54:33,234 BAD EPOCHS (no improvement): 4
879
+ 2021-01-16 08:55:12,409 ----------------------------------------------------------------------------------------------------
880
+ 2021-01-16 08:55:12,409 Testing using best model ...
881
+ 2021-01-16 08:56:13,946 0.9021 0.9087 0.9054
882
+ 2021-01-16 08:56:13,946
883
+ Results:
884
+ - F1-score (micro) 0.9054
885
+ - F1-score (macro) 0.8961
886
+
887
+ By class:
888
+ LOC tp: 942 - fp: 87 - fn: 142 - precision: 0.9155 - recall: 0.8690 - f1-score: 0.8916
889
+ MISC tp: 272 - fp: 57 - fn: 68 - precision: 0.8267 - recall: 0.8000 - f1-score: 0.8132
890
+ ORG tp: 1292 - fp: 188 - fn: 108 - precision: 0.8730 - recall: 0.9229 - f1-score: 0.8972
891
+ PER tp: 728 - fp: 19 - fn: 7 - precision: 0.9746 - recall: 0.9905 - f1-score: 0.9825
892
+ 2021-01-16 08:56:13,946 ----------------------------------------------------------------------------------------------------