Hugging Face's logo

amtam0
/
timer-ner-en

Token Classification
Flair
PyTorch
English
sequence-tagger-model
Model card Files Community
amtam0 commited on
Commit
f63b3fd
•
1 Parent(s): 17a7ae0

init

Browse files
Files changed (6) hide show
  1. README.md +32 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. pytorch_model.bin +3 -0
  5. test.tsv +0 -0
  6. training.log +364 -0
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - flair
4
+ - token-classification
5
+ - sequence-tagger-model
6
+ language: en
7
+ widget:
8
+ - text: "12 sets of 2 minutes 38 minutes between each set"
9
+
10
+ ---
11
+
12
+ 7-class NER English model using [Flair TransformerWordEmbeddings - distilroberta-base](https://github.com/flairNLP/flair/).
13
+
14
+ | **tag** | **meaning** |
15
+ |---------------------------------|-----------|
16
+ | nb_rounds | Number of rounds |
17
+ | duration_br_sd | Duration btwn rounds in seconds |
18
+ | duration_br_min | Duration btwn rounds in minutes |
19
+ | duration_br_hr | Duration btwn rounds in hours |
20
+ | duration_wt_sd | workout duration in seconds |
21
+ | duration_wt_min | workout duration in minutes |
22
+ | duration_wt_hr | workout duration in hours |
23
+ ---
24
+ The dataset was created manually (perfectible). Sentences example :
25
+ ```
26
+ 19 sets of 3 minutes 21 minutes between sets
27
+ start 7 sets of 32 seconds
28
+ create 13 sets of 26 seconds
29
+ init 8 series of 3 hours
30
+ 2 sets of 30 seconds 35 minutes between each cycle
31
+ ...
32
+ ```
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP BAD_EPOCHS LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 15:37:11 0 0.0001 0.16075978090894327 0.0029305333737283945 0.9992 0.9992 0.9992 0.9992
3
+ 2 15:39:39 0 0.0001 0.11129908844900666 0.0013541270745918155 0.9992 0.9992 0.9992 0.9992
4
+ 3 15:42:09 1 0.0001 0.11176801912461394 0.0017125594895333052 0.9992 0.9992 0.9992 0.9992
5
+ 4 15:44:39 2 0.0001 0.11077808575201452 0.0035813269205391407 0.9992 0.9992 0.9992 0.9992
6
+ 5 15:47:07 0 0.0001 0.10987376058836824 0.0010140719823539257 0.9995 0.9995 0.9995 0.9995
7
+ 6 15:49:35 1 0.0001 0.10985530377211841 0.0014548080507665873 0.9993 0.9993 0.9993 0.9993
8
+ 7 15:52:04 2 0.0001 0.11081814550640288 0.0011286081280559301 0.9994 0.9994 0.9994 0.9994
9
+ 8 15:54:33 0 0.0001 0.1101565688396648 0.0014515728689730167 0.9995 0.9995 0.9995 0.9995
10
+ 9 15:57:02 1 0.0001 0.11015787282151847 0.0028099738992750645 0.9994 0.9994 0.9994 0.9994
11
+ 10 15:59:31 2 0.0001 0.1096125644685161 0.004609304014593363 0.9993 0.9993 0.9993 0.9993
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6178fe753987ccc16cf513c1d15ab22cd01d29eadcfa580549d99aaa771b7840
3
+ size 338076137
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,364 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2021-11-17 15:34:49,923 ----------------------------------------------------------------------------------------------------
2
+ 2021-11-17 15:34:49,924 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): RobertaModel(
5
+ (embeddings): RobertaEmbeddings(
6
+ (word_embeddings): Embedding(50265, 768, padding_idx=1)
7
+ (position_embeddings): Embedding(514, 768, padding_idx=1)
8
+ (token_type_embeddings): Embedding(1, 768)
9
+ (LayerNorm): LayerNorm((768,), 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=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): RobertaSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): RobertaIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ )
31
+ (output): RobertaOutput(
32
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
33
+ (LayerNorm): LayerNorm((768,), 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=768, out_features=768, bias=True)
41
+ (key): Linear(in_features=768, out_features=768, bias=True)
42
+ (value): Linear(in_features=768, out_features=768, bias=True)
43
+ (dropout): Dropout(p=0.1, inplace=False)
44
+ )
45
+ (output): RobertaSelfOutput(
46
+ (dense): Linear(in_features=768, out_features=768, bias=True)
47
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
48
+ (dropout): Dropout(p=0.1, inplace=False)
49
+ )
50
+ )
51
+ (intermediate): RobertaIntermediate(
52
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
53
+ )
54
+ (output): RobertaOutput(
55
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
56
+ (LayerNorm): LayerNorm((768,), 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=768, out_features=768, bias=True)
64
+ (key): Linear(in_features=768, out_features=768, bias=True)
65
+ (value): Linear(in_features=768, out_features=768, bias=True)
66
+ (dropout): Dropout(p=0.1, inplace=False)
67
+ )
68
+ (output): RobertaSelfOutput(
69
+ (dense): Linear(in_features=768, out_features=768, bias=True)
70
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
71
+ (dropout): Dropout(p=0.1, inplace=False)
72
+ )
73
+ )
74
+ (intermediate): RobertaIntermediate(
75
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
76
+ )
77
+ (output): RobertaOutput(
78
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
79
+ (LayerNorm): LayerNorm((768,), 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=768, out_features=768, bias=True)
87
+ (key): Linear(in_features=768, out_features=768, bias=True)
88
+ (value): Linear(in_features=768, out_features=768, bias=True)
89
+ (dropout): Dropout(p=0.1, inplace=False)
90
+ )
91
+ (output): RobertaSelfOutput(
92
+ (dense): Linear(in_features=768, out_features=768, bias=True)
93
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
94
+ (dropout): Dropout(p=0.1, inplace=False)
95
+ )
96
+ )
97
+ (intermediate): RobertaIntermediate(
98
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
99
+ )
100
+ (output): RobertaOutput(
101
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
102
+ (LayerNorm): LayerNorm((768,), 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=768, out_features=768, bias=True)
110
+ (key): Linear(in_features=768, out_features=768, bias=True)
111
+ (value): Linear(in_features=768, out_features=768, bias=True)
112
+ (dropout): Dropout(p=0.1, inplace=False)
113
+ )
114
+ (output): RobertaSelfOutput(
115
+ (dense): Linear(in_features=768, out_features=768, bias=True)
116
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
117
+ (dropout): Dropout(p=0.1, inplace=False)
118
+ )
119
+ )
120
+ (intermediate): RobertaIntermediate(
121
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
122
+ )
123
+ (output): RobertaOutput(
124
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
125
+ (LayerNorm): LayerNorm((768,), 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=768, out_features=768, bias=True)
133
+ (key): Linear(in_features=768, out_features=768, bias=True)
134
+ (value): Linear(in_features=768, out_features=768, bias=True)
135
+ (dropout): Dropout(p=0.1, inplace=False)
136
+ )
137
+ (output): RobertaSelfOutput(
138
+ (dense): Linear(in_features=768, out_features=768, bias=True)
139
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
140
+ (dropout): Dropout(p=0.1, inplace=False)
141
+ )
142
+ )
143
+ (intermediate): RobertaIntermediate(
144
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
145
+ )
146
+ (output): RobertaOutput(
147
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
148
+ (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)
149
+ (dropout): Dropout(p=0.1, inplace=False)
150
+ )
151
+ )
152
+ )
153
+ )
154
+ (pooler): RobertaPooler(
155
+ (dense): Linear(in_features=768, out_features=768, bias=True)
156
+ (activation): Tanh()
157
+ )
158
+ )
159
+ )
160
+ (word_dropout): WordDropout(p=0.05)
161
+ (locked_dropout): LockedDropout(p=0.5)
162
+ (embedding2nn): Linear(in_features=1536, out_features=1536, bias=True)
163
+ (linear): Linear(in_features=1536, out_features=16, bias=True)
164
+ (beta): 1.0
165
+ (weights): None
166
+ (weight_tensor) None
167
+ )"
168
+ 2021-11-17 15:34:49,924 ----------------------------------------------------------------------------------------------------
169
+ 2021-11-17 15:34:49,925 Corpus: "Corpus: 56700 train + 6300 dev + 7000 test sentences"
170
+ 2021-11-17 15:34:49,925 ----------------------------------------------------------------------------------------------------
171
+ 2021-11-17 15:34:49,926 Parameters:
172
+ 2021-11-17 15:34:49,926 - learning_rate: "5e-05"
173
+ 2021-11-17 15:34:49,926 - mini_batch_size: "64"
174
+ 2021-11-17 15:34:49,926 - patience: "3"
175
+ 2021-11-17 15:34:49,927 - anneal_factor: "0.5"
176
+ 2021-11-17 15:34:49,927 - max_epochs: "10"
177
+ 2021-11-17 15:34:49,927 - shuffle: "True"
178
+ 2021-11-17 15:34:49,928 - train_with_dev: "False"
179
+ 2021-11-17 15:34:49,928 - batch_growth_annealing: "False"
180
+ 2021-11-17 15:34:49,928 ----------------------------------------------------------------------------------------------------
181
+ 2021-11-17 15:34:49,929 Model training base path: "training/flair_ner/17112021_152905"
182
+ 2021-11-17 15:34:49,930 ----------------------------------------------------------------------------------------------------
183
+ 2021-11-17 15:34:49,930 Device: cuda
184
+ 2021-11-17 15:34:49,931 ----------------------------------------------------------------------------------------------------
185
+ 2021-11-17 15:34:49,931 Embeddings storage mode: cpu
186
+ 2021-11-17 15:34:49,933 ----------------------------------------------------------------------------------------------------
187
+ 2021-11-17 15:35:02,874 epoch 1 - iter 88/886 - loss 0.50644155 - samples/sec: 435.49 - lr: 0.000050
188
+ 2021-11-17 15:35:15,686 epoch 1 - iter 176/886 - loss 0.32420832 - samples/sec: 439.83 - lr: 0.000050
189
+ 2021-11-17 15:35:28,472 epoch 1 - iter 264/886 - loss 0.25984089 - samples/sec: 440.71 - lr: 0.000050
190
+ 2021-11-17 15:35:41,245 epoch 1 - iter 352/886 - loss 0.22670251 - samples/sec: 441.16 - lr: 0.000050
191
+ 2021-11-17 15:35:54,419 epoch 1 - iter 440/886 - loss 0.20579280 - samples/sec: 427.72 - lr: 0.000050
192
+ 2021-11-17 15:36:07,202 epoch 1 - iter 528/886 - loss 0.19081105 - samples/sec: 440.90 - lr: 0.000050
193
+ 2021-11-17 15:36:19,841 epoch 1 - iter 616/886 - loss 0.18055071 - samples/sec: 445.85 - lr: 0.000050
194
+ 2021-11-17 15:36:32,361 epoch 1 - iter 704/886 - loss 0.17219026 - samples/sec: 450.10 - lr: 0.000050
195
+ 2021-11-17 15:36:45,001 epoch 1 - iter 792/886 - loss 0.16603222 - samples/sec: 445.79 - lr: 0.000050
196
+ 2021-11-17 15:36:57,735 epoch 1 - iter 880/886 - loss 0.16102375 - samples/sec: 442.72 - lr: 0.000050
197
+ 2021-11-17 15:36:58,592 ----------------------------------------------------------------------------------------------------
198
+ 2021-11-17 15:36:58,593 EPOCH 1 done: loss 0.1608 - lr 0.0000500
199
+ 2021-11-17 15:37:11,841 DEV : loss 0.0029305333737283945 - f1-score (micro avg) 0.9992
200
+ 2021-11-17 15:37:11,924 BAD EPOCHS (no improvement): 0
201
+ 2021-11-17 15:37:11,924 saving best model
202
+ 2021-11-17 15:37:12,293 ----------------------------------------------------------------------------------------------------
203
+ 2021-11-17 15:37:25,475 epoch 2 - iter 88/886 - loss 0.11026321 - samples/sec: 427.67 - lr: 0.000050
204
+ 2021-11-17 15:37:38,477 epoch 2 - iter 176/886 - loss 0.11169786 - samples/sec: 433.62 - lr: 0.000050
205
+ 2021-11-17 15:37:51,386 epoch 2 - iter 264/886 - loss 0.11076006 - samples/sec: 436.59 - lr: 0.000050
206
+ 2021-11-17 15:38:04,316 epoch 2 - iter 352/886 - loss 0.11026275 - samples/sec: 435.86 - lr: 0.000050
207
+ 2021-11-17 15:38:17,224 epoch 2 - iter 440/886 - loss 0.11058185 - samples/sec: 436.60 - lr: 0.000050
208
+ 2021-11-17 15:38:30,171 epoch 2 - iter 528/886 - loss 0.11105888 - samples/sec: 435.31 - lr: 0.000050
209
+ 2021-11-17 15:38:43,248 epoch 2 - iter 616/886 - loss 0.11093445 - samples/sec: 431.17 - lr: 0.000050
210
+ 2021-11-17 15:38:56,137 epoch 2 - iter 704/886 - loss 0.11079835 - samples/sec: 437.26 - lr: 0.000050
211
+ 2021-11-17 15:39:09,395 epoch 2 - iter 792/886 - loss 0.11148766 - samples/sec: 425.17 - lr: 0.000050
212
+ 2021-11-17 15:39:22,450 epoch 2 - iter 880/886 - loss 0.11140394 - samples/sec: 431.78 - lr: 0.000050
213
+ 2021-11-17 15:39:23,318 ----------------------------------------------------------------------------------------------------
214
+ 2021-11-17 15:39:23,318 EPOCH 2 done: loss 0.1113 - lr 0.0000500
215
+ 2021-11-17 15:39:39,217 DEV : loss 0.0013541270745918155 - f1-score (micro avg) 0.9992
216
+ 2021-11-17 15:39:39,304 BAD EPOCHS (no improvement): 0
217
+ 2021-11-17 15:39:39,305 ----------------------------------------------------------------------------------------------------
218
+ 2021-11-17 15:39:52,661 epoch 3 - iter 88/886 - loss 0.10886323 - samples/sec: 422.03 - lr: 0.000050
219
+ 2021-11-17 15:40:05,912 epoch 3 - iter 176/886 - loss 0.10787832 - samples/sec: 425.49 - lr: 0.000050
220
+ 2021-11-17 15:40:19,212 epoch 3 - iter 264/886 - loss 0.11035842 - samples/sec: 423.74 - lr: 0.000050
221
+ 2021-11-17 15:40:32,505 epoch 3 - iter 352/886 - loss 0.11104986 - samples/sec: 424.15 - lr: 0.000050
222
+ 2021-11-17 15:40:45,782 epoch 3 - iter 440/886 - loss 0.11091610 - samples/sec: 424.49 - lr: 0.000050
223
+ 2021-11-17 15:40:59,163 epoch 3 - iter 528/886 - loss 0.11110444 - samples/sec: 421.17 - lr: 0.000050
224
+ 2021-11-17 15:41:12,392 epoch 3 - iter 616/886 - loss 0.11146392 - samples/sec: 426.23 - lr: 0.000050
225
+ 2021-11-17 15:41:25,673 epoch 3 - iter 704/886 - loss 0.11154272 - samples/sec: 424.34 - lr: 0.000050
226
+ 2021-11-17 15:41:38,940 epoch 3 - iter 792/886 - loss 0.11160924 - samples/sec: 424.88 - lr: 0.000050
227
+ 2021-11-17 15:41:52,243 epoch 3 - iter 880/886 - loss 0.11176415 - samples/sec: 423.61 - lr: 0.000050
228
+ 2021-11-17 15:41:53,139 ----------------------------------------------------------------------------------------------------
229
+ 2021-11-17 15:41:53,141 EPOCH 3 done: loss 0.1118 - lr 0.0000500
230
+ 2021-11-17 15:42:09,290 DEV : loss 0.0017125594895333052 - f1-score (micro avg) 0.9992
231
+ 2021-11-17 15:42:09,373 BAD EPOCHS (no improvement): 1
232
+ 2021-11-17 15:42:09,374 ----------------------------------------------------------------------------------------------------
233
+ 2021-11-17 15:42:22,858 epoch 4 - iter 88/886 - loss 0.10978185 - samples/sec: 418.00 - lr: 0.000050
234
+ 2021-11-17 15:42:36,074 epoch 4 - iter 176/886 - loss 0.10973528 - samples/sec: 426.43 - lr: 0.000050
235
+ 2021-11-17 15:42:49,423 epoch 4 - iter 264/886 - loss 0.11060583 - samples/sec: 422.19 - lr: 0.000050
236
+ 2021-11-17 15:43:02,798 epoch 4 - iter 352/886 - loss 0.11082956 - samples/sec: 421.55 - lr: 0.000050
237
+ 2021-11-17 15:43:16,118 epoch 4 - iter 440/886 - loss 0.11054231 - samples/sec: 423.16 - lr: 0.000050
238
+ 2021-11-17 15:43:29,471 epoch 4 - iter 528/886 - loss 0.11108359 - samples/sec: 422.07 - lr: 0.000050
239
+ 2021-11-17 15:43:42,869 epoch 4 - iter 616/886 - loss 0.11117851 - samples/sec: 420.64 - lr: 0.000050
240
+ 2021-11-17 15:43:56,526 epoch 4 - iter 704/886 - loss 0.11137181 - samples/sec: 412.67 - lr: 0.000050
241
+ 2021-11-17 15:44:10,054 epoch 4 - iter 792/886 - loss 0.11142306 - samples/sec: 416.60 - lr: 0.000050
242
+ 2021-11-17 15:44:23,264 epoch 4 - iter 880/886 - loss 0.11088636 - samples/sec: 426.62 - lr: 0.000050
243
+ 2021-11-17 15:44:24,146 ----------------------------------------------------------------------------------------------------
244
+ 2021-11-17 15:44:24,146 EPOCH 4 done: loss 0.1108 - lr 0.0000500
245
+ 2021-11-17 15:44:39,706 DEV : loss 0.0035813269205391407 - f1-score (micro avg) 0.9992
246
+ 2021-11-17 15:44:39,791 BAD EPOCHS (no improvement): 2
247
+ 2021-11-17 15:44:39,791 ----------------------------------------------------------------------------------------------------
248
+ 2021-11-17 15:44:53,041 epoch 5 - iter 88/886 - loss 0.10802392 - samples/sec: 425.46 - lr: 0.000050
249
+ 2021-11-17 15:45:06,325 epoch 5 - iter 176/886 - loss 0.10760262 - samples/sec: 424.24 - lr: 0.000050
250
+ 2021-11-17 15:45:19,569 epoch 5 - iter 264/886 - loss 0.10806256 - samples/sec: 425.73 - lr: 0.000050
251
+ 2021-11-17 15:45:32,761 epoch 5 - iter 352/886 - loss 0.10865681 - samples/sec: 427.42 - lr: 0.000050
252
+ 2021-11-17 15:45:45,855 epoch 5 - iter 440/886 - loss 0.10912184 - samples/sec: 430.61 - lr: 0.000050
253
+ 2021-11-17 15:45:59,034 epoch 5 - iter 528/886 - loss 0.10891177 - samples/sec: 427.65 - lr: 0.000050
254
+ 2021-11-17 15:46:12,303 epoch 5 - iter 616/886 - loss 0.10963959 - samples/sec: 424.90 - lr: 0.000050
255
+ 2021-11-17 15:46:25,367 epoch 5 - iter 704/886 - loss 0.10977588 - samples/sec: 431.42 - lr: 0.000050
256
+ 2021-11-17 15:46:38,535 epoch 5 - iter 792/886 - loss 0.10983991 - samples/sec: 427.99 - lr: 0.000050
257
+ 2021-11-17 15:46:52,036 epoch 5 - iter 880/886 - loss 0.10983081 - samples/sec: 417.44 - lr: 0.000050
258
+ 2021-11-17 15:46:52,981 ----------------------------------------------------------------------------------------------------
259
+ 2021-11-17 15:46:52,981 EPOCH 5 done: loss 0.1099 - lr 0.0000500
260
+ 2021-11-17 15:47:07,506 DEV : loss 0.0010140719823539257 - f1-score (micro avg) 0.9995
261
+ 2021-11-17 15:47:07,591 BAD EPOCHS (no improvement): 0
262
+ 2021-11-17 15:47:07,592 saving best model
263
+ 2021-11-17 15:47:08,183 ----------------------------------------------------------------------------------------------------
264
+ 2021-11-17 15:47:21,511 epoch 6 - iter 88/886 - loss 0.10567650 - samples/sec: 422.90 - lr: 0.000050
265
+ 2021-11-17 15:47:34,509 epoch 6 - iter 176/886 - loss 0.10887869 - samples/sec: 433.61 - lr: 0.000050
266
+ 2021-11-17 15:47:47,528 epoch 6 - iter 264/886 - loss 0.10842350 - samples/sec: 432.88 - lr: 0.000050
267
+ 2021-11-17 15:48:00,526 epoch 6 - iter 352/886 - loss 0.10983462 - samples/sec: 433.80 - lr: 0.000050
268
+ 2021-11-17 15:48:13,643 epoch 6 - iter 440/886 - loss 0.10883770 - samples/sec: 429.63 - lr: 0.000050
269
+ 2021-11-17 15:48:26,632 epoch 6 - iter 528/886 - loss 0.10926475 - samples/sec: 434.11 - lr: 0.000050
270
+ 2021-11-17 15:48:39,864 epoch 6 - iter 616/886 - loss 0.10987226 - samples/sec: 425.93 - lr: 0.000050
271
+ 2021-11-17 15:48:52,954 epoch 6 - iter 704/886 - loss 0.11003466 - samples/sec: 430.54 - lr: 0.000050
272
+ 2021-11-17 15:49:06,114 epoch 6 - iter 792/886 - loss 0.11000339 - samples/sec: 428.26 - lr: 0.000050
273
+ 2021-11-17 15:49:19,283 epoch 6 - iter 880/886 - loss 0.10986999 - samples/sec: 427.94 - lr: 0.000050
274
+ 2021-11-17 15:49:20,160 ----------------------------------------------------------------------------------------------------
275
+ 2021-11-17 15:49:20,161 EPOCH 6 done: loss 0.1099 - lr 0.0000500
276
+ 2021-11-17 15:49:35,569 DEV : loss 0.0014548080507665873 - f1-score (micro avg) 0.9993
277
+ 2021-11-17 15:49:35,652 BAD EPOCHS (no improvement): 1
278
+ 2021-11-17 15:49:35,653 ----------------------------------------------------------------------------------------------------
279
+ 2021-11-17 15:49:48,878 epoch 7 - iter 88/886 - loss 0.10951206 - samples/sec: 426.18 - lr: 0.000050
280
+ 2021-11-17 15:50:01,971 epoch 7 - iter 176/886 - loss 0.11032338 - samples/sec: 430.47 - lr: 0.000050
281
+ 2021-11-17 15:50:15,172 epoch 7 - iter 264/886 - loss 0.11045747 - samples/sec: 426.91 - lr: 0.000050
282
+ 2021-11-17 15:50:28,317 epoch 7 - iter 352/886 - loss 0.11071942 - samples/sec: 428.73 - lr: 0.000050
283
+ 2021-11-17 15:50:41,502 epoch 7 - iter 440/886 - loss 0.11000396 - samples/sec: 427.62 - lr: 0.000050
284
+ 2021-11-17 15:50:54,735 epoch 7 - iter 528/886 - loss 0.11036286 - samples/sec: 425.91 - lr: 0.000050
285
+ 2021-11-17 15:51:08,179 epoch 7 - iter 616/886 - loss 0.11044996 - samples/sec: 419.40 - lr: 0.000050
286
+ 2021-11-17 15:51:21,435 epoch 7 - iter 704/886 - loss 0.11062300 - samples/sec: 425.15 - lr: 0.000050
287
+ 2021-11-17 15:51:34,569 epoch 7 - iter 792/886 - loss 0.11050441 - samples/sec: 429.10 - lr: 0.000050
288
+ 2021-11-17 15:51:47,616 epoch 7 - iter 880/886 - loss 0.11081751 - samples/sec: 432.02 - lr: 0.000050
289
+ 2021-11-17 15:51:48,504 ----------------------------------------------------------------------------------------------------
290
+ 2021-11-17 15:51:48,504 EPOCH 7 done: loss 0.1108 - lr 0.0000500
291
+ 2021-11-17 15:52:04,138 DEV : loss 0.0011286081280559301 - f1-score (micro avg) 0.9994
292
+ 2021-11-17 15:52:04,221 BAD EPOCHS (no improvement): 2
293
+ 2021-11-17 15:52:04,221 ----------------------------------------------------------------------------------------------------
294
+ 2021-11-17 15:52:17,523 epoch 8 - iter 88/886 - loss 0.10894525 - samples/sec: 423.73 - lr: 0.000050
295
+ 2021-11-17 15:52:30,625 epoch 8 - iter 176/886 - loss 0.11013192 - samples/sec: 430.14 - lr: 0.000050
296
+ 2021-11-17 15:52:43,834 epoch 8 - iter 264/886 - loss 0.11008158 - samples/sec: 426.69 - lr: 0.000050
297
+ 2021-11-17 15:52:57,028 epoch 8 - iter 352/886 - loss 0.11060585 - samples/sec: 427.15 - lr: 0.000050
298
+ 2021-11-17 15:53:10,298 epoch 8 - iter 440/886 - loss 0.11058677 - samples/sec: 424.70 - lr: 0.000050
299
+ 2021-11-17 15:53:23,599 epoch 8 - iter 528/886 - loss 0.11039821 - samples/sec: 423.70 - lr: 0.000050
300
+ 2021-11-17 15:53:36,716 epoch 8 - iter 616/886 - loss 0.11030582 - samples/sec: 429.67 - lr: 0.000050
301
+ 2021-11-17 15:53:49,982 epoch 8 - iter 704/886 - loss 0.10977816 - samples/sec: 424.83 - lr: 0.000050
302
+ 2021-11-17 15:54:03,181 epoch 8 - iter 792/886 - loss 0.11012337 - samples/sec: 426.98 - lr: 0.000050
303
+ 2021-11-17 15:54:16,462 epoch 8 - iter 880/886 - loss 0.11017103 - samples/sec: 424.37 - lr: 0.000050
304
+ 2021-11-17 15:54:17,329 ----------------------------------------------------------------------------------------------------
305
+ 2021-11-17 15:54:17,329 EPOCH 8 done: loss 0.1102 - lr 0.0000500
306
+ 2021-11-17 15:54:32,948 DEV : loss 0.0014515728689730167 - f1-score (micro avg) 0.9995
307
+ 2021-11-17 15:54:33,031 BAD EPOCHS (no improvement): 0
308
+ 2021-11-17 15:54:33,032 saving best model
309
+ 2021-11-17 15:54:33,637 ----------------------------------------------------------------------------------------------------
310
+ 2021-11-17 15:54:46,858 epoch 9 - iter 88/886 - loss 0.10922566 - samples/sec: 426.35 - lr: 0.000050
311
+ 2021-11-17 15:54:59,965 epoch 9 - iter 176/886 - loss 0.11082640 - samples/sec: 429.99 - lr: 0.000050
312
+ 2021-11-17 15:55:13,176 epoch 9 - iter 264/886 - loss 0.11164660 - samples/sec: 426.60 - lr: 0.000050
313
+ 2021-11-17 15:55:26,289 epoch 9 - iter 352/886 - loss 0.11113663 - samples/sec: 429.99 - lr: 0.000050
314
+ 2021-11-17 15:55:40,047 epoch 9 - iter 440/886 - loss 0.11075153 - samples/sec: 409.63 - lr: 0.000050
315
+ 2021-11-17 15:55:53,772 epoch 9 - iter 528/886 - loss 0.11070955 - samples/sec: 410.63 - lr: 0.000050
316
+ 2021-11-17 15:56:07,050 epoch 9 - iter 616/886 - loss 0.11027549 - samples/sec: 424.44 - lr: 0.000050
317
+ 2021-11-17 15:56:20,322 epoch 9 - iter 704/886 - loss 0.11003220 - samples/sec: 424.64 - lr: 0.000050
318
+ 2021-11-17 15:56:33,497 epoch 9 - iter 792/886 - loss 0.10976900 - samples/sec: 427.78 - lr: 0.000050
319
+ 2021-11-17 15:56:46,751 epoch 9 - iter 880/886 - loss 0.11015739 - samples/sec: 425.22 - lr: 0.000050
320
+ 2021-11-17 15:56:47,659 ----------------------------------------------------------------------------------------------------
321
+ 2021-11-17 15:56:47,660 EPOCH 9 done: loss 0.1102 - lr 0.0000500
322
+ 2021-11-17 15:57:02,117 DEV : loss 0.0028099738992750645 - f1-score (micro avg) 0.9994
323
+ 2021-11-17 15:57:02,205 BAD EPOCHS (no improvement): 1
324
+ 2021-11-17 15:57:02,206 ----------------------------------------------------------------------------------------------------
325
+ 2021-11-17 15:57:15,740 epoch 10 - iter 88/886 - loss 0.11323596 - samples/sec: 416.50 - lr: 0.000050
326
+ 2021-11-17 15:57:28,942 epoch 10 - iter 176/886 - loss 0.11324876 - samples/sec: 426.89 - lr: 0.000050
327
+ 2021-11-17 15:57:42,141 epoch 10 - iter 264/886 - loss 0.11189004 - samples/sec: 426.98 - lr: 0.000050
328
+ 2021-11-17 15:57:55,416 epoch 10 - iter 352/886 - loss 0.11062028 - samples/sec: 424.72 - lr: 0.000050
329
+ 2021-11-17 15:58:08,673 epoch 10 - iter 440/886 - loss 0.10959000 - samples/sec: 425.11 - lr: 0.000050
330
+ 2021-11-17 15:58:21,918 epoch 10 - iter 528/886 - loss 0.10964689 - samples/sec: 425.52 - lr: 0.000050
331
+ 2021-11-17 15:58:35,102 epoch 10 - iter 616/886 - loss 0.11011373 - samples/sec: 427.66 - lr: 0.000050
332
+ 2021-11-17 15:58:48,156 epoch 10 - iter 704/886 - loss 0.10975773 - samples/sec: 431.74 - lr: 0.000050
333
+ 2021-11-17 15:59:01,225 epoch 10 - iter 792/886 - loss 0.10955614 - samples/sec: 431.43 - lr: 0.000050
334
+ 2021-11-17 15:59:14,205 epoch 10 - iter 880/886 - loss 0.10966756 - samples/sec: 434.19 - lr: 0.000050
335
+ 2021-11-17 15:59:15,113 ----------------------------------------------------------------------------------------------------
336
+ 2021-11-17 15:59:15,114 EPOCH 10 done: loss 0.1096 - lr 0.0000500
337
+ 2021-11-17 15:59:30,962 DEV : loss 0.004609304014593363 - f1-score (micro avg) 0.9993
338
+ 2021-11-17 15:59:31,047 BAD EPOCHS (no improvement): 2
339
+ 2021-11-17 15:59:31,418 ----------------------------------------------------------------------------------------------------
340
+ 2021-11-17 15:59:31,419 loading file training/flair_ner/17112021_152905/best-model.pt
341
+ 2021-11-17 15:59:49,424 0.9993 0.9993 0.9993 0.9993
342
+ 2021-11-17 15:59:49,425
343
+ Results:
344
+ - F-score (micro) 0.9993
345
+ - F-score (macro) 0.9984
346
+ - Accuracy 0.9993
347
+
348
+ By class:
349
+ precision recall f1-score support
350
+
351
+ nb_rounds 0.9988 0.9991 0.9990 6882
352
+ duration_br_min 0.9997 0.9979 0.9988 3303
353
+ duration_wt_sd 1.0000 1.0000 1.0000 3251
354
+ duration_wt_min 1.0000 1.0000 1.0000 2698
355
+ duration_br_sd 0.9995 0.9995 0.9995 2003
356
+ duration_wt_hr 1.0000 1.0000 1.0000 1068
357
+ duration_br_hr 0.9830 1.0000 0.9914 231
358
+
359
+ micro avg 0.9993 0.9993 0.9993 19436
360
+ macro avg 0.9973 0.9995 0.9984 19436
361
+ weighted avg 0.9993 0.9993 0.9993 19436
362
+ samples avg 0.9993 0.9993 0.9993 19436
363
+
364
+ 2021-11-17 15:59:49,425 ----------------------------------------------------------------------------------------------------