Hugging Face's logo

hmbert
/
flair-hipe-2022-hipe2020-de

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
d3a365d
•
1 Parent(s): 75359d8

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61bbdc58806da6b3a51e7c98489a25a709ab09dabc76e7f26bbecec9b4dd2a2
3
+ size 443335879
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 LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 12:23:58 0.0000 0.6340 0.1836 0.6270 0.5731 0.5989 0.4394
3
+ 2 12:24:50 0.0000 0.1594 0.1390 0.7209 0.7131 0.7170 0.5779
4
+ 3 12:25:43 0.0000 0.0887 0.1498 0.7359 0.7537 0.7447 0.6082
5
+ 4 12:26:34 0.0000 0.0572 0.1670 0.7524 0.7506 0.7515 0.6210
6
+ 5 12:27:26 0.0000 0.0418 0.1815 0.7601 0.7780 0.7689 0.6436
7
+ 6 12:28:17 0.0000 0.0249 0.1979 0.7365 0.8084 0.7708 0.6430
8
+ 7 12:29:09 0.0000 0.0165 0.2128 0.7710 0.8030 0.7867 0.6639
9
+ 8 12:30:00 0.0000 0.0097 0.2147 0.7950 0.8006 0.7978 0.6781
10
+ 9 12:30:54 0.0000 0.0063 0.2354 0.7936 0.7967 0.7952 0.6722
11
+ 10 12:31:45 0.0000 0.0042 0.2287 0.7866 0.7983 0.7924 0.6691
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 12:23:10,194 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 12:23:10,195 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
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): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 12:23:10,195 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 12:23:10,195 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
52
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
53
+ 2023-10-13 12:23:10,195 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 12:23:10,195 Train: 3575 sentences
55
+ 2023-10-13 12:23:10,195 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 12:23:10,195 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 12:23:10,195 Training Params:
58
+ 2023-10-13 12:23:10,195 - learning_rate: "3e-05"
59
+ 2023-10-13 12:23:10,195 - mini_batch_size: "4"
60
+ 2023-10-13 12:23:10,195 - max_epochs: "10"
61
+ 2023-10-13 12:23:10,195 - shuffle: "True"
62
+ 2023-10-13 12:23:10,196 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 12:23:10,196 Plugins:
64
+ 2023-10-13 12:23:10,196 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 12:23:10,196 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 12:23:10,196 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 12:23:10,196 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 12:23:10,196 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 12:23:10,196 Computation:
70
+ 2023-10-13 12:23:10,196 - compute on device: cuda:0
71
+ 2023-10-13 12:23:10,196 - embedding storage: none
72
+ 2023-10-13 12:23:10,196 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 12:23:10,196 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
74
+ 2023-10-13 12:23:10,196 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 12:23:10,196 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 12:23:14,561 epoch 1 - iter 89/894 - loss 3.10167065 - time (sec): 4.36 - samples/sec: 1836.58 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 12:23:18,929 epoch 1 - iter 178/894 - loss 2.04262052 - time (sec): 8.73 - samples/sec: 1838.99 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 12:23:23,191 epoch 1 - iter 267/894 - loss 1.47032662 - time (sec): 12.99 - samples/sec: 1919.00 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 12:23:27,431 epoch 1 - iter 356/894 - loss 1.21051529 - time (sec): 17.23 - samples/sec: 1916.83 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 12:23:31,569 epoch 1 - iter 445/894 - loss 1.02631486 - time (sec): 21.37 - samples/sec: 1959.98 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 12:23:36,164 epoch 1 - iter 534/894 - loss 0.88774045 - time (sec): 25.97 - samples/sec: 2010.02 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 12:23:40,328 epoch 1 - iter 623/894 - loss 0.80641379 - time (sec): 30.13 - samples/sec: 2007.12 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 12:23:44,841 epoch 1 - iter 712/894 - loss 0.73642288 - time (sec): 34.64 - samples/sec: 1998.57 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 12:23:49,049 epoch 1 - iter 801/894 - loss 0.68713278 - time (sec): 38.85 - samples/sec: 1987.57 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 12:23:53,392 epoch 1 - iter 890/894 - loss 0.63696695 - time (sec): 43.19 - samples/sec: 1991.95 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 12:23:53,573 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 12:23:53,574 EPOCH 1 done: loss 0.6340 - lr: 0.000030
88
+ 2023-10-13 12:23:58,634 DEV : loss 0.1835888773202896 - f1-score (micro avg) 0.5989
89
+ 2023-10-13 12:23:58,663 saving best model
90
+ 2023-10-13 12:23:59,015 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 12:24:03,466 epoch 2 - iter 89/894 - loss 0.20312042 - time (sec): 4.45 - samples/sec: 1933.81 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 12:24:08,010 epoch 2 - iter 178/894 - loss 0.19771800 - time (sec): 8.99 - samples/sec: 1893.98 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 12:24:12,088 epoch 2 - iter 267/894 - loss 0.18381905 - time (sec): 13.07 - samples/sec: 1929.95 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 12:24:16,167 epoch 2 - iter 356/894 - loss 0.18005035 - time (sec): 17.15 - samples/sec: 1986.03 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 12:24:20,416 epoch 2 - iter 445/894 - loss 0.17303291 - time (sec): 21.40 - samples/sec: 1970.70 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 12:24:24,735 epoch 2 - iter 534/894 - loss 0.17208210 - time (sec): 25.72 - samples/sec: 2001.50 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 12:24:28,879 epoch 2 - iter 623/894 - loss 0.16599635 - time (sec): 29.86 - samples/sec: 2002.87 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 12:24:33,171 epoch 2 - iter 712/894 - loss 0.16263272 - time (sec): 34.15 - samples/sec: 2024.19 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 12:24:37,429 epoch 2 - iter 801/894 - loss 0.15971559 - time (sec): 38.41 - samples/sec: 2027.57 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 12:24:41,579 epoch 2 - iter 890/894 - loss 0.15954822 - time (sec): 42.56 - samples/sec: 2024.08 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 12:24:41,766 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 12:24:41,766 EPOCH 2 done: loss 0.1594 - lr: 0.000027
103
+ 2023-10-13 12:24:50,035 DEV : loss 0.13900581002235413 - f1-score (micro avg) 0.717
104
+ 2023-10-13 12:24:50,066 saving best model
105
+ 2023-10-13 12:24:50,907 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 12:24:55,312 epoch 3 - iter 89/894 - loss 0.08955154 - time (sec): 4.40 - samples/sec: 1959.52 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 12:24:59,630 epoch 3 - iter 178/894 - loss 0.08525409 - time (sec): 8.72 - samples/sec: 2094.68 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 12:25:03,783 epoch 3 - iter 267/894 - loss 0.08743891 - time (sec): 12.87 - samples/sec: 2136.94 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 12:25:07,837 epoch 3 - iter 356/894 - loss 0.08203209 - time (sec): 16.93 - samples/sec: 2154.98 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 12:25:12,061 epoch 3 - iter 445/894 - loss 0.08840063 - time (sec): 21.15 - samples/sec: 2149.93 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 12:25:16,072 epoch 3 - iter 534/894 - loss 0.08896715 - time (sec): 25.16 - samples/sec: 2112.47 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 12:25:20,538 epoch 3 - iter 623/894 - loss 0.08701667 - time (sec): 29.63 - samples/sec: 2076.88 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 12:25:25,148 epoch 3 - iter 712/894 - loss 0.08815847 - time (sec): 34.24 - samples/sec: 2030.04 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 12:25:29,745 epoch 3 - iter 801/894 - loss 0.08990165 - time (sec): 38.84 - samples/sec: 2005.45 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 12:25:34,431 epoch 3 - iter 890/894 - loss 0.08911325 - time (sec): 43.52 - samples/sec: 1979.02 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 12:25:34,625 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 12:25:34,625 EPOCH 3 done: loss 0.0887 - lr: 0.000023
118
+ 2023-10-13 12:25:43,288 DEV : loss 0.14982320368289948 - f1-score (micro avg) 0.7447
119
+ 2023-10-13 12:25:43,319 saving best model
120
+ 2023-10-13 12:25:43,780 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 12:25:47,748 epoch 4 - iter 89/894 - loss 0.04933864 - time (sec): 3.96 - samples/sec: 1926.49 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 12:25:52,068 epoch 4 - iter 178/894 - loss 0.04682326 - time (sec): 8.28 - samples/sec: 2051.15 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 12:25:56,138 epoch 4 - iter 267/894 - loss 0.05684560 - time (sec): 12.35 - samples/sec: 2049.73 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 12:26:00,190 epoch 4 - iter 356/894 - loss 0.05827360 - time (sec): 16.40 - samples/sec: 2070.32 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 12:26:04,426 epoch 4 - iter 445/894 - loss 0.05752293 - time (sec): 20.63 - samples/sec: 2014.80 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 12:26:09,200 epoch 4 - iter 534/894 - loss 0.05616595 - time (sec): 25.41 - samples/sec: 2044.01 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 12:26:13,441 epoch 4 - iter 623/894 - loss 0.05742081 - time (sec): 29.65 - samples/sec: 2040.15 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 12:26:17,568 epoch 4 - iter 712/894 - loss 0.05840359 - time (sec): 33.78 - samples/sec: 2031.02 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 12:26:21,693 epoch 4 - iter 801/894 - loss 0.05795915 - time (sec): 37.90 - samples/sec: 2052.24 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 12:26:25,851 epoch 4 - iter 890/894 - loss 0.05741204 - time (sec): 42.06 - samples/sec: 2050.78 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 12:26:26,043 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 12:26:26,043 EPOCH 4 done: loss 0.0572 - lr: 0.000020
133
+ 2023-10-13 12:26:34,825 DEV : loss 0.16696369647979736 - f1-score (micro avg) 0.7515
134
+ 2023-10-13 12:26:34,854 saving best model
135
+ 2023-10-13 12:26:35,218 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 12:26:39,447 epoch 5 - iter 89/894 - loss 0.08290902 - time (sec): 4.23 - samples/sec: 1924.41 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 12:26:43,739 epoch 5 - iter 178/894 - loss 0.05714557 - time (sec): 8.52 - samples/sec: 1883.19 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 12:26:47,911 epoch 5 - iter 267/894 - loss 0.05015082 - time (sec): 12.69 - samples/sec: 1949.88 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 12:26:52,185 epoch 5 - iter 356/894 - loss 0.04668232 - time (sec): 16.97 - samples/sec: 2009.99 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 12:26:56,346 epoch 5 - iter 445/894 - loss 0.04376156 - time (sec): 21.13 - samples/sec: 2035.25 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 12:27:00,517 epoch 5 - iter 534/894 - loss 0.04233902 - time (sec): 25.30 - samples/sec: 2032.31 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 12:27:04,633 epoch 5 - iter 623/894 - loss 0.04487302 - time (sec): 29.41 - samples/sec: 2055.83 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 12:27:08,861 epoch 5 - iter 712/894 - loss 0.04491408 - time (sec): 33.64 - samples/sec: 2075.25 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 12:27:12,963 epoch 5 - iter 801/894 - loss 0.04271529 - time (sec): 37.74 - samples/sec: 2078.21 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 12:27:17,117 epoch 5 - iter 890/894 - loss 0.04193496 - time (sec): 41.90 - samples/sec: 2057.49 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 12:27:17,315 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 12:27:17,316 EPOCH 5 done: loss 0.0418 - lr: 0.000017
148
+ 2023-10-13 12:27:26,372 DEV : loss 0.18145021796226501 - f1-score (micro avg) 0.7689
149
+ 2023-10-13 12:27:26,403 saving best model
150
+ 2023-10-13 12:27:26,950 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 12:27:31,158 epoch 6 - iter 89/894 - loss 0.03384747 - time (sec): 4.21 - samples/sec: 2063.80 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 12:27:35,381 epoch 6 - iter 178/894 - loss 0.03067694 - time (sec): 8.43 - samples/sec: 2009.41 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 12:27:39,388 epoch 6 - iter 267/894 - loss 0.02591000 - time (sec): 12.44 - samples/sec: 2017.20 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-13 12:27:43,453 epoch 6 - iter 356/894 - loss 0.02772844 - time (sec): 16.50 - samples/sec: 2044.51 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 12:27:47,471 epoch 6 - iter 445/894 - loss 0.02576901 - time (sec): 20.52 - samples/sec: 2046.17 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 12:27:51,589 epoch 6 - iter 534/894 - loss 0.02535571 - time (sec): 24.64 - samples/sec: 2047.25 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-13 12:27:55,665 epoch 6 - iter 623/894 - loss 0.02569978 - time (sec): 28.71 - samples/sec: 2039.91 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 12:27:59,772 epoch 6 - iter 712/894 - loss 0.02713449 - time (sec): 32.82 - samples/sec: 2040.92 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 12:28:03,995 epoch 6 - iter 801/894 - loss 0.02621730 - time (sec): 37.04 - samples/sec: 2050.38 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-13 12:28:08,477 epoch 6 - iter 890/894 - loss 0.02491693 - time (sec): 41.52 - samples/sec: 2070.94 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-13 12:28:08,690 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 12:28:08,690 EPOCH 6 done: loss 0.0249 - lr: 0.000013
163
+ 2023-10-13 12:28:17,448 DEV : loss 0.19793881475925446 - f1-score (micro avg) 0.7708
164
+ 2023-10-13 12:28:17,486 saving best model
165
+ 2023-10-13 12:28:17,952 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-13 12:28:22,165 epoch 7 - iter 89/894 - loss 0.01290534 - time (sec): 4.21 - samples/sec: 2063.90 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 12:28:26,299 epoch 7 - iter 178/894 - loss 0.01077333 - time (sec): 8.34 - samples/sec: 2068.13 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-13 12:28:30,531 epoch 7 - iter 267/894 - loss 0.01262376 - time (sec): 12.58 - samples/sec: 2091.58 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 12:28:34,912 epoch 7 - iter 356/894 - loss 0.01632707 - time (sec): 16.96 - samples/sec: 2069.76 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 12:28:38,942 epoch 7 - iter 445/894 - loss 0.01462341 - time (sec): 20.99 - samples/sec: 2058.62 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-13 12:28:43,173 epoch 7 - iter 534/894 - loss 0.01445585 - time (sec): 25.22 - samples/sec: 2054.37 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 12:28:47,307 epoch 7 - iter 623/894 - loss 0.01536119 - time (sec): 29.35 - samples/sec: 2046.50 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 12:28:51,469 epoch 7 - iter 712/894 - loss 0.01608270 - time (sec): 33.51 - samples/sec: 2042.72 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-13 12:28:55,582 epoch 7 - iter 801/894 - loss 0.01607712 - time (sec): 37.63 - samples/sec: 2025.83 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 12:29:00,577 epoch 7 - iter 890/894 - loss 0.01659841 - time (sec): 42.62 - samples/sec: 2019.13 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-13 12:29:00,789 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-13 12:29:00,789 EPOCH 7 done: loss 0.0165 - lr: 0.000010
178
+ 2023-10-13 12:29:09,562 DEV : loss 0.21279636025428772 - f1-score (micro avg) 0.7867
179
+ 2023-10-13 12:29:09,594 saving best model
180
+ 2023-10-13 12:29:10,053 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-13 12:29:14,068 epoch 8 - iter 89/894 - loss 0.00681915 - time (sec): 4.01 - samples/sec: 2093.44 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-13 12:29:18,659 epoch 8 - iter 178/894 - loss 0.01159880 - time (sec): 8.60 - samples/sec: 2102.46 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 12:29:22,841 epoch 8 - iter 267/894 - loss 0.01058804 - time (sec): 12.78 - samples/sec: 2064.98 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-13 12:29:27,156 epoch 8 - iter 356/894 - loss 0.00878485 - time (sec): 17.10 - samples/sec: 2048.58 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-13 12:29:31,282 epoch 8 - iter 445/894 - loss 0.00963028 - time (sec): 21.22 - samples/sec: 2016.59 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 12:29:35,452 epoch 8 - iter 534/894 - loss 0.00874697 - time (sec): 25.39 - samples/sec: 2038.40 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-13 12:29:39,587 epoch 8 - iter 623/894 - loss 0.00881807 - time (sec): 29.53 - samples/sec: 2052.68 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-13 12:29:43,671 epoch 8 - iter 712/894 - loss 0.00946149 - time (sec): 33.61 - samples/sec: 2049.34 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 12:29:47,674 epoch 8 - iter 801/894 - loss 0.00989863 - time (sec): 37.62 - samples/sec: 2060.11 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-13 12:29:51,882 epoch 8 - iter 890/894 - loss 0.00969459 - time (sec): 41.82 - samples/sec: 2060.95 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-13 12:29:52,062 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-13 12:29:52,062 EPOCH 8 done: loss 0.0097 - lr: 0.000007
193
+ 2023-10-13 12:30:00,901 DEV : loss 0.21466292440891266 - f1-score (micro avg) 0.7978
194
+ 2023-10-13 12:30:00,932 saving best model
195
+ 2023-10-13 12:30:01,395 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-13 12:30:05,934 epoch 9 - iter 89/894 - loss 0.00422191 - time (sec): 4.54 - samples/sec: 1907.01 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 12:30:10,054 epoch 9 - iter 178/894 - loss 0.00542088 - time (sec): 8.66 - samples/sec: 1970.11 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-13 12:30:14,177 epoch 9 - iter 267/894 - loss 0.00600949 - time (sec): 12.78 - samples/sec: 1982.58 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-13 12:30:18,237 epoch 9 - iter 356/894 - loss 0.00585206 - time (sec): 16.84 - samples/sec: 2022.13 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 12:30:22,725 epoch 9 - iter 445/894 - loss 0.00653931 - time (sec): 21.33 - samples/sec: 2054.47 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-13 12:30:26,910 epoch 9 - iter 534/894 - loss 0.00584633 - time (sec): 25.51 - samples/sec: 2046.84 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-13 12:30:31,048 epoch 9 - iter 623/894 - loss 0.00599610 - time (sec): 29.65 - samples/sec: 2043.13 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 12:30:35,839 epoch 9 - iter 712/894 - loss 0.00549033 - time (sec): 34.44 - samples/sec: 2017.01 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-13 12:30:40,447 epoch 9 - iter 801/894 - loss 0.00560849 - time (sec): 39.05 - samples/sec: 1985.39 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-13 12:30:45,313 epoch 9 - iter 890/894 - loss 0.00613256 - time (sec): 43.92 - samples/sec: 1962.55 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-13 12:30:45,531 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-13 12:30:45,531 EPOCH 9 done: loss 0.0063 - lr: 0.000003
208
+ 2023-10-13 12:30:54,311 DEV : loss 0.2354293167591095 - f1-score (micro avg) 0.7952
209
+ 2023-10-13 12:30:54,341 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-13 12:30:58,510 epoch 10 - iter 89/894 - loss 0.00042234 - time (sec): 4.17 - samples/sec: 2217.34 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 12:31:02,778 epoch 10 - iter 178/894 - loss 0.00238956 - time (sec): 8.44 - samples/sec: 2054.95 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-13 12:31:06,822 epoch 10 - iter 267/894 - loss 0.00321158 - time (sec): 12.48 - samples/sec: 2063.83 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 12:31:11,256 epoch 10 - iter 356/894 - loss 0.00253060 - time (sec): 16.91 - samples/sec: 2101.06 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 12:31:15,638 epoch 10 - iter 445/894 - loss 0.00264548 - time (sec): 21.30 - samples/sec: 2061.39 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-13 12:31:20,218 epoch 10 - iter 534/894 - loss 0.00484149 - time (sec): 25.88 - samples/sec: 2025.23 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 12:31:24,200 epoch 10 - iter 623/894 - loss 0.00448904 - time (sec): 29.86 - samples/sec: 2013.87 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 12:31:28,368 epoch 10 - iter 712/894 - loss 0.00433090 - time (sec): 34.03 - samples/sec: 2021.05 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 12:31:32,402 epoch 10 - iter 801/894 - loss 0.00434765 - time (sec): 38.06 - samples/sec: 2021.53 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 12:31:36,864 epoch 10 - iter 890/894 - loss 0.00420725 - time (sec): 42.52 - samples/sec: 2028.32 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-13 12:31:37,058 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-13 12:31:37,059 EPOCH 10 done: loss 0.0042 - lr: 0.000000
222
+ 2023-10-13 12:31:45,825 DEV : loss 0.22871056199073792 - f1-score (micro avg) 0.7924
223
+ 2023-10-13 12:31:46,193 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-13 12:31:46,194 Loading model from best epoch ...
225
+ 2023-10-13 12:31:47,848 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
226
+ 2023-10-13 12:31:52,388
227
+ Results:
228
+ - F-score (micro) 0.746
229
+ - F-score (macro) 0.6695
230
+ - Accuracy 0.6143
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.8104 0.8607 0.8348 596
236
+ pers 0.6807 0.7297 0.7043 333
237
+ org 0.5285 0.4924 0.5098 132
238
+ prod 0.7368 0.4242 0.5385 66
239
+ time 0.7451 0.7755 0.7600 49
240
+
241
+ micro avg 0.7379 0.7543 0.7460 1176
242
+ macro avg 0.7003 0.6565 0.6695 1176
243
+ weighted avg 0.7352 0.7543 0.7416 1176
244
+
245
+ 2023-10-13 12:31:52,388 ----------------------------------------------------------------------------------------------------