Hugging Face's logo

stefan-it
/
hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
e807e5b
•
1 Parent(s): b3f8d37

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +243 -0
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 18:16:14,534 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 18:16:14,535 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 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=25, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-23 18:16:14,535 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 18:16:14,535 MultiCorpus: 1214 train + 266 dev + 251 test sentences
52
+ - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
53
+ 2023-10-23 18:16:14,535 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 18:16:14,535 Train: 1214 sentences
55
+ 2023-10-23 18:16:14,536 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 18:16:14,536 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 18:16:14,536 Training Params:
58
+ 2023-10-23 18:16:14,536 - learning_rate: "5e-05"
59
+ 2023-10-23 18:16:14,536 - mini_batch_size: "4"
60
+ 2023-10-23 18:16:14,536 - max_epochs: "10"
61
+ 2023-10-23 18:16:14,536 - shuffle: "True"
62
+ 2023-10-23 18:16:14,536 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 18:16:14,536 Plugins:
64
+ 2023-10-23 18:16:14,536 - TensorboardLogger
65
+ 2023-10-23 18:16:14,536 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 18:16:14,536 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 18:16:14,536 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 18:16:14,536 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 18:16:14,536 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 18:16:14,536 Computation:
71
+ 2023-10-23 18:16:14,536 - compute on device: cuda:0
72
+ 2023-10-23 18:16:14,536 - embedding storage: none
73
+ 2023-10-23 18:16:14,536 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 18:16:14,536 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-23 18:16:14,536 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 18:16:14,536 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 18:16:14,537 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 18:16:16,168 epoch 1 - iter 30/304 - loss 2.81106393 - time (sec): 1.63 - samples/sec: 1868.20 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-23 18:16:17,803 epoch 1 - iter 60/304 - loss 1.93076019 - time (sec): 3.26 - samples/sec: 1809.64 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-23 18:16:19,444 epoch 1 - iter 90/304 - loss 1.46147412 - time (sec): 4.91 - samples/sec: 1814.82 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-23 18:16:21,083 epoch 1 - iter 120/304 - loss 1.20065349 - time (sec): 6.54 - samples/sec: 1830.61 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-23 18:16:22,722 epoch 1 - iter 150/304 - loss 1.01442418 - time (sec): 8.18 - samples/sec: 1840.20 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-23 18:16:24,360 epoch 1 - iter 180/304 - loss 0.89232529 - time (sec): 9.82 - samples/sec: 1850.31 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-23 18:16:25,998 epoch 1 - iter 210/304 - loss 0.78694129 - time (sec): 11.46 - samples/sec: 1858.68 - lr: 0.000034 - momentum: 0.000000
85
+ 2023-10-23 18:16:27,642 epoch 1 - iter 240/304 - loss 0.71551296 - time (sec): 13.10 - samples/sec: 1858.63 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-23 18:16:29,280 epoch 1 - iter 270/304 - loss 0.64584501 - time (sec): 14.74 - samples/sec: 1871.71 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-23 18:16:30,918 epoch 1 - iter 300/304 - loss 0.60271094 - time (sec): 16.38 - samples/sec: 1866.99 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-23 18:16:31,135 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 18:16:31,135 EPOCH 1 done: loss 0.5980 - lr: 0.000049
90
+ 2023-10-23 18:16:31,913 DEV : loss 0.16384108364582062 - f1-score (micro avg) 0.704
91
+ 2023-10-23 18:16:31,921 saving best model
92
+ 2023-10-23 18:16:32,319 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 18:16:33,933 epoch 2 - iter 30/304 - loss 0.13187891 - time (sec): 1.61 - samples/sec: 1921.94 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-23 18:16:35,566 epoch 2 - iter 60/304 - loss 0.12737012 - time (sec): 3.25 - samples/sec: 1942.32 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-23 18:16:37,200 epoch 2 - iter 90/304 - loss 0.12304473 - time (sec): 4.88 - samples/sec: 1887.11 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-23 18:16:38,830 epoch 2 - iter 120/304 - loss 0.12231441 - time (sec): 6.51 - samples/sec: 1875.57 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-23 18:16:40,451 epoch 2 - iter 150/304 - loss 0.12142969 - time (sec): 8.13 - samples/sec: 1860.22 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-23 18:16:42,079 epoch 2 - iter 180/304 - loss 0.12168571 - time (sec): 9.76 - samples/sec: 1866.79 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-23 18:16:43,699 epoch 2 - iter 210/304 - loss 0.12781452 - time (sec): 11.38 - samples/sec: 1840.27 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-23 18:16:45,340 epoch 2 - iter 240/304 - loss 0.12865335 - time (sec): 13.02 - samples/sec: 1857.53 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-23 18:16:46,971 epoch 2 - iter 270/304 - loss 0.12960732 - time (sec): 14.65 - samples/sec: 1863.18 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-23 18:16:48,610 epoch 2 - iter 300/304 - loss 0.12332332 - time (sec): 16.29 - samples/sec: 1880.23 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-23 18:16:48,825 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 18:16:48,825 EPOCH 2 done: loss 0.1226 - lr: 0.000045
105
+ 2023-10-23 18:16:49,711 DEV : loss 0.14167819917201996 - f1-score (micro avg) 0.8188
106
+ 2023-10-23 18:16:49,718 saving best model
107
+ 2023-10-23 18:16:50,248 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 18:16:51,875 epoch 3 - iter 30/304 - loss 0.07030755 - time (sec): 1.63 - samples/sec: 1785.11 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-23 18:16:53,518 epoch 3 - iter 60/304 - loss 0.07494672 - time (sec): 3.27 - samples/sec: 1911.69 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-23 18:16:55,156 epoch 3 - iter 90/304 - loss 0.08781157 - time (sec): 4.91 - samples/sec: 1927.02 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-23 18:16:56,786 epoch 3 - iter 120/304 - loss 0.08801500 - time (sec): 6.54 - samples/sec: 1902.16 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-23 18:16:58,422 epoch 3 - iter 150/304 - loss 0.08096093 - time (sec): 8.17 - samples/sec: 1922.15 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-23 18:17:00,061 epoch 3 - iter 180/304 - loss 0.08068663 - time (sec): 9.81 - samples/sec: 1898.78 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-23 18:17:01,697 epoch 3 - iter 210/304 - loss 0.08424806 - time (sec): 11.45 - samples/sec: 1878.13 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-23 18:17:03,312 epoch 3 - iter 240/304 - loss 0.08231945 - time (sec): 13.06 - samples/sec: 1900.07 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-23 18:17:04,951 epoch 3 - iter 270/304 - loss 0.07987312 - time (sec): 14.70 - samples/sec: 1880.03 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-23 18:17:06,596 epoch 3 - iter 300/304 - loss 0.08623195 - time (sec): 16.35 - samples/sec: 1876.47 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-23 18:17:06,810 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 18:17:06,810 EPOCH 3 done: loss 0.0874 - lr: 0.000039
120
+ 2023-10-23 18:17:07,670 DEV : loss 0.1868170201778412 - f1-score (micro avg) 0.8171
121
+ 2023-10-23 18:17:07,678 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-23 18:17:09,306 epoch 4 - iter 30/304 - loss 0.03795868 - time (sec): 1.63 - samples/sec: 2070.92 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-23 18:17:10,945 epoch 4 - iter 60/304 - loss 0.03436106 - time (sec): 3.27 - samples/sec: 1990.77 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-23 18:17:12,583 epoch 4 - iter 90/304 - loss 0.05396697 - time (sec): 4.90 - samples/sec: 1900.22 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-23 18:17:14,225 epoch 4 - iter 120/304 - loss 0.04411729 - time (sec): 6.55 - samples/sec: 1907.64 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-23 18:17:15,858 epoch 4 - iter 150/304 - loss 0.04620010 - time (sec): 8.18 - samples/sec: 1892.75 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-23 18:17:17,502 epoch 4 - iter 180/304 - loss 0.05291311 - time (sec): 9.82 - samples/sec: 1887.18 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-23 18:17:19,138 epoch 4 - iter 210/304 - loss 0.06392533 - time (sec): 11.46 - samples/sec: 1888.42 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-23 18:17:20,771 epoch 4 - iter 240/304 - loss 0.06336046 - time (sec): 13.09 - samples/sec: 1883.10 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-23 18:17:22,404 epoch 4 - iter 270/304 - loss 0.06184609 - time (sec): 14.73 - samples/sec: 1879.24 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-23 18:17:24,030 epoch 4 - iter 300/304 - loss 0.05887253 - time (sec): 16.35 - samples/sec: 1870.50 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-23 18:17:24,245 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-23 18:17:24,246 EPOCH 4 done: loss 0.0581 - lr: 0.000033
134
+ 2023-10-23 18:17:25,250 DEV : loss 0.1909182071685791 - f1-score (micro avg) 0.8271
135
+ 2023-10-23 18:17:25,257 saving best model
136
+ 2023-10-23 18:17:25,783 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-23 18:17:27,406 epoch 5 - iter 30/304 - loss 0.01744137 - time (sec): 1.62 - samples/sec: 1937.30 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-23 18:17:29,031 epoch 5 - iter 60/304 - loss 0.03338940 - time (sec): 3.25 - samples/sec: 1879.20 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-23 18:17:30,666 epoch 5 - iter 90/304 - loss 0.04690048 - time (sec): 4.88 - samples/sec: 1914.80 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-23 18:17:32,300 epoch 5 - iter 120/304 - loss 0.04346722 - time (sec): 6.52 - samples/sec: 1895.35 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-23 18:17:33,937 epoch 5 - iter 150/304 - loss 0.04056557 - time (sec): 8.15 - samples/sec: 1924.73 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-23 18:17:35,568 epoch 5 - iter 180/304 - loss 0.03650648 - time (sec): 9.78 - samples/sec: 1908.95 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-23 18:17:37,208 epoch 5 - iter 210/304 - loss 0.03565747 - time (sec): 11.42 - samples/sec: 1898.72 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-23 18:17:38,842 epoch 5 - iter 240/304 - loss 0.03624900 - time (sec): 13.06 - samples/sec: 1893.31 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-23 18:17:40,473 epoch 5 - iter 270/304 - loss 0.03997973 - time (sec): 14.69 - samples/sec: 1879.27 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-23 18:17:41,959 epoch 5 - iter 300/304 - loss 0.04238227 - time (sec): 16.17 - samples/sec: 1887.18 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-23 18:17:42,137 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-23 18:17:42,137 EPOCH 5 done: loss 0.0438 - lr: 0.000028
149
+ 2023-10-23 18:17:42,996 DEV : loss 0.20630058646202087 - f1-score (micro avg) 0.8014
150
+ 2023-10-23 18:17:43,003 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-23 18:17:44,652 epoch 6 - iter 30/304 - loss 0.07524903 - time (sec): 1.65 - samples/sec: 1896.84 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-23 18:17:46,280 epoch 6 - iter 60/304 - loss 0.05025896 - time (sec): 3.28 - samples/sec: 1832.90 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-23 18:17:47,919 epoch 6 - iter 90/304 - loss 0.04756550 - time (sec): 4.91 - samples/sec: 1879.40 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-23 18:17:49,557 epoch 6 - iter 120/304 - loss 0.03855495 - time (sec): 6.55 - samples/sec: 1856.87 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-23 18:17:51,183 epoch 6 - iter 150/304 - loss 0.04185719 - time (sec): 8.18 - samples/sec: 1851.78 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-23 18:17:52,810 epoch 6 - iter 180/304 - loss 0.03650979 - time (sec): 9.81 - samples/sec: 1838.74 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-23 18:17:54,443 epoch 6 - iter 210/304 - loss 0.03600914 - time (sec): 11.44 - samples/sec: 1845.91 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-23 18:17:56,084 epoch 6 - iter 240/304 - loss 0.03276981 - time (sec): 13.08 - samples/sec: 1865.06 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-23 18:17:57,720 epoch 6 - iter 270/304 - loss 0.03306713 - time (sec): 14.72 - samples/sec: 1862.62 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-23 18:17:59,360 epoch 6 - iter 300/304 - loss 0.03105096 - time (sec): 16.36 - samples/sec: 1876.42 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-23 18:17:59,574 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-23 18:17:59,574 EPOCH 6 done: loss 0.0308 - lr: 0.000022
163
+ 2023-10-23 18:18:00,427 DEV : loss 0.22646591067314148 - f1-score (micro avg) 0.8223
164
+ 2023-10-23 18:18:00,434 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-23 18:18:02,066 epoch 7 - iter 30/304 - loss 0.02843019 - time (sec): 1.63 - samples/sec: 1922.19 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-23 18:18:03,702 epoch 7 - iter 60/304 - loss 0.02264544 - time (sec): 3.27 - samples/sec: 1886.65 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-23 18:18:05,338 epoch 7 - iter 90/304 - loss 0.02267803 - time (sec): 4.90 - samples/sec: 1896.52 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-23 18:18:06,978 epoch 7 - iter 120/304 - loss 0.02033071 - time (sec): 6.54 - samples/sec: 1923.53 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-23 18:18:08,606 epoch 7 - iter 150/304 - loss 0.01831766 - time (sec): 8.17 - samples/sec: 1905.74 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-23 18:18:10,240 epoch 7 - iter 180/304 - loss 0.01927033 - time (sec): 9.80 - samples/sec: 1898.80 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-23 18:18:11,864 epoch 7 - iter 210/304 - loss 0.02071687 - time (sec): 11.43 - samples/sec: 1888.28 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-23 18:18:13,494 epoch 7 - iter 240/304 - loss 0.02263808 - time (sec): 13.06 - samples/sec: 1867.41 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-23 18:18:15,133 epoch 7 - iter 270/304 - loss 0.02451109 - time (sec): 14.70 - samples/sec: 1891.99 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-23 18:18:16,761 epoch 7 - iter 300/304 - loss 0.02486620 - time (sec): 16.33 - samples/sec: 1880.23 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-23 18:18:16,975 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-23 18:18:16,975 EPOCH 7 done: loss 0.0246 - lr: 0.000017
177
+ 2023-10-23 18:18:17,816 DEV : loss 0.20806437730789185 - f1-score (micro avg) 0.8262
178
+ 2023-10-23 18:18:17,823 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-23 18:18:19,440 epoch 8 - iter 30/304 - loss 0.03017504 - time (sec): 1.62 - samples/sec: 1665.61 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-23 18:18:21,061 epoch 8 - iter 60/304 - loss 0.01475323 - time (sec): 3.24 - samples/sec: 1791.60 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-23 18:18:22,689 epoch 8 - iter 90/304 - loss 0.01529115 - time (sec): 4.86 - samples/sec: 1824.73 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-23 18:18:24,301 epoch 8 - iter 120/304 - loss 0.01367787 - time (sec): 6.48 - samples/sec: 1797.21 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-23 18:18:25,946 epoch 8 - iter 150/304 - loss 0.01317154 - time (sec): 8.12 - samples/sec: 1874.76 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-23 18:18:27,541 epoch 8 - iter 180/304 - loss 0.01616983 - time (sec): 9.72 - samples/sec: 1901.04 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-23 18:18:29,175 epoch 8 - iter 210/304 - loss 0.01609663 - time (sec): 11.35 - samples/sec: 1892.89 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-23 18:18:30,814 epoch 8 - iter 240/304 - loss 0.01486684 - time (sec): 12.99 - samples/sec: 1926.77 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-23 18:18:32,438 epoch 8 - iter 270/304 - loss 0.01438102 - time (sec): 14.61 - samples/sec: 1916.14 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-23 18:18:34,068 epoch 8 - iter 300/304 - loss 0.01467520 - time (sec): 16.24 - samples/sec: 1888.31 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-23 18:18:34,281 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-23 18:18:34,281 EPOCH 8 done: loss 0.0145 - lr: 0.000011
191
+ 2023-10-23 18:18:35,114 DEV : loss 0.21577374637126923 - f1-score (micro avg) 0.8517
192
+ 2023-10-23 18:18:35,121 saving best model
193
+ 2023-10-23 18:18:35,654 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-23 18:18:37,296 epoch 9 - iter 30/304 - loss 0.02217251 - time (sec): 1.64 - samples/sec: 2016.73 - lr: 0.000011 - momentum: 0.000000
195
+ 2023-10-23 18:18:38,925 epoch 9 - iter 60/304 - loss 0.01548730 - time (sec): 3.27 - samples/sec: 1914.58 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-23 18:18:40,571 epoch 9 - iter 90/304 - loss 0.01781690 - time (sec): 4.91 - samples/sec: 1919.16 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-23 18:18:42,193 epoch 9 - iter 120/304 - loss 0.01604254 - time (sec): 6.54 - samples/sec: 1837.29 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-23 18:18:43,837 epoch 9 - iter 150/304 - loss 0.01483913 - time (sec): 8.18 - samples/sec: 1874.20 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-23 18:18:45,472 epoch 9 - iter 180/304 - loss 0.01278405 - time (sec): 9.82 - samples/sec: 1863.31 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-23 18:18:47,113 epoch 9 - iter 210/304 - loss 0.01183613 - time (sec): 11.46 - samples/sec: 1865.42 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-23 18:18:48,744 epoch 9 - iter 240/304 - loss 0.01173901 - time (sec): 13.09 - samples/sec: 1862.89 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-23 18:18:50,377 epoch 9 - iter 270/304 - loss 0.01107654 - time (sec): 14.72 - samples/sec: 1868.29 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-23 18:18:52,020 epoch 9 - iter 300/304 - loss 0.01093778 - time (sec): 16.36 - samples/sec: 1872.44 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-23 18:18:52,237 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-23 18:18:52,237 EPOCH 9 done: loss 0.0108 - lr: 0.000006
206
+ 2023-10-23 18:18:53,118 DEV : loss 0.2204783409833908 - f1-score (micro avg) 0.8473
207
+ 2023-10-23 18:18:53,125 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-23 18:18:54,762 epoch 10 - iter 30/304 - loss 0.00097800 - time (sec): 1.64 - samples/sec: 1856.40 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-23 18:18:56,397 epoch 10 - iter 60/304 - loss 0.00905964 - time (sec): 3.27 - samples/sec: 1873.85 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-23 18:18:58,043 epoch 10 - iter 90/304 - loss 0.00780886 - time (sec): 4.92 - samples/sec: 1900.28 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-23 18:18:59,671 epoch 10 - iter 120/304 - loss 0.00866515 - time (sec): 6.55 - samples/sec: 1865.78 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-23 18:19:01,310 epoch 10 - iter 150/304 - loss 0.00766781 - time (sec): 8.18 - samples/sec: 1880.41 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-23 18:19:02,940 epoch 10 - iter 180/304 - loss 0.00744633 - time (sec): 9.81 - samples/sec: 1878.27 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-23 18:19:04,571 epoch 10 - iter 210/304 - loss 0.00780657 - time (sec): 11.44 - samples/sec: 1870.69 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-23 18:19:06,209 epoch 10 - iter 240/304 - loss 0.00784100 - time (sec): 13.08 - samples/sec: 1892.77 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-23 18:19:07,839 epoch 10 - iter 270/304 - loss 0.00724030 - time (sec): 14.71 - samples/sec: 1877.08 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-23 18:19:09,472 epoch 10 - iter 300/304 - loss 0.00659561 - time (sec): 16.35 - samples/sec: 1872.36 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-23 18:19:09,686 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-23 18:19:09,686 EPOCH 10 done: loss 0.0065 - lr: 0.000000
220
+ 2023-10-23 18:19:10,517 DEV : loss 0.22362594306468964 - f1-score (micro avg) 0.8427
221
+ 2023-10-23 18:19:10,914 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-23 18:19:10,915 Loading model from best epoch ...
223
+ 2023-10-23 18:19:12,690 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
224
+ 2023-10-23 18:19:13,529
225
+ Results:
226
+ - F-score (micro) 0.8081
227
+ - F-score (macro) 0.7142
228
+ - Accuracy 0.6874
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ scope 0.8013 0.8278 0.8143 151
234
+ work 0.6855 0.8947 0.7763 95
235
+ pers 0.8037 0.8958 0.8473 96
236
+ date 0.3333 0.3333 0.3333 3
237
+ loc 1.0000 0.6667 0.8000 3
238
+
239
+ micro avg 0.7628 0.8592 0.8081 348
240
+ macro avg 0.7248 0.7237 0.7142 348
241
+ weighted avg 0.7680 0.8592 0.8088 348
242
+
243
+ 2023-10-23 18:19:13,529 ----------------------------------------------------------------------------------------------------