Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
d8f1638
•
1 Parent(s): ea5cdeb

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +248 -0
training.log ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 14:51:33,665 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 14:51:33,666 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 14:51:33,666 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 14:51:33,666 MultiCorpus: 1100 train + 206 dev + 240 test sentences
52
+ - NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
53
+ 2023-10-23 14:51:33,666 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 14:51:33,666 Train: 1100 sentences
55
+ 2023-10-23 14:51:33,666 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 14:51:33,666 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 14:51:33,666 Training Params:
58
+ 2023-10-23 14:51:33,666 - learning_rate: "3e-05"
59
+ 2023-10-23 14:51:33,666 - mini_batch_size: "4"
60
+ 2023-10-23 14:51:33,666 - max_epochs: "10"
61
+ 2023-10-23 14:51:33,666 - shuffle: "True"
62
+ 2023-10-23 14:51:33,666 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 14:51:33,666 Plugins:
64
+ 2023-10-23 14:51:33,666 - TensorboardLogger
65
+ 2023-10-23 14:51:33,666 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 14:51:33,666 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 14:51:33,667 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 14:51:33,667 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 14:51:33,667 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 14:51:33,667 Computation:
71
+ 2023-10-23 14:51:33,667 - compute on device: cuda:0
72
+ 2023-10-23 14:51:33,667 - embedding storage: none
73
+ 2023-10-23 14:51:33,667 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 14:51:33,667 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-23 14:51:33,667 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 14:51:33,667 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 14:51:33,667 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 14:51:36,118 epoch 1 - iter 27/275 - loss 3.76030068 - time (sec): 2.45 - samples/sec: 920.61 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-23 14:51:37,502 epoch 1 - iter 54/275 - loss 2.96902549 - time (sec): 3.83 - samples/sec: 1141.80 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-23 14:51:38,999 epoch 1 - iter 81/275 - loss 2.35139223 - time (sec): 5.33 - samples/sec: 1198.48 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-23 14:51:40,377 epoch 1 - iter 108/275 - loss 1.89822180 - time (sec): 6.71 - samples/sec: 1282.13 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-23 14:51:41,879 epoch 1 - iter 135/275 - loss 1.64164622 - time (sec): 8.21 - samples/sec: 1327.52 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-23 14:51:43,282 epoch 1 - iter 162/275 - loss 1.44032124 - time (sec): 9.61 - samples/sec: 1354.11 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-23 14:51:44,700 epoch 1 - iter 189/275 - loss 1.28091475 - time (sec): 11.03 - samples/sec: 1384.41 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-23 14:51:46,155 epoch 1 - iter 216/275 - loss 1.14720675 - time (sec): 12.49 - samples/sec: 1410.01 - lr: 0.000023 - momentum: 0.000000
86
+ 2023-10-23 14:51:47,580 epoch 1 - iter 243/275 - loss 1.03078045 - time (sec): 13.91 - samples/sec: 1453.56 - lr: 0.000026 - momentum: 0.000000
87
+ 2023-10-23 14:51:48,990 epoch 1 - iter 270/275 - loss 0.95387520 - time (sec): 15.32 - samples/sec: 1455.89 - lr: 0.000029 - momentum: 0.000000
88
+ 2023-10-23 14:51:49,295 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 14:51:49,295 EPOCH 1 done: loss 0.9430 - lr: 0.000029
90
+ 2023-10-23 14:51:49,715 DEV : loss 0.19450944662094116 - f1-score (micro avg) 0.754
91
+ 2023-10-23 14:51:49,720 saving best model
92
+ 2023-10-23 14:51:50,181 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 14:51:51,576 epoch 2 - iter 27/275 - loss 0.16817983 - time (sec): 1.39 - samples/sec: 1484.89 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-23 14:51:52,989 epoch 2 - iter 54/275 - loss 0.13521295 - time (sec): 2.81 - samples/sec: 1555.17 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-23 14:51:54,461 epoch 2 - iter 81/275 - loss 0.15603419 - time (sec): 4.28 - samples/sec: 1534.63 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-23 14:51:55,873 epoch 2 - iter 108/275 - loss 0.16617353 - time (sec): 5.69 - samples/sec: 1551.22 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-23 14:51:57,276 epoch 2 - iter 135/275 - loss 0.16037825 - time (sec): 7.09 - samples/sec: 1569.62 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-23 14:51:58,579 epoch 2 - iter 162/275 - loss 0.16018872 - time (sec): 8.40 - samples/sec: 1587.20 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-23 14:51:59,976 epoch 2 - iter 189/275 - loss 0.16213256 - time (sec): 9.79 - samples/sec: 1603.60 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-23 14:52:01,268 epoch 2 - iter 216/275 - loss 0.16255960 - time (sec): 11.09 - samples/sec: 1601.19 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-23 14:52:02,575 epoch 2 - iter 243/275 - loss 0.16177479 - time (sec): 12.39 - samples/sec: 1626.33 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-23 14:52:03,884 epoch 2 - iter 270/275 - loss 0.16005825 - time (sec): 13.70 - samples/sec: 1637.61 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-23 14:52:04,167 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 14:52:04,167 EPOCH 2 done: loss 0.1590 - lr: 0.000027
105
+ 2023-10-23 14:52:04,693 DEV : loss 0.14087921380996704 - f1-score (micro avg) 0.8186
106
+ 2023-10-23 14:52:04,698 saving best model
107
+ 2023-10-23 14:52:05,312 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 14:52:06,704 epoch 3 - iter 27/275 - loss 0.08749511 - time (sec): 1.39 - samples/sec: 1529.91 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-23 14:52:08,163 epoch 3 - iter 54/275 - loss 0.08996595 - time (sec): 2.85 - samples/sec: 1567.37 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-23 14:52:09,565 epoch 3 - iter 81/275 - loss 0.07783644 - time (sec): 4.25 - samples/sec: 1647.07 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-23 14:52:10,958 epoch 3 - iter 108/275 - loss 0.08738457 - time (sec): 5.64 - samples/sec: 1587.28 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-23 14:52:12,556 epoch 3 - iter 135/275 - loss 0.09031569 - time (sec): 7.24 - samples/sec: 1565.46 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-23 14:52:13,940 epoch 3 - iter 162/275 - loss 0.08700344 - time (sec): 8.63 - samples/sec: 1551.18 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-23 14:52:15,368 epoch 3 - iter 189/275 - loss 0.09749654 - time (sec): 10.06 - samples/sec: 1544.21 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-23 14:52:16,673 epoch 3 - iter 216/275 - loss 0.09678369 - time (sec): 11.36 - samples/sec: 1557.87 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-23 14:52:17,998 epoch 3 - iter 243/275 - loss 0.09737047 - time (sec): 12.68 - samples/sec: 1579.72 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-23 14:52:19,404 epoch 3 - iter 270/275 - loss 0.09843592 - time (sec): 14.09 - samples/sec: 1586.75 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-23 14:52:19,664 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 14:52:19,664 EPOCH 3 done: loss 0.0972 - lr: 0.000023
120
+ 2023-10-23 14:52:20,208 DEV : loss 0.16271711885929108 - f1-score (micro avg) 0.832
121
+ 2023-10-23 14:52:20,213 saving best model
122
+ 2023-10-23 14:52:20,764 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 14:52:22,164 epoch 4 - iter 27/275 - loss 0.09045084 - time (sec): 1.40 - samples/sec: 1553.16 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-23 14:52:23,595 epoch 4 - iter 54/275 - loss 0.08002820 - time (sec): 2.83 - samples/sec: 1622.98 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-23 14:52:24,901 epoch 4 - iter 81/275 - loss 0.07686002 - time (sec): 4.14 - samples/sec: 1628.96 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-23 14:52:26,261 epoch 4 - iter 108/275 - loss 0.07765183 - time (sec): 5.50 - samples/sec: 1624.85 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-23 14:52:27,647 epoch 4 - iter 135/275 - loss 0.07194057 - time (sec): 6.88 - samples/sec: 1615.78 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-23 14:52:29,032 epoch 4 - iter 162/275 - loss 0.07075261 - time (sec): 8.27 - samples/sec: 1577.70 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-23 14:52:30,432 epoch 4 - iter 189/275 - loss 0.07211105 - time (sec): 9.67 - samples/sec: 1587.44 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-23 14:52:31,797 epoch 4 - iter 216/275 - loss 0.07529380 - time (sec): 11.03 - samples/sec: 1613.99 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-23 14:52:33,196 epoch 4 - iter 243/275 - loss 0.07198357 - time (sec): 12.43 - samples/sec: 1609.00 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-23 14:52:34,569 epoch 4 - iter 270/275 - loss 0.07106318 - time (sec): 13.80 - samples/sec: 1621.75 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-23 14:52:34,812 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 14:52:34,812 EPOCH 4 done: loss 0.0712 - lr: 0.000020
135
+ 2023-10-23 14:52:35,342 DEV : loss 0.156390979886055 - f1-score (micro avg) 0.8345
136
+ 2023-10-23 14:52:35,347 saving best model
137
+ 2023-10-23 14:52:35,958 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-23 14:52:37,327 epoch 5 - iter 27/275 - loss 0.03811944 - time (sec): 1.37 - samples/sec: 1511.28 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-23 14:52:38,717 epoch 5 - iter 54/275 - loss 0.04905995 - time (sec): 2.76 - samples/sec: 1566.02 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-23 14:52:40,114 epoch 5 - iter 81/275 - loss 0.04532731 - time (sec): 4.15 - samples/sec: 1582.81 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-23 14:52:41,530 epoch 5 - iter 108/275 - loss 0.05491363 - time (sec): 5.57 - samples/sec: 1567.00 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-23 14:52:42,913 epoch 5 - iter 135/275 - loss 0.05232614 - time (sec): 6.95 - samples/sec: 1563.41 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-23 14:52:44,364 epoch 5 - iter 162/275 - loss 0.04940998 - time (sec): 8.40 - samples/sec: 1565.20 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-23 14:52:45,749 epoch 5 - iter 189/275 - loss 0.04778139 - time (sec): 9.79 - samples/sec: 1578.83 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-23 14:52:47,153 epoch 5 - iter 216/275 - loss 0.05341423 - time (sec): 11.19 - samples/sec: 1585.88 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-23 14:52:48,596 epoch 5 - iter 243/275 - loss 0.05397692 - time (sec): 12.64 - samples/sec: 1586.48 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-23 14:52:49,977 epoch 5 - iter 270/275 - loss 0.05183480 - time (sec): 14.02 - samples/sec: 1594.84 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-23 14:52:50,228 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-23 14:52:50,228 EPOCH 5 done: loss 0.0517 - lr: 0.000017
150
+ 2023-10-23 14:52:50,767 DEV : loss 0.1555197536945343 - f1-score (micro avg) 0.8662
151
+ 2023-10-23 14:52:50,772 saving best model
152
+ 2023-10-23 14:52:51,322 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-23 14:52:52,768 epoch 6 - iter 27/275 - loss 0.05170272 - time (sec): 1.44 - samples/sec: 1613.70 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-23 14:52:54,152 epoch 6 - iter 54/275 - loss 0.03843071 - time (sec): 2.83 - samples/sec: 1584.45 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-23 14:52:55,541 epoch 6 - iter 81/275 - loss 0.03440502 - time (sec): 4.22 - samples/sec: 1615.84 - lr: 0.000016 - momentum: 0.000000
156
+ 2023-10-23 14:52:56,991 epoch 6 - iter 108/275 - loss 0.03812148 - time (sec): 5.67 - samples/sec: 1616.93 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-23 14:52:58,368 epoch 6 - iter 135/275 - loss 0.03963989 - time (sec): 7.04 - samples/sec: 1608.15 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-23 14:52:59,844 epoch 6 - iter 162/275 - loss 0.04065051 - time (sec): 8.52 - samples/sec: 1586.96 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-23 14:53:01,230 epoch 6 - iter 189/275 - loss 0.03839786 - time (sec): 9.91 - samples/sec: 1594.46 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-23 14:53:02,632 epoch 6 - iter 216/275 - loss 0.04073106 - time (sec): 11.31 - samples/sec: 1589.21 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-23 14:53:04,056 epoch 6 - iter 243/275 - loss 0.03969929 - time (sec): 12.73 - samples/sec: 1591.47 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-23 14:53:05,456 epoch 6 - iter 270/275 - loss 0.04061644 - time (sec): 14.13 - samples/sec: 1581.07 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-23 14:53:05,717 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-23 14:53:05,717 EPOCH 6 done: loss 0.0402 - lr: 0.000013
165
+ 2023-10-23 14:53:06,253 DEV : loss 0.16560792922973633 - f1-score (micro avg) 0.8671
166
+ 2023-10-23 14:53:06,258 saving best model
167
+ 2023-10-23 14:53:06,859 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-23 14:53:08,317 epoch 7 - iter 27/275 - loss 0.00265191 - time (sec): 1.46 - samples/sec: 1397.17 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-23 14:53:09,652 epoch 7 - iter 54/275 - loss 0.01398723 - time (sec): 2.79 - samples/sec: 1563.25 - lr: 0.000013 - momentum: 0.000000
170
+ 2023-10-23 14:53:11,083 epoch 7 - iter 81/275 - loss 0.02775533 - time (sec): 4.22 - samples/sec: 1556.99 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-23 14:53:12,449 epoch 7 - iter 108/275 - loss 0.03402506 - time (sec): 5.59 - samples/sec: 1606.20 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-23 14:53:13,804 epoch 7 - iter 135/275 - loss 0.02753248 - time (sec): 6.94 - samples/sec: 1624.36 - lr: 0.000012 - momentum: 0.000000
173
+ 2023-10-23 14:53:15,228 epoch 7 - iter 162/275 - loss 0.03091741 - time (sec): 8.37 - samples/sec: 1636.47 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-23 14:53:16,616 epoch 7 - iter 189/275 - loss 0.02768566 - time (sec): 9.75 - samples/sec: 1627.12 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-23 14:53:17,992 epoch 7 - iter 216/275 - loss 0.02673091 - time (sec): 11.13 - samples/sec: 1619.87 - lr: 0.000011 - momentum: 0.000000
176
+ 2023-10-23 14:53:19,436 epoch 7 - iter 243/275 - loss 0.02610998 - time (sec): 12.57 - samples/sec: 1601.55 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-23 14:53:20,816 epoch 7 - iter 270/275 - loss 0.02775259 - time (sec): 13.96 - samples/sec: 1602.26 - lr: 0.000010 - momentum: 0.000000
178
+ 2023-10-23 14:53:21,071 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-23 14:53:21,071 EPOCH 7 done: loss 0.0280 - lr: 0.000010
180
+ 2023-10-23 14:53:21,597 DEV : loss 0.16052626073360443 - f1-score (micro avg) 0.875
181
+ 2023-10-23 14:53:21,603 saving best model
182
+ 2023-10-23 14:53:22,286 ----------------------------------------------------------------------------------------------------
183
+ 2023-10-23 14:53:23,750 epoch 8 - iter 27/275 - loss 0.04936288 - time (sec): 1.46 - samples/sec: 1528.40 - lr: 0.000010 - momentum: 0.000000
184
+ 2023-10-23 14:53:25,133 epoch 8 - iter 54/275 - loss 0.04354247 - time (sec): 2.84 - samples/sec: 1603.51 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-23 14:53:26,515 epoch 8 - iter 81/275 - loss 0.03367946 - time (sec): 4.22 - samples/sec: 1558.37 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-23 14:53:27,889 epoch 8 - iter 108/275 - loss 0.02870090 - time (sec): 5.60 - samples/sec: 1632.80 - lr: 0.000009 - momentum: 0.000000
187
+ 2023-10-23 14:53:29,313 epoch 8 - iter 135/275 - loss 0.02468517 - time (sec): 7.02 - samples/sec: 1619.99 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-23 14:53:30,564 epoch 8 - iter 162/275 - loss 0.02304861 - time (sec): 8.27 - samples/sec: 1652.63 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-23 14:53:31,821 epoch 8 - iter 189/275 - loss 0.02146790 - time (sec): 9.53 - samples/sec: 1655.76 - lr: 0.000008 - momentum: 0.000000
190
+ 2023-10-23 14:53:33,087 epoch 8 - iter 216/275 - loss 0.01984298 - time (sec): 10.80 - samples/sec: 1675.71 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-23 14:53:34,347 epoch 8 - iter 243/275 - loss 0.01897873 - time (sec): 12.06 - samples/sec: 1676.08 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-23 14:53:35,613 epoch 8 - iter 270/275 - loss 0.01918661 - time (sec): 13.32 - samples/sec: 1673.72 - lr: 0.000007 - momentum: 0.000000
193
+ 2023-10-23 14:53:35,847 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-23 14:53:35,848 EPOCH 8 done: loss 0.0188 - lr: 0.000007
195
+ 2023-10-23 14:53:36,372 DEV : loss 0.16693733632564545 - f1-score (micro avg) 0.8722
196
+ 2023-10-23 14:53:36,377 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-23 14:53:37,694 epoch 9 - iter 27/275 - loss 0.01861865 - time (sec): 1.32 - samples/sec: 1575.51 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-23 14:53:38,944 epoch 9 - iter 54/275 - loss 0.01361342 - time (sec): 2.57 - samples/sec: 1738.65 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-23 14:53:40,188 epoch 9 - iter 81/275 - loss 0.01073145 - time (sec): 3.81 - samples/sec: 1744.90 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-23 14:53:41,460 epoch 9 - iter 108/275 - loss 0.01121247 - time (sec): 5.08 - samples/sec: 1751.86 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-23 14:53:42,707 epoch 9 - iter 135/275 - loss 0.01189528 - time (sec): 6.33 - samples/sec: 1781.63 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-23 14:53:44,008 epoch 9 - iter 162/275 - loss 0.01615819 - time (sec): 7.63 - samples/sec: 1802.89 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-23 14:53:45,277 epoch 9 - iter 189/275 - loss 0.01994894 - time (sec): 8.90 - samples/sec: 1780.91 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-23 14:53:46,516 epoch 9 - iter 216/275 - loss 0.01836120 - time (sec): 10.14 - samples/sec: 1753.83 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-23 14:53:47,802 epoch 9 - iter 243/275 - loss 0.01720199 - time (sec): 11.42 - samples/sec: 1749.97 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-23 14:53:49,092 epoch 9 - iter 270/275 - loss 0.01601844 - time (sec): 12.71 - samples/sec: 1770.01 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-23 14:53:49,320 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-23 14:53:49,320 EPOCH 9 done: loss 0.0158 - lr: 0.000003
209
+ 2023-10-23 14:53:49,846 DEV : loss 0.17052848637104034 - f1-score (micro avg) 0.8771
210
+ 2023-10-23 14:53:49,851 saving best model
211
+ 2023-10-23 14:53:50,424 ----------------------------------------------------------------------------------------------------
212
+ 2023-10-23 14:53:51,862 epoch 10 - iter 27/275 - loss 0.00049426 - time (sec): 1.44 - samples/sec: 1504.14 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-23 14:53:53,265 epoch 10 - iter 54/275 - loss 0.00551470 - time (sec): 2.84 - samples/sec: 1553.44 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-23 14:53:54,689 epoch 10 - iter 81/275 - loss 0.00500161 - time (sec): 4.26 - samples/sec: 1574.51 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-23 14:53:56,024 epoch 10 - iter 108/275 - loss 0.00422058 - time (sec): 5.60 - samples/sec: 1559.22 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-23 14:53:57,322 epoch 10 - iter 135/275 - loss 0.00602318 - time (sec): 6.90 - samples/sec: 1566.35 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-23 14:53:58,708 epoch 10 - iter 162/275 - loss 0.00524299 - time (sec): 8.28 - samples/sec: 1607.88 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 14:53:59,960 epoch 10 - iter 189/275 - loss 0.00665176 - time (sec): 9.53 - samples/sec: 1624.64 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 14:54:01,208 epoch 10 - iter 216/275 - loss 0.00581924 - time (sec): 10.78 - samples/sec: 1646.89 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-23 14:54:02,468 epoch 10 - iter 243/275 - loss 0.00887703 - time (sec): 12.04 - samples/sec: 1682.46 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-23 14:54:03,751 epoch 10 - iter 270/275 - loss 0.00927128 - time (sec): 13.33 - samples/sec: 1683.37 - lr: 0.000000 - momentum: 0.000000
222
+ 2023-10-23 14:54:03,981 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-23 14:54:03,981 EPOCH 10 done: loss 0.0107 - lr: 0.000000
224
+ 2023-10-23 14:54:04,511 DEV : loss 0.1703922599554062 - f1-score (micro avg) 0.8806
225
+ 2023-10-23 14:54:04,517 saving best model
226
+ 2023-10-23 14:54:05,535 ----------------------------------------------------------------------------------------------------
227
+ 2023-10-23 14:54:05,536 Loading model from best epoch ...
228
+ 2023-10-23 14:54:07,515 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-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
229
+ 2023-10-23 14:54:08,212
230
+ Results:
231
+ - F-score (micro) 0.9069
232
+ - F-score (macro) 0.7836
233
+ - Accuracy 0.8398
234
+
235
+ By class:
236
+ precision recall f1-score support
237
+
238
+ scope 0.8971 0.8920 0.8946 176
239
+ pers 0.9760 0.9531 0.9644 128
240
+ work 0.8533 0.8649 0.8591 74
241
+ object 0.6667 1.0000 0.8000 2
242
+ loc 0.3333 0.5000 0.4000 2
243
+
244
+ micro avg 0.9081 0.9058 0.9069 382
245
+ macro avg 0.7453 0.8420 0.7836 382
246
+ weighted avg 0.9109 0.9058 0.9080 382
247
+
248
+ 2023-10-23 14:54:08,213 ----------------------------------------------------------------------------------------------------