Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
7e591bc
•
1 Parent(s): f1fc758

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +246 -0
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 15:51:57,497 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 15:51:57,498 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 15:51:57,498 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 15:51:57,498 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 15:51:57,498 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 15:51:57,499 Train: 1100 sentences
55
+ 2023-10-23 15:51:57,499 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 15:51:57,499 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 15:51:57,499 Training Params:
58
+ 2023-10-23 15:51:57,499 - learning_rate: "5e-05"
59
+ 2023-10-23 15:51:57,499 - mini_batch_size: "4"
60
+ 2023-10-23 15:51:57,499 - max_epochs: "10"
61
+ 2023-10-23 15:51:57,499 - shuffle: "True"
62
+ 2023-10-23 15:51:57,499 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 15:51:57,499 Plugins:
64
+ 2023-10-23 15:51:57,499 - TensorboardLogger
65
+ 2023-10-23 15:51:57,499 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 15:51:57,499 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 15:51:57,499 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 15:51:57,499 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 15:51:57,499 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 15:51:57,499 Computation:
71
+ 2023-10-23 15:51:57,499 - compute on device: cuda:0
72
+ 2023-10-23 15:51:57,499 - embedding storage: none
73
+ 2023-10-23 15:51:57,499 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 15:51:57,499 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-23 15:51:57,499 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 15:51:57,499 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 15:51:57,499 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 15:51:58,821 epoch 1 - iter 27/275 - loss 2.64810433 - time (sec): 1.32 - samples/sec: 1353.57 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-23 15:52:00,167 epoch 1 - iter 54/275 - loss 1.83490599 - time (sec): 2.67 - samples/sec: 1526.70 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-23 15:52:01,507 epoch 1 - iter 81/275 - loss 1.48707717 - time (sec): 4.01 - samples/sec: 1615.59 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-23 15:52:02,867 epoch 1 - iter 108/275 - loss 1.25898807 - time (sec): 5.37 - samples/sec: 1654.13 - lr: 0.000019 - momentum: 0.000000
82
+ 2023-10-23 15:52:04,220 epoch 1 - iter 135/275 - loss 1.09035369 - time (sec): 6.72 - samples/sec: 1659.42 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-23 15:52:05,547 epoch 1 - iter 162/275 - loss 0.95463488 - time (sec): 8.05 - samples/sec: 1671.29 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-23 15:52:06,938 epoch 1 - iter 189/275 - loss 0.86593875 - time (sec): 9.44 - samples/sec: 1651.35 - lr: 0.000034 - momentum: 0.000000
85
+ 2023-10-23 15:52:08,332 epoch 1 - iter 216/275 - loss 0.77581041 - time (sec): 10.83 - samples/sec: 1668.19 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-23 15:52:09,731 epoch 1 - iter 243/275 - loss 0.71487665 - time (sec): 12.23 - samples/sec: 1660.58 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-23 15:52:11,121 epoch 1 - iter 270/275 - loss 0.66787877 - time (sec): 13.62 - samples/sec: 1644.92 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-23 15:52:11,374 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 15:52:11,374 EPOCH 1 done: loss 0.6618 - lr: 0.000049
90
+ 2023-10-23 15:52:11,794 DEV : loss 0.179626926779747 - f1-score (micro avg) 0.7718
91
+ 2023-10-23 15:52:11,799 saving best model
92
+ 2023-10-23 15:52:12,196 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 15:52:13,602 epoch 2 - iter 27/275 - loss 0.19354437 - time (sec): 1.40 - samples/sec: 1809.51 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-23 15:52:14,993 epoch 2 - iter 54/275 - loss 0.20163780 - time (sec): 2.80 - samples/sec: 1639.26 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-23 15:52:16,380 epoch 2 - iter 81/275 - loss 0.17039530 - time (sec): 4.18 - samples/sec: 1591.50 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-23 15:52:17,774 epoch 2 - iter 108/275 - loss 0.17475614 - time (sec): 5.58 - samples/sec: 1543.31 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-23 15:52:19,204 epoch 2 - iter 135/275 - loss 0.16444749 - time (sec): 7.01 - samples/sec: 1539.34 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-23 15:52:20,781 epoch 2 - iter 162/275 - loss 0.16649597 - time (sec): 8.58 - samples/sec: 1501.31 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-23 15:52:22,208 epoch 2 - iter 189/275 - loss 0.15541591 - time (sec): 10.01 - samples/sec: 1510.50 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-23 15:52:23,629 epoch 2 - iter 216/275 - loss 0.15842844 - time (sec): 11.43 - samples/sec: 1527.32 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-23 15:52:25,043 epoch 2 - iter 243/275 - loss 0.15889443 - time (sec): 12.85 - samples/sec: 1538.23 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-23 15:52:26,452 epoch 2 - iter 270/275 - loss 0.15806273 - time (sec): 14.25 - samples/sec: 1566.28 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-23 15:52:26,716 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 15:52:26,717 EPOCH 2 done: loss 0.1588 - lr: 0.000045
105
+ 2023-10-23 15:52:27,252 DEV : loss 0.16758960485458374 - f1-score (micro avg) 0.8019
106
+ 2023-10-23 15:52:27,257 saving best model
107
+ 2023-10-23 15:52:27,803 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 15:52:29,170 epoch 3 - iter 27/275 - loss 0.12366499 - time (sec): 1.36 - samples/sec: 1712.37 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-23 15:52:30,511 epoch 3 - iter 54/275 - loss 0.10372222 - time (sec): 2.70 - samples/sec: 1680.75 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-23 15:52:31,880 epoch 3 - iter 81/275 - loss 0.10568938 - time (sec): 4.07 - samples/sec: 1658.05 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-23 15:52:33,251 epoch 3 - iter 108/275 - loss 0.10353497 - time (sec): 5.44 - samples/sec: 1666.27 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-23 15:52:34,612 epoch 3 - iter 135/275 - loss 0.09569370 - time (sec): 6.81 - samples/sec: 1672.37 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-23 15:52:35,955 epoch 3 - iter 162/275 - loss 0.09029367 - time (sec): 8.15 - samples/sec: 1669.38 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-23 15:52:37,322 epoch 3 - iter 189/275 - loss 0.09163925 - time (sec): 9.52 - samples/sec: 1663.19 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-23 15:52:38,707 epoch 3 - iter 216/275 - loss 0.09751995 - time (sec): 10.90 - samples/sec: 1648.00 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-23 15:52:40,073 epoch 3 - iter 243/275 - loss 0.10012864 - time (sec): 12.27 - samples/sec: 1656.28 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-23 15:52:41,385 epoch 3 - iter 270/275 - loss 0.09615579 - time (sec): 13.58 - samples/sec: 1640.19 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-23 15:52:41,630 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 15:52:41,630 EPOCH 3 done: loss 0.0982 - lr: 0.000039
120
+ 2023-10-23 15:52:42,169 DEV : loss 0.1806371957063675 - f1-score (micro avg) 0.84
121
+ 2023-10-23 15:52:42,174 saving best model
122
+ 2023-10-23 15:52:42,723 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 15:52:44,124 epoch 4 - iter 27/275 - loss 0.11872071 - time (sec): 1.40 - samples/sec: 1659.62 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-23 15:52:45,466 epoch 4 - iter 54/275 - loss 0.08762465 - time (sec): 2.74 - samples/sec: 1721.30 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-23 15:52:46,772 epoch 4 - iter 81/275 - loss 0.08315257 - time (sec): 4.04 - samples/sec: 1659.82 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-23 15:52:48,068 epoch 4 - iter 108/275 - loss 0.07259559 - time (sec): 5.34 - samples/sec: 1646.58 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-23 15:52:49,413 epoch 4 - iter 135/275 - loss 0.06971542 - time (sec): 6.69 - samples/sec: 1682.02 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-23 15:52:50,757 epoch 4 - iter 162/275 - loss 0.07403488 - time (sec): 8.03 - samples/sec: 1701.06 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-23 15:52:52,181 epoch 4 - iter 189/275 - loss 0.06823022 - time (sec): 9.45 - samples/sec: 1682.76 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-23 15:52:53,576 epoch 4 - iter 216/275 - loss 0.07045628 - time (sec): 10.85 - samples/sec: 1662.31 - lr: 0.000035 - momentum: 0.000000
131
+ 2023-10-23 15:52:54,990 epoch 4 - iter 243/275 - loss 0.06840953 - time (sec): 12.26 - samples/sec: 1624.01 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-23 15:52:56,380 epoch 4 - iter 270/275 - loss 0.06924410 - time (sec): 13.65 - samples/sec: 1638.06 - lr: 0.000034 - momentum: 0.000000
133
+ 2023-10-23 15:52:56,636 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 15:52:56,636 EPOCH 4 done: loss 0.0694 - lr: 0.000034
135
+ 2023-10-23 15:52:57,168 DEV : loss 0.14905601739883423 - f1-score (micro avg) 0.8714
136
+ 2023-10-23 15:52:57,173 saving best model
137
+ 2023-10-23 15:52:57,715 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-23 15:52:59,088 epoch 5 - iter 27/275 - loss 0.04803966 - time (sec): 1.37 - samples/sec: 1701.69 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-23 15:53:00,481 epoch 5 - iter 54/275 - loss 0.06866180 - time (sec): 2.76 - samples/sec: 1631.46 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-23 15:53:01,893 epoch 5 - iter 81/275 - loss 0.05926000 - time (sec): 4.17 - samples/sec: 1619.86 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-23 15:53:03,281 epoch 5 - iter 108/275 - loss 0.04963370 - time (sec): 5.56 - samples/sec: 1603.80 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-23 15:53:04,688 epoch 5 - iter 135/275 - loss 0.05658941 - time (sec): 6.97 - samples/sec: 1621.04 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-23 15:53:06,093 epoch 5 - iter 162/275 - loss 0.05275609 - time (sec): 8.37 - samples/sec: 1599.71 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-23 15:53:07,500 epoch 5 - iter 189/275 - loss 0.05027437 - time (sec): 9.78 - samples/sec: 1599.91 - lr: 0.000030 - momentum: 0.000000
145
+ 2023-10-23 15:53:08,924 epoch 5 - iter 216/275 - loss 0.04932611 - time (sec): 11.21 - samples/sec: 1596.52 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-23 15:53:10,325 epoch 5 - iter 243/275 - loss 0.05382881 - time (sec): 12.61 - samples/sec: 1578.66 - lr: 0.000029 - momentum: 0.000000
147
+ 2023-10-23 15:53:11,739 epoch 5 - iter 270/275 - loss 0.05098833 - time (sec): 14.02 - samples/sec: 1587.32 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-23 15:53:11,992 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-23 15:53:11,992 EPOCH 5 done: loss 0.0507 - lr: 0.000028
150
+ 2023-10-23 15:53:12,527 DEV : loss 0.1650022566318512 - f1-score (micro avg) 0.8724
151
+ 2023-10-23 15:53:12,533 saving best model
152
+ 2023-10-23 15:53:13,088 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-23 15:53:14,537 epoch 6 - iter 27/275 - loss 0.00692271 - time (sec): 1.45 - samples/sec: 1743.64 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-23 15:53:15,926 epoch 6 - iter 54/275 - loss 0.02989654 - time (sec): 2.83 - samples/sec: 1571.81 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-23 15:53:17,328 epoch 6 - iter 81/275 - loss 0.02792755 - time (sec): 4.24 - samples/sec: 1564.99 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-23 15:53:18,738 epoch 6 - iter 108/275 - loss 0.02765114 - time (sec): 5.65 - samples/sec: 1597.13 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-23 15:53:20,147 epoch 6 - iter 135/275 - loss 0.02524505 - time (sec): 7.06 - samples/sec: 1587.87 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-23 15:53:21,557 epoch 6 - iter 162/275 - loss 0.02776897 - time (sec): 8.47 - samples/sec: 1566.30 - lr: 0.000025 - momentum: 0.000000
159
+ 2023-10-23 15:53:22,900 epoch 6 - iter 189/275 - loss 0.02839678 - time (sec): 9.81 - samples/sec: 1571.02 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-23 15:53:24,269 epoch 6 - iter 216/275 - loss 0.02881164 - time (sec): 11.18 - samples/sec: 1576.51 - lr: 0.000024 - momentum: 0.000000
161
+ 2023-10-23 15:53:25,664 epoch 6 - iter 243/275 - loss 0.03172496 - time (sec): 12.57 - samples/sec: 1587.99 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-23 15:53:27,075 epoch 6 - iter 270/275 - loss 0.03269819 - time (sec): 13.98 - samples/sec: 1597.39 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-23 15:53:27,343 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-23 15:53:27,343 EPOCH 6 done: loss 0.0332 - lr: 0.000022
165
+ 2023-10-23 15:53:27,884 DEV : loss 0.165008082985878 - f1-score (micro avg) 0.8825
166
+ 2023-10-23 15:53:27,890 saving best model
167
+ 2023-10-23 15:53:28,432 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-23 15:53:29,759 epoch 7 - iter 27/275 - loss 0.03004289 - time (sec): 1.32 - samples/sec: 1768.40 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-23 15:53:31,121 epoch 7 - iter 54/275 - loss 0.02755990 - time (sec): 2.69 - samples/sec: 1634.52 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-23 15:53:32,468 epoch 7 - iter 81/275 - loss 0.02623236 - time (sec): 4.03 - samples/sec: 1606.70 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-23 15:53:33,820 epoch 7 - iter 108/275 - loss 0.02598619 - time (sec): 5.38 - samples/sec: 1648.23 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-23 15:53:35,203 epoch 7 - iter 135/275 - loss 0.02416610 - time (sec): 6.77 - samples/sec: 1642.59 - lr: 0.000020 - momentum: 0.000000
173
+ 2023-10-23 15:53:36,540 epoch 7 - iter 162/275 - loss 0.02452176 - time (sec): 8.10 - samples/sec: 1628.01 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-23 15:53:37,892 epoch 7 - iter 189/275 - loss 0.02358188 - time (sec): 9.46 - samples/sec: 1642.33 - lr: 0.000019 - momentum: 0.000000
175
+ 2023-10-23 15:53:39,212 epoch 7 - iter 216/275 - loss 0.02191696 - time (sec): 10.78 - samples/sec: 1659.22 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-23 15:53:40,556 epoch 7 - iter 243/275 - loss 0.02403767 - time (sec): 12.12 - samples/sec: 1667.16 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-23 15:53:41,896 epoch 7 - iter 270/275 - loss 0.02337190 - time (sec): 13.46 - samples/sec: 1658.48 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-23 15:53:42,151 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-23 15:53:42,152 EPOCH 7 done: loss 0.0230 - lr: 0.000017
180
+ 2023-10-23 15:53:42,689 DEV : loss 0.16212137043476105 - f1-score (micro avg) 0.8764
181
+ 2023-10-23 15:53:42,694 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-23 15:53:44,021 epoch 8 - iter 27/275 - loss 0.03973778 - time (sec): 1.33 - samples/sec: 1641.32 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-23 15:53:45,394 epoch 8 - iter 54/275 - loss 0.02648907 - time (sec): 2.70 - samples/sec: 1695.49 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-23 15:53:46,757 epoch 8 - iter 81/275 - loss 0.02530064 - time (sec): 4.06 - samples/sec: 1649.28 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-23 15:53:48,129 epoch 8 - iter 108/275 - loss 0.02187305 - time (sec): 5.43 - samples/sec: 1687.18 - lr: 0.000015 - momentum: 0.000000
186
+ 2023-10-23 15:53:49,477 epoch 8 - iter 135/275 - loss 0.01955675 - time (sec): 6.78 - samples/sec: 1696.35 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-23 15:53:50,832 epoch 8 - iter 162/275 - loss 0.01740010 - time (sec): 8.14 - samples/sec: 1717.17 - lr: 0.000014 - momentum: 0.000000
188
+ 2023-10-23 15:53:52,186 epoch 8 - iter 189/275 - loss 0.01676100 - time (sec): 9.49 - samples/sec: 1688.69 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-23 15:53:53,535 epoch 8 - iter 216/275 - loss 0.01505490 - time (sec): 10.84 - samples/sec: 1664.98 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-23 15:53:54,906 epoch 8 - iter 243/275 - loss 0.01536436 - time (sec): 12.21 - samples/sec: 1652.09 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-23 15:53:56,238 epoch 8 - iter 270/275 - loss 0.01475368 - time (sec): 13.54 - samples/sec: 1647.04 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-23 15:53:56,480 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-23 15:53:56,480 EPOCH 8 done: loss 0.0154 - lr: 0.000011
194
+ 2023-10-23 15:53:57,013 DEV : loss 0.17422381043434143 - f1-score (micro avg) 0.8873
195
+ 2023-10-23 15:53:57,019 saving best model
196
+ 2023-10-23 15:53:57,566 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-23 15:53:58,903 epoch 9 - iter 27/275 - loss 0.01095488 - time (sec): 1.34 - samples/sec: 1702.86 - lr: 0.000011 - momentum: 0.000000
198
+ 2023-10-23 15:54:00,288 epoch 9 - iter 54/275 - loss 0.00940144 - time (sec): 2.72 - samples/sec: 1683.98 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-23 15:54:01,674 epoch 9 - iter 81/275 - loss 0.01506953 - time (sec): 4.11 - samples/sec: 1654.32 - lr: 0.000010 - momentum: 0.000000
200
+ 2023-10-23 15:54:03,064 epoch 9 - iter 108/275 - loss 0.01534731 - time (sec): 5.50 - samples/sec: 1634.29 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-23 15:54:04,465 epoch 9 - iter 135/275 - loss 0.01222164 - time (sec): 6.90 - samples/sec: 1639.34 - lr: 0.000009 - momentum: 0.000000
202
+ 2023-10-23 15:54:05,835 epoch 9 - iter 162/275 - loss 0.01073052 - time (sec): 8.27 - samples/sec: 1655.88 - lr: 0.000008 - momentum: 0.000000
203
+ 2023-10-23 15:54:07,212 epoch 9 - iter 189/275 - loss 0.00980372 - time (sec): 9.64 - samples/sec: 1639.50 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-23 15:54:08,577 epoch 9 - iter 216/275 - loss 0.00910948 - time (sec): 11.01 - samples/sec: 1644.32 - lr: 0.000007 - momentum: 0.000000
205
+ 2023-10-23 15:54:09,952 epoch 9 - iter 243/275 - loss 0.00861179 - time (sec): 12.38 - samples/sec: 1636.73 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-23 15:54:11,336 epoch 9 - iter 270/275 - loss 0.00873483 - time (sec): 13.77 - samples/sec: 1632.00 - lr: 0.000006 - momentum: 0.000000
207
+ 2023-10-23 15:54:11,596 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-23 15:54:11,596 EPOCH 9 done: loss 0.0086 - lr: 0.000006
209
+ 2023-10-23 15:54:12,138 DEV : loss 0.17060527205467224 - f1-score (micro avg) 0.8862
210
+ 2023-10-23 15:54:12,144 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-23 15:54:13,506 epoch 10 - iter 27/275 - loss 0.00040091 - time (sec): 1.36 - samples/sec: 1548.35 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-23 15:54:14,844 epoch 10 - iter 54/275 - loss 0.00059839 - time (sec): 2.70 - samples/sec: 1612.29 - lr: 0.000005 - momentum: 0.000000
213
+ 2023-10-23 15:54:16,170 epoch 10 - iter 81/275 - loss 0.00106300 - time (sec): 4.02 - samples/sec: 1670.09 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-23 15:54:17,527 epoch 10 - iter 108/275 - loss 0.00081409 - time (sec): 5.38 - samples/sec: 1681.74 - lr: 0.000004 - momentum: 0.000000
215
+ 2023-10-23 15:54:18,898 epoch 10 - iter 135/275 - loss 0.00325952 - time (sec): 6.75 - samples/sec: 1647.07 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-23 15:54:20,253 epoch 10 - iter 162/275 - loss 0.00476398 - time (sec): 8.11 - samples/sec: 1619.34 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-23 15:54:21,624 epoch 10 - iter 189/275 - loss 0.00493019 - time (sec): 9.48 - samples/sec: 1611.15 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-23 15:54:22,987 epoch 10 - iter 216/275 - loss 0.00603623 - time (sec): 10.84 - samples/sec: 1626.70 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 15:54:24,336 epoch 10 - iter 243/275 - loss 0.00625175 - time (sec): 12.19 - samples/sec: 1636.88 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-23 15:54:25,709 epoch 10 - iter 270/275 - loss 0.00581465 - time (sec): 13.56 - samples/sec: 1646.57 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-23 15:54:25,960 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-23 15:54:25,960 EPOCH 10 done: loss 0.0057 - lr: 0.000000
223
+ 2023-10-23 15:54:26,504 DEV : loss 0.17152057588100433 - f1-score (micro avg) 0.8809
224
+ 2023-10-23 15:54:26,910 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-23 15:54:26,912 Loading model from best epoch ...
226
+ 2023-10-23 15:54:28,582 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
227
+ 2023-10-23 15:54:29,253
228
+ Results:
229
+ - F-score (micro) 0.8976
230
+ - F-score (macro) 0.7692
231
+ - Accuracy 0.8281
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ scope 0.8864 0.8864 0.8864 176
237
+ pers 0.9837 0.9453 0.9641 128
238
+ work 0.8077 0.8514 0.8289 74
239
+ object 0.5000 0.5000 0.5000 2
240
+ loc 1.0000 0.5000 0.6667 2
241
+
242
+ micro avg 0.9000 0.8953 0.8976 382
243
+ macro avg 0.8356 0.7366 0.7692 382
244
+ weighted avg 0.9023 0.8953 0.8981 382
245
+
246
+ 2023-10-23 15:54:29,253 ----------------------------------------------------------------------------------------------------