Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs4-wsFalse-e10-lr5e-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
7b62e6a
·
1 Parent(s): 1daa4f2

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 14:54:38,464 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 14:54:38,465 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 14:54:38,465 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 14:54:38,465 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 14:54:38,465 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 14:54:38,465 Train: 1100 sentences
55
+ 2023-10-23 14:54:38,465 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 14:54:38,466 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 14:54:38,466 Training Params:
58
+ 2023-10-23 14:54:38,466 - learning_rate: "5e-05"
59
+ 2023-10-23 14:54:38,466 - mini_batch_size: "4"
60
+ 2023-10-23 14:54:38,466 - max_epochs: "10"
61
+ 2023-10-23 14:54:38,466 - shuffle: "True"
62
+ 2023-10-23 14:54:38,466 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 14:54:38,466 Plugins:
64
+ 2023-10-23 14:54:38,466 - TensorboardLogger
65
+ 2023-10-23 14:54:38,466 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 14:54:38,466 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 14:54:38,466 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 14:54:38,466 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 14:54:38,466 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 14:54:38,466 Computation:
71
+ 2023-10-23 14:54:38,466 - compute on device: cuda:0
72
+ 2023-10-23 14:54:38,466 - embedding storage: none
73
+ 2023-10-23 14:54:38,466 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 14:54:38,466 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-23 14:54:38,466 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 14:54:38,466 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 14:54:38,467 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 14:54:39,837 epoch 1 - iter 27/275 - loss 3.54901463 - time (sec): 1.37 - samples/sec: 1647.62 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-23 14:54:41,219 epoch 1 - iter 54/275 - loss 2.55169799 - time (sec): 2.75 - samples/sec: 1591.03 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-23 14:54:42,504 epoch 1 - iter 81/275 - loss 2.01311931 - time (sec): 4.04 - samples/sec: 1582.75 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-23 14:54:43,970 epoch 1 - iter 108/275 - loss 1.62540194 - time (sec): 5.50 - samples/sec: 1563.34 - lr: 0.000019 - momentum: 0.000000
82
+ 2023-10-23 14:54:45,261 epoch 1 - iter 135/275 - loss 1.40163223 - time (sec): 6.79 - samples/sec: 1604.46 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-23 14:54:46,555 epoch 1 - iter 162/275 - loss 1.22138066 - time (sec): 8.09 - samples/sec: 1609.68 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-23 14:54:47,956 epoch 1 - iter 189/275 - loss 1.08294085 - time (sec): 9.49 - samples/sec: 1609.54 - lr: 0.000034 - momentum: 0.000000
85
+ 2023-10-23 14:54:49,258 epoch 1 - iter 216/275 - loss 0.96861500 - time (sec): 10.79 - samples/sec: 1631.63 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-23 14:54:50,620 epoch 1 - iter 243/275 - loss 0.87158657 - time (sec): 12.15 - samples/sec: 1664.06 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-23 14:54:52,096 epoch 1 - iter 270/275 - loss 0.81214683 - time (sec): 13.63 - samples/sec: 1636.76 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-23 14:54:52,336 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 14:54:52,336 EPOCH 1 done: loss 0.8035 - lr: 0.000049
90
+ 2023-10-23 14:54:52,952 DEV : loss 0.17498381435871124 - f1-score (micro avg) 0.7917
91
+ 2023-10-23 14:54:52,958 saving best model
92
+ 2023-10-23 14:54:53,409 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 14:54:54,795 epoch 2 - iter 27/275 - loss 0.15914900 - time (sec): 1.39 - samples/sec: 1494.17 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-23 14:54:56,170 epoch 2 - iter 54/275 - loss 0.13023111 - time (sec): 2.76 - samples/sec: 1581.78 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-23 14:54:57,517 epoch 2 - iter 81/275 - loss 0.15940045 - time (sec): 4.11 - samples/sec: 1598.95 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-23 14:54:58,981 epoch 2 - iter 108/275 - loss 0.16714004 - time (sec): 5.57 - samples/sec: 1584.55 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-23 14:55:00,369 epoch 2 - iter 135/275 - loss 0.15991853 - time (sec): 6.96 - samples/sec: 1599.96 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-23 14:55:01,773 epoch 2 - iter 162/275 - loss 0.15772377 - time (sec): 8.36 - samples/sec: 1593.78 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-23 14:55:03,211 epoch 2 - iter 189/275 - loss 0.16052498 - time (sec): 9.80 - samples/sec: 1602.46 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-23 14:55:04,624 epoch 2 - iter 216/275 - loss 0.16324730 - time (sec): 11.21 - samples/sec: 1582.91 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-23 14:55:06,037 epoch 2 - iter 243/275 - loss 0.16144814 - time (sec): 12.63 - samples/sec: 1596.21 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-23 14:55:07,527 epoch 2 - iter 270/275 - loss 0.16078769 - time (sec): 14.12 - samples/sec: 1589.39 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-23 14:55:07,781 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 14:55:07,781 EPOCH 2 done: loss 0.1597 - lr: 0.000045
105
+ 2023-10-23 14:55:08,318 DEV : loss 0.15628834068775177 - f1-score (micro avg) 0.8055
106
+ 2023-10-23 14:55:08,324 saving best model
107
+ 2023-10-23 14:55:08,881 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 14:55:10,337 epoch 3 - iter 27/275 - loss 0.08812881 - time (sec): 1.45 - samples/sec: 1462.99 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-23 14:55:11,748 epoch 3 - iter 54/275 - loss 0.08847784 - time (sec): 2.87 - samples/sec: 1558.40 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-23 14:55:13,182 epoch 3 - iter 81/275 - loss 0.07313031 - time (sec): 4.30 - samples/sec: 1628.38 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-23 14:55:14,611 epoch 3 - iter 108/275 - loss 0.08347202 - time (sec): 5.73 - samples/sec: 1564.03 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-23 14:55:16,008 epoch 3 - iter 135/275 - loss 0.08779793 - time (sec): 7.13 - samples/sec: 1591.13 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-23 14:55:17,439 epoch 3 - iter 162/275 - loss 0.08875300 - time (sec): 8.56 - samples/sec: 1563.87 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-23 14:55:18,819 epoch 3 - iter 189/275 - loss 0.09459545 - time (sec): 9.94 - samples/sec: 1562.57 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-23 14:55:20,209 epoch 3 - iter 216/275 - loss 0.10171802 - time (sec): 11.33 - samples/sec: 1562.40 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-23 14:55:21,698 epoch 3 - iter 243/275 - loss 0.10409310 - time (sec): 12.82 - samples/sec: 1563.61 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-23 14:55:23,096 epoch 3 - iter 270/275 - loss 0.10457900 - time (sec): 14.21 - samples/sec: 1573.03 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-23 14:55:23,356 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 14:55:23,356 EPOCH 3 done: loss 0.1044 - lr: 0.000039
120
+ 2023-10-23 14:55:23,893 DEV : loss 0.1477883756160736 - f1-score (micro avg) 0.8385
121
+ 2023-10-23 14:55:23,898 saving best model
122
+ 2023-10-23 14:55:24,466 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 14:55:25,863 epoch 4 - iter 27/275 - loss 0.07640797 - time (sec): 1.40 - samples/sec: 1557.01 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-23 14:55:27,240 epoch 4 - iter 54/275 - loss 0.06608480 - time (sec): 2.77 - samples/sec: 1656.63 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-23 14:55:28,689 epoch 4 - iter 81/275 - loss 0.06231996 - time (sec): 4.22 - samples/sec: 1595.91 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-23 14:55:30,049 epoch 4 - iter 108/275 - loss 0.07864302 - time (sec): 5.58 - samples/sec: 1599.71 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-23 14:55:31,448 epoch 4 - iter 135/275 - loss 0.07419910 - time (sec): 6.98 - samples/sec: 1592.78 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-23 14:55:32,834 epoch 4 - iter 162/275 - loss 0.07282452 - time (sec): 8.37 - samples/sec: 1558.75 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-23 14:55:34,248 epoch 4 - iter 189/275 - loss 0.07174299 - time (sec): 9.78 - samples/sec: 1568.95 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-23 14:55:35,662 epoch 4 - iter 216/275 - loss 0.07442378 - time (sec): 11.19 - samples/sec: 1590.50 - lr: 0.000035 - momentum: 0.000000
131
+ 2023-10-23 14:55:37,144 epoch 4 - iter 243/275 - loss 0.07271638 - time (sec): 12.68 - samples/sec: 1577.78 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-23 14:55:38,532 epoch 4 - iter 270/275 - loss 0.07319171 - time (sec): 14.07 - samples/sec: 1591.59 - lr: 0.000034 - momentum: 0.000000
133
+ 2023-10-23 14:55:38,789 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 14:55:38,789 EPOCH 4 done: loss 0.0731 - lr: 0.000034
135
+ 2023-10-23 14:55:39,329 DEV : loss 0.18502165377140045 - f1-score (micro avg) 0.8409
136
+ 2023-10-23 14:55:39,335 saving best model
137
+ 2023-10-23 14:55:39,964 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-23 14:55:41,255 epoch 5 - iter 27/275 - loss 0.04166896 - time (sec): 1.29 - samples/sec: 1603.97 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-23 14:55:42,629 epoch 5 - iter 54/275 - loss 0.04983816 - time (sec): 2.66 - samples/sec: 1621.26 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-23 14:55:44,100 epoch 5 - iter 81/275 - loss 0.04501342 - time (sec): 4.13 - samples/sec: 1590.75 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-23 14:55:45,476 epoch 5 - iter 108/275 - loss 0.05586914 - time (sec): 5.51 - samples/sec: 1584.23 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-23 14:55:46,863 epoch 5 - iter 135/275 - loss 0.05421157 - time (sec): 6.90 - samples/sec: 1576.24 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-23 14:55:48,286 epoch 5 - iter 162/275 - loss 0.05070705 - time (sec): 8.32 - samples/sec: 1581.07 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-23 14:55:49,663 epoch 5 - iter 189/275 - loss 0.05163137 - time (sec): 9.70 - samples/sec: 1593.84 - lr: 0.000030 - momentum: 0.000000
145
+ 2023-10-23 14:55:51,038 epoch 5 - iter 216/275 - loss 0.05338643 - time (sec): 11.07 - samples/sec: 1603.31 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-23 14:55:52,524 epoch 5 - iter 243/275 - loss 0.05383510 - time (sec): 12.56 - samples/sec: 1596.30 - lr: 0.000029 - momentum: 0.000000
147
+ 2023-10-23 14:55:53,896 epoch 5 - iter 270/275 - loss 0.05235085 - time (sec): 13.93 - samples/sec: 1604.80 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-23 14:55:54,149 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-23 14:55:54,149 EPOCH 5 done: loss 0.0521 - lr: 0.000028
150
+ 2023-10-23 14:55:54,731 DEV : loss 0.16544707119464874 - f1-score (micro avg) 0.8726
151
+ 2023-10-23 14:55:54,739 saving best model
152
+ 2023-10-23 14:55:55,327 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-23 14:55:56,728 epoch 6 - iter 27/275 - loss 0.04967590 - time (sec): 1.40 - samples/sec: 1665.24 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-23 14:55:58,208 epoch 6 - iter 54/275 - loss 0.03094678 - time (sec): 2.88 - samples/sec: 1556.17 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-23 14:55:59,588 epoch 6 - iter 81/275 - loss 0.02896501 - time (sec): 4.26 - samples/sec: 1599.82 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-23 14:56:00,989 epoch 6 - iter 108/275 - loss 0.03526391 - time (sec): 5.66 - samples/sec: 1618.86 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-23 14:56:02,437 epoch 6 - iter 135/275 - loss 0.03239069 - time (sec): 7.11 - samples/sec: 1593.70 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-23 14:56:03,825 epoch 6 - iter 162/275 - loss 0.03578939 - time (sec): 8.50 - samples/sec: 1591.40 - lr: 0.000025 - momentum: 0.000000
159
+ 2023-10-23 14:56:05,204 epoch 6 - iter 189/275 - loss 0.03462987 - time (sec): 9.88 - samples/sec: 1599.41 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-23 14:56:06,700 epoch 6 - iter 216/275 - loss 0.03742467 - time (sec): 11.37 - samples/sec: 1580.38 - lr: 0.000024 - momentum: 0.000000
161
+ 2023-10-23 14:56:08,100 epoch 6 - iter 243/275 - loss 0.03717473 - time (sec): 12.77 - samples/sec: 1586.59 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-23 14:56:09,436 epoch 6 - iter 270/275 - loss 0.03776266 - time (sec): 14.11 - samples/sec: 1583.86 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-23 14:56:09,725 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-23 14:56:09,725 EPOCH 6 done: loss 0.0373 - lr: 0.000022
165
+ 2023-10-23 14:56:10,269 DEV : loss 0.1738327592611313 - f1-score (micro avg) 0.8707
166
+ 2023-10-23 14:56:10,275 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-23 14:56:11,673 epoch 7 - iter 27/275 - loss 0.00127920 - time (sec): 1.40 - samples/sec: 1457.02 - lr: 0.000022 - momentum: 0.000000
168
+ 2023-10-23 14:56:13,113 epoch 7 - iter 54/275 - loss 0.01080133 - time (sec): 2.84 - samples/sec: 1538.36 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-23 14:56:14,506 epoch 7 - iter 81/275 - loss 0.02139160 - time (sec): 4.23 - samples/sec: 1554.33 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-23 14:56:15,892 epoch 7 - iter 108/275 - loss 0.02729322 - time (sec): 5.62 - samples/sec: 1598.36 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-23 14:56:17,325 epoch 7 - iter 135/275 - loss 0.02406231 - time (sec): 7.05 - samples/sec: 1599.99 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-23 14:56:18,715 epoch 7 - iter 162/275 - loss 0.02542767 - time (sec): 8.44 - samples/sec: 1622.61 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-23 14:56:20,103 epoch 7 - iter 189/275 - loss 0.02433666 - time (sec): 9.83 - samples/sec: 1615.23 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-23 14:56:21,551 epoch 7 - iter 216/275 - loss 0.02464916 - time (sec): 11.27 - samples/sec: 1599.25 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-23 14:56:22,942 epoch 7 - iter 243/275 - loss 0.02430269 - time (sec): 12.67 - samples/sec: 1590.03 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-23 14:56:24,351 epoch 7 - iter 270/275 - loss 0.02611469 - time (sec): 14.07 - samples/sec: 1588.72 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-23 14:56:24,643 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-23 14:56:24,643 EPOCH 7 done: loss 0.0260 - lr: 0.000017
179
+ 2023-10-23 14:56:25,201 DEV : loss 0.186258465051651 - f1-score (micro avg) 0.8609
180
+ 2023-10-23 14:56:25,207 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-23 14:56:26,590 epoch 8 - iter 27/275 - loss 0.03896849 - time (sec): 1.38 - samples/sec: 1614.17 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-23 14:56:28,046 epoch 8 - iter 54/275 - loss 0.04307024 - time (sec): 2.84 - samples/sec: 1606.22 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-23 14:56:29,443 epoch 8 - iter 81/275 - loss 0.03600209 - time (sec): 4.23 - samples/sec: 1554.50 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-23 14:56:30,834 epoch 8 - iter 108/275 - loss 0.03150252 - time (sec): 5.63 - samples/sec: 1624.76 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-23 14:56:32,225 epoch 8 - iter 135/275 - loss 0.02668930 - time (sec): 7.02 - samples/sec: 1621.35 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-23 14:56:33,612 epoch 8 - iter 162/275 - loss 0.02269288 - time (sec): 8.40 - samples/sec: 1626.96 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-23 14:56:34,995 epoch 8 - iter 189/275 - loss 0.01988105 - time (sec): 9.79 - samples/sec: 1612.35 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-23 14:56:36,418 epoch 8 - iter 216/275 - loss 0.01799722 - time (sec): 11.21 - samples/sec: 1613.99 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-23 14:56:37,802 epoch 8 - iter 243/275 - loss 0.01760660 - time (sec): 12.59 - samples/sec: 1604.66 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-23 14:56:39,179 epoch 8 - iter 270/275 - loss 0.01828583 - time (sec): 13.97 - samples/sec: 1595.99 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-23 14:56:39,435 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-23 14:56:39,435 EPOCH 8 done: loss 0.0179 - lr: 0.000011
193
+ 2023-10-23 14:56:39,994 DEV : loss 0.17826218903064728 - f1-score (micro avg) 0.8789
194
+ 2023-10-23 14:56:40,000 saving best model
195
+ 2023-10-23 14:56:40,622 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-23 14:56:42,015 epoch 9 - iter 27/275 - loss 0.01410229 - time (sec): 1.39 - samples/sec: 1492.28 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-23 14:56:43,499 epoch 9 - iter 54/275 - loss 0.00910369 - time (sec): 2.87 - samples/sec: 1552.93 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-23 14:56:44,879 epoch 9 - iter 81/275 - loss 0.01001360 - time (sec): 4.25 - samples/sec: 1563.30 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-23 14:56:46,267 epoch 9 - iter 108/275 - loss 0.00999808 - time (sec): 5.64 - samples/sec: 1578.20 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-23 14:56:47,712 epoch 9 - iter 135/275 - loss 0.00920188 - time (sec): 7.09 - samples/sec: 1591.26 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-23 14:56:49,101 epoch 9 - iter 162/275 - loss 0.01224581 - time (sec): 8.47 - samples/sec: 1623.15 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-23 14:56:50,495 epoch 9 - iter 189/275 - loss 0.01508912 - time (sec): 9.87 - samples/sec: 1605.92 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-23 14:56:51,957 epoch 9 - iter 216/275 - loss 0.01347674 - time (sec): 11.33 - samples/sec: 1569.29 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-23 14:56:53,359 epoch 9 - iter 243/275 - loss 0.01230472 - time (sec): 12.73 - samples/sec: 1570.16 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-23 14:56:54,777 epoch 9 - iter 270/275 - loss 0.01152654 - time (sec): 14.15 - samples/sec: 1590.37 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-23 14:56:55,037 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-23 14:56:55,037 EPOCH 9 done: loss 0.0114 - lr: 0.000006
208
+ 2023-10-23 14:56:55,576 DEV : loss 0.17446668446063995 - f1-score (micro avg) 0.8744
209
+ 2023-10-23 14:56:55,582 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-23 14:56:56,976 epoch 10 - iter 27/275 - loss 0.00128395 - time (sec): 1.39 - samples/sec: 1551.22 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-23 14:56:58,404 epoch 10 - iter 54/275 - loss 0.00241595 - time (sec): 2.82 - samples/sec: 1563.69 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-23 14:56:59,785 epoch 10 - iter 81/275 - loss 0.00254273 - time (sec): 4.20 - samples/sec: 1597.44 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-23 14:57:01,167 epoch 10 - iter 108/275 - loss 0.00198485 - time (sec): 5.58 - samples/sec: 1563.16 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-23 14:57:02,544 epoch 10 - iter 135/275 - loss 0.00295137 - time (sec): 6.96 - samples/sec: 1551.79 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-23 14:57:03,939 epoch 10 - iter 162/275 - loss 0.00249428 - time (sec): 8.36 - samples/sec: 1593.55 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-23 14:57:05,320 epoch 10 - iter 189/275 - loss 0.00404438 - time (sec): 9.74 - samples/sec: 1590.81 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-23 14:57:06,774 epoch 10 - iter 216/275 - loss 0.00360873 - time (sec): 11.19 - samples/sec: 1586.80 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 14:57:08,175 epoch 10 - iter 243/275 - loss 0.00703358 - time (sec): 12.59 - samples/sec: 1608.97 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 14:57:09,568 epoch 10 - iter 270/275 - loss 0.00695034 - time (sec): 13.99 - samples/sec: 1603.92 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-23 14:57:09,828 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-23 14:57:09,828 EPOCH 10 done: loss 0.0077 - lr: 0.000000
222
+ 2023-10-23 14:57:10,533 DEV : loss 0.1813785582780838 - f1-score (micro avg) 0.8744
223
+ 2023-10-23 14:57:10,988 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-23 14:57:10,989 Loading model from best epoch ...
225
+ 2023-10-23 14:57:12,892 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
226
+ 2023-10-23 14:57:13,441
227
+ Results:
228
+ - F-score (micro) 0.9137
229
+ - F-score (macro) 0.7465
230
+ - Accuracy 0.8494
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ scope 0.9123 0.8864 0.8991 176
236
+ pers 0.9839 0.9531 0.9683 128
237
+ work 0.8649 0.8649 0.8649 74
238
+ object 1.0000 1.0000 1.0000 2
239
+ loc 0.0000 0.0000 0.0000 2
240
+
241
+ micro avg 0.9272 0.9005 0.9137 382
242
+ macro avg 0.7522 0.7409 0.7465 382
243
+ weighted avg 0.9228 0.9005 0.9115 382
244
+
245
+ 2023-10-23 14:57:13,441 ----------------------------------------------------------------------------------------------------