Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
a84b49a
·
1 Parent(s): 1990c31

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7be2d4d49e5718c98be921a90da203d73707221bcb6405fb849f0862c13c62
3
+ size 443335879
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 11:52:09 0.0000 0.6686 0.1965 0.4963 0.5708 0.5309 0.3740
3
+ 2 11:53:01 0.0000 0.1606 0.1443 0.6874 0.7357 0.7107 0.5752
4
+ 3 11:53:52 0.0000 0.0930 0.1516 0.6914 0.7725 0.7297 0.5934
5
+ 4 11:54:45 0.0000 0.0540 0.1677 0.7087 0.7819 0.7435 0.6101
6
+ 5 11:55:37 0.0000 0.0391 0.1899 0.7704 0.7897 0.7799 0.6546
7
+ 6 11:56:28 0.0000 0.0267 0.2090 0.7740 0.7952 0.7844 0.6574
8
+ 7 11:57:19 0.0000 0.0164 0.2053 0.7495 0.8069 0.7771 0.6503
9
+ 8 11:58:12 0.0000 0.0108 0.2299 0.7718 0.8014 0.7863 0.6613
10
+ 9 11:59:03 0.0000 0.0069 0.2348 0.7728 0.8030 0.7876 0.6622
11
+ 10 11:59:54 0.0000 0.0052 0.2303 0.7696 0.7967 0.7829 0.6570
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 11:51:21,482 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 11:51:21,483 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 11:51:21,483 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 11:51:21,484 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
52
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
53
+ 2023-10-13 11:51:21,484 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 11:51:21,484 Train: 3575 sentences
55
+ 2023-10-13 11:51:21,484 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 11:51:21,484 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 11:51:21,484 Training Params:
58
+ 2023-10-13 11:51:21,484 - learning_rate: "3e-05"
59
+ 2023-10-13 11:51:21,484 - mini_batch_size: "4"
60
+ 2023-10-13 11:51:21,484 - max_epochs: "10"
61
+ 2023-10-13 11:51:21,484 - shuffle: "True"
62
+ 2023-10-13 11:51:21,484 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 11:51:21,484 Plugins:
64
+ 2023-10-13 11:51:21,484 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 11:51:21,484 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 11:51:21,484 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 11:51:21,484 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 11:51:21,484 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 11:51:21,484 Computation:
70
+ 2023-10-13 11:51:21,484 - compute on device: cuda:0
71
+ 2023-10-13 11:51:21,484 - embedding storage: none
72
+ 2023-10-13 11:51:21,484 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 11:51:21,484 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 11:51:21,484 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 11:51:21,485 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 11:51:25,904 epoch 1 - iter 89/894 - loss 2.95964861 - time (sec): 4.42 - samples/sec: 2164.33 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 11:51:29,956 epoch 1 - iter 178/894 - loss 2.03271239 - time (sec): 8.47 - samples/sec: 2071.90 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 11:51:33,863 epoch 1 - iter 267/894 - loss 1.55405415 - time (sec): 12.38 - samples/sec: 2043.74 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 11:51:38,226 epoch 1 - iter 356/894 - loss 1.26339446 - time (sec): 16.74 - samples/sec: 2022.31 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 11:51:43,014 epoch 1 - iter 445/894 - loss 1.08674410 - time (sec): 21.53 - samples/sec: 1951.65 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 11:51:47,265 epoch 1 - iter 534/894 - loss 0.95226748 - time (sec): 25.78 - samples/sec: 1976.18 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 11:51:51,515 epoch 1 - iter 623/894 - loss 0.85745994 - time (sec): 30.03 - samples/sec: 1982.65 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 11:51:56,037 epoch 1 - iter 712/894 - loss 0.77246236 - time (sec): 34.55 - samples/sec: 2000.83 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 11:52:00,247 epoch 1 - iter 801/894 - loss 0.71803691 - time (sec): 38.76 - samples/sec: 1989.55 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 11:52:04,660 epoch 1 - iter 890/894 - loss 0.67103102 - time (sec): 43.17 - samples/sec: 1994.21 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 11:52:04,875 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 11:52:04,875 EPOCH 1 done: loss 0.6686 - lr: 0.000030
88
+ 2023-10-13 11:52:09,723 DEV : loss 0.19651389122009277 - f1-score (micro avg) 0.5309
89
+ 2023-10-13 11:52:09,750 saving best model
90
+ 2023-10-13 11:52:10,106 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 11:52:14,483 epoch 2 - iter 89/894 - loss 0.17874743 - time (sec): 4.38 - samples/sec: 1975.04 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 11:52:18,914 epoch 2 - iter 178/894 - loss 0.19245308 - time (sec): 8.81 - samples/sec: 1960.17 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 11:52:23,050 epoch 2 - iter 267/894 - loss 0.19114956 - time (sec): 12.94 - samples/sec: 2005.26 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 11:52:27,558 epoch 2 - iter 356/894 - loss 0.18340530 - time (sec): 17.45 - samples/sec: 1969.09 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 11:52:31,687 epoch 2 - iter 445/894 - loss 0.17962511 - time (sec): 21.58 - samples/sec: 1964.32 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 11:52:35,844 epoch 2 - iter 534/894 - loss 0.16974435 - time (sec): 25.74 - samples/sec: 1987.80 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 11:52:39,913 epoch 2 - iter 623/894 - loss 0.16649731 - time (sec): 29.81 - samples/sec: 2025.68 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 11:52:44,091 epoch 2 - iter 712/894 - loss 0.16541807 - time (sec): 33.98 - samples/sec: 2020.71 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 11:52:48,107 epoch 2 - iter 801/894 - loss 0.16505264 - time (sec): 38.00 - samples/sec: 2021.06 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 11:52:52,575 epoch 2 - iter 890/894 - loss 0.16086628 - time (sec): 42.47 - samples/sec: 2030.90 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 11:52:52,761 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 11:52:52,761 EPOCH 2 done: loss 0.1606 - lr: 0.000027
103
+ 2023-10-13 11:53:01,183 DEV : loss 0.14430980384349823 - f1-score (micro avg) 0.7107
104
+ 2023-10-13 11:53:01,211 saving best model
105
+ 2023-10-13 11:53:01,665 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 11:53:05,704 epoch 3 - iter 89/894 - loss 0.09107293 - time (sec): 4.04 - samples/sec: 1935.11 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 11:53:09,734 epoch 3 - iter 178/894 - loss 0.08954741 - time (sec): 8.07 - samples/sec: 2005.89 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 11:53:14,016 epoch 3 - iter 267/894 - loss 0.09709904 - time (sec): 12.35 - samples/sec: 1972.74 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 11:53:18,466 epoch 3 - iter 356/894 - loss 0.09035845 - time (sec): 16.80 - samples/sec: 1978.54 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 11:53:22,769 epoch 3 - iter 445/894 - loss 0.09195587 - time (sec): 21.10 - samples/sec: 2011.97 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 11:53:26,791 epoch 3 - iter 534/894 - loss 0.09116096 - time (sec): 25.12 - samples/sec: 2044.47 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 11:53:30,992 epoch 3 - iter 623/894 - loss 0.09292099 - time (sec): 29.32 - samples/sec: 2045.35 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 11:53:35,224 epoch 3 - iter 712/894 - loss 0.09454837 - time (sec): 33.56 - samples/sec: 2041.67 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 11:53:39,463 epoch 3 - iter 801/894 - loss 0.09328361 - time (sec): 37.80 - samples/sec: 2036.11 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 11:53:43,927 epoch 3 - iter 890/894 - loss 0.09323024 - time (sec): 42.26 - samples/sec: 2040.91 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 11:53:44,111 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 11:53:44,111 EPOCH 3 done: loss 0.0930 - lr: 0.000023
118
+ 2023-10-13 11:53:52,652 DEV : loss 0.15164530277252197 - f1-score (micro avg) 0.7297
119
+ 2023-10-13 11:53:52,681 saving best model
120
+ 2023-10-13 11:53:53,170 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 11:53:57,485 epoch 4 - iter 89/894 - loss 0.06575092 - time (sec): 4.31 - samples/sec: 2092.37 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 11:54:01,695 epoch 4 - iter 178/894 - loss 0.05914120 - time (sec): 8.52 - samples/sec: 2014.16 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 11:54:06,062 epoch 4 - iter 267/894 - loss 0.05800368 - time (sec): 12.89 - samples/sec: 2038.84 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 11:54:10,598 epoch 4 - iter 356/894 - loss 0.05785617 - time (sec): 17.42 - samples/sec: 2074.47 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 11:54:14,848 epoch 4 - iter 445/894 - loss 0.05338580 - time (sec): 21.67 - samples/sec: 2068.37 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 11:54:19,056 epoch 4 - iter 534/894 - loss 0.05470941 - time (sec): 25.88 - samples/sec: 2069.24 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 11:54:23,203 epoch 4 - iter 623/894 - loss 0.05504567 - time (sec): 30.03 - samples/sec: 2059.01 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 11:54:27,507 epoch 4 - iter 712/894 - loss 0.05336567 - time (sec): 34.33 - samples/sec: 2046.02 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 11:54:31,882 epoch 4 - iter 801/894 - loss 0.05371459 - time (sec): 38.71 - samples/sec: 2005.64 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 11:54:36,420 epoch 4 - iter 890/894 - loss 0.05405224 - time (sec): 43.24 - samples/sec: 1993.65 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 11:54:36,623 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 11:54:36,623 EPOCH 4 done: loss 0.0540 - lr: 0.000020
133
+ 2023-10-13 11:54:45,586 DEV : loss 0.16767126321792603 - f1-score (micro avg) 0.7435
134
+ 2023-10-13 11:54:45,629 saving best model
135
+ 2023-10-13 11:54:46,202 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 11:54:51,104 epoch 5 - iter 89/894 - loss 0.03833014 - time (sec): 4.90 - samples/sec: 1983.32 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 11:54:55,089 epoch 5 - iter 178/894 - loss 0.04134649 - time (sec): 8.89 - samples/sec: 1998.30 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 11:54:59,154 epoch 5 - iter 267/894 - loss 0.04407342 - time (sec): 12.95 - samples/sec: 2053.09 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 11:55:03,033 epoch 5 - iter 356/894 - loss 0.04265799 - time (sec): 16.83 - samples/sec: 2061.37 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 11:55:07,321 epoch 5 - iter 445/894 - loss 0.03938600 - time (sec): 21.12 - samples/sec: 2070.49 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 11:55:11,359 epoch 5 - iter 534/894 - loss 0.03873257 - time (sec): 25.16 - samples/sec: 2086.45 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 11:55:15,767 epoch 5 - iter 623/894 - loss 0.03834078 - time (sec): 29.56 - samples/sec: 2053.11 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 11:55:20,229 epoch 5 - iter 712/894 - loss 0.03793415 - time (sec): 34.03 - samples/sec: 2041.73 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 11:55:24,623 epoch 5 - iter 801/894 - loss 0.03750295 - time (sec): 38.42 - samples/sec: 2023.69 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 11:55:28,852 epoch 5 - iter 890/894 - loss 0.03928703 - time (sec): 42.65 - samples/sec: 2021.24 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 11:55:29,052 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 11:55:29,053 EPOCH 5 done: loss 0.0391 - lr: 0.000017
148
+ 2023-10-13 11:55:37,512 DEV : loss 0.18989010155200958 - f1-score (micro avg) 0.7799
149
+ 2023-10-13 11:55:37,539 saving best model
150
+ 2023-10-13 11:55:38,022 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 11:55:42,488 epoch 6 - iter 89/894 - loss 0.01887461 - time (sec): 4.46 - samples/sec: 1941.41 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 11:55:46,559 epoch 6 - iter 178/894 - loss 0.02591767 - time (sec): 8.54 - samples/sec: 1919.28 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 11:55:51,042 epoch 6 - iter 267/894 - loss 0.02075761 - time (sec): 13.02 - samples/sec: 1962.56 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-13 11:55:55,321 epoch 6 - iter 356/894 - loss 0.01989266 - time (sec): 17.30 - samples/sec: 1991.06 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 11:55:59,294 epoch 6 - iter 445/894 - loss 0.01956611 - time (sec): 21.27 - samples/sec: 1975.13 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 11:56:03,300 epoch 6 - iter 534/894 - loss 0.02114777 - time (sec): 25.28 - samples/sec: 1989.27 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-13 11:56:07,317 epoch 6 - iter 623/894 - loss 0.02490253 - time (sec): 29.29 - samples/sec: 1985.00 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 11:56:11,703 epoch 6 - iter 712/894 - loss 0.02394661 - time (sec): 33.68 - samples/sec: 2029.61 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 11:56:15,930 epoch 6 - iter 801/894 - loss 0.02522246 - time (sec): 37.91 - samples/sec: 2028.41 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-13 11:56:20,141 epoch 6 - iter 890/894 - loss 0.02648157 - time (sec): 42.12 - samples/sec: 2044.57 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-13 11:56:20,322 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 11:56:20,322 EPOCH 6 done: loss 0.0267 - lr: 0.000013
163
+ 2023-10-13 11:56:28,672 DEV : loss 0.20904241502285004 - f1-score (micro avg) 0.7844
164
+ 2023-10-13 11:56:28,699 saving best model
165
+ 2023-10-13 11:56:29,218 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-13 11:56:33,169 epoch 7 - iter 89/894 - loss 0.01644043 - time (sec): 3.95 - samples/sec: 2225.26 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 11:56:37,137 epoch 7 - iter 178/894 - loss 0.01652289 - time (sec): 7.92 - samples/sec: 2160.68 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-13 11:56:41,572 epoch 7 - iter 267/894 - loss 0.01444836 - time (sec): 12.35 - samples/sec: 2206.43 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 11:56:45,757 epoch 7 - iter 356/894 - loss 0.01344021 - time (sec): 16.54 - samples/sec: 2154.40 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 11:56:50,038 epoch 7 - iter 445/894 - loss 0.01503458 - time (sec): 20.82 - samples/sec: 2132.69 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-13 11:56:54,094 epoch 7 - iter 534/894 - loss 0.01470901 - time (sec): 24.87 - samples/sec: 2114.67 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 11:56:58,166 epoch 7 - iter 623/894 - loss 0.01436044 - time (sec): 28.95 - samples/sec: 2105.78 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 11:57:02,335 epoch 7 - iter 712/894 - loss 0.01450503 - time (sec): 33.12 - samples/sec: 2089.24 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-13 11:57:06,532 epoch 7 - iter 801/894 - loss 0.01496761 - time (sec): 37.31 - samples/sec: 2065.77 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 11:57:11,096 epoch 7 - iter 890/894 - loss 0.01642279 - time (sec): 41.88 - samples/sec: 2060.17 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-13 11:57:11,276 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-13 11:57:11,276 EPOCH 7 done: loss 0.0164 - lr: 0.000010
178
+ 2023-10-13 11:57:19,774 DEV : loss 0.20529742538928986 - f1-score (micro avg) 0.7771
179
+ 2023-10-13 11:57:19,803 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 11:57:24,304 epoch 8 - iter 89/894 - loss 0.00943737 - time (sec): 4.50 - samples/sec: 1926.13 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-13 11:57:28,703 epoch 8 - iter 178/894 - loss 0.00873977 - time (sec): 8.90 - samples/sec: 1997.92 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 11:57:32,928 epoch 8 - iter 267/894 - loss 0.00852614 - time (sec): 13.12 - samples/sec: 2048.20 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 11:57:37,165 epoch 8 - iter 356/894 - loss 0.00785977 - time (sec): 17.36 - samples/sec: 2099.61 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-13 11:57:41,318 epoch 8 - iter 445/894 - loss 0.01056320 - time (sec): 21.51 - samples/sec: 2052.03 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 11:57:45,668 epoch 8 - iter 534/894 - loss 0.01160587 - time (sec): 25.86 - samples/sec: 2034.90 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 11:57:49,941 epoch 8 - iter 623/894 - loss 0.01157603 - time (sec): 30.14 - samples/sec: 2046.21 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-13 11:57:54,347 epoch 8 - iter 712/894 - loss 0.01161656 - time (sec): 34.54 - samples/sec: 2024.50 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 11:57:58,702 epoch 8 - iter 801/894 - loss 0.01109661 - time (sec): 38.90 - samples/sec: 2007.73 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 11:58:03,248 epoch 8 - iter 890/894 - loss 0.01081817 - time (sec): 43.44 - samples/sec: 1983.66 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-13 11:58:03,431 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 11:58:03,431 EPOCH 8 done: loss 0.0108 - lr: 0.000007
192
+ 2023-10-13 11:58:11,986 DEV : loss 0.22993013262748718 - f1-score (micro avg) 0.7863
193
+ 2023-10-13 11:58:12,017 saving best model
194
+ 2023-10-13 11:58:12,506 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-13 11:58:16,908 epoch 9 - iter 89/894 - loss 0.01082872 - time (sec): 4.40 - samples/sec: 1878.92 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 11:58:21,317 epoch 9 - iter 178/894 - loss 0.00801392 - time (sec): 8.81 - samples/sec: 1995.09 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 11:58:25,532 epoch 9 - iter 267/894 - loss 0.00706807 - time (sec): 13.02 - samples/sec: 1987.89 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-13 11:58:29,789 epoch 9 - iter 356/894 - loss 0.00604321 - time (sec): 17.28 - samples/sec: 2045.69 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 11:58:34,164 epoch 9 - iter 445/894 - loss 0.00629406 - time (sec): 21.66 - samples/sec: 2040.71 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 11:58:38,525 epoch 9 - iter 534/894 - loss 0.00647986 - time (sec): 26.02 - samples/sec: 2054.88 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-13 11:58:42,646 epoch 9 - iter 623/894 - loss 0.00640126 - time (sec): 30.14 - samples/sec: 2057.71 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 11:58:46,740 epoch 9 - iter 712/894 - loss 0.00619220 - time (sec): 34.23 - samples/sec: 2045.28 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 11:58:50,747 epoch 9 - iter 801/894 - loss 0.00657126 - time (sec): 38.24 - samples/sec: 2044.79 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-13 11:58:54,968 epoch 9 - iter 890/894 - loss 0.00688760 - time (sec): 42.46 - samples/sec: 2028.36 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-13 11:58:55,162 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 11:58:55,162 EPOCH 9 done: loss 0.0069 - lr: 0.000003
207
+ 2023-10-13 11:59:03,625 DEV : loss 0.23477818071842194 - f1-score (micro avg) 0.7876
208
+ 2023-10-13 11:59:03,654 saving best model
209
+ 2023-10-13 11:59:04,113 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-13 11:59:08,444 epoch 10 - iter 89/894 - loss 0.01073514 - time (sec): 4.33 - samples/sec: 2029.84 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 11:59:12,635 epoch 10 - iter 178/894 - loss 0.00686412 - time (sec): 8.52 - samples/sec: 1962.81 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-13 11:59:16,883 epoch 10 - iter 267/894 - loss 0.00526322 - time (sec): 12.77 - samples/sec: 1980.29 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 11:59:20,948 epoch 10 - iter 356/894 - loss 0.00548186 - time (sec): 16.83 - samples/sec: 2024.96 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 11:59:25,163 epoch 10 - iter 445/894 - loss 0.00532709 - time (sec): 21.05 - samples/sec: 2055.07 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-13 11:59:29,369 epoch 10 - iter 534/894 - loss 0.00531083 - time (sec): 25.25 - samples/sec: 2067.81 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 11:59:33,663 epoch 10 - iter 623/894 - loss 0.00505531 - time (sec): 29.55 - samples/sec: 2062.69 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 11:59:37,654 epoch 10 - iter 712/894 - loss 0.00524732 - time (sec): 33.54 - samples/sec: 2063.87 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 11:59:41,725 epoch 10 - iter 801/894 - loss 0.00519244 - time (sec): 37.61 - samples/sec: 2050.62 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 11:59:45,901 epoch 10 - iter 890/894 - loss 0.00521658 - time (sec): 41.79 - samples/sec: 2062.61 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-13 11:59:46,077 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-13 11:59:46,077 EPOCH 10 done: loss 0.0052 - lr: 0.000000
222
+ 2023-10-13 11:59:54,618 DEV : loss 0.2303038239479065 - f1-score (micro avg) 0.7829
223
+ 2023-10-13 11:59:55,005 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-13 11:59:55,006 Loading model from best epoch ...
225
+ 2023-10-13 11:59:56,539 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
226
+ 2023-10-13 12:00:00,808
227
+ Results:
228
+ - F-score (micro) 0.7548
229
+ - F-score (macro) 0.6753
230
+ - Accuracy 0.6264
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.8098 0.8574 0.8329 596
236
+ pers 0.6917 0.7748 0.7309 333
237
+ org 0.5826 0.5076 0.5425 132
238
+ prod 0.6444 0.4394 0.5225 66
239
+ time 0.7400 0.7551 0.7475 49
240
+
241
+ micro avg 0.7430 0.7670 0.7548 1176
242
+ macro avg 0.6937 0.6668 0.6753 1176
243
+ weighted avg 0.7387 0.7670 0.7505 1176
244
+
245
+ 2023-10-13 12:00:00,808 ----------------------------------------------------------------------------------------------------