Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
d5ab866
•
1 Parent(s): db00bea

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 +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afda2f07c95ea03ec4abbfcef87c7511593f6f326209751c95ab174578e17f36
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 13:59:54 0.0000 0.6530 0.2207 0.3816 0.5356 0.4457 0.2953
3
+ 2 14:00:46 0.0000 0.1598 0.1421 0.7456 0.6919 0.7178 0.5739
4
+ 3 14:01:37 0.0000 0.0896 0.1751 0.7222 0.7154 0.7188 0.5729
5
+ 4 14:02:29 0.0000 0.0550 0.1759 0.7708 0.7756 0.7732 0.6467
6
+ 5 14:03:21 0.0000 0.0422 0.2164 0.7693 0.7482 0.7586 0.6300
7
+ 6 14:04:11 0.0000 0.0253 0.2231 0.7520 0.7991 0.7748 0.6489
8
+ 7 14:05:02 0.0000 0.0190 0.2205 0.7858 0.7889 0.7874 0.6621
9
+ 8 14:05:54 0.0000 0.0110 0.2309 0.7596 0.8053 0.7818 0.6552
10
+ 9 14:06:43 0.0000 0.0078 0.2273 0.7840 0.7975 0.7907 0.6675
11
+ 10 14:07:35 0.0000 0.0042 0.2397 0.7852 0.7889 0.7871 0.6621
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 13:59:05,671 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 13:59:05,672 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 13:59:05,673 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 13:59:05,673 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 13:59:05,673 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 13:59:05,673 Train: 3575 sentences
55
+ 2023-10-13 13:59:05,673 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 13:59:05,673 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 13:59:05,673 Training Params:
58
+ 2023-10-13 13:59:05,673 - learning_rate: "3e-05"
59
+ 2023-10-13 13:59:05,673 - mini_batch_size: "4"
60
+ 2023-10-13 13:59:05,673 - max_epochs: "10"
61
+ 2023-10-13 13:59:05,673 - shuffle: "True"
62
+ 2023-10-13 13:59:05,673 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 13:59:05,673 Plugins:
64
+ 2023-10-13 13:59:05,673 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 13:59:05,673 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 13:59:05,673 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 13:59:05,673 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 13:59:05,673 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 13:59:05,673 Computation:
70
+ 2023-10-13 13:59:05,673 - compute on device: cuda:0
71
+ 2023-10-13 13:59:05,673 - embedding storage: none
72
+ 2023-10-13 13:59:05,673 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 13:59:05,673 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
74
+ 2023-10-13 13:59:05,673 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 13:59:05,673 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 13:59:10,356 epoch 1 - iter 89/894 - loss 2.78687185 - time (sec): 4.68 - samples/sec: 2106.96 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 13:59:14,946 epoch 1 - iter 178/894 - loss 1.83667772 - time (sec): 9.27 - samples/sec: 2055.86 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 13:59:19,189 epoch 1 - iter 267/894 - loss 1.43542315 - time (sec): 13.51 - samples/sec: 2027.71 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 13:59:23,693 epoch 1 - iter 356/894 - loss 1.17984185 - time (sec): 18.02 - samples/sec: 2009.61 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 13:59:28,080 epoch 1 - iter 445/894 - loss 1.01423099 - time (sec): 22.41 - samples/sec: 2003.28 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 13:59:32,229 epoch 1 - iter 534/894 - loss 0.89883445 - time (sec): 26.55 - samples/sec: 2006.04 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 13:59:36,530 epoch 1 - iter 623/894 - loss 0.81343620 - time (sec): 30.86 - samples/sec: 2003.90 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 13:59:40,596 epoch 1 - iter 712/894 - loss 0.74697113 - time (sec): 34.92 - samples/sec: 2003.94 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 13:59:44,813 epoch 1 - iter 801/894 - loss 0.69901099 - time (sec): 39.14 - samples/sec: 1992.02 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 13:59:49,162 epoch 1 - iter 890/894 - loss 0.65455551 - time (sec): 43.49 - samples/sec: 1982.71 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 13:59:49,345 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 13:59:49,345 EPOCH 1 done: loss 0.6530 - lr: 0.000030
88
+ 2023-10-13 13:59:54,460 DEV : loss 0.22069643437862396 - f1-score (micro avg) 0.4457
89
+ 2023-10-13 13:59:54,489 saving best model
90
+ 2023-10-13 13:59:54,852 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 13:59:59,095 epoch 2 - iter 89/894 - loss 0.21678149 - time (sec): 4.24 - samples/sec: 2179.46 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 14:00:03,212 epoch 2 - iter 178/894 - loss 0.20637428 - time (sec): 8.36 - samples/sec: 2122.46 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 14:00:07,486 epoch 2 - iter 267/894 - loss 0.18885318 - time (sec): 12.63 - samples/sec: 2054.15 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 14:00:11,671 epoch 2 - iter 356/894 - loss 0.18912920 - time (sec): 16.82 - samples/sec: 1995.39 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 14:00:15,864 epoch 2 - iter 445/894 - loss 0.18128960 - time (sec): 21.01 - samples/sec: 2004.53 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 14:00:20,094 epoch 2 - iter 534/894 - loss 0.17655364 - time (sec): 25.24 - samples/sec: 2008.08 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 14:00:24,412 epoch 2 - iter 623/894 - loss 0.17463665 - time (sec): 29.56 - samples/sec: 2008.60 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 14:00:28,546 epoch 2 - iter 712/894 - loss 0.17003642 - time (sec): 33.69 - samples/sec: 2022.78 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 14:00:32,975 epoch 2 - iter 801/894 - loss 0.16477203 - time (sec): 38.12 - samples/sec: 2022.96 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 14:00:37,248 epoch 2 - iter 890/894 - loss 0.15965603 - time (sec): 42.39 - samples/sec: 2029.18 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 14:00:37,442 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 14:00:37,443 EPOCH 2 done: loss 0.1598 - lr: 0.000027
103
+ 2023-10-13 14:00:46,037 DEV : loss 0.14208738505840302 - f1-score (micro avg) 0.7178
104
+ 2023-10-13 14:00:46,066 saving best model
105
+ 2023-10-13 14:00:46,463 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 14:00:50,367 epoch 3 - iter 89/894 - loss 0.08594613 - time (sec): 3.90 - samples/sec: 2356.98 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 14:00:54,422 epoch 3 - iter 178/894 - loss 0.08369345 - time (sec): 7.95 - samples/sec: 2254.26 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 14:00:58,892 epoch 3 - iter 267/894 - loss 0.08631861 - time (sec): 12.42 - samples/sec: 2194.91 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 14:01:03,116 epoch 3 - iter 356/894 - loss 0.09399803 - time (sec): 16.65 - samples/sec: 2180.17 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 14:01:07,312 epoch 3 - iter 445/894 - loss 0.09227099 - time (sec): 20.84 - samples/sec: 2131.23 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 14:01:11,394 epoch 3 - iter 534/894 - loss 0.08961269 - time (sec): 24.93 - samples/sec: 2118.12 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 14:01:15,548 epoch 3 - iter 623/894 - loss 0.08926189 - time (sec): 29.08 - samples/sec: 2088.02 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 14:01:19,898 epoch 3 - iter 712/894 - loss 0.08854898 - time (sec): 33.43 - samples/sec: 2071.83 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 14:01:24,094 epoch 3 - iter 801/894 - loss 0.09027434 - time (sec): 37.63 - samples/sec: 2072.85 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 14:01:28,366 epoch 3 - iter 890/894 - loss 0.08943881 - time (sec): 41.90 - samples/sec: 2057.69 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 14:01:28,554 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 14:01:28,555 EPOCH 3 done: loss 0.0896 - lr: 0.000023
118
+ 2023-10-13 14:01:37,288 DEV : loss 0.17507663369178772 - f1-score (micro avg) 0.7188
119
+ 2023-10-13 14:01:37,319 saving best model
120
+ 2023-10-13 14:01:37,762 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 14:01:42,145 epoch 4 - iter 89/894 - loss 0.06767294 - time (sec): 4.38 - samples/sec: 2121.65 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 14:01:46,275 epoch 4 - iter 178/894 - loss 0.05727936 - time (sec): 8.51 - samples/sec: 2055.35 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 14:01:50,725 epoch 4 - iter 267/894 - loss 0.05517981 - time (sec): 12.96 - samples/sec: 2132.81 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 14:01:55,093 epoch 4 - iter 356/894 - loss 0.05360690 - time (sec): 17.33 - samples/sec: 2059.97 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 14:01:59,440 epoch 4 - iter 445/894 - loss 0.05613746 - time (sec): 21.68 - samples/sec: 2036.80 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 14:02:03,973 epoch 4 - iter 534/894 - loss 0.05432807 - time (sec): 26.21 - samples/sec: 2041.73 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 14:02:08,074 epoch 4 - iter 623/894 - loss 0.05420372 - time (sec): 30.31 - samples/sec: 2035.05 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 14:02:12,407 epoch 4 - iter 712/894 - loss 0.05430444 - time (sec): 34.64 - samples/sec: 2017.28 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 14:02:16,824 epoch 4 - iter 801/894 - loss 0.05503820 - time (sec): 39.06 - samples/sec: 1997.10 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 14:02:20,917 epoch 4 - iter 890/894 - loss 0.05517788 - time (sec): 43.15 - samples/sec: 1998.15 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 14:02:21,086 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 14:02:21,086 EPOCH 4 done: loss 0.0550 - lr: 0.000020
133
+ 2023-10-13 14:02:29,857 DEV : loss 0.1758618950843811 - f1-score (micro avg) 0.7732
134
+ 2023-10-13 14:02:29,888 saving best model
135
+ 2023-10-13 14:02:30,330 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 14:02:34,484 epoch 5 - iter 89/894 - loss 0.04873389 - time (sec): 4.15 - samples/sec: 2100.67 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 14:02:38,547 epoch 5 - iter 178/894 - loss 0.04344402 - time (sec): 8.22 - samples/sec: 2073.36 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 14:02:42,978 epoch 5 - iter 267/894 - loss 0.04040407 - time (sec): 12.65 - samples/sec: 2074.89 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 14:02:47,075 epoch 5 - iter 356/894 - loss 0.04336586 - time (sec): 16.74 - samples/sec: 2078.07 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 14:02:51,549 epoch 5 - iter 445/894 - loss 0.04035000 - time (sec): 21.22 - samples/sec: 2077.28 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 14:02:56,031 epoch 5 - iter 534/894 - loss 0.04155502 - time (sec): 25.70 - samples/sec: 2052.38 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 14:03:00,133 epoch 5 - iter 623/894 - loss 0.04118576 - time (sec): 29.80 - samples/sec: 2049.18 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 14:03:04,263 epoch 5 - iter 712/894 - loss 0.04243180 - time (sec): 33.93 - samples/sec: 2059.10 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 14:03:08,233 epoch 5 - iter 801/894 - loss 0.04346817 - time (sec): 37.90 - samples/sec: 2051.91 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 14:03:12,313 epoch 5 - iter 890/894 - loss 0.04227829 - time (sec): 41.98 - samples/sec: 2051.66 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 14:03:12,492 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 14:03:12,492 EPOCH 5 done: loss 0.0422 - lr: 0.000017
148
+ 2023-10-13 14:03:21,052 DEV : loss 0.21636423468589783 - f1-score (micro avg) 0.7586
149
+ 2023-10-13 14:03:21,082 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 14:03:25,209 epoch 6 - iter 89/894 - loss 0.02959950 - time (sec): 4.13 - samples/sec: 2027.47 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-13 14:03:29,374 epoch 6 - iter 178/894 - loss 0.03041622 - time (sec): 8.29 - samples/sec: 2022.79 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 14:03:33,930 epoch 6 - iter 267/894 - loss 0.02982755 - time (sec): 12.85 - samples/sec: 2110.95 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 14:03:38,083 epoch 6 - iter 356/894 - loss 0.02840678 - time (sec): 17.00 - samples/sec: 2107.91 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-13 14:03:42,318 epoch 6 - iter 445/894 - loss 0.02439814 - time (sec): 21.23 - samples/sec: 2148.64 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 14:03:46,400 epoch 6 - iter 534/894 - loss 0.02387052 - time (sec): 25.32 - samples/sec: 2115.66 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 14:03:50,491 epoch 6 - iter 623/894 - loss 0.02627774 - time (sec): 29.41 - samples/sec: 2094.16 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-13 14:03:54,444 epoch 6 - iter 712/894 - loss 0.02611411 - time (sec): 33.36 - samples/sec: 2096.49 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 14:03:58,750 epoch 6 - iter 801/894 - loss 0.02642882 - time (sec): 37.67 - samples/sec: 2083.07 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 14:04:02,893 epoch 6 - iter 890/894 - loss 0.02543964 - time (sec): 41.81 - samples/sec: 2061.05 - lr: 0.000013 - momentum: 0.000000
160
+ 2023-10-13 14:04:03,077 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 14:04:03,077 EPOCH 6 done: loss 0.0253 - lr: 0.000013
162
+ 2023-10-13 14:04:11,728 DEV : loss 0.22308549284934998 - f1-score (micro avg) 0.7748
163
+ 2023-10-13 14:04:11,757 saving best model
164
+ 2023-10-13 14:04:12,161 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 14:04:16,257 epoch 7 - iter 89/894 - loss 0.02342834 - time (sec): 4.09 - samples/sec: 1907.60 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 14:04:20,373 epoch 7 - iter 178/894 - loss 0.01878172 - time (sec): 8.21 - samples/sec: 1906.72 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 14:04:24,689 epoch 7 - iter 267/894 - loss 0.01651681 - time (sec): 12.53 - samples/sec: 2025.15 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 14:04:28,711 epoch 7 - iter 356/894 - loss 0.01547954 - time (sec): 16.55 - samples/sec: 2062.11 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 14:04:32,900 epoch 7 - iter 445/894 - loss 0.01621027 - time (sec): 20.74 - samples/sec: 2078.64 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 14:04:37,016 epoch 7 - iter 534/894 - loss 0.01622332 - time (sec): 24.85 - samples/sec: 2065.55 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 14:04:41,065 epoch 7 - iter 623/894 - loss 0.01952617 - time (sec): 28.90 - samples/sec: 2061.60 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 14:04:45,354 epoch 7 - iter 712/894 - loss 0.01927350 - time (sec): 33.19 - samples/sec: 2074.03 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 14:04:49,409 epoch 7 - iter 801/894 - loss 0.01943370 - time (sec): 37.25 - samples/sec: 2078.79 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 14:04:53,615 epoch 7 - iter 890/894 - loss 0.01911541 - time (sec): 41.45 - samples/sec: 2078.73 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 14:04:53,797 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 14:04:53,798 EPOCH 7 done: loss 0.0190 - lr: 0.000010
177
+ 2023-10-13 14:05:02,382 DEV : loss 0.22052636742591858 - f1-score (micro avg) 0.7874
178
+ 2023-10-13 14:05:02,411 saving best model
179
+ 2023-10-13 14:05:02,860 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 14:05:07,095 epoch 8 - iter 89/894 - loss 0.02089063 - time (sec): 4.23 - samples/sec: 1998.48 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-13 14:05:11,191 epoch 8 - iter 178/894 - loss 0.01335054 - time (sec): 8.33 - samples/sec: 1999.28 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 14:05:15,576 epoch 8 - iter 267/894 - loss 0.01272066 - time (sec): 12.71 - samples/sec: 2051.24 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 14:05:20,074 epoch 8 - iter 356/894 - loss 0.01073740 - time (sec): 17.21 - samples/sec: 2060.29 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-13 14:05:24,453 epoch 8 - iter 445/894 - loss 0.01077757 - time (sec): 21.59 - samples/sec: 2033.73 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 14:05:28,583 epoch 8 - iter 534/894 - loss 0.01273554 - time (sec): 25.72 - samples/sec: 2035.61 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 14:05:32,581 epoch 8 - iter 623/894 - loss 0.01165437 - time (sec): 29.72 - samples/sec: 2048.18 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-13 14:05:36,812 epoch 8 - iter 712/894 - loss 0.01154346 - time (sec): 33.95 - samples/sec: 2041.28 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 14:05:41,166 epoch 8 - iter 801/894 - loss 0.01126916 - time (sec): 38.30 - samples/sec: 2025.15 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 14:05:45,386 epoch 8 - iter 890/894 - loss 0.01101390 - time (sec): 42.52 - samples/sec: 2027.19 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-13 14:05:45,568 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 14:05:45,568 EPOCH 8 done: loss 0.0110 - lr: 0.000007
192
+ 2023-10-13 14:05:54,276 DEV : loss 0.2309163361787796 - f1-score (micro avg) 0.7818
193
+ 2023-10-13 14:05:54,312 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-13 14:05:58,405 epoch 9 - iter 89/894 - loss 0.01279159 - time (sec): 4.09 - samples/sec: 2015.47 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 14:06:02,792 epoch 9 - iter 178/894 - loss 0.00812077 - time (sec): 8.48 - samples/sec: 2094.57 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 14:06:07,082 epoch 9 - iter 267/894 - loss 0.00730535 - time (sec): 12.77 - samples/sec: 2101.53 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 14:06:11,210 epoch 9 - iter 356/894 - loss 0.00765185 - time (sec): 16.90 - samples/sec: 2090.82 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 14:06:15,353 epoch 9 - iter 445/894 - loss 0.00827821 - time (sec): 21.04 - samples/sec: 2067.90 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 14:06:19,386 epoch 9 - iter 534/894 - loss 0.00813367 - time (sec): 25.07 - samples/sec: 2077.50 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 14:06:23,376 epoch 9 - iter 623/894 - loss 0.00782058 - time (sec): 29.06 - samples/sec: 2091.14 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 14:06:27,185 epoch 9 - iter 712/894 - loss 0.00770643 - time (sec): 32.87 - samples/sec: 2110.21 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 14:06:31,208 epoch 9 - iter 801/894 - loss 0.00809901 - time (sec): 36.89 - samples/sec: 2103.75 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 14:06:35,301 epoch 9 - iter 890/894 - loss 0.00769231 - time (sec): 40.99 - samples/sec: 2103.26 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-13 14:06:35,476 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-13 14:06:35,476 EPOCH 9 done: loss 0.0078 - lr: 0.000003
206
+ 2023-10-13 14:06:43,950 DEV : loss 0.22727501392364502 - f1-score (micro avg) 0.7907
207
+ 2023-10-13 14:06:43,981 saving best model
208
+ 2023-10-13 14:06:44,434 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 14:06:48,668 epoch 10 - iter 89/894 - loss 0.00069532 - time (sec): 4.23 - samples/sec: 2026.94 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 14:06:52,763 epoch 10 - iter 178/894 - loss 0.00187676 - time (sec): 8.32 - samples/sec: 1977.80 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 14:06:57,063 epoch 10 - iter 267/894 - loss 0.00160918 - time (sec): 12.62 - samples/sec: 1980.70 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 14:07:01,190 epoch 10 - iter 356/894 - loss 0.00268265 - time (sec): 16.75 - samples/sec: 1978.24 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 14:07:05,561 epoch 10 - iter 445/894 - loss 0.00291641 - time (sec): 21.12 - samples/sec: 2028.66 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 14:07:10,116 epoch 10 - iter 534/894 - loss 0.00309688 - time (sec): 25.68 - samples/sec: 2031.17 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 14:07:14,396 epoch 10 - iter 623/894 - loss 0.00368422 - time (sec): 29.96 - samples/sec: 2020.05 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 14:07:18,425 epoch 10 - iter 712/894 - loss 0.00400810 - time (sec): 33.99 - samples/sec: 2016.92 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 14:07:22,574 epoch 10 - iter 801/894 - loss 0.00391063 - time (sec): 38.13 - samples/sec: 2042.67 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 14:07:26,627 epoch 10 - iter 890/894 - loss 0.00425085 - time (sec): 42.19 - samples/sec: 2043.03 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 14:07:26,804 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 14:07:26,805 EPOCH 10 done: loss 0.0042 - lr: 0.000000
221
+ 2023-10-13 14:07:35,443 DEV : loss 0.2396899163722992 - f1-score (micro avg) 0.7871
222
+ 2023-10-13 14:07:35,827 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 14:07:35,828 Loading model from best epoch ...
224
+ 2023-10-13 14:07:37,300 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
225
+ 2023-10-13 14:07:41,958
226
+ Results:
227
+ - F-score (micro) 0.748
228
+ - F-score (macro) 0.6772
229
+ - Accuracy 0.6177
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8271 0.8591 0.8428 596
235
+ pers 0.6449 0.7417 0.6899 333
236
+ org 0.5872 0.4848 0.5311 132
237
+ prod 0.6182 0.5152 0.5620 66
238
+ time 0.7451 0.7755 0.7600 49
239
+
240
+ micro avg 0.7354 0.7611 0.7480 1176
241
+ macro avg 0.6845 0.6753 0.6772 1176
242
+ weighted avg 0.7335 0.7611 0.7453 1176
243
+
244
+ 2023-10-13 14:07:41,958 ----------------------------------------------------------------------------------------------------