Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmbert_tiny-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
a508f10
•
1 Parent(s): cc7caec

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697792795.46dc0c540dd0.5704.0 +3 -0
  5. test.tsv +0 -0
  6. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956e5a7090d22479760302f7da2d10534e009bf97448ddd5e9dc22f060f917be
3
+ size 19045986
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 09:06:59 0.0000 0.9635 0.1460 0.0000 0.0000 0.0000 0.0000
3
+ 2 09:07:24 0.0000 0.1964 0.0964 0.6838 0.3376 0.4520 0.3008
4
+ 3 09:07:49 0.0000 0.1593 0.0897 0.6168 0.4346 0.5099 0.3552
5
+ 4 09:08:14 0.0000 0.1485 0.0877 0.6313 0.5274 0.5747 0.4223
6
+ 5 09:08:39 0.0000 0.1363 0.0856 0.6226 0.5570 0.5880 0.4385
7
+ 6 09:09:04 0.0000 0.1321 0.0882 0.6273 0.5823 0.6039 0.4585
8
+ 7 09:09:29 0.0000 0.1266 0.0885 0.5949 0.5949 0.5949 0.4490
9
+ 8 09:09:54 0.0000 0.1233 0.0905 0.6372 0.5781 0.6062 0.4613
10
+ 9 09:10:18 0.0000 0.1193 0.0919 0.6295 0.5949 0.6117 0.4684
11
+ 10 09:10:43 0.0000 0.1167 0.0932 0.6634 0.5738 0.6154 0.4739
runs/events.out.tfevents.1697792795.46dc0c540dd0.5704.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d68d5d4b0fad3c18fbb47141dbdc8cb6f4dcf39f58266860a3b8b1a5758c02
3
+ size 864636
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-20 09:06:35,409 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-20 09:06:35,409 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), 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=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-20 09:06:35,410 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-20 09:06:35,410 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
52
+ - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
53
+ 2023-10-20 09:06:35,410 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-20 09:06:35,410 Train: 6183 sentences
55
+ 2023-10-20 09:06:35,410 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-20 09:06:35,410 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-20 09:06:35,410 Training Params:
58
+ 2023-10-20 09:06:35,410 - learning_rate: "3e-05"
59
+ 2023-10-20 09:06:35,410 - mini_batch_size: "4"
60
+ 2023-10-20 09:06:35,410 - max_epochs: "10"
61
+ 2023-10-20 09:06:35,410 - shuffle: "True"
62
+ 2023-10-20 09:06:35,410 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-20 09:06:35,411 Plugins:
64
+ 2023-10-20 09:06:35,411 - TensorboardLogger
65
+ 2023-10-20 09:06:35,411 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-20 09:06:35,411 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-20 09:06:35,411 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-20 09:06:35,411 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-20 09:06:35,411 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-20 09:06:35,411 Computation:
71
+ 2023-10-20 09:06:35,411 - compute on device: cuda:0
72
+ 2023-10-20 09:06:35,411 - embedding storage: none
73
+ 2023-10-20 09:06:35,411 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-20 09:06:35,411 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-20 09:06:35,411 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-20 09:06:35,411 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-20 09:06:35,411 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-20 09:06:37,833 epoch 1 - iter 154/1546 - loss 3.28397095 - time (sec): 2.42 - samples/sec: 5244.37 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-20 09:06:40,154 epoch 1 - iter 308/1546 - loss 2.99105285 - time (sec): 4.74 - samples/sec: 5139.46 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-20 09:06:42,531 epoch 1 - iter 462/1546 - loss 2.52293414 - time (sec): 7.12 - samples/sec: 5133.11 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-20 09:06:44,753 epoch 1 - iter 616/1546 - loss 2.02560749 - time (sec): 9.34 - samples/sec: 5282.45 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-20 09:06:46,974 epoch 1 - iter 770/1546 - loss 1.67950423 - time (sec): 11.56 - samples/sec: 5315.86 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-20 09:06:49,149 epoch 1 - iter 924/1546 - loss 1.45624081 - time (sec): 13.74 - samples/sec: 5319.42 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-20 09:06:51,518 epoch 1 - iter 1078/1546 - loss 1.28121677 - time (sec): 16.11 - samples/sec: 5324.77 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-20 09:06:53,979 epoch 1 - iter 1232/1546 - loss 1.14682597 - time (sec): 18.57 - samples/sec: 5319.74 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-20 09:06:56,359 epoch 1 - iter 1386/1546 - loss 1.05075802 - time (sec): 20.95 - samples/sec: 5283.56 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-20 09:06:58,781 epoch 1 - iter 1540/1546 - loss 0.96746300 - time (sec): 23.37 - samples/sec: 5294.97 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-20 09:06:58,888 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-20 09:06:58,888 EPOCH 1 done: loss 0.9635 - lr: 0.000030
90
+ 2023-10-20 09:06:59,562 DEV : loss 0.1460493505001068 - f1-score (micro avg) 0.0
91
+ 2023-10-20 09:06:59,573 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-20 09:07:01,954 epoch 2 - iter 154/1546 - loss 0.23058634 - time (sec): 2.38 - samples/sec: 5219.28 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-20 09:07:04,312 epoch 2 - iter 308/1546 - loss 0.22254356 - time (sec): 4.74 - samples/sec: 5059.52 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-20 09:07:06,666 epoch 2 - iter 462/1546 - loss 0.22366210 - time (sec): 7.09 - samples/sec: 4999.49 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-20 09:07:09,084 epoch 2 - iter 616/1546 - loss 0.21092520 - time (sec): 9.51 - samples/sec: 5084.24 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-20 09:07:11,446 epoch 2 - iter 770/1546 - loss 0.20806216 - time (sec): 11.87 - samples/sec: 5152.85 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-20 09:07:13,762 epoch 2 - iter 924/1546 - loss 0.20526902 - time (sec): 14.19 - samples/sec: 5138.44 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-20 09:07:16,170 epoch 2 - iter 1078/1546 - loss 0.20379508 - time (sec): 16.60 - samples/sec: 5111.99 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-20 09:07:18,549 epoch 2 - iter 1232/1546 - loss 0.20172155 - time (sec): 18.98 - samples/sec: 5138.82 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-20 09:07:20,996 epoch 2 - iter 1386/1546 - loss 0.20086049 - time (sec): 21.42 - samples/sec: 5126.79 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-20 09:07:23,418 epoch 2 - iter 1540/1546 - loss 0.19704649 - time (sec): 23.84 - samples/sec: 5183.51 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-20 09:07:23,513 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-20 09:07:23,513 EPOCH 2 done: loss 0.1964 - lr: 0.000027
104
+ 2023-10-20 09:07:24,832 DEV : loss 0.09642348438501358 - f1-score (micro avg) 0.452
105
+ 2023-10-20 09:07:24,844 saving best model
106
+ 2023-10-20 09:07:24,878 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-20 09:07:27,163 epoch 3 - iter 154/1546 - loss 0.16756513 - time (sec): 2.28 - samples/sec: 5008.14 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-20 09:07:29,473 epoch 3 - iter 308/1546 - loss 0.15306420 - time (sec): 4.59 - samples/sec: 5243.02 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-20 09:07:31,759 epoch 3 - iter 462/1546 - loss 0.14828552 - time (sec): 6.88 - samples/sec: 5298.73 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-20 09:07:34,118 epoch 3 - iter 616/1546 - loss 0.15847543 - time (sec): 9.24 - samples/sec: 5349.69 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-20 09:07:36,476 epoch 3 - iter 770/1546 - loss 0.15836327 - time (sec): 11.60 - samples/sec: 5290.33 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-20 09:07:38,811 epoch 3 - iter 924/1546 - loss 0.15990269 - time (sec): 13.93 - samples/sec: 5374.68 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-20 09:07:41,185 epoch 3 - iter 1078/1546 - loss 0.16137110 - time (sec): 16.31 - samples/sec: 5359.58 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-20 09:07:43,553 epoch 3 - iter 1232/1546 - loss 0.16066108 - time (sec): 18.67 - samples/sec: 5353.33 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-20 09:07:45,922 epoch 3 - iter 1386/1546 - loss 0.16038985 - time (sec): 21.04 - samples/sec: 5281.58 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-20 09:07:48,314 epoch 3 - iter 1540/1546 - loss 0.15944440 - time (sec): 23.44 - samples/sec: 5277.46 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-20 09:07:48,405 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-20 09:07:48,405 EPOCH 3 done: loss 0.1593 - lr: 0.000023
119
+ 2023-10-20 09:07:49,466 DEV : loss 0.0896943062543869 - f1-score (micro avg) 0.5099
120
+ 2023-10-20 09:07:49,477 saving best model
121
+ 2023-10-20 09:07:49,512 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-20 09:07:51,999 epoch 4 - iter 154/1546 - loss 0.15769143 - time (sec): 2.49 - samples/sec: 5070.16 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-20 09:07:54,306 epoch 4 - iter 308/1546 - loss 0.14433493 - time (sec): 4.79 - samples/sec: 5182.99 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-20 09:07:56,624 epoch 4 - iter 462/1546 - loss 0.15210379 - time (sec): 7.11 - samples/sec: 5030.59 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-20 09:07:58,995 epoch 4 - iter 616/1546 - loss 0.15295122 - time (sec): 9.48 - samples/sec: 5109.69 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-20 09:08:01,502 epoch 4 - iter 770/1546 - loss 0.15434920 - time (sec): 11.99 - samples/sec: 5061.65 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-20 09:08:03,980 epoch 4 - iter 924/1546 - loss 0.15086170 - time (sec): 14.47 - samples/sec: 5039.38 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-20 09:08:06,343 epoch 4 - iter 1078/1546 - loss 0.14718520 - time (sec): 16.83 - samples/sec: 5118.47 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-20 09:08:08,710 epoch 4 - iter 1232/1546 - loss 0.14718548 - time (sec): 19.20 - samples/sec: 5163.73 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-20 09:08:11,129 epoch 4 - iter 1386/1546 - loss 0.14835468 - time (sec): 21.62 - samples/sec: 5143.52 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-20 09:08:13,586 epoch 4 - iter 1540/1546 - loss 0.14859824 - time (sec): 24.07 - samples/sec: 5144.69 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-20 09:08:13,668 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-20 09:08:13,669 EPOCH 4 done: loss 0.1485 - lr: 0.000020
134
+ 2023-10-20 09:08:14,728 DEV : loss 0.08766192942857742 - f1-score (micro avg) 0.5747
135
+ 2023-10-20 09:08:14,738 saving best model
136
+ 2023-10-20 09:08:14,771 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-20 09:08:17,083 epoch 5 - iter 154/1546 - loss 0.12769709 - time (sec): 2.31 - samples/sec: 5337.69 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-20 09:08:19,442 epoch 5 - iter 308/1546 - loss 0.13094414 - time (sec): 4.67 - samples/sec: 5128.06 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-20 09:08:21,893 epoch 5 - iter 462/1546 - loss 0.13300073 - time (sec): 7.12 - samples/sec: 5051.31 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-20 09:08:24,311 epoch 5 - iter 616/1546 - loss 0.13238196 - time (sec): 9.54 - samples/sec: 5160.07 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-20 09:08:26,690 epoch 5 - iter 770/1546 - loss 0.13428010 - time (sec): 11.92 - samples/sec: 5219.68 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-20 09:08:29,059 epoch 5 - iter 924/1546 - loss 0.13243603 - time (sec): 14.29 - samples/sec: 5203.51 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-20 09:08:31,427 epoch 5 - iter 1078/1546 - loss 0.13095759 - time (sec): 16.66 - samples/sec: 5184.83 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-20 09:08:33,859 epoch 5 - iter 1232/1546 - loss 0.13464576 - time (sec): 19.09 - samples/sec: 5174.45 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-20 09:08:36,291 epoch 5 - iter 1386/1546 - loss 0.13608735 - time (sec): 21.52 - samples/sec: 5199.06 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-20 09:08:38,636 epoch 5 - iter 1540/1546 - loss 0.13658634 - time (sec): 23.86 - samples/sec: 5187.95 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-20 09:08:38,723 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-20 09:08:38,723 EPOCH 5 done: loss 0.1363 - lr: 0.000017
149
+ 2023-10-20 09:08:39,806 DEV : loss 0.08561883121728897 - f1-score (micro avg) 0.588
150
+ 2023-10-20 09:08:39,817 saving best model
151
+ 2023-10-20 09:08:39,849 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-20 09:08:42,216 epoch 6 - iter 154/1546 - loss 0.10872815 - time (sec): 2.37 - samples/sec: 5045.83 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-20 09:08:44,590 epoch 6 - iter 308/1546 - loss 0.11960726 - time (sec): 4.74 - samples/sec: 5003.13 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-20 09:08:46,973 epoch 6 - iter 462/1546 - loss 0.13441599 - time (sec): 7.12 - samples/sec: 5024.85 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-20 09:08:49,131 epoch 6 - iter 616/1546 - loss 0.13530848 - time (sec): 9.28 - samples/sec: 5247.57 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-20 09:08:51,443 epoch 6 - iter 770/1546 - loss 0.14041532 - time (sec): 11.59 - samples/sec: 5202.06 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-20 09:08:53,814 epoch 6 - iter 924/1546 - loss 0.13528183 - time (sec): 13.96 - samples/sec: 5249.94 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-20 09:08:56,177 epoch 6 - iter 1078/1546 - loss 0.13227395 - time (sec): 16.33 - samples/sec: 5253.32 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-20 09:08:58,522 epoch 6 - iter 1232/1546 - loss 0.13103216 - time (sec): 18.67 - samples/sec: 5297.52 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-20 09:09:00,904 epoch 6 - iter 1386/1546 - loss 0.12991021 - time (sec): 21.05 - samples/sec: 5249.58 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-20 09:09:03,307 epoch 6 - iter 1540/1546 - loss 0.13230097 - time (sec): 23.46 - samples/sec: 5276.90 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-20 09:09:03,406 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-20 09:09:03,406 EPOCH 6 done: loss 0.1321 - lr: 0.000013
164
+ 2023-10-20 09:09:04,491 DEV : loss 0.08819162845611572 - f1-score (micro avg) 0.6039
165
+ 2023-10-20 09:09:04,502 saving best model
166
+ 2023-10-20 09:09:04,536 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-20 09:09:07,006 epoch 7 - iter 154/1546 - loss 0.11723149 - time (sec): 2.47 - samples/sec: 5437.44 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-20 09:09:09,369 epoch 7 - iter 308/1546 - loss 0.11870071 - time (sec): 4.83 - samples/sec: 5146.87 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-20 09:09:11,751 epoch 7 - iter 462/1546 - loss 0.11534894 - time (sec): 7.21 - samples/sec: 5251.42 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-20 09:09:14,090 epoch 7 - iter 616/1546 - loss 0.12686834 - time (sec): 9.55 - samples/sec: 5179.35 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-20 09:09:16,467 epoch 7 - iter 770/1546 - loss 0.12653362 - time (sec): 11.93 - samples/sec: 5208.68 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-20 09:09:18,835 epoch 7 - iter 924/1546 - loss 0.12736348 - time (sec): 14.30 - samples/sec: 5228.86 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-20 09:09:21,220 epoch 7 - iter 1078/1546 - loss 0.12994923 - time (sec): 16.68 - samples/sec: 5236.09 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-20 09:09:23,602 epoch 7 - iter 1232/1546 - loss 0.12775059 - time (sec): 19.06 - samples/sec: 5245.07 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-20 09:09:26,092 epoch 7 - iter 1386/1546 - loss 0.12761801 - time (sec): 21.56 - samples/sec: 5181.77 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-20 09:09:28,442 epoch 7 - iter 1540/1546 - loss 0.12680413 - time (sec): 23.91 - samples/sec: 5179.14 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-20 09:09:28,532 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-20 09:09:28,532 EPOCH 7 done: loss 0.1266 - lr: 0.000010
179
+ 2023-10-20 09:09:29,594 DEV : loss 0.08853663504123688 - f1-score (micro avg) 0.5949
180
+ 2023-10-20 09:09:29,605 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-20 09:09:31,902 epoch 8 - iter 154/1546 - loss 0.10560379 - time (sec): 2.30 - samples/sec: 5298.60 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-20 09:09:34,349 epoch 8 - iter 308/1546 - loss 0.12872546 - time (sec): 4.74 - samples/sec: 5252.11 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-20 09:09:36,720 epoch 8 - iter 462/1546 - loss 0.13119470 - time (sec): 7.11 - samples/sec: 5187.26 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-20 09:09:39,051 epoch 8 - iter 616/1546 - loss 0.12502116 - time (sec): 9.45 - samples/sec: 5215.10 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-20 09:09:41,413 epoch 8 - iter 770/1546 - loss 0.12112850 - time (sec): 11.81 - samples/sec: 5278.34 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-20 09:09:43,859 epoch 8 - iter 924/1546 - loss 0.12463981 - time (sec): 14.25 - samples/sec: 5309.41 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-20 09:09:46,162 epoch 8 - iter 1078/1546 - loss 0.12423906 - time (sec): 16.56 - samples/sec: 5263.09 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-20 09:09:48,482 epoch 8 - iter 1232/1546 - loss 0.12613505 - time (sec): 18.88 - samples/sec: 5225.70 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-20 09:09:50,918 epoch 8 - iter 1386/1546 - loss 0.12382574 - time (sec): 21.31 - samples/sec: 5199.99 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-20 09:09:53,355 epoch 8 - iter 1540/1546 - loss 0.12351904 - time (sec): 23.75 - samples/sec: 5219.53 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-20 09:09:53,443 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-20 09:09:53,443 EPOCH 8 done: loss 0.1233 - lr: 0.000007
193
+ 2023-10-20 09:09:54,533 DEV : loss 0.09046540409326553 - f1-score (micro avg) 0.6062
194
+ 2023-10-20 09:09:54,545 saving best model
195
+ 2023-10-20 09:09:54,583 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-20 09:09:56,973 epoch 9 - iter 154/1546 - loss 0.12165880 - time (sec): 2.39 - samples/sec: 5120.10 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-20 09:09:59,354 epoch 9 - iter 308/1546 - loss 0.11720672 - time (sec): 4.77 - samples/sec: 5174.59 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-20 09:10:01,652 epoch 9 - iter 462/1546 - loss 0.10950130 - time (sec): 7.07 - samples/sec: 5397.14 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-20 09:10:03,813 epoch 9 - iter 616/1546 - loss 0.11189291 - time (sec): 9.23 - samples/sec: 5423.30 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-20 09:10:05,958 epoch 9 - iter 770/1546 - loss 0.11566478 - time (sec): 11.37 - samples/sec: 5567.08 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-20 09:10:08,178 epoch 9 - iter 924/1546 - loss 0.12061263 - time (sec): 13.59 - samples/sec: 5535.08 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-20 09:10:10,589 epoch 9 - iter 1078/1546 - loss 0.12124174 - time (sec): 16.01 - samples/sec: 5494.20 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-20 09:10:12,970 epoch 9 - iter 1232/1546 - loss 0.12235867 - time (sec): 18.39 - samples/sec: 5445.86 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-20 09:10:15,300 epoch 9 - iter 1386/1546 - loss 0.12037485 - time (sec): 20.72 - samples/sec: 5384.65 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-20 09:10:17,700 epoch 9 - iter 1540/1546 - loss 0.11940803 - time (sec): 23.12 - samples/sec: 5359.10 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-20 09:10:17,787 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-20 09:10:17,787 EPOCH 9 done: loss 0.1193 - lr: 0.000003
208
+ 2023-10-20 09:10:18,860 DEV : loss 0.09189001470804214 - f1-score (micro avg) 0.6117
209
+ 2023-10-20 09:10:18,871 saving best model
210
+ 2023-10-20 09:10:18,902 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-20 09:10:21,118 epoch 10 - iter 154/1546 - loss 0.12687807 - time (sec): 2.22 - samples/sec: 5422.87 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-20 09:10:23,371 epoch 10 - iter 308/1546 - loss 0.12068074 - time (sec): 4.47 - samples/sec: 5568.10 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-20 09:10:25,575 epoch 10 - iter 462/1546 - loss 0.12030419 - time (sec): 6.67 - samples/sec: 5713.42 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-20 09:10:27,713 epoch 10 - iter 616/1546 - loss 0.11605372 - time (sec): 8.81 - samples/sec: 5773.02 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-20 09:10:30,067 epoch 10 - iter 770/1546 - loss 0.11801476 - time (sec): 11.16 - samples/sec: 5649.92 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-20 09:10:32,425 epoch 10 - iter 924/1546 - loss 0.11442404 - time (sec): 13.52 - samples/sec: 5565.71 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-20 09:10:34,785 epoch 10 - iter 1078/1546 - loss 0.11142937 - time (sec): 15.88 - samples/sec: 5542.35 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-20 09:10:37,138 epoch 10 - iter 1232/1546 - loss 0.11098365 - time (sec): 18.24 - samples/sec: 5458.00 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-20 09:10:39,490 epoch 10 - iter 1386/1546 - loss 0.11535574 - time (sec): 20.59 - samples/sec: 5430.96 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-20 09:10:41,875 epoch 10 - iter 1540/1546 - loss 0.11683715 - time (sec): 22.97 - samples/sec: 5397.34 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-20 09:10:41,963 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-20 09:10:41,963 EPOCH 10 done: loss 0.1167 - lr: 0.000000
223
+ 2023-10-20 09:10:43,032 DEV : loss 0.0931963250041008 - f1-score (micro avg) 0.6154
224
+ 2023-10-20 09:10:43,043 saving best model
225
+ 2023-10-20 09:10:43,106 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-20 09:10:43,106 Loading model from best epoch ...
227
+ 2023-10-20 09:10:43,182 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
228
+ 2023-10-20 09:10:46,022
229
+ Results:
230
+ - F-score (micro) 0.5552
231
+ - F-score (macro) 0.2272
232
+ - Accuracy 0.4001
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ LOC 0.6223 0.6321 0.6272 946
238
+ BUILDING 0.1333 0.0108 0.0200 185
239
+ STREET 0.5000 0.0179 0.0345 56
240
+
241
+ micro avg 0.6145 0.5063 0.5552 1187
242
+ macro avg 0.4185 0.2203 0.2272 1187
243
+ weighted avg 0.5403 0.5063 0.5046 1187
244
+
245
+ 2023-10-20 09:10:46,022 ----------------------------------------------------------------------------------------------------