Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmbert_tiny-bs8-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
c375c9d
•
1 Parent(s): c5d5538

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.1697793312.46dc0c540dd0.5704.2 +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 sha256:053cbed85ccceca55b9a0d8e5ec7ddfb5e360a667ebca83b77f8c6114c47066b
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 09:15:31 0.0000 1.1740 0.1500 0.0000 0.0000 0.0000 0.0000
3
+ 2 09:15:49 0.0000 0.2087 0.1045 0.6591 0.1224 0.2064 0.1174
4
+ 3 09:16:08 0.0000 0.1680 0.0877 0.6076 0.4051 0.4861 0.3333
5
+ 4 09:16:27 0.0000 0.1499 0.0848 0.6757 0.4219 0.5195 0.3663
6
+ 5 09:16:45 0.0000 0.1381 0.0803 0.6568 0.4684 0.5468 0.3950
7
+ 6 09:17:04 0.0000 0.1316 0.0779 0.6462 0.5316 0.5833 0.4345
8
+ 7 09:17:22 0.0000 0.1262 0.0777 0.6157 0.5612 0.5872 0.4404
9
+ 8 09:17:41 0.0000 0.1214 0.0786 0.6598 0.5401 0.5940 0.4491
10
+ 9 09:18:00 0.0000 0.1202 0.0775 0.6394 0.5612 0.5978 0.4524
11
+ 10 09:18:18 0.0000 0.1189 0.0781 0.6485 0.5527 0.5968 0.4517
runs/events.out.tfevents.1697793312.46dc0c540dd0.5704.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab1f4816f8b4498e0962b469ca9e8cfdaea5332b155535484597a3c5c04b4fe
3
+ size 434848
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 09:15:12,661 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-20 09:15:12,661 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 09:15:12,661 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-20 09:15:12,661 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 09:15:12,661 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-20 09:15:12,661 Train: 6183 sentences
55
+ 2023-10-20 09:15:12,661 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-20 09:15:12,661 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-20 09:15:12,661 Training Params:
58
+ 2023-10-20 09:15:12,661 - learning_rate: "3e-05"
59
+ 2023-10-20 09:15:12,661 - mini_batch_size: "8"
60
+ 2023-10-20 09:15:12,661 - max_epochs: "10"
61
+ 2023-10-20 09:15:12,661 - shuffle: "True"
62
+ 2023-10-20 09:15:12,661 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-20 09:15:12,661 Plugins:
64
+ 2023-10-20 09:15:12,661 - TensorboardLogger
65
+ 2023-10-20 09:15:12,662 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-20 09:15:12,662 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-20 09:15:12,662 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-20 09:15:12,662 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-20 09:15:12,662 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-20 09:15:12,662 Computation:
71
+ 2023-10-20 09:15:12,662 - compute on device: cuda:0
72
+ 2023-10-20 09:15:12,662 - embedding storage: none
73
+ 2023-10-20 09:15:12,662 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-20 09:15:12,662 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-20 09:15:12,662 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-20 09:15:12,662 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-20 09:15:12,662 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-20 09:15:14,192 epoch 1 - iter 77/773 - loss 3.33952986 - time (sec): 1.53 - samples/sec: 8303.34 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-20 09:15:15,870 epoch 1 - iter 154/773 - loss 3.15376051 - time (sec): 3.21 - samples/sec: 7599.49 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-20 09:15:17,643 epoch 1 - iter 231/773 - loss 2.86285749 - time (sec): 4.98 - samples/sec: 7338.12 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-20 09:15:19,406 epoch 1 - iter 308/773 - loss 2.46722800 - time (sec): 6.74 - samples/sec: 7316.92 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-20 09:15:21,097 epoch 1 - iter 385/773 - loss 2.08159163 - time (sec): 8.43 - samples/sec: 7287.20 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-20 09:15:22,893 epoch 1 - iter 462/773 - loss 1.80370396 - time (sec): 10.23 - samples/sec: 7143.10 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-20 09:15:24,673 epoch 1 - iter 539/773 - loss 1.58250891 - time (sec): 12.01 - samples/sec: 7140.71 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-20 09:15:26,482 epoch 1 - iter 616/773 - loss 1.40958823 - time (sec): 13.82 - samples/sec: 7147.35 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-20 09:15:28,279 epoch 1 - iter 693/773 - loss 1.28574327 - time (sec): 15.62 - samples/sec: 7086.91 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-20 09:15:30,017 epoch 1 - iter 770/773 - loss 1.17895676 - time (sec): 17.35 - samples/sec: 7130.19 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-20 09:15:30,086 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-20 09:15:30,086 EPOCH 1 done: loss 1.1740 - lr: 0.000030
90
+ 2023-10-20 09:15:31,013 DEV : loss 0.14998705685138702 - f1-score (micro avg) 0.0
91
+ 2023-10-20 09:15:31,024 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-20 09:15:32,728 epoch 2 - iter 77/773 - loss 0.24465311 - time (sec): 1.70 - samples/sec: 7292.65 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-20 09:15:34,422 epoch 2 - iter 154/773 - loss 0.23774020 - time (sec): 3.40 - samples/sec: 7056.70 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-20 09:15:36,135 epoch 2 - iter 231/773 - loss 0.24048091 - time (sec): 5.11 - samples/sec: 6938.55 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-20 09:15:37,877 epoch 2 - iter 308/773 - loss 0.22885706 - time (sec): 6.85 - samples/sec: 7056.28 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-20 09:15:39,449 epoch 2 - iter 385/773 - loss 0.22732366 - time (sec): 8.42 - samples/sec: 7262.06 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-20 09:15:41,053 epoch 2 - iter 462/773 - loss 0.22283623 - time (sec): 10.03 - samples/sec: 7270.02 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-20 09:15:42,778 epoch 2 - iter 539/773 - loss 0.22091189 - time (sec): 11.75 - samples/sec: 7218.38 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-20 09:15:44,509 epoch 2 - iter 616/773 - loss 0.21641942 - time (sec): 13.49 - samples/sec: 7231.27 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-20 09:15:46,296 epoch 2 - iter 693/773 - loss 0.21432633 - time (sec): 15.27 - samples/sec: 7192.00 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-20 09:15:48,070 epoch 2 - iter 770/773 - loss 0.20934767 - time (sec): 17.05 - samples/sec: 7251.00 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-20 09:15:48,144 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-20 09:15:48,145 EPOCH 2 done: loss 0.2087 - lr: 0.000027
104
+ 2023-10-20 09:15:49,200 DEV : loss 0.10451915115118027 - f1-score (micro avg) 0.2064
105
+ 2023-10-20 09:15:49,212 saving best model
106
+ 2023-10-20 09:15:49,242 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-20 09:15:50,941 epoch 3 - iter 77/773 - loss 0.18760397 - time (sec): 1.70 - samples/sec: 6733.13 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-20 09:15:52,749 epoch 3 - iter 154/773 - loss 0.17290474 - time (sec): 3.51 - samples/sec: 6870.26 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-20 09:15:54,525 epoch 3 - iter 231/773 - loss 0.16574787 - time (sec): 5.28 - samples/sec: 6901.08 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-20 09:15:56,360 epoch 3 - iter 308/773 - loss 0.17220049 - time (sec): 7.12 - samples/sec: 6944.67 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-20 09:15:58,130 epoch 3 - iter 385/773 - loss 0.17055457 - time (sec): 8.89 - samples/sec: 6903.34 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-20 09:16:00,200 epoch 3 - iter 462/773 - loss 0.17102499 - time (sec): 10.96 - samples/sec: 6834.09 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-20 09:16:02,000 epoch 3 - iter 539/773 - loss 0.17156964 - time (sec): 12.76 - samples/sec: 6850.19 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-20 09:16:03,740 epoch 3 - iter 616/773 - loss 0.16973025 - time (sec): 14.50 - samples/sec: 6895.67 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-20 09:16:05,425 epoch 3 - iter 693/773 - loss 0.16937423 - time (sec): 16.18 - samples/sec: 6868.31 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-20 09:16:07,199 epoch 3 - iter 770/773 - loss 0.16819305 - time (sec): 17.96 - samples/sec: 6887.55 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-20 09:16:07,273 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-20 09:16:07,273 EPOCH 3 done: loss 0.1680 - lr: 0.000023
119
+ 2023-10-20 09:16:08,371 DEV : loss 0.0877489447593689 - f1-score (micro avg) 0.4861
120
+ 2023-10-20 09:16:08,383 saving best model
121
+ 2023-10-20 09:16:08,418 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-20 09:16:10,216 epoch 4 - iter 77/773 - loss 0.16112576 - time (sec): 1.80 - samples/sec: 7014.62 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-20 09:16:11,957 epoch 4 - iter 154/773 - loss 0.15054189 - time (sec): 3.54 - samples/sec: 7020.61 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-20 09:16:13,681 epoch 4 - iter 231/773 - loss 0.15757889 - time (sec): 5.26 - samples/sec: 6798.16 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-20 09:16:15,454 epoch 4 - iter 308/773 - loss 0.15835643 - time (sec): 7.04 - samples/sec: 6887.47 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-20 09:16:17,147 epoch 4 - iter 385/773 - loss 0.15939542 - time (sec): 8.73 - samples/sec: 6952.52 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-20 09:16:18,879 epoch 4 - iter 462/773 - loss 0.15526926 - time (sec): 10.46 - samples/sec: 6969.98 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-20 09:16:20,636 epoch 4 - iter 539/773 - loss 0.15163147 - time (sec): 12.22 - samples/sec: 7051.10 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-20 09:16:22,428 epoch 4 - iter 616/773 - loss 0.15053741 - time (sec): 14.01 - samples/sec: 7075.84 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-20 09:16:24,135 epoch 4 - iter 693/773 - loss 0.15041744 - time (sec): 15.72 - samples/sec: 7074.15 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-20 09:16:25,852 epoch 4 - iter 770/773 - loss 0.14997795 - time (sec): 17.43 - samples/sec: 7104.06 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-20 09:16:25,917 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-20 09:16:25,917 EPOCH 4 done: loss 0.1499 - lr: 0.000020
134
+ 2023-10-20 09:16:26,996 DEV : loss 0.08475784212350845 - f1-score (micro avg) 0.5195
135
+ 2023-10-20 09:16:27,007 saving best model
136
+ 2023-10-20 09:16:27,046 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-20 09:16:28,737 epoch 5 - iter 77/773 - loss 0.13296687 - time (sec): 1.69 - samples/sec: 7299.21 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-20 09:16:30,473 epoch 5 - iter 154/773 - loss 0.13988942 - time (sec): 3.43 - samples/sec: 6991.62 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-20 09:16:32,180 epoch 5 - iter 231/773 - loss 0.14188857 - time (sec): 5.13 - samples/sec: 7007.76 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-20 09:16:33,909 epoch 5 - iter 308/773 - loss 0.13800861 - time (sec): 6.86 - samples/sec: 7172.74 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-20 09:16:35,608 epoch 5 - iter 385/773 - loss 0.13726507 - time (sec): 8.56 - samples/sec: 7265.92 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-20 09:16:37,518 epoch 5 - iter 462/773 - loss 0.13563549 - time (sec): 10.47 - samples/sec: 7100.19 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-20 09:16:39,257 epoch 5 - iter 539/773 - loss 0.13353442 - time (sec): 12.21 - samples/sec: 7072.29 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-20 09:16:40,988 epoch 5 - iter 616/773 - loss 0.13630665 - time (sec): 13.94 - samples/sec: 7084.86 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-20 09:16:42,795 epoch 5 - iter 693/773 - loss 0.13728145 - time (sec): 15.75 - samples/sec: 7104.29 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-20 09:16:44,524 epoch 5 - iter 770/773 - loss 0.13822704 - time (sec): 17.48 - samples/sec: 7084.17 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-20 09:16:44,587 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-20 09:16:44,587 EPOCH 5 done: loss 0.1381 - lr: 0.000017
149
+ 2023-10-20 09:16:45,681 DEV : loss 0.08033832907676697 - f1-score (micro avg) 0.5468
150
+ 2023-10-20 09:16:45,693 saving best model
151
+ 2023-10-20 09:16:45,728 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-20 09:16:47,419 epoch 6 - iter 77/773 - loss 0.11510914 - time (sec): 1.69 - samples/sec: 7063.17 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-20 09:16:49,141 epoch 6 - iter 154/773 - loss 0.12357112 - time (sec): 3.41 - samples/sec: 6951.14 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-20 09:16:50,894 epoch 6 - iter 231/773 - loss 0.13493875 - time (sec): 5.16 - samples/sec: 6930.16 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-20 09:16:52,666 epoch 6 - iter 308/773 - loss 0.13607145 - time (sec): 6.94 - samples/sec: 7020.17 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-20 09:16:54,438 epoch 6 - iter 385/773 - loss 0.14047184 - time (sec): 8.71 - samples/sec: 6924.28 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-20 09:16:56,257 epoch 6 - iter 462/773 - loss 0.13593672 - time (sec): 10.53 - samples/sec: 6963.41 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-20 09:16:57,977 epoch 6 - iter 539/773 - loss 0.13231574 - time (sec): 12.25 - samples/sec: 7002.98 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-20 09:16:59,741 epoch 6 - iter 616/773 - loss 0.13109122 - time (sec): 14.01 - samples/sec: 7059.51 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-20 09:17:01,314 epoch 6 - iter 693/773 - loss 0.13015771 - time (sec): 15.58 - samples/sec: 7092.09 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-20 09:17:03,013 epoch 6 - iter 770/773 - loss 0.13172020 - time (sec): 17.28 - samples/sec: 7161.60 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-20 09:17:03,081 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-20 09:17:03,082 EPOCH 6 done: loss 0.1316 - lr: 0.000013
164
+ 2023-10-20 09:17:04,172 DEV : loss 0.07792612910270691 - f1-score (micro avg) 0.5833
165
+ 2023-10-20 09:17:04,184 saving best model
166
+ 2023-10-20 09:17:04,222 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-20 09:17:05,950 epoch 7 - iter 77/773 - loss 0.12524588 - time (sec): 1.73 - samples/sec: 7772.00 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-20 09:17:07,631 epoch 7 - iter 154/773 - loss 0.12230570 - time (sec): 3.41 - samples/sec: 7297.43 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-20 09:17:09,492 epoch 7 - iter 231/773 - loss 0.11811755 - time (sec): 5.27 - samples/sec: 7190.68 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-20 09:17:11,333 epoch 7 - iter 308/773 - loss 0.12745433 - time (sec): 7.11 - samples/sec: 6958.52 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-20 09:17:12,836 epoch 7 - iter 385/773 - loss 0.12730702 - time (sec): 8.61 - samples/sec: 7215.29 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-20 09:17:14,570 epoch 7 - iter 462/773 - loss 0.12624463 - time (sec): 10.35 - samples/sec: 7225.78 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-20 09:17:16,355 epoch 7 - iter 539/773 - loss 0.12879208 - time (sec): 12.13 - samples/sec: 7200.24 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-20 09:17:18,072 epoch 7 - iter 616/773 - loss 0.12718972 - time (sec): 13.85 - samples/sec: 7220.27 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-20 09:17:19,851 epoch 7 - iter 693/773 - loss 0.12645319 - time (sec): 15.63 - samples/sec: 7147.23 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-20 09:17:21,728 epoch 7 - iter 770/773 - loss 0.12643290 - time (sec): 17.51 - samples/sec: 7072.56 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-20 09:17:21,794 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-20 09:17:21,795 EPOCH 7 done: loss 0.1262 - lr: 0.000010
179
+ 2023-10-20 09:17:22,891 DEV : loss 0.0776781365275383 - f1-score (micro avg) 0.5872
180
+ 2023-10-20 09:17:22,903 saving best model
181
+ 2023-10-20 09:17:22,938 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-20 09:17:24,719 epoch 8 - iter 77/773 - loss 0.10583346 - time (sec): 1.78 - samples/sec: 6834.39 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-20 09:17:26,504 epoch 8 - iter 154/773 - loss 0.12530026 - time (sec): 3.57 - samples/sec: 6987.51 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-20 09:17:28,247 epoch 8 - iter 231/773 - loss 0.12693031 - time (sec): 5.31 - samples/sec: 6952.20 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-20 09:17:29,969 epoch 8 - iter 308/773 - loss 0.12130837 - time (sec): 7.03 - samples/sec: 7006.83 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-20 09:17:31,722 epoch 8 - iter 385/773 - loss 0.11920464 - time (sec): 8.78 - samples/sec: 7095.66 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-20 09:17:33,516 epoch 8 - iter 462/773 - loss 0.12199633 - time (sec): 10.58 - samples/sec: 7154.64 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-20 09:17:35,189 epoch 8 - iter 539/773 - loss 0.12080649 - time (sec): 12.25 - samples/sec: 7113.25 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-20 09:17:37,007 epoch 8 - iter 616/773 - loss 0.12327536 - time (sec): 14.07 - samples/sec: 7011.62 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-20 09:17:38,708 epoch 8 - iter 693/773 - loss 0.12158899 - time (sec): 15.77 - samples/sec: 7028.09 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-20 09:17:40,487 epoch 8 - iter 770/773 - loss 0.12160387 - time (sec): 17.55 - samples/sec: 7063.84 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-20 09:17:40,546 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-20 09:17:40,547 EPOCH 8 done: loss 0.1214 - lr: 0.000007
194
+ 2023-10-20 09:17:41,635 DEV : loss 0.078594870865345 - f1-score (micro avg) 0.594
195
+ 2023-10-20 09:17:41,648 saving best model
196
+ 2023-10-20 09:17:41,684 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-20 09:17:43,444 epoch 9 - iter 77/773 - loss 0.11865783 - time (sec): 1.76 - samples/sec: 6953.78 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-20 09:17:45,352 epoch 9 - iter 154/773 - loss 0.11779580 - time (sec): 3.67 - samples/sec: 6731.92 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-20 09:17:47,177 epoch 9 - iter 231/773 - loss 0.11079074 - time (sec): 5.49 - samples/sec: 6945.20 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-20 09:17:48,925 epoch 9 - iter 308/773 - loss 0.11269628 - time (sec): 7.24 - samples/sec: 6912.83 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-20 09:17:50,690 epoch 9 - iter 385/773 - loss 0.11775128 - time (sec): 9.01 - samples/sec: 7031.36 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-20 09:17:52,442 epoch 9 - iter 462/773 - loss 0.12178041 - time (sec): 10.76 - samples/sec: 6994.68 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-20 09:17:54,230 epoch 9 - iter 539/773 - loss 0.12266438 - time (sec): 12.55 - samples/sec: 7009.50 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-20 09:17:55,948 epoch 9 - iter 616/773 - loss 0.12347143 - time (sec): 14.26 - samples/sec: 7020.21 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-20 09:17:57,590 epoch 9 - iter 693/773 - loss 0.12164974 - time (sec): 15.91 - samples/sec: 7013.24 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-20 09:17:59,268 epoch 9 - iter 770/773 - loss 0.12028417 - time (sec): 17.58 - samples/sec: 7045.20 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-20 09:17:59,328 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-20 09:17:59,328 EPOCH 9 done: loss 0.1202 - lr: 0.000003
209
+ 2023-10-20 09:18:00,418 DEV : loss 0.07745374739170074 - f1-score (micro avg) 0.5978
210
+ 2023-10-20 09:18:00,430 saving best model
211
+ 2023-10-20 09:18:00,463 ----------------------------------------------------------------------------------------------------
212
+ 2023-10-20 09:18:02,196 epoch 10 - iter 77/773 - loss 0.13395817 - time (sec): 1.73 - samples/sec: 6936.02 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-20 09:18:03,975 epoch 10 - iter 154/773 - loss 0.12555449 - time (sec): 3.51 - samples/sec: 7085.61 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-20 09:18:05,577 epoch 10 - iter 231/773 - loss 0.12235248 - time (sec): 5.11 - samples/sec: 7455.37 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-20 09:18:07,115 epoch 10 - iter 308/773 - loss 0.11713785 - time (sec): 6.65 - samples/sec: 7646.12 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-20 09:18:08,958 epoch 10 - iter 385/773 - loss 0.11947063 - time (sec): 8.49 - samples/sec: 7426.05 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-20 09:18:10,695 epoch 10 - iter 462/773 - loss 0.11681252 - time (sec): 10.23 - samples/sec: 7355.83 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-20 09:18:12,412 epoch 10 - iter 539/773 - loss 0.11331848 - time (sec): 11.95 - samples/sec: 7367.65 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-20 09:18:14,164 epoch 10 - iter 616/773 - loss 0.11310343 - time (sec): 13.70 - samples/sec: 7264.87 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-20 09:18:15,932 epoch 10 - iter 693/773 - loss 0.11715195 - time (sec): 15.47 - samples/sec: 7228.65 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-20 09:18:17,637 epoch 10 - iter 770/773 - loss 0.11898981 - time (sec): 17.17 - samples/sec: 7219.65 - lr: 0.000000 - momentum: 0.000000
222
+ 2023-10-20 09:18:17,698 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-20 09:18:17,698 EPOCH 10 done: loss 0.1189 - lr: 0.000000
224
+ 2023-10-20 09:18:18,836 DEV : loss 0.07805749028921127 - f1-score (micro avg) 0.5968
225
+ 2023-10-20 09:18:18,880 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-20 09:18:18,881 Loading model from best epoch ...
227
+ 2023-10-20 09:18:18,958 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 09:18:21,824
229
+ Results:
230
+ - F-score (micro) 0.5601
231
+ - F-score (macro) 0.2106
232
+ - Accuracy 0.4021
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ LOC 0.6210 0.6427 0.6317 946
238
+ BUILDING 0.0000 0.0000 0.0000 185
239
+ STREET 0.0000 0.0000 0.0000 56
240
+
241
+ micro avg 0.6179 0.5122 0.5601 1187
242
+ macro avg 0.2070 0.2142 0.2106 1187
243
+ weighted avg 0.4949 0.5122 0.5034 1187
244
+
245
+ 2023-10-20 09:18:21,824 ----------------------------------------------------------------------------------------------------