Hugging Face's logo

hmbert-tiny
/
flair-hipe-2022-topres19th-en

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
12099be
·
1 Parent(s): e286828

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.1697793053.46dc0c540dd0.5704.1 +3 -0
  5. test.tsv +0 -0
  6. training.log +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:164bea4ce6b698ac455526a18bf53e73b187a9efddc2dbb406fa771d5effd0f5
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 09:11:17 0.0000 0.7972 0.1220 0.0000 0.0000 0.0000 0.0000
3
+ 2 09:11:42 0.0000 0.1756 0.0904 0.6541 0.4388 0.5253 0.3688
4
+ 3 09:12:07 0.0000 0.1439 0.0873 0.6429 0.5316 0.5820 0.4300
5
+ 4 09:12:32 0.0000 0.1315 0.0871 0.5885 0.6034 0.5958 0.4483
6
+ 5 09:12:57 0.0000 0.1176 0.0894 0.6620 0.5949 0.6267 0.4879
7
+ 6 09:13:22 0.0000 0.1120 0.0940 0.6444 0.6118 0.6277 0.4833
8
+ 7 09:13:47 0.0000 0.1047 0.0970 0.5821 0.6582 0.6178 0.4671
9
+ 8 09:14:12 0.0000 0.0999 0.0993 0.6610 0.6582 0.6596 0.5132
10
+ 9 09:14:37 0.0000 0.0955 0.1032 0.6828 0.6540 0.6681 0.5236
11
+ 10 09:15:02 0.0000 0.0914 0.1045 0.7009 0.6329 0.6652 0.5190
runs/events.out.tfevents.1697793053.46dc0c540dd0.5704.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fde4dc8347dbde64d982472d6196ada14d8ea0e7c34bd6507d6a8fc492fedd7
3
+ size 864636
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-20 09:10:53,344 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-20 09:10:53,345 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 09:10:53,345 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-20 09:10:53,345 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 09:10:53,345 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-20 09:10:53,345 Train: 6183 sentences
55
+ 2023-10-20 09:10:53,345 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-20 09:10:53,345 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-20 09:10:53,345 Training Params:
58
+ 2023-10-20 09:10:53,345 - learning_rate: "5e-05"
59
+ 2023-10-20 09:10:53,345 - mini_batch_size: "4"
60
+ 2023-10-20 09:10:53,345 - max_epochs: "10"
61
+ 2023-10-20 09:10:53,345 - shuffle: "True"
62
+ 2023-10-20 09:10:53,345 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-20 09:10:53,345 Plugins:
64
+ 2023-10-20 09:10:53,345 - TensorboardLogger
65
+ 2023-10-20 09:10:53,345 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-20 09:10:53,345 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-20 09:10:53,345 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-20 09:10:53,345 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-20 09:10:53,345 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-20 09:10:53,345 Computation:
71
+ 2023-10-20 09:10:53,346 - compute on device: cuda:0
72
+ 2023-10-20 09:10:53,346 - embedding storage: none
73
+ 2023-10-20 09:10:53,346 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-20 09:10:53,346 Model training base path: "hmbench-topres19th/en-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-20 09:10:53,346 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-20 09:10:53,346 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-20 09:10:53,346 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-20 09:10:55,493 epoch 1 - iter 154/1546 - loss 3.21325929 - time (sec): 2.15 - samples/sec: 5915.84 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-20 09:10:57,852 epoch 1 - iter 308/1546 - loss 2.73136394 - time (sec): 4.51 - samples/sec: 5409.73 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-20 09:11:00,247 epoch 1 - iter 462/1546 - loss 2.10367644 - time (sec): 6.90 - samples/sec: 5296.07 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-20 09:11:02,599 epoch 1 - iter 616/1546 - loss 1.64790228 - time (sec): 9.25 - samples/sec: 5332.98 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-20 09:11:04,927 epoch 1 - iter 770/1546 - loss 1.36724939 - time (sec): 11.58 - samples/sec: 5307.28 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-20 09:11:07,272 epoch 1 - iter 924/1546 - loss 1.19033908 - time (sec): 13.93 - samples/sec: 5247.46 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-20 09:11:09,645 epoch 1 - iter 1078/1546 - loss 1.05213539 - time (sec): 16.30 - samples/sec: 5262.07 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-20 09:11:12,045 epoch 1 - iter 1232/1546 - loss 0.94506634 - time (sec): 18.70 - samples/sec: 5282.40 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-20 09:11:14,435 epoch 1 - iter 1386/1546 - loss 0.86827104 - time (sec): 21.09 - samples/sec: 5248.10 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-20 09:11:16,826 epoch 1 - iter 1540/1546 - loss 0.80053304 - time (sec): 23.48 - samples/sec: 5269.99 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-20 09:11:16,921 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-20 09:11:16,921 EPOCH 1 done: loss 0.7972 - lr: 0.000050
90
+ 2023-10-20 09:11:17,909 DEV : loss 0.12200508266687393 - f1-score (micro avg) 0.0
91
+ 2023-10-20 09:11:17,920 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-20 09:11:20,258 epoch 2 - iter 154/1546 - loss 0.20037114 - time (sec): 2.34 - samples/sec: 5316.00 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-20 09:11:22,588 epoch 2 - iter 308/1546 - loss 0.19373175 - time (sec): 4.67 - samples/sec: 5136.35 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-20 09:11:24,881 epoch 2 - iter 462/1546 - loss 0.19375140 - time (sec): 6.96 - samples/sec: 5094.82 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-20 09:11:27,027 epoch 2 - iter 616/1546 - loss 0.18263563 - time (sec): 9.11 - samples/sec: 5310.30 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-20 09:11:29,497 epoch 2 - iter 770/1546 - loss 0.18103908 - time (sec): 11.58 - samples/sec: 5284.82 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-20 09:11:31,857 epoch 2 - iter 924/1546 - loss 0.17969558 - time (sec): 13.94 - samples/sec: 5231.40 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-20 09:11:34,265 epoch 2 - iter 1078/1546 - loss 0.18008258 - time (sec): 16.34 - samples/sec: 5191.02 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-20 09:11:36,727 epoch 2 - iter 1232/1546 - loss 0.17929640 - time (sec): 18.81 - samples/sec: 5185.00 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-20 09:11:39,118 epoch 2 - iter 1386/1546 - loss 0.17901491 - time (sec): 21.20 - samples/sec: 5181.36 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-20 09:11:41,576 epoch 2 - iter 1540/1546 - loss 0.17615955 - time (sec): 23.66 - samples/sec: 5224.96 - lr: 0.000044 - momentum: 0.000000
102
+ 2023-10-20 09:11:41,695 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-20 09:11:41,696 EPOCH 2 done: loss 0.1756 - lr: 0.000044
104
+ 2023-10-20 09:11:42,775 DEV : loss 0.0903642475605011 - f1-score (micro avg) 0.5253
105
+ 2023-10-20 09:11:42,786 saving best model
106
+ 2023-10-20 09:11:42,817 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-20 09:11:45,188 epoch 3 - iter 154/1546 - loss 0.14713794 - time (sec): 2.37 - samples/sec: 4827.32 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-20 09:11:47,561 epoch 3 - iter 308/1546 - loss 0.13527283 - time (sec): 4.74 - samples/sec: 5079.03 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-20 09:11:49,960 epoch 3 - iter 462/1546 - loss 0.13016097 - time (sec): 7.14 - samples/sec: 5104.38 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-20 09:11:52,338 epoch 3 - iter 616/1546 - loss 0.14160502 - time (sec): 9.52 - samples/sec: 5192.01 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-20 09:11:54,684 epoch 3 - iter 770/1546 - loss 0.14258890 - time (sec): 11.87 - samples/sec: 5170.42 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-20 09:11:57,136 epoch 3 - iter 924/1546 - loss 0.14415601 - time (sec): 14.32 - samples/sec: 5230.21 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-20 09:11:59,513 epoch 3 - iter 1078/1546 - loss 0.14532688 - time (sec): 16.69 - samples/sec: 5234.95 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-20 09:12:01,862 epoch 3 - iter 1232/1546 - loss 0.14491438 - time (sec): 19.04 - samples/sec: 5249.51 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-20 09:12:04,229 epoch 3 - iter 1386/1546 - loss 0.14477599 - time (sec): 21.41 - samples/sec: 5190.93 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-20 09:12:06,637 epoch 3 - iter 1540/1546 - loss 0.14405777 - time (sec): 23.82 - samples/sec: 5192.53 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-20 09:12:06,735 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-20 09:12:06,735 EPOCH 3 done: loss 0.1439 - lr: 0.000039
119
+ 2023-10-20 09:12:07,826 DEV : loss 0.08732243627309799 - f1-score (micro avg) 0.582
120
+ 2023-10-20 09:12:07,838 saving best model
121
+ 2023-10-20 09:12:07,879 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-20 09:12:10,199 epoch 4 - iter 154/1546 - loss 0.13584888 - time (sec): 2.32 - samples/sec: 5435.78 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-20 09:12:12,467 epoch 4 - iter 308/1546 - loss 0.12847974 - time (sec): 4.59 - samples/sec: 5415.61 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-20 09:12:14,783 epoch 4 - iter 462/1546 - loss 0.13330930 - time (sec): 6.90 - samples/sec: 5182.03 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-20 09:12:17,100 epoch 4 - iter 616/1546 - loss 0.13475968 - time (sec): 9.22 - samples/sec: 5255.10 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-20 09:12:19,561 epoch 4 - iter 770/1546 - loss 0.13542888 - time (sec): 11.68 - samples/sec: 5195.27 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-20 09:12:21,912 epoch 4 - iter 924/1546 - loss 0.13268362 - time (sec): 14.03 - samples/sec: 5195.45 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-20 09:12:24,358 epoch 4 - iter 1078/1546 - loss 0.12936714 - time (sec): 16.48 - samples/sec: 5228.09 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-20 09:12:26,745 epoch 4 - iter 1232/1546 - loss 0.12991586 - time (sec): 18.87 - samples/sec: 5254.54 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-20 09:12:29,152 epoch 4 - iter 1386/1546 - loss 0.13125019 - time (sec): 21.27 - samples/sec: 5226.79 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-20 09:12:31,639 epoch 4 - iter 1540/1546 - loss 0.13168722 - time (sec): 23.76 - samples/sec: 5212.55 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-20 09:12:31,729 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-20 09:12:31,729 EPOCH 4 done: loss 0.1315 - lr: 0.000033
134
+ 2023-10-20 09:12:32,821 DEV : loss 0.08709011971950531 - f1-score (micro avg) 0.5958
135
+ 2023-10-20 09:12:32,833 saving best model
136
+ 2023-10-20 09:12:32,866 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-20 09:12:35,352 epoch 5 - iter 154/1546 - loss 0.11043084 - time (sec): 2.49 - samples/sec: 4962.99 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-20 09:12:37,696 epoch 5 - iter 308/1546 - loss 0.11299564 - time (sec): 4.83 - samples/sec: 4959.49 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-20 09:12:40,158 epoch 5 - iter 462/1546 - loss 0.11388012 - time (sec): 7.29 - samples/sec: 4934.01 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-20 09:12:42,525 epoch 5 - iter 616/1546 - loss 0.11338971 - time (sec): 9.66 - samples/sec: 5096.42 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-20 09:12:44,869 epoch 5 - iter 770/1546 - loss 0.11529993 - time (sec): 12.00 - samples/sec: 5183.06 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-20 09:12:47,199 epoch 5 - iter 924/1546 - loss 0.11409167 - time (sec): 14.33 - samples/sec: 5187.40 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-20 09:12:49,549 epoch 5 - iter 1078/1546 - loss 0.11280483 - time (sec): 16.68 - samples/sec: 5176.64 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-20 09:12:51,894 epoch 5 - iter 1232/1546 - loss 0.11613611 - time (sec): 19.03 - samples/sec: 5190.84 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-20 09:12:54,227 epoch 5 - iter 1386/1546 - loss 0.11738124 - time (sec): 21.36 - samples/sec: 5237.78 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-20 09:12:56,571 epoch 5 - iter 1540/1546 - loss 0.11782489 - time (sec): 23.70 - samples/sec: 5223.13 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-20 09:12:56,657 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-20 09:12:56,658 EPOCH 5 done: loss 0.1176 - lr: 0.000028
149
+ 2023-10-20 09:12:57,747 DEV : loss 0.08939941972494125 - f1-score (micro avg) 0.6267
150
+ 2023-10-20 09:12:57,758 saving best model
151
+ 2023-10-20 09:12:57,799 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-20 09:13:00,159 epoch 6 - iter 154/1546 - loss 0.08872161 - time (sec): 2.36 - samples/sec: 5059.99 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-20 09:13:02,464 epoch 6 - iter 308/1546 - loss 0.09968058 - time (sec): 4.66 - samples/sec: 5084.02 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-20 09:13:04,684 epoch 6 - iter 462/1546 - loss 0.11229809 - time (sec): 6.88 - samples/sec: 5199.05 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-20 09:13:06,997 epoch 6 - iter 616/1546 - loss 0.11419551 - time (sec): 9.20 - samples/sec: 5295.49 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-20 09:13:09,350 epoch 6 - iter 770/1546 - loss 0.11917538 - time (sec): 11.55 - samples/sec: 5221.45 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-20 09:13:11,733 epoch 6 - iter 924/1546 - loss 0.11515995 - time (sec): 13.93 - samples/sec: 5261.77 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-20 09:13:14,094 epoch 6 - iter 1078/1546 - loss 0.11259375 - time (sec): 16.29 - samples/sec: 5263.95 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-20 09:13:16,462 epoch 6 - iter 1232/1546 - loss 0.11096846 - time (sec): 18.66 - samples/sec: 5300.25 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-20 09:13:18,893 epoch 6 - iter 1386/1546 - loss 0.10972238 - time (sec): 21.09 - samples/sec: 5240.06 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-20 09:13:21,286 epoch 6 - iter 1540/1546 - loss 0.11215844 - time (sec): 23.49 - samples/sec: 5270.28 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-20 09:13:21,383 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-20 09:13:21,383 EPOCH 6 done: loss 0.1120 - lr: 0.000022
164
+ 2023-10-20 09:13:22,455 DEV : loss 0.09400177001953125 - f1-score (micro avg) 0.6277
165
+ 2023-10-20 09:13:22,466 saving best model
166
+ 2023-10-20 09:13:22,504 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-20 09:13:24,908 epoch 7 - iter 154/1546 - loss 0.09411116 - time (sec): 2.40 - samples/sec: 5586.60 - lr: 0.000022 - momentum: 0.000000
168
+ 2023-10-20 09:13:27,265 epoch 7 - iter 308/1546 - loss 0.09632697 - time (sec): 4.76 - samples/sec: 5224.96 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-20 09:13:29,641 epoch 7 - iter 462/1546 - loss 0.09562559 - time (sec): 7.14 - samples/sec: 5309.35 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-20 09:13:31,989 epoch 7 - iter 616/1546 - loss 0.10402549 - time (sec): 9.48 - samples/sec: 5216.81 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-20 09:13:34,288 epoch 7 - iter 770/1546 - loss 0.10461845 - time (sec): 11.78 - samples/sec: 5274.04 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-20 09:13:36,410 epoch 7 - iter 924/1546 - loss 0.10415072 - time (sec): 13.90 - samples/sec: 5376.86 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-20 09:13:38,645 epoch 7 - iter 1078/1546 - loss 0.10743332 - time (sec): 16.14 - samples/sec: 5412.25 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-20 09:13:41,006 epoch 7 - iter 1232/1546 - loss 0.10558366 - time (sec): 18.50 - samples/sec: 5404.84 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-20 09:13:43,579 epoch 7 - iter 1386/1546 - loss 0.10551425 - time (sec): 21.07 - samples/sec: 5300.25 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-20 09:13:45,933 epoch 7 - iter 1540/1546 - loss 0.10494098 - time (sec): 23.43 - samples/sec: 5284.63 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-20 09:13:46,027 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-20 09:13:46,027 EPOCH 7 done: loss 0.1047 - lr: 0.000017
179
+ 2023-10-20 09:13:47,115 DEV : loss 0.09695922583341599 - f1-score (micro avg) 0.6178
180
+ 2023-10-20 09:13:47,126 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-20 09:13:49,425 epoch 8 - iter 154/1546 - loss 0.08797545 - time (sec): 2.30 - samples/sec: 5296.74 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-20 09:13:51,802 epoch 8 - iter 308/1546 - loss 0.10794391 - time (sec): 4.68 - samples/sec: 5329.23 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-20 09:13:54,171 epoch 8 - iter 462/1546 - loss 0.10855675 - time (sec): 7.04 - samples/sec: 5239.55 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-20 09:13:56,557 epoch 8 - iter 616/1546 - loss 0.10232047 - time (sec): 9.43 - samples/sec: 5223.60 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-20 09:13:58,954 epoch 8 - iter 770/1546 - loss 0.09935293 - time (sec): 11.83 - samples/sec: 5269.56 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-20 09:14:01,388 epoch 8 - iter 924/1546 - loss 0.10163157 - time (sec): 14.26 - samples/sec: 5306.60 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-20 09:14:03,750 epoch 8 - iter 1078/1546 - loss 0.10110793 - time (sec): 16.62 - samples/sec: 5242.19 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-20 09:14:06,284 epoch 8 - iter 1232/1546 - loss 0.10225598 - time (sec): 19.16 - samples/sec: 5149.27 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-20 09:14:08,735 epoch 8 - iter 1386/1546 - loss 0.10032493 - time (sec): 21.61 - samples/sec: 5128.91 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-20 09:14:11,087 epoch 8 - iter 1540/1546 - loss 0.10017520 - time (sec): 23.96 - samples/sec: 5173.61 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-20 09:14:11,172 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-20 09:14:11,173 EPOCH 8 done: loss 0.0999 - lr: 0.000011
193
+ 2023-10-20 09:14:12,276 DEV : loss 0.0992686077952385 - f1-score (micro avg) 0.6596
194
+ 2023-10-20 09:14:12,288 saving best model
195
+ 2023-10-20 09:14:12,327 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-20 09:14:14,673 epoch 9 - iter 154/1546 - loss 0.09650209 - time (sec): 2.34 - samples/sec: 5217.56 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-20 09:14:17,050 epoch 9 - iter 308/1546 - loss 0.09691759 - time (sec): 4.72 - samples/sec: 5228.76 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-20 09:14:19,749 epoch 9 - iter 462/1546 - loss 0.08896325 - time (sec): 7.42 - samples/sec: 5141.17 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-20 09:14:22,118 epoch 9 - iter 616/1546 - loss 0.09060288 - time (sec): 9.79 - samples/sec: 5112.64 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-20 09:14:24,967 epoch 9 - iter 770/1546 - loss 0.09200760 - time (sec): 12.64 - samples/sec: 5010.50 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-20 09:14:27,319 epoch 9 - iter 924/1546 - loss 0.09609571 - time (sec): 14.99 - samples/sec: 5019.42 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-20 09:14:29,709 epoch 9 - iter 1078/1546 - loss 0.09667665 - time (sec): 17.38 - samples/sec: 5059.47 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-20 09:14:31,891 epoch 9 - iter 1232/1546 - loss 0.09768930 - time (sec): 19.56 - samples/sec: 5118.55 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-20 09:14:33,996 epoch 9 - iter 1386/1546 - loss 0.09587500 - time (sec): 21.67 - samples/sec: 5148.30 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-20 09:14:36,398 epoch 9 - iter 1540/1546 - loss 0.09560318 - time (sec): 24.07 - samples/sec: 5146.90 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-20 09:14:36,489 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-20 09:14:36,489 EPOCH 9 done: loss 0.0955 - lr: 0.000006
208
+ 2023-10-20 09:14:37,585 DEV : loss 0.10322442650794983 - f1-score (micro avg) 0.6681
209
+ 2023-10-20 09:14:37,599 saving best model
210
+ 2023-10-20 09:14:37,640 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-20 09:14:40,061 epoch 10 - iter 154/1546 - loss 0.10143281 - time (sec): 2.42 - samples/sec: 4964.82 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-20 09:14:42,441 epoch 10 - iter 308/1546 - loss 0.09450071 - time (sec): 4.80 - samples/sec: 5182.99 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-20 09:14:44,855 epoch 10 - iter 462/1546 - loss 0.09346281 - time (sec): 7.21 - samples/sec: 5283.85 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-20 09:14:47,239 epoch 10 - iter 616/1546 - loss 0.08973317 - time (sec): 9.60 - samples/sec: 5299.01 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-20 09:14:49,607 epoch 10 - iter 770/1546 - loss 0.09059757 - time (sec): 11.97 - samples/sec: 5271.13 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-20 09:14:51,921 epoch 10 - iter 924/1546 - loss 0.08753361 - time (sec): 14.28 - samples/sec: 5270.05 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-20 09:14:54,314 epoch 10 - iter 1078/1546 - loss 0.08603652 - time (sec): 16.67 - samples/sec: 5279.61 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-20 09:14:56,639 epoch 10 - iter 1232/1546 - loss 0.08568308 - time (sec): 19.00 - samples/sec: 5238.99 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-20 09:14:58,992 epoch 10 - iter 1386/1546 - loss 0.09015758 - time (sec): 21.35 - samples/sec: 5236.68 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-20 09:15:01,422 epoch 10 - iter 1540/1546 - loss 0.09146122 - time (sec): 23.78 - samples/sec: 5213.58 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-20 09:15:01,505 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-20 09:15:01,505 EPOCH 10 done: loss 0.0914 - lr: 0.000000
223
+ 2023-10-20 09:15:02,613 DEV : loss 0.10447753965854645 - f1-score (micro avg) 0.6652
224
+ 2023-10-20 09:15:02,654 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-20 09:15:02,654 Loading model from best epoch ...
226
+ 2023-10-20 09:15:02,745 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
227
+ 2023-10-20 09:15:05,674
228
+ Results:
229
+ - F-score (micro) 0.5997
230
+ - F-score (macro) 0.4121
231
+ - Accuracy 0.4447
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.6404 0.6776 0.6584 946
237
+ BUILDING 0.3924 0.1676 0.2348 185
238
+ STREET 0.8571 0.2143 0.3429 56
239
+
240
+ micro avg 0.6252 0.5762 0.5997 1187
241
+ macro avg 0.6300 0.3531 0.4121 1187
242
+ weighted avg 0.6119 0.5762 0.5775 1187
243
+
244
+ 2023-10-20 09:15:05,674 ----------------------------------------------------------------------------------------------------