Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbert_tiny-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
f7fd11a
·
1 Parent(s): 8a6ae4f

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.1697669756.46dc0c540dd0.3571.14 +3 -0
  5. test.tsv +0 -0
  6. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfe6367477ddaffe29e0aac3185fc2ac034064acb996cf5b2e1feea25de4c865
3
+ size 19045922
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 22:56:16 0.0000 1.2718 0.3835 0.0000 0.0000 0.0000 0.0000
3
+ 2 22:56:36 0.0000 0.2406 0.2568 0.6818 0.0620 0.1136 0.0605
4
+ 3 22:56:56 0.0000 0.1986 0.2375 0.6234 0.1488 0.2402 0.1382
5
+ 4 22:57:16 0.0000 0.1804 0.2189 0.5694 0.2459 0.3434 0.2131
6
+ 5 22:57:36 0.0000 0.1721 0.2160 0.6129 0.2552 0.3603 0.2254
7
+ 6 22:57:56 0.0000 0.1627 0.2046 0.5962 0.3554 0.4453 0.2958
8
+ 7 22:58:16 0.0000 0.1588 0.2028 0.5785 0.3502 0.4363 0.2875
9
+ 8 22:58:36 0.0000 0.1528 0.2011 0.5934 0.3543 0.4437 0.2937
10
+ 9 22:58:55 0.0000 0.1524 0.1940 0.5676 0.3905 0.4627 0.3116
11
+ 10 22:59:15 0.0000 0.1503 0.1958 0.5714 0.3802 0.4566 0.3062
runs/events.out.tfevents.1697669756.46dc0c540dd0.3571.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e975fad10449c8963385f125811b637f5137de082b98cd1ba0a2111c286ce6
3
+ size 407048
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 22:55:56,510 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 22:55:56,510 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
+ 2023-10-18 22:55:56,510 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 22:55:56,510 MultiCorpus: 5777 train + 722 dev + 723 test sentences
52
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
53
+ 2023-10-18 22:55:56,510 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 22:55:56,510 Train: 5777 sentences
55
+ 2023-10-18 22:55:56,510 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 22:55:56,510 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 22:55:56,510 Training Params:
58
+ 2023-10-18 22:55:56,510 - learning_rate: "3e-05"
59
+ 2023-10-18 22:55:56,510 - mini_batch_size: "8"
60
+ 2023-10-18 22:55:56,510 - max_epochs: "10"
61
+ 2023-10-18 22:55:56,510 - shuffle: "True"
62
+ 2023-10-18 22:55:56,510 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 22:55:56,510 Plugins:
64
+ 2023-10-18 22:55:56,511 - TensorboardLogger
65
+ 2023-10-18 22:55:56,511 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 22:55:56,511 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 22:55:56,511 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 22:55:56,511 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 22:55:56,511 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 22:55:56,511 Computation:
71
+ 2023-10-18 22:55:56,511 - compute on device: cuda:0
72
+ 2023-10-18 22:55:56,511 - embedding storage: none
73
+ 2023-10-18 22:55:56,511 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 22:55:56,511 Model training base path: "hmbench-icdar/nl-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-18 22:55:56,511 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 22:55:56,511 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 22:55:56,511 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 22:55:58,254 epoch 1 - iter 72/723 - loss 3.42262036 - time (sec): 1.74 - samples/sec: 9302.87 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 22:56:00,005 epoch 1 - iter 144/723 - loss 3.24227113 - time (sec): 3.49 - samples/sec: 9609.69 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 22:56:01,802 epoch 1 - iter 216/723 - loss 2.95510672 - time (sec): 5.29 - samples/sec: 9718.03 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 22:56:03,598 epoch 1 - iter 288/723 - loss 2.57569294 - time (sec): 7.09 - samples/sec: 9834.91 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 22:56:05,446 epoch 1 - iter 360/723 - loss 2.21089906 - time (sec): 8.93 - samples/sec: 9689.02 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 22:56:07,307 epoch 1 - iter 432/723 - loss 1.92171641 - time (sec): 10.80 - samples/sec: 9584.33 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 22:56:09,078 epoch 1 - iter 504/723 - loss 1.70254512 - time (sec): 12.57 - samples/sec: 9580.68 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 22:56:10,968 epoch 1 - iter 576/723 - loss 1.52679826 - time (sec): 14.46 - samples/sec: 9625.95 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 22:56:12,823 epoch 1 - iter 648/723 - loss 1.38048154 - time (sec): 16.31 - samples/sec: 9688.82 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 22:56:14,681 epoch 1 - iter 720/723 - loss 1.27452802 - time (sec): 18.17 - samples/sec: 9669.11 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-18 22:56:14,747 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 22:56:14,747 EPOCH 1 done: loss 1.2718 - lr: 0.000030
90
+ 2023-10-18 22:56:16,024 DEV : loss 0.383542537689209 - f1-score (micro avg) 0.0
91
+ 2023-10-18 22:56:16,039 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 22:56:17,801 epoch 2 - iter 72/723 - loss 0.26690832 - time (sec): 1.76 - samples/sec: 10084.86 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 22:56:19,552 epoch 2 - iter 144/723 - loss 0.27198191 - time (sec): 3.51 - samples/sec: 9845.28 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 22:56:21,325 epoch 2 - iter 216/723 - loss 0.26855355 - time (sec): 5.28 - samples/sec: 9696.90 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 22:56:23,331 epoch 2 - iter 288/723 - loss 0.25857843 - time (sec): 7.29 - samples/sec: 9665.14 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 22:56:25,245 epoch 2 - iter 360/723 - loss 0.25269809 - time (sec): 9.21 - samples/sec: 9480.00 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 22:56:27,132 epoch 2 - iter 432/723 - loss 0.24641116 - time (sec): 11.09 - samples/sec: 9490.38 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 22:56:28,913 epoch 2 - iter 504/723 - loss 0.24268049 - time (sec): 12.87 - samples/sec: 9567.70 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 22:56:30,665 epoch 2 - iter 576/723 - loss 0.24535974 - time (sec): 14.63 - samples/sec: 9572.90 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 22:56:32,433 epoch 2 - iter 648/723 - loss 0.24136581 - time (sec): 16.39 - samples/sec: 9638.28 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 22:56:34,226 epoch 2 - iter 720/723 - loss 0.24079891 - time (sec): 18.19 - samples/sec: 9647.42 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 22:56:34,291 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 22:56:34,291 EPOCH 2 done: loss 0.2406 - lr: 0.000027
104
+ 2023-10-18 22:56:36,363 DEV : loss 0.2568000555038452 - f1-score (micro avg) 0.1136
105
+ 2023-10-18 22:56:36,378 saving best model
106
+ 2023-10-18 22:56:36,409 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 22:56:38,173 epoch 3 - iter 72/723 - loss 0.20902337 - time (sec): 1.76 - samples/sec: 10632.39 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 22:56:40,014 epoch 3 - iter 144/723 - loss 0.21487658 - time (sec): 3.60 - samples/sec: 10443.35 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 22:56:41,785 epoch 3 - iter 216/723 - loss 0.20843859 - time (sec): 5.38 - samples/sec: 10261.69 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-18 22:56:43,590 epoch 3 - iter 288/723 - loss 0.20311414 - time (sec): 7.18 - samples/sec: 10178.10 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 22:56:45,423 epoch 3 - iter 360/723 - loss 0.20319710 - time (sec): 9.01 - samples/sec: 10025.50 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 22:56:47,180 epoch 3 - iter 432/723 - loss 0.20226321 - time (sec): 10.77 - samples/sec: 9889.11 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-18 22:56:48,993 epoch 3 - iter 504/723 - loss 0.20421469 - time (sec): 12.58 - samples/sec: 9890.71 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 22:56:50,707 epoch 3 - iter 576/723 - loss 0.20341312 - time (sec): 14.30 - samples/sec: 9879.51 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 22:56:52,498 epoch 3 - iter 648/723 - loss 0.19940795 - time (sec): 16.09 - samples/sec: 9891.77 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-18 22:56:54,232 epoch 3 - iter 720/723 - loss 0.19888487 - time (sec): 17.82 - samples/sec: 9845.70 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-18 22:56:54,305 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 22:56:54,305 EPOCH 3 done: loss 0.1986 - lr: 0.000023
119
+ 2023-10-18 22:56:56,067 DEV : loss 0.23752760887145996 - f1-score (micro avg) 0.2402
120
+ 2023-10-18 22:56:56,081 saving best model
121
+ 2023-10-18 22:56:56,117 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 22:56:57,864 epoch 4 - iter 72/723 - loss 0.18226854 - time (sec): 1.75 - samples/sec: 9748.99 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 22:56:59,625 epoch 4 - iter 144/723 - loss 0.17750412 - time (sec): 3.51 - samples/sec: 9415.68 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-18 22:57:01,393 epoch 4 - iter 216/723 - loss 0.18220143 - time (sec): 5.28 - samples/sec: 9528.19 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 22:57:03,194 epoch 4 - iter 288/723 - loss 0.18036256 - time (sec): 7.08 - samples/sec: 9602.73 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 22:57:04,967 epoch 4 - iter 360/723 - loss 0.18084117 - time (sec): 8.85 - samples/sec: 9642.48 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-18 22:57:06,777 epoch 4 - iter 432/723 - loss 0.18157715 - time (sec): 10.66 - samples/sec: 9629.56 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 22:57:08,656 epoch 4 - iter 504/723 - loss 0.17979702 - time (sec): 12.54 - samples/sec: 9608.03 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 22:57:10,668 epoch 4 - iter 576/723 - loss 0.18168708 - time (sec): 14.55 - samples/sec: 9652.05 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-18 22:57:12,484 epoch 4 - iter 648/723 - loss 0.18042569 - time (sec): 16.37 - samples/sec: 9619.66 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 22:57:14,305 epoch 4 - iter 720/723 - loss 0.18043801 - time (sec): 18.19 - samples/sec: 9660.63 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-18 22:57:14,373 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 22:57:14,373 EPOCH 4 done: loss 0.1804 - lr: 0.000020
134
+ 2023-10-18 22:57:16,480 DEV : loss 0.21891361474990845 - f1-score (micro avg) 0.3434
135
+ 2023-10-18 22:57:16,495 saving best model
136
+ 2023-10-18 22:57:16,531 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 22:57:18,323 epoch 5 - iter 72/723 - loss 0.17790732 - time (sec): 1.79 - samples/sec: 9958.89 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-18 22:57:20,100 epoch 5 - iter 144/723 - loss 0.17861548 - time (sec): 3.57 - samples/sec: 10105.93 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 22:57:21,842 epoch 5 - iter 216/723 - loss 0.17749356 - time (sec): 5.31 - samples/sec: 10116.70 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 22:57:23,657 epoch 5 - iter 288/723 - loss 0.17769605 - time (sec): 7.13 - samples/sec: 9890.75 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-18 22:57:25,353 epoch 5 - iter 360/723 - loss 0.17341481 - time (sec): 8.82 - samples/sec: 9828.62 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 22:57:27,135 epoch 5 - iter 432/723 - loss 0.17512851 - time (sec): 10.60 - samples/sec: 9813.50 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 22:57:28,937 epoch 5 - iter 504/723 - loss 0.17373162 - time (sec): 12.40 - samples/sec: 9795.38 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-18 22:57:30,802 epoch 5 - iter 576/723 - loss 0.17323872 - time (sec): 14.27 - samples/sec: 9816.46 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 22:57:32,548 epoch 5 - iter 648/723 - loss 0.17259816 - time (sec): 16.02 - samples/sec: 9833.06 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 22:57:34,416 epoch 5 - iter 720/723 - loss 0.17201555 - time (sec): 17.88 - samples/sec: 9836.04 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-18 22:57:34,471 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 22:57:34,471 EPOCH 5 done: loss 0.1721 - lr: 0.000017
149
+ 2023-10-18 22:57:36,235 DEV : loss 0.21598245203495026 - f1-score (micro avg) 0.3603
150
+ 2023-10-18 22:57:36,250 saving best model
151
+ 2023-10-18 22:57:36,284 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 22:57:38,054 epoch 6 - iter 72/723 - loss 0.16484753 - time (sec): 1.77 - samples/sec: 9347.04 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 22:57:39,819 epoch 6 - iter 144/723 - loss 0.15606069 - time (sec): 3.53 - samples/sec: 9582.22 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-18 22:57:41,637 epoch 6 - iter 216/723 - loss 0.15864873 - time (sec): 5.35 - samples/sec: 9773.71 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-18 22:57:43,473 epoch 6 - iter 288/723 - loss 0.15870321 - time (sec): 7.19 - samples/sec: 9828.73 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 22:57:45,196 epoch 6 - iter 360/723 - loss 0.16234323 - time (sec): 8.91 - samples/sec: 9815.47 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-18 22:57:46,945 epoch 6 - iter 432/723 - loss 0.15856690 - time (sec): 10.66 - samples/sec: 9844.04 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-18 22:57:48,750 epoch 6 - iter 504/723 - loss 0.16153975 - time (sec): 12.47 - samples/sec: 9746.37 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 22:57:50,516 epoch 6 - iter 576/723 - loss 0.15864405 - time (sec): 14.23 - samples/sec: 9779.22 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-18 22:57:52,302 epoch 6 - iter 648/723 - loss 0.16169816 - time (sec): 16.02 - samples/sec: 9789.70 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-18 22:57:54,492 epoch 6 - iter 720/723 - loss 0.16273531 - time (sec): 18.21 - samples/sec: 9651.21 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-18 22:57:54,553 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 22:57:54,553 EPOCH 6 done: loss 0.1627 - lr: 0.000013
164
+ 2023-10-18 22:57:56,329 DEV : loss 0.20462197065353394 - f1-score (micro avg) 0.4453
165
+ 2023-10-18 22:57:56,343 saving best model
166
+ 2023-10-18 22:57:56,380 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 22:57:58,120 epoch 7 - iter 72/723 - loss 0.15662991 - time (sec): 1.74 - samples/sec: 9472.72 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-18 22:57:59,877 epoch 7 - iter 144/723 - loss 0.15924704 - time (sec): 3.50 - samples/sec: 9819.69 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-18 22:58:01,664 epoch 7 - iter 216/723 - loss 0.16189171 - time (sec): 5.28 - samples/sec: 9682.85 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 22:58:03,519 epoch 7 - iter 288/723 - loss 0.16308365 - time (sec): 7.14 - samples/sec: 9742.21 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-18 22:58:05,279 epoch 7 - iter 360/723 - loss 0.15997371 - time (sec): 8.90 - samples/sec: 9728.59 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-18 22:58:07,107 epoch 7 - iter 432/723 - loss 0.15929076 - time (sec): 10.73 - samples/sec: 9703.79 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 22:58:08,914 epoch 7 - iter 504/723 - loss 0.15943523 - time (sec): 12.53 - samples/sec: 9763.34 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-18 22:58:10,735 epoch 7 - iter 576/723 - loss 0.15929299 - time (sec): 14.35 - samples/sec: 9753.67 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-18 22:58:12,561 epoch 7 - iter 648/723 - loss 0.16055045 - time (sec): 16.18 - samples/sec: 9764.87 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-18 22:58:14,285 epoch 7 - iter 720/723 - loss 0.15893188 - time (sec): 17.90 - samples/sec: 9809.31 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-18 22:58:14,357 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 22:58:14,357 EPOCH 7 done: loss 0.1588 - lr: 0.000010
179
+ 2023-10-18 22:58:16,151 DEV : loss 0.20282398164272308 - f1-score (micro avg) 0.4363
180
+ 2023-10-18 22:58:16,166 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-18 22:58:17,915 epoch 8 - iter 72/723 - loss 0.17813877 - time (sec): 1.75 - samples/sec: 9433.30 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-18 22:58:19,745 epoch 8 - iter 144/723 - loss 0.16727864 - time (sec): 3.58 - samples/sec: 9705.54 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-18 22:58:21,556 epoch 8 - iter 216/723 - loss 0.16087750 - time (sec): 5.39 - samples/sec: 9840.08 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-18 22:58:23,697 epoch 8 - iter 288/723 - loss 0.16062473 - time (sec): 7.53 - samples/sec: 9269.48 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-18 22:58:25,503 epoch 8 - iter 360/723 - loss 0.15637198 - time (sec): 9.34 - samples/sec: 9412.21 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-18 22:58:27,293 epoch 8 - iter 432/723 - loss 0.15307484 - time (sec): 11.13 - samples/sec: 9499.23 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-18 22:58:29,140 epoch 8 - iter 504/723 - loss 0.15285181 - time (sec): 12.97 - samples/sec: 9527.96 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-18 22:58:30,949 epoch 8 - iter 576/723 - loss 0.15081701 - time (sec): 14.78 - samples/sec: 9483.93 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-18 22:58:32,695 epoch 8 - iter 648/723 - loss 0.15212614 - time (sec): 16.53 - samples/sec: 9541.68 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-18 22:58:34,593 epoch 8 - iter 720/723 - loss 0.15293930 - time (sec): 18.43 - samples/sec: 9539.14 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-18 22:58:34,658 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-18 22:58:34,658 EPOCH 8 done: loss 0.1528 - lr: 0.000007
193
+ 2023-10-18 22:58:36,427 DEV : loss 0.20108488202095032 - f1-score (micro avg) 0.4437
194
+ 2023-10-18 22:58:36,441 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-18 22:58:38,298 epoch 9 - iter 72/723 - loss 0.15671408 - time (sec): 1.86 - samples/sec: 9684.00 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-18 22:58:40,047 epoch 9 - iter 144/723 - loss 0.15606990 - time (sec): 3.61 - samples/sec: 9977.58 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-18 22:58:41,672 epoch 9 - iter 216/723 - loss 0.14775714 - time (sec): 5.23 - samples/sec: 10078.84 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-18 22:58:43,185 epoch 9 - iter 288/723 - loss 0.14736930 - time (sec): 6.74 - samples/sec: 10426.94 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-18 22:58:44,941 epoch 9 - iter 360/723 - loss 0.14937082 - time (sec): 8.50 - samples/sec: 10387.93 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-18 22:58:46,773 epoch 9 - iter 432/723 - loss 0.14931943 - time (sec): 10.33 - samples/sec: 10324.00 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-18 22:58:48,632 epoch 9 - iter 504/723 - loss 0.15130844 - time (sec): 12.19 - samples/sec: 10210.11 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-18 22:58:50,375 epoch 9 - iter 576/723 - loss 0.15312491 - time (sec): 13.93 - samples/sec: 10138.98 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-18 22:58:52,141 epoch 9 - iter 648/723 - loss 0.15285247 - time (sec): 15.70 - samples/sec: 10116.75 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-18 22:58:53,970 epoch 9 - iter 720/723 - loss 0.15229974 - time (sec): 17.53 - samples/sec: 10023.57 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-18 22:58:54,038 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-18 22:58:54,038 EPOCH 9 done: loss 0.1524 - lr: 0.000003
207
+ 2023-10-18 22:58:55,801 DEV : loss 0.19397485256195068 - f1-score (micro avg) 0.4627
208
+ 2023-10-18 22:58:55,816 saving best model
209
+ 2023-10-18 22:58:55,853 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-18 22:58:57,695 epoch 10 - iter 72/723 - loss 0.15773780 - time (sec): 1.84 - samples/sec: 9363.32 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-18 22:58:59,247 epoch 10 - iter 144/723 - loss 0.16358437 - time (sec): 3.39 - samples/sec: 10063.93 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-18 22:59:00,997 epoch 10 - iter 216/723 - loss 0.16315365 - time (sec): 5.14 - samples/sec: 10100.77 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-18 22:59:02,867 epoch 10 - iter 288/723 - loss 0.15797071 - time (sec): 7.01 - samples/sec: 10138.78 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-18 22:59:04,640 epoch 10 - iter 360/723 - loss 0.15242034 - time (sec): 8.79 - samples/sec: 10132.19 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-18 22:59:06,374 epoch 10 - iter 432/723 - loss 0.15330741 - time (sec): 10.52 - samples/sec: 10040.08 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-18 22:59:08,160 epoch 10 - iter 504/723 - loss 0.14940519 - time (sec): 12.31 - samples/sec: 10018.59 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 22:59:10,041 epoch 10 - iter 576/723 - loss 0.14798129 - time (sec): 14.19 - samples/sec: 9994.37 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 22:59:11,814 epoch 10 - iter 648/723 - loss 0.14933500 - time (sec): 15.96 - samples/sec: 9919.85 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-18 22:59:13,565 epoch 10 - iter 720/723 - loss 0.15018807 - time (sec): 17.71 - samples/sec: 9915.89 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 22:59:13,636 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-18 22:59:13,636 EPOCH 10 done: loss 0.1503 - lr: 0.000000
222
+ 2023-10-18 22:59:15,409 DEV : loss 0.19576019048690796 - f1-score (micro avg) 0.4566
223
+ 2023-10-18 22:59:15,453 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 22:59:15,453 Loading model from best epoch ...
225
+ 2023-10-18 22:59:15,532 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
226
+ 2023-10-18 22:59:16,857
227
+ Results:
228
+ - F-score (micro) 0.4758
229
+ - F-score (macro) 0.3265
230
+ - Accuracy 0.322
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ LOC 0.5332 0.5437 0.5384 458
236
+ PER 0.6653 0.3299 0.4411 482
237
+ ORG 0.0000 0.0000 0.0000 69
238
+
239
+ micro avg 0.5779 0.4044 0.4758 1009
240
+ macro avg 0.3995 0.2912 0.3265 1009
241
+ weighted avg 0.5598 0.4044 0.4551 1009
242
+
243
+ 2023-10-18 22:59:16,857 ----------------------------------------------------------------------------------------------------