Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
a017383
•
1 Parent(s): ef73556

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.1697670916.46dc0c540dd0.3571.19 +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:da24c2b577a9aa88759fb4b856cf1bc4019292848c1438616b7488b910833cc9
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 23:15:35 0.0000 0.7741 0.2759 0.5714 0.0041 0.0082 0.0041
3
+ 2 23:15:55 0.0000 0.2053 0.2405 0.6980 0.1074 0.1862 0.1033
4
+ 3 23:16:15 0.0000 0.1744 0.1973 0.6274 0.3409 0.4418 0.2890
5
+ 4 23:16:35 0.0000 0.1573 0.1840 0.5826 0.4008 0.4749 0.3193
6
+ 5 23:16:55 0.0000 0.1448 0.1784 0.5720 0.4349 0.4941 0.3376
7
+ 6 23:17:15 0.0000 0.1334 0.1817 0.5959 0.4236 0.4952 0.3355
8
+ 7 23:17:35 0.0000 0.1281 0.1717 0.5932 0.4866 0.5346 0.3723
9
+ 8 23:17:56 0.0000 0.1221 0.1794 0.6157 0.4618 0.5277 0.3643
10
+ 9 23:18:15 0.0000 0.1197 0.1729 0.5876 0.4814 0.5292 0.3681
11
+ 10 23:18:35 0.0000 0.1190 0.1752 0.5972 0.4793 0.5318 0.3700
runs/events.out.tfevents.1697670916.46dc0c540dd0.3571.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7844b96eedcf0f8bae2de9f43398936da01e290197b521d905f3225067ca337
3
+ size 407048
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 23:15:16,265 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 23:15:16,266 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 23:15:16,266 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 23:15:16,266 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 23:15:16,266 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 23:15:16,266 Train: 5777 sentences
55
+ 2023-10-18 23:15:16,266 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 23:15:16,266 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 23:15:16,266 Training Params:
58
+ 2023-10-18 23:15:16,266 - learning_rate: "5e-05"
59
+ 2023-10-18 23:15:16,266 - mini_batch_size: "8"
60
+ 2023-10-18 23:15:16,266 - max_epochs: "10"
61
+ 2023-10-18 23:15:16,266 - shuffle: "True"
62
+ 2023-10-18 23:15:16,266 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 23:15:16,266 Plugins:
64
+ 2023-10-18 23:15:16,266 - TensorboardLogger
65
+ 2023-10-18 23:15:16,266 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 23:15:16,266 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 23:15:16,266 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 23:15:16,266 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 23:15:16,267 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 23:15:16,267 Computation:
71
+ 2023-10-18 23:15:16,267 - compute on device: cuda:0
72
+ 2023-10-18 23:15:16,267 - embedding storage: none
73
+ 2023-10-18 23:15:16,267 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 23:15:16,267 Model training base path: "hmbench-icdar/nl-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-18 23:15:16,267 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 23:15:16,267 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 23:15:16,267 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 23:15:18,125 epoch 1 - iter 72/723 - loss 2.40908332 - time (sec): 1.86 - samples/sec: 9509.35 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 23:15:19,840 epoch 1 - iter 144/723 - loss 2.18163332 - time (sec): 3.57 - samples/sec: 9437.85 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 23:15:21,665 epoch 1 - iter 216/723 - loss 1.79762825 - time (sec): 5.40 - samples/sec: 9717.50 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 23:15:23,570 epoch 1 - iter 288/723 - loss 1.47395731 - time (sec): 7.30 - samples/sec: 9671.73 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 23:15:25,411 epoch 1 - iter 360/723 - loss 1.24759954 - time (sec): 9.14 - samples/sec: 9756.94 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-18 23:15:27,208 epoch 1 - iter 432/723 - loss 1.11186962 - time (sec): 10.94 - samples/sec: 9610.13 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-18 23:15:28,981 epoch 1 - iter 504/723 - loss 0.99525058 - time (sec): 12.71 - samples/sec: 9687.61 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-18 23:15:30,762 epoch 1 - iter 576/723 - loss 0.89980120 - time (sec): 14.50 - samples/sec: 9757.34 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-18 23:15:32,561 epoch 1 - iter 648/723 - loss 0.83006529 - time (sec): 16.29 - samples/sec: 9756.67 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-18 23:15:34,301 epoch 1 - iter 720/723 - loss 0.77620201 - time (sec): 18.03 - samples/sec: 9734.29 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-18 23:15:34,369 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 23:15:34,369 EPOCH 1 done: loss 0.7741 - lr: 0.000050
90
+ 2023-10-18 23:15:35,657 DEV : loss 0.2758811414241791 - f1-score (micro avg) 0.0082
91
+ 2023-10-18 23:15:35,671 saving best model
92
+ 2023-10-18 23:15:35,701 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-18 23:15:37,598 epoch 2 - iter 72/723 - loss 0.25857317 - time (sec): 1.90 - samples/sec: 9119.75 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 23:15:39,477 epoch 2 - iter 144/723 - loss 0.23888287 - time (sec): 3.78 - samples/sec: 9439.22 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-18 23:15:41,200 epoch 2 - iter 216/723 - loss 0.23446606 - time (sec): 5.50 - samples/sec: 9413.80 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 23:15:42,964 epoch 2 - iter 288/723 - loss 0.22142250 - time (sec): 7.26 - samples/sec: 9657.27 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-18 23:15:44,709 epoch 2 - iter 360/723 - loss 0.21787192 - time (sec): 9.01 - samples/sec: 9648.55 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 23:15:46,447 epoch 2 - iter 432/723 - loss 0.21454913 - time (sec): 10.75 - samples/sec: 9633.59 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-18 23:15:48,218 epoch 2 - iter 504/723 - loss 0.21228027 - time (sec): 12.52 - samples/sec: 9686.73 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 23:15:50,039 epoch 2 - iter 576/723 - loss 0.21139498 - time (sec): 14.34 - samples/sec: 9809.15 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-18 23:15:51,821 epoch 2 - iter 648/723 - loss 0.20851881 - time (sec): 16.12 - samples/sec: 9824.09 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 23:15:53,645 epoch 2 - iter 720/723 - loss 0.20557912 - time (sec): 17.94 - samples/sec: 9786.99 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-18 23:15:53,709 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-18 23:15:53,710 EPOCH 2 done: loss 0.2053 - lr: 0.000044
105
+ 2023-10-18 23:15:55,808 DEV : loss 0.2405446618795395 - f1-score (micro avg) 0.1862
106
+ 2023-10-18 23:15:55,822 saving best model
107
+ 2023-10-18 23:15:55,858 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-18 23:15:57,614 epoch 3 - iter 72/723 - loss 0.17701188 - time (sec): 1.76 - samples/sec: 10573.26 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-18 23:15:59,375 epoch 3 - iter 144/723 - loss 0.18046644 - time (sec): 3.52 - samples/sec: 10214.55 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 23:16:01,273 epoch 3 - iter 216/723 - loss 0.17924447 - time (sec): 5.41 - samples/sec: 10016.01 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-18 23:16:03,056 epoch 3 - iter 288/723 - loss 0.17534354 - time (sec): 7.20 - samples/sec: 9979.60 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 23:16:04,795 epoch 3 - iter 360/723 - loss 0.17549661 - time (sec): 8.94 - samples/sec: 9890.73 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-18 23:16:06,577 epoch 3 - iter 432/723 - loss 0.17806596 - time (sec): 10.72 - samples/sec: 9864.63 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 23:16:08,395 epoch 3 - iter 504/723 - loss 0.17649226 - time (sec): 12.54 - samples/sec: 9759.78 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-18 23:16:10,276 epoch 3 - iter 576/723 - loss 0.17718147 - time (sec): 14.42 - samples/sec: 9766.82 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 23:16:12,017 epoch 3 - iter 648/723 - loss 0.17435274 - time (sec): 16.16 - samples/sec: 9788.62 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 23:16:13,753 epoch 3 - iter 720/723 - loss 0.17453446 - time (sec): 17.89 - samples/sec: 9819.40 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-18 23:16:13,814 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-18 23:16:13,814 EPOCH 3 done: loss 0.1744 - lr: 0.000039
120
+ 2023-10-18 23:16:15,580 DEV : loss 0.19726891815662384 - f1-score (micro avg) 0.4418
121
+ 2023-10-18 23:16:15,595 saving best model
122
+ 2023-10-18 23:16:15,630 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-18 23:16:17,465 epoch 4 - iter 72/723 - loss 0.19970285 - time (sec): 1.83 - samples/sec: 9313.18 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 23:16:19,232 epoch 4 - iter 144/723 - loss 0.16333378 - time (sec): 3.60 - samples/sec: 9634.99 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-18 23:16:21,027 epoch 4 - iter 216/723 - loss 0.16709855 - time (sec): 5.40 - samples/sec: 9499.46 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 23:16:22,919 epoch 4 - iter 288/723 - loss 0.16278167 - time (sec): 7.29 - samples/sec: 9586.69 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-18 23:16:24,700 epoch 4 - iter 360/723 - loss 0.16462834 - time (sec): 9.07 - samples/sec: 9779.30 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 23:16:26,498 epoch 4 - iter 432/723 - loss 0.16054808 - time (sec): 10.87 - samples/sec: 9870.03 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-18 23:16:28,289 epoch 4 - iter 504/723 - loss 0.15875214 - time (sec): 12.66 - samples/sec: 9784.37 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 23:16:30,002 epoch 4 - iter 576/723 - loss 0.15882572 - time (sec): 14.37 - samples/sec: 9832.90 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 23:16:32,220 epoch 4 - iter 648/723 - loss 0.15908778 - time (sec): 16.59 - samples/sec: 9607.35 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-18 23:16:33,961 epoch 4 - iter 720/723 - loss 0.15739102 - time (sec): 18.33 - samples/sec: 9590.24 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-18 23:16:34,026 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-18 23:16:34,026 EPOCH 4 done: loss 0.1573 - lr: 0.000033
135
+ 2023-10-18 23:16:35,788 DEV : loss 0.18398496508598328 - f1-score (micro avg) 0.4749
136
+ 2023-10-18 23:16:35,803 saving best model
137
+ 2023-10-18 23:16:35,838 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-18 23:16:37,539 epoch 5 - iter 72/723 - loss 0.16602905 - time (sec): 1.70 - samples/sec: 9888.68 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-18 23:16:39,324 epoch 5 - iter 144/723 - loss 0.15855908 - time (sec): 3.49 - samples/sec: 9666.77 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 23:16:41,069 epoch 5 - iter 216/723 - loss 0.15565325 - time (sec): 5.23 - samples/sec: 9589.97 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-18 23:16:42,855 epoch 5 - iter 288/723 - loss 0.15137039 - time (sec): 7.02 - samples/sec: 9638.72 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 23:16:44,673 epoch 5 - iter 360/723 - loss 0.15306731 - time (sec): 8.84 - samples/sec: 9834.34 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-18 23:16:46,518 epoch 5 - iter 432/723 - loss 0.14937650 - time (sec): 10.68 - samples/sec: 9838.86 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 23:16:48,257 epoch 5 - iter 504/723 - loss 0.14562850 - time (sec): 12.42 - samples/sec: 9845.97 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 23:16:49,944 epoch 5 - iter 576/723 - loss 0.14633530 - time (sec): 14.11 - samples/sec: 9882.96 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-18 23:16:51,751 epoch 5 - iter 648/723 - loss 0.14812330 - time (sec): 15.91 - samples/sec: 9847.09 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 23:16:53,692 epoch 5 - iter 720/723 - loss 0.14451958 - time (sec): 17.85 - samples/sec: 9841.50 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-18 23:16:53,748 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-18 23:16:53,748 EPOCH 5 done: loss 0.1448 - lr: 0.000028
150
+ 2023-10-18 23:16:55,530 DEV : loss 0.1783648133277893 - f1-score (micro avg) 0.4941
151
+ 2023-10-18 23:16:55,544 saving best model
152
+ 2023-10-18 23:16:55,580 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-18 23:16:57,339 epoch 6 - iter 72/723 - loss 0.12412838 - time (sec): 1.76 - samples/sec: 10153.63 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 23:16:59,153 epoch 6 - iter 144/723 - loss 0.12845739 - time (sec): 3.57 - samples/sec: 10111.64 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-18 23:17:01,000 epoch 6 - iter 216/723 - loss 0.13059131 - time (sec): 5.42 - samples/sec: 10079.33 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 23:17:02,729 epoch 6 - iter 288/723 - loss 0.13011154 - time (sec): 7.15 - samples/sec: 10062.07 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-18 23:17:04,837 epoch 6 - iter 360/723 - loss 0.13108817 - time (sec): 9.26 - samples/sec: 9646.45 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 23:17:06,702 epoch 6 - iter 432/723 - loss 0.13199062 - time (sec): 11.12 - samples/sec: 9684.01 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-18 23:17:08,534 epoch 6 - iter 504/723 - loss 0.13635868 - time (sec): 12.95 - samples/sec: 9661.56 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-18 23:17:10,365 epoch 6 - iter 576/723 - loss 0.13682865 - time (sec): 14.78 - samples/sec: 9566.59 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 23:17:12,189 epoch 6 - iter 648/723 - loss 0.13499612 - time (sec): 16.61 - samples/sec: 9533.05 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-18 23:17:13,891 epoch 6 - iter 720/723 - loss 0.13337880 - time (sec): 18.31 - samples/sec: 9592.34 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-18 23:17:13,955 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-18 23:17:13,955 EPOCH 6 done: loss 0.1334 - lr: 0.000022
165
+ 2023-10-18 23:17:15,731 DEV : loss 0.18174949288368225 - f1-score (micro avg) 0.4952
166
+ 2023-10-18 23:17:15,745 saving best model
167
+ 2023-10-18 23:17:15,781 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-18 23:17:17,561 epoch 7 - iter 72/723 - loss 0.11870149 - time (sec): 1.78 - samples/sec: 9897.22 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-18 23:17:19,339 epoch 7 - iter 144/723 - loss 0.12495624 - time (sec): 3.56 - samples/sec: 9460.86 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-18 23:17:21,174 epoch 7 - iter 216/723 - loss 0.12415400 - time (sec): 5.39 - samples/sec: 9681.31 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-18 23:17:23,015 epoch 7 - iter 288/723 - loss 0.12335361 - time (sec): 7.23 - samples/sec: 9529.01 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-18 23:17:24,834 epoch 7 - iter 360/723 - loss 0.12487733 - time (sec): 9.05 - samples/sec: 9600.12 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-18 23:17:26,642 epoch 7 - iter 432/723 - loss 0.12677615 - time (sec): 10.86 - samples/sec: 9665.79 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-18 23:17:28,481 epoch 7 - iter 504/723 - loss 0.12846292 - time (sec): 12.70 - samples/sec: 9621.48 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-18 23:17:30,414 epoch 7 - iter 576/723 - loss 0.12813188 - time (sec): 14.63 - samples/sec: 9660.86 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-18 23:17:32,221 epoch 7 - iter 648/723 - loss 0.12928188 - time (sec): 16.44 - samples/sec: 9623.10 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-18 23:17:33,963 epoch 7 - iter 720/723 - loss 0.12811456 - time (sec): 18.18 - samples/sec: 9668.44 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-18 23:17:34,024 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-18 23:17:34,024 EPOCH 7 done: loss 0.1281 - lr: 0.000017
180
+ 2023-10-18 23:17:35,808 DEV : loss 0.1717141568660736 - f1-score (micro avg) 0.5346
181
+ 2023-10-18 23:17:35,823 saving best model
182
+ 2023-10-18 23:17:35,858 ----------------------------------------------------------------------------------------------------
183
+ 2023-10-18 23:17:38,073 epoch 8 - iter 72/723 - loss 0.12299219 - time (sec): 2.21 - samples/sec: 8057.14 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-18 23:17:39,830 epoch 8 - iter 144/723 - loss 0.11754273 - time (sec): 3.97 - samples/sec: 8740.64 - lr: 0.000016 - momentum: 0.000000
185
+ 2023-10-18 23:17:41,690 epoch 8 - iter 216/723 - loss 0.11975555 - time (sec): 5.83 - samples/sec: 9103.15 - lr: 0.000015 - momentum: 0.000000
186
+ 2023-10-18 23:17:43,614 epoch 8 - iter 288/723 - loss 0.11991985 - time (sec): 7.75 - samples/sec: 9207.08 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-18 23:17:45,415 epoch 8 - iter 360/723 - loss 0.12012028 - time (sec): 9.56 - samples/sec: 9293.87 - lr: 0.000014 - momentum: 0.000000
188
+ 2023-10-18 23:17:47,181 epoch 8 - iter 432/723 - loss 0.12323901 - time (sec): 11.32 - samples/sec: 9411.71 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-18 23:17:48,997 epoch 8 - iter 504/723 - loss 0.12390650 - time (sec): 13.14 - samples/sec: 9515.34 - lr: 0.000013 - momentum: 0.000000
190
+ 2023-10-18 23:17:50,731 epoch 8 - iter 576/723 - loss 0.12261161 - time (sec): 14.87 - samples/sec: 9531.16 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-18 23:17:52,540 epoch 8 - iter 648/723 - loss 0.12309668 - time (sec): 16.68 - samples/sec: 9526.96 - lr: 0.000012 - momentum: 0.000000
192
+ 2023-10-18 23:17:54,314 epoch 8 - iter 720/723 - loss 0.12212658 - time (sec): 18.46 - samples/sec: 9518.50 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-18 23:17:54,372 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-18 23:17:54,372 EPOCH 8 done: loss 0.1221 - lr: 0.000011
195
+ 2023-10-18 23:17:56,154 DEV : loss 0.17939499020576477 - f1-score (micro avg) 0.5277
196
+ 2023-10-18 23:17:56,168 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-18 23:17:57,932 epoch 9 - iter 72/723 - loss 0.10482754 - time (sec): 1.76 - samples/sec: 10587.13 - lr: 0.000011 - momentum: 0.000000
198
+ 2023-10-18 23:17:59,777 epoch 9 - iter 144/723 - loss 0.11941581 - time (sec): 3.61 - samples/sec: 10252.77 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-18 23:18:01,519 epoch 9 - iter 216/723 - loss 0.11428472 - time (sec): 5.35 - samples/sec: 10270.88 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-18 23:18:03,294 epoch 9 - iter 288/723 - loss 0.11765545 - time (sec): 7.13 - samples/sec: 10286.21 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-18 23:18:05,075 epoch 9 - iter 360/723 - loss 0.12157267 - time (sec): 8.91 - samples/sec: 10049.91 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-18 23:18:06,761 epoch 9 - iter 432/723 - loss 0.11936636 - time (sec): 10.59 - samples/sec: 10058.03 - lr: 0.000008 - momentum: 0.000000
203
+ 2023-10-18 23:18:08,276 epoch 9 - iter 504/723 - loss 0.11873180 - time (sec): 12.11 - samples/sec: 10211.95 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-18 23:18:09,884 epoch 9 - iter 576/723 - loss 0.11689872 - time (sec): 13.71 - samples/sec: 10369.22 - lr: 0.000007 - momentum: 0.000000
205
+ 2023-10-18 23:18:11,685 epoch 9 - iter 648/723 - loss 0.11799321 - time (sec): 15.52 - samples/sec: 10271.81 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-18 23:18:13,436 epoch 9 - iter 720/723 - loss 0.11948734 - time (sec): 17.27 - samples/sec: 10181.80 - lr: 0.000006 - momentum: 0.000000
207
+ 2023-10-18 23:18:13,495 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-18 23:18:13,495 EPOCH 9 done: loss 0.1197 - lr: 0.000006
209
+ 2023-10-18 23:18:15,639 DEV : loss 0.17294184863567352 - f1-score (micro avg) 0.5292
210
+ 2023-10-18 23:18:15,655 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-18 23:18:17,542 epoch 10 - iter 72/723 - loss 0.12361351 - time (sec): 1.89 - samples/sec: 9438.66 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-18 23:18:19,410 epoch 10 - iter 144/723 - loss 0.11590017 - time (sec): 3.76 - samples/sec: 9446.32 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-18 23:18:21,248 epoch 10 - iter 216/723 - loss 0.11549287 - time (sec): 5.59 - samples/sec: 9439.46 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-18 23:18:23,070 epoch 10 - iter 288/723 - loss 0.11632240 - time (sec): 7.41 - samples/sec: 9349.45 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-18 23:18:24,972 epoch 10 - iter 360/723 - loss 0.12476098 - time (sec): 9.32 - samples/sec: 9447.80 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-18 23:18:26,863 epoch 10 - iter 432/723 - loss 0.12139655 - time (sec): 11.21 - samples/sec: 9515.38 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-18 23:18:28,705 epoch 10 - iter 504/723 - loss 0.12203358 - time (sec): 13.05 - samples/sec: 9588.11 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-18 23:18:30,467 epoch 10 - iter 576/723 - loss 0.12185105 - time (sec): 14.81 - samples/sec: 9508.37 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 23:18:32,221 epoch 10 - iter 648/723 - loss 0.12023157 - time (sec): 16.57 - samples/sec: 9540.08 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-18 23:18:34,016 epoch 10 - iter 720/723 - loss 0.11895430 - time (sec): 18.36 - samples/sec: 9573.31 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-18 23:18:34,073 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-18 23:18:34,073 EPOCH 10 done: loss 0.1190 - lr: 0.000000
223
+ 2023-10-18 23:18:35,874 DEV : loss 0.1752191036939621 - f1-score (micro avg) 0.5318
224
+ 2023-10-18 23:18:35,921 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-18 23:18:35,921 Loading model from best epoch ...
226
+ 2023-10-18 23:18:36,002 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
227
+ 2023-10-18 23:18:37,353
228
+ Results:
229
+ - F-score (micro) 0.5439
230
+ - F-score (macro) 0.3773
231
+ - Accuracy 0.3802
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ PER 0.5046 0.4564 0.4793 482
237
+ LOC 0.6705 0.6354 0.6525 458
238
+ ORG 0.0000 0.0000 0.0000 69
239
+
240
+ micro avg 0.5874 0.5064 0.5439 1009
241
+ macro avg 0.3917 0.3639 0.3773 1009
242
+ weighted avg 0.5454 0.5064 0.5251 1009
243
+
244
+ 2023-10-18 23:18:37,353 ----------------------------------------------------------------------------------------------------