Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbert_tiny-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
46ddc51
•
1 Parent(s): f5d8f15

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.1697668800.46dc0c540dd0.3571.10 +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:c745a20d54264ca4c69bc48d5f2c4b812cebe845504f3ee31f599fb20314a9de
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 22:40:19 0.0000 1.1102 0.3578 0.0000 0.0000 0.0000 0.0000
3
+ 2 22:40:39 0.0000 0.2362 0.2550 0.7872 0.1147 0.2002 0.1113
4
+ 3 22:40:58 0.0000 0.1949 0.2252 0.6936 0.2128 0.3257 0.1966
5
+ 4 22:41:18 0.0000 0.1797 0.2068 0.6376 0.2800 0.3891 0.2455
6
+ 5 22:41:37 0.0000 0.1682 0.2108 0.6563 0.3058 0.4172 0.2698
7
+ 6 22:41:57 0.0000 0.1620 0.1961 0.6224 0.3388 0.4388 0.2885
8
+ 7 22:42:17 0.0000 0.1557 0.1865 0.6310 0.4081 0.4956 0.3382
9
+ 8 22:42:37 0.0000 0.1509 0.1936 0.6354 0.3709 0.4684 0.3130
10
+ 9 22:42:57 0.0000 0.1474 0.1860 0.6362 0.4029 0.4934 0.3356
11
+ 10 22:43:17 0.0000 0.1456 0.1870 0.6328 0.3988 0.4892 0.3319
runs/events.out.tfevents.1697668800.46dc0c540dd0.3571.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f452b25e5546554f08b8879508fa93f250ce952af343b7592826cd79daf8e603
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 22:40:00,249 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 22:40:00,249 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 22:40:00,249 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 22:40:00,249 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 22:40:00,249 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 22:40:00,249 Train: 5777 sentences
55
+ 2023-10-18 22:40:00,249 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 22:40:00,250 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 22:40:00,250 Training Params:
58
+ 2023-10-18 22:40:00,250 - learning_rate: "3e-05"
59
+ 2023-10-18 22:40:00,250 - mini_batch_size: "8"
60
+ 2023-10-18 22:40:00,250 - max_epochs: "10"
61
+ 2023-10-18 22:40:00,250 - shuffle: "True"
62
+ 2023-10-18 22:40:00,250 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 22:40:00,250 Plugins:
64
+ 2023-10-18 22:40:00,250 - TensorboardLogger
65
+ 2023-10-18 22:40:00,250 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 22:40:00,250 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 22:40:00,250 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 22:40:00,250 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 22:40:00,250 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 22:40:00,250 Computation:
71
+ 2023-10-18 22:40:00,250 - compute on device: cuda:0
72
+ 2023-10-18 22:40:00,250 - embedding storage: none
73
+ 2023-10-18 22:40:00,250 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 22:40:00,250 Model training base path: "hmbench-icdar/nl-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-18 22:40:00,250 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 22:40:00,250 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 22:40:00,250 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 22:40:02,113 epoch 1 - iter 72/723 - loss 2.98841079 - time (sec): 1.86 - samples/sec: 9578.47 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 22:40:04,053 epoch 1 - iter 144/723 - loss 2.79139642 - time (sec): 3.80 - samples/sec: 9516.22 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 22:40:05,867 epoch 1 - iter 216/723 - loss 2.52716576 - time (sec): 5.62 - samples/sec: 9503.17 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 22:40:07,667 epoch 1 - iter 288/723 - loss 2.18597493 - time (sec): 7.42 - samples/sec: 9593.00 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 22:40:09,442 epoch 1 - iter 360/723 - loss 1.85823175 - time (sec): 9.19 - samples/sec: 9731.15 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 22:40:11,226 epoch 1 - iter 432/723 - loss 1.61794529 - time (sec): 10.98 - samples/sec: 9752.10 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 22:40:13,025 epoch 1 - iter 504/723 - loss 1.43043055 - time (sec): 12.77 - samples/sec: 9802.57 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 22:40:14,790 epoch 1 - iter 576/723 - loss 1.29820059 - time (sec): 14.54 - samples/sec: 9794.94 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 22:40:16,555 epoch 1 - iter 648/723 - loss 1.19724166 - time (sec): 16.30 - samples/sec: 9758.71 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 22:40:18,265 epoch 1 - iter 720/723 - loss 1.11187930 - time (sec): 18.01 - samples/sec: 9759.03 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-18 22:40:18,320 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 22:40:18,320 EPOCH 1 done: loss 1.1102 - lr: 0.000030
90
+ 2023-10-18 22:40:19,582 DEV : loss 0.35777369141578674 - f1-score (micro avg) 0.0
91
+ 2023-10-18 22:40:19,596 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 22:40:21,365 epoch 2 - iter 72/723 - loss 0.27341211 - time (sec): 1.77 - samples/sec: 9574.80 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 22:40:23,118 epoch 2 - iter 144/723 - loss 0.27156084 - time (sec): 3.52 - samples/sec: 9803.83 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 22:40:24,968 epoch 2 - iter 216/723 - loss 0.25524188 - time (sec): 5.37 - samples/sec: 9778.40 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 22:40:26,723 epoch 2 - iter 288/723 - loss 0.25718151 - time (sec): 7.13 - samples/sec: 9726.70 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 22:40:28,489 epoch 2 - iter 360/723 - loss 0.25119017 - time (sec): 8.89 - samples/sec: 9725.42 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 22:40:30,277 epoch 2 - iter 432/723 - loss 0.24390917 - time (sec): 10.68 - samples/sec: 9774.04 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 22:40:32,050 epoch 2 - iter 504/723 - loss 0.24273201 - time (sec): 12.45 - samples/sec: 9809.63 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 22:40:33,864 epoch 2 - iter 576/723 - loss 0.24040013 - time (sec): 14.27 - samples/sec: 9892.91 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 22:40:35,585 epoch 2 - iter 648/723 - loss 0.23365611 - time (sec): 15.99 - samples/sec: 9932.90 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 22:40:37,385 epoch 2 - iter 720/723 - loss 0.23607899 - time (sec): 17.79 - samples/sec: 9875.14 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 22:40:37,455 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 22:40:37,455 EPOCH 2 done: loss 0.2362 - lr: 0.000027
104
+ 2023-10-18 22:40:39,578 DEV : loss 0.2550312876701355 - f1-score (micro avg) 0.2002
105
+ 2023-10-18 22:40:39,592 saving best model
106
+ 2023-10-18 22:40:39,622 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 22:40:41,214 epoch 3 - iter 72/723 - loss 0.22079626 - time (sec): 1.59 - samples/sec: 10781.78 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 22:40:42,794 epoch 3 - iter 144/723 - loss 0.20244048 - time (sec): 3.17 - samples/sec: 11109.25 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 22:40:44,423 epoch 3 - iter 216/723 - loss 0.19849172 - time (sec): 4.80 - samples/sec: 11002.12 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-18 22:40:46,182 epoch 3 - iter 288/723 - loss 0.19769252 - time (sec): 6.56 - samples/sec: 10779.32 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 22:40:47,893 epoch 3 - iter 360/723 - loss 0.19995418 - time (sec): 8.27 - samples/sec: 10451.44 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 22:40:49,679 epoch 3 - iter 432/723 - loss 0.20011392 - time (sec): 10.06 - samples/sec: 10377.07 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-18 22:40:51,486 epoch 3 - iter 504/723 - loss 0.19929608 - time (sec): 11.86 - samples/sec: 10340.39 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 22:40:53,195 epoch 3 - iter 576/723 - loss 0.20030929 - time (sec): 13.57 - samples/sec: 10252.78 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 22:40:54,998 epoch 3 - iter 648/723 - loss 0.20073613 - time (sec): 15.38 - samples/sec: 10270.49 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-18 22:40:56,810 epoch 3 - iter 720/723 - loss 0.19498318 - time (sec): 17.19 - samples/sec: 10222.93 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-18 22:40:56,873 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 22:40:56,873 EPOCH 3 done: loss 0.1949 - lr: 0.000023
119
+ 2023-10-18 22:40:58,634 DEV : loss 0.2251613438129425 - f1-score (micro avg) 0.3257
120
+ 2023-10-18 22:40:58,648 saving best model
121
+ 2023-10-18 22:40:58,686 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 22:41:00,437 epoch 4 - iter 72/723 - loss 0.19403979 - time (sec): 1.75 - samples/sec: 10149.67 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 22:41:02,183 epoch 4 - iter 144/723 - loss 0.18784146 - time (sec): 3.50 - samples/sec: 9748.92 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-18 22:41:03,952 epoch 4 - iter 216/723 - loss 0.19203285 - time (sec): 5.26 - samples/sec: 9895.01 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 22:41:05,781 epoch 4 - iter 288/723 - loss 0.18324681 - time (sec): 7.09 - samples/sec: 9871.53 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 22:41:07,582 epoch 4 - iter 360/723 - loss 0.18156486 - time (sec): 8.89 - samples/sec: 9953.49 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-18 22:41:09,325 epoch 4 - iter 432/723 - loss 0.18116754 - time (sec): 10.64 - samples/sec: 9991.78 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 22:41:11,053 epoch 4 - iter 504/723 - loss 0.18093047 - time (sec): 12.37 - samples/sec: 9946.49 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 22:41:12,847 epoch 4 - iter 576/723 - loss 0.18201373 - time (sec): 14.16 - samples/sec: 9930.77 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-18 22:41:14,597 epoch 4 - iter 648/723 - loss 0.18085010 - time (sec): 15.91 - samples/sec: 9954.75 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 22:41:16,329 epoch 4 - iter 720/723 - loss 0.17999634 - time (sec): 17.64 - samples/sec: 9957.84 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-18 22:41:16,401 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 22:41:16,401 EPOCH 4 done: loss 0.1797 - lr: 0.000020
134
+ 2023-10-18 22:41:18,476 DEV : loss 0.20678313076496124 - f1-score (micro avg) 0.3891
135
+ 2023-10-18 22:41:18,490 saving best model
136
+ 2023-10-18 22:41:18,525 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 22:41:20,277 epoch 5 - iter 72/723 - loss 0.17834339 - time (sec): 1.75 - samples/sec: 9709.97 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-18 22:41:22,062 epoch 5 - iter 144/723 - loss 0.16479979 - time (sec): 3.54 - samples/sec: 9719.79 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 22:41:23,813 epoch 5 - iter 216/723 - loss 0.16544296 - time (sec): 5.29 - samples/sec: 9775.51 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 22:41:25,599 epoch 5 - iter 288/723 - loss 0.16908757 - time (sec): 7.07 - samples/sec: 9698.46 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-18 22:41:27,411 epoch 5 - iter 360/723 - loss 0.16724889 - time (sec): 8.89 - samples/sec: 9833.64 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 22:41:29,173 epoch 5 - iter 432/723 - loss 0.16559838 - time (sec): 10.65 - samples/sec: 9937.96 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 22:41:30,855 epoch 5 - iter 504/723 - loss 0.16547999 - time (sec): 12.33 - samples/sec: 9999.51 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-18 22:41:32,671 epoch 5 - iter 576/723 - loss 0.16944376 - time (sec): 14.15 - samples/sec: 10007.08 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 22:41:34,392 epoch 5 - iter 648/723 - loss 0.17032973 - time (sec): 15.87 - samples/sec: 9953.67 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 22:41:36,124 epoch 5 - iter 720/723 - loss 0.16793137 - time (sec): 17.60 - samples/sec: 9971.25 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-18 22:41:36,187 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 22:41:36,187 EPOCH 5 done: loss 0.1682 - lr: 0.000017
149
+ 2023-10-18 22:41:37,950 DEV : loss 0.21079857647418976 - f1-score (micro avg) 0.4172
150
+ 2023-10-18 22:41:37,965 saving best model
151
+ 2023-10-18 22:41:38,003 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 22:41:39,687 epoch 6 - iter 72/723 - loss 0.15977195 - time (sec): 1.68 - samples/sec: 9982.07 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 22:41:41,451 epoch 6 - iter 144/723 - loss 0.16016708 - time (sec): 3.45 - samples/sec: 10061.70 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-18 22:41:43,215 epoch 6 - iter 216/723 - loss 0.16708014 - time (sec): 5.21 - samples/sec: 10028.21 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-18 22:41:45,039 epoch 6 - iter 288/723 - loss 0.16529748 - time (sec): 7.04 - samples/sec: 10064.56 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 22:41:46,864 epoch 6 - iter 360/723 - loss 0.16782442 - time (sec): 8.86 - samples/sec: 10167.58 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-18 22:41:48,558 epoch 6 - iter 432/723 - loss 0.16816204 - time (sec): 10.55 - samples/sec: 10059.28 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-18 22:41:50,301 epoch 6 - iter 504/723 - loss 0.16538144 - time (sec): 12.30 - samples/sec: 10045.86 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 22:41:52,379 epoch 6 - iter 576/723 - loss 0.16214967 - time (sec): 14.38 - samples/sec: 9747.49 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-18 22:41:53,863 epoch 6 - iter 648/723 - loss 0.16245142 - time (sec): 15.86 - samples/sec: 9935.83 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-18 22:41:55,341 epoch 6 - iter 720/723 - loss 0.16180617 - time (sec): 17.34 - samples/sec: 10132.02 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-18 22:41:55,395 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 22:41:55,395 EPOCH 6 done: loss 0.1620 - lr: 0.000013
164
+ 2023-10-18 22:41:57,177 DEV : loss 0.19605979323387146 - f1-score (micro avg) 0.4388
165
+ 2023-10-18 22:41:57,192 saving best model
166
+ 2023-10-18 22:41:57,229 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 22:41:59,142 epoch 7 - iter 72/723 - loss 0.15681213 - time (sec): 1.91 - samples/sec: 9891.47 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-18 22:42:01,017 epoch 7 - iter 144/723 - loss 0.16028128 - time (sec): 3.79 - samples/sec: 9988.93 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-18 22:42:02,852 epoch 7 - iter 216/723 - loss 0.15737959 - time (sec): 5.62 - samples/sec: 9661.12 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 22:42:04,713 epoch 7 - iter 288/723 - loss 0.15461758 - time (sec): 7.48 - samples/sec: 9652.08 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-18 22:42:06,639 epoch 7 - iter 360/723 - loss 0.15562415 - time (sec): 9.41 - samples/sec: 9633.34 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-18 22:42:08,393 epoch 7 - iter 432/723 - loss 0.15601858 - time (sec): 11.16 - samples/sec: 9547.00 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 22:42:10,195 epoch 7 - iter 504/723 - loss 0.15634551 - time (sec): 12.97 - samples/sec: 9604.06 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-18 22:42:11,917 epoch 7 - iter 576/723 - loss 0.15605432 - time (sec): 14.69 - samples/sec: 9593.42 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-18 22:42:13,742 epoch 7 - iter 648/723 - loss 0.15788652 - time (sec): 16.51 - samples/sec: 9581.30 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-18 22:42:15,506 epoch 7 - iter 720/723 - loss 0.15585343 - time (sec): 18.28 - samples/sec: 9595.68 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-18 22:42:15,576 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 22:42:15,577 EPOCH 7 done: loss 0.1557 - lr: 0.000010
179
+ 2023-10-18 22:42:17,340 DEV : loss 0.18651294708251953 - f1-score (micro avg) 0.4956
180
+ 2023-10-18 22:42:17,355 saving best model
181
+ 2023-10-18 22:42:17,391 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-18 22:42:19,153 epoch 8 - iter 72/723 - loss 0.14374815 - time (sec): 1.76 - samples/sec: 10673.65 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-18 22:42:20,917 epoch 8 - iter 144/723 - loss 0.14794415 - time (sec): 3.53 - samples/sec: 10127.24 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-18 22:42:22,804 epoch 8 - iter 216/723 - loss 0.14360194 - time (sec): 5.41 - samples/sec: 10006.46 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-18 22:42:25,061 epoch 8 - iter 288/723 - loss 0.14897909 - time (sec): 7.67 - samples/sec: 9460.82 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-18 22:42:26,865 epoch 8 - iter 360/723 - loss 0.14900531 - time (sec): 9.47 - samples/sec: 9464.33 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-18 22:42:28,695 epoch 8 - iter 432/723 - loss 0.15163665 - time (sec): 11.30 - samples/sec: 9484.24 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-18 22:42:30,451 epoch 8 - iter 504/723 - loss 0.15049384 - time (sec): 13.06 - samples/sec: 9426.82 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-18 22:42:32,371 epoch 8 - iter 576/723 - loss 0.15391483 - time (sec): 14.98 - samples/sec: 9457.19 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-18 22:42:34,142 epoch 8 - iter 648/723 - loss 0.15242765 - time (sec): 16.75 - samples/sec: 9459.25 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-18 22:42:35,955 epoch 8 - iter 720/723 - loss 0.15035247 - time (sec): 18.56 - samples/sec: 9469.65 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-18 22:42:36,018 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-18 22:42:36,018 EPOCH 8 done: loss 0.1509 - lr: 0.000007
194
+ 2023-10-18 22:42:37,781 DEV : loss 0.1935824304819107 - f1-score (micro avg) 0.4684
195
+ 2023-10-18 22:42:37,796 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-18 22:42:39,582 epoch 9 - iter 72/723 - loss 0.14444690 - time (sec): 1.78 - samples/sec: 10509.51 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-18 22:42:41,335 epoch 9 - iter 144/723 - loss 0.14963003 - time (sec): 3.54 - samples/sec: 10394.85 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-18 22:42:43,151 epoch 9 - iter 216/723 - loss 0.14951345 - time (sec): 5.35 - samples/sec: 10242.28 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-18 22:42:45,037 epoch 9 - iter 288/723 - loss 0.15149133 - time (sec): 7.24 - samples/sec: 10096.19 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-18 22:42:46,793 epoch 9 - iter 360/723 - loss 0.15160429 - time (sec): 9.00 - samples/sec: 9962.62 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-18 22:42:48,624 epoch 9 - iter 432/723 - loss 0.15049137 - time (sec): 10.83 - samples/sec: 9947.91 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-18 22:42:50,372 epoch 9 - iter 504/723 - loss 0.15011278 - time (sec): 12.58 - samples/sec: 9938.17 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-18 22:42:52,084 epoch 9 - iter 576/723 - loss 0.14872092 - time (sec): 14.29 - samples/sec: 9907.26 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-18 22:42:53,983 epoch 9 - iter 648/723 - loss 0.14660520 - time (sec): 16.19 - samples/sec: 9860.50 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-18 22:42:55,746 epoch 9 - iter 720/723 - loss 0.14745168 - time (sec): 17.95 - samples/sec: 9787.18 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-18 22:42:55,805 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-18 22:42:55,805 EPOCH 9 done: loss 0.1474 - lr: 0.000003
208
+ 2023-10-18 22:42:57,583 DEV : loss 0.18601642549037933 - f1-score (micro avg) 0.4934
209
+ 2023-10-18 22:42:57,598 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-18 22:42:59,400 epoch 10 - iter 72/723 - loss 0.14058348 - time (sec): 1.80 - samples/sec: 9685.58 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-18 22:43:01,619 epoch 10 - iter 144/723 - loss 0.12600196 - time (sec): 4.02 - samples/sec: 8799.97 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-18 22:43:03,414 epoch 10 - iter 216/723 - loss 0.13939819 - time (sec): 5.82 - samples/sec: 9148.79 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-18 22:43:05,189 epoch 10 - iter 288/723 - loss 0.14322160 - time (sec): 7.59 - samples/sec: 9259.14 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-18 22:43:07,030 epoch 10 - iter 360/723 - loss 0.14226797 - time (sec): 9.43 - samples/sec: 9420.73 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-18 22:43:08,799 epoch 10 - iter 432/723 - loss 0.14213505 - time (sec): 11.20 - samples/sec: 9483.74 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-18 22:43:10,537 epoch 10 - iter 504/723 - loss 0.14173779 - time (sec): 12.94 - samples/sec: 9470.36 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 22:43:12,404 epoch 10 - iter 576/723 - loss 0.14185805 - time (sec): 14.81 - samples/sec: 9513.49 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 22:43:14,188 epoch 10 - iter 648/723 - loss 0.14424631 - time (sec): 16.59 - samples/sec: 9497.25 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-18 22:43:16,019 epoch 10 - iter 720/723 - loss 0.14588941 - time (sec): 18.42 - samples/sec: 9528.18 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 22:43:16,079 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-18 22:43:16,080 EPOCH 10 done: loss 0.1456 - lr: 0.000000
222
+ 2023-10-18 22:43:17,855 DEV : loss 0.1870052069425583 - f1-score (micro avg) 0.4892
223
+ 2023-10-18 22:43:17,901 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 22:43:17,902 Loading model from best epoch ...
225
+ 2023-10-18 22:43:17,984 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 22:43:19,327
227
+ Results:
228
+ - F-score (micro) 0.5152
229
+ - F-score (macro) 0.3532
230
+ - Accuracy 0.3613
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ LOC 0.5805 0.5983 0.5892 458
236
+ PER 0.6744 0.3610 0.4703 482
237
+ ORG 0.0000 0.0000 0.0000 69
238
+
239
+ micro avg 0.6137 0.4440 0.5152 1009
240
+ macro avg 0.4183 0.3197 0.3532 1009
241
+ weighted avg 0.5857 0.4440 0.4921 1009
242
+
243
+ 2023-10-18 22:43:19,327 ----------------------------------------------------------------------------------------------------