Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbert_tiny-bs4-wsFalse-e10-lr5e-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
d8c6207
•
1 Parent(s): 833542a

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.1697669484.46dc0c540dd0.3571.13 +3 -0
  5. test.tsv +0 -0
  6. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc21e45c54589240c6b0706981caf47399f743d8ece8a7d2772b337ae0fccd16
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 22:51:50 0.0000 0.8477 0.2889 0.7826 0.0186 0.0363 0.0185
3
+ 2 22:52:15 0.0000 0.1991 0.2434 0.6599 0.2004 0.3074 0.1848
4
+ 3 22:52:41 0.0000 0.1663 0.2106 0.5479 0.3430 0.4219 0.2776
5
+ 4 22:53:08 0.0000 0.1515 0.1963 0.5726 0.4236 0.4869 0.3314
6
+ 5 22:53:34 0.0000 0.1378 0.1869 0.5907 0.4742 0.5261 0.3681
7
+ 6 22:54:00 0.0000 0.1292 0.1867 0.5977 0.4804 0.5326 0.3729
8
+ 7 22:54:27 0.0000 0.1216 0.1910 0.5947 0.5093 0.5487 0.3870
9
+ 8 22:54:53 0.0000 0.1166 0.1996 0.6168 0.4855 0.5434 0.3821
10
+ 9 22:55:18 0.0000 0.1130 0.1941 0.6005 0.5310 0.5636 0.4028
11
+ 10 22:55:44 0.0000 0.1119 0.1994 0.6082 0.5196 0.5604 0.3986
runs/events.out.tfevents.1697669484.46dc0c540dd0.3571.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:098ef5e79ea89bd51e8de3b85911b1fbfd68e09a75587419d9a34bfb81b001aa
3
+ size 808480
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 22:51:24,698 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 22:51:24,698 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 22:51:24,698 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 22:51:24,699 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 22:51:24,699 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 22:51:24,699 Train: 5777 sentences
55
+ 2023-10-18 22:51:24,699 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 22:51:24,699 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 22:51:24,699 Training Params:
58
+ 2023-10-18 22:51:24,699 - learning_rate: "5e-05"
59
+ 2023-10-18 22:51:24,699 - mini_batch_size: "4"
60
+ 2023-10-18 22:51:24,699 - max_epochs: "10"
61
+ 2023-10-18 22:51:24,699 - shuffle: "True"
62
+ 2023-10-18 22:51:24,699 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 22:51:24,699 Plugins:
64
+ 2023-10-18 22:51:24,699 - TensorboardLogger
65
+ 2023-10-18 22:51:24,699 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 22:51:24,699 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 22:51:24,699 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 22:51:24,699 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 22:51:24,699 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 22:51:24,699 Computation:
71
+ 2023-10-18 22:51:24,699 - compute on device: cuda:0
72
+ 2023-10-18 22:51:24,699 - embedding storage: none
73
+ 2023-10-18 22:51:24,699 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 22:51:24,699 Model training base path: "hmbench-icdar/nl-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-18 22:51:24,699 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 22:51:24,699 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 22:51:24,699 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 22:51:27,059 epoch 1 - iter 144/1445 - loss 3.29539325 - time (sec): 2.36 - samples/sec: 6871.85 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 22:51:29,599 epoch 1 - iter 288/1445 - loss 2.80667047 - time (sec): 4.90 - samples/sec: 6851.93 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 22:51:32,037 epoch 1 - iter 432/1445 - loss 2.17298777 - time (sec): 7.34 - samples/sec: 7006.80 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 22:51:34,467 epoch 1 - iter 576/1445 - loss 1.69993643 - time (sec): 9.77 - samples/sec: 7136.03 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 22:51:36,827 epoch 1 - iter 720/1445 - loss 1.42956310 - time (sec): 12.13 - samples/sec: 7137.99 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-18 22:51:39,163 epoch 1 - iter 864/1445 - loss 1.24708491 - time (sec): 14.46 - samples/sec: 7154.15 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-18 22:51:41,607 epoch 1 - iter 1008/1445 - loss 1.11449457 - time (sec): 16.91 - samples/sec: 7121.10 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-18 22:51:44,080 epoch 1 - iter 1152/1445 - loss 1.00767761 - time (sec): 19.38 - samples/sec: 7180.56 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-18 22:51:46,593 epoch 1 - iter 1296/1445 - loss 0.91487367 - time (sec): 21.89 - samples/sec: 7218.53 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-18 22:51:49,002 epoch 1 - iter 1440/1445 - loss 0.84936645 - time (sec): 24.30 - samples/sec: 7229.17 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-18 22:51:49,078 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 22:51:49,079 EPOCH 1 done: loss 0.8477 - lr: 0.000050
90
+ 2023-10-18 22:51:50,368 DEV : loss 0.28886058926582336 - f1-score (micro avg) 0.0363
91
+ 2023-10-18 22:51:50,382 saving best model
92
+ 2023-10-18 22:51:50,413 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-18 22:51:52,534 epoch 2 - iter 144/1445 - loss 0.20771123 - time (sec): 2.12 - samples/sec: 8378.68 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 22:51:54,705 epoch 2 - iter 288/1445 - loss 0.21302193 - time (sec): 4.29 - samples/sec: 8059.18 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-18 22:51:57,097 epoch 2 - iter 432/1445 - loss 0.21308278 - time (sec): 6.68 - samples/sec: 7668.37 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 22:51:59,685 epoch 2 - iter 576/1445 - loss 0.20687075 - time (sec): 9.27 - samples/sec: 7600.92 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-18 22:52:02,218 epoch 2 - iter 720/1445 - loss 0.20244105 - time (sec): 11.80 - samples/sec: 7393.23 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 22:52:04,652 epoch 2 - iter 864/1445 - loss 0.19886336 - time (sec): 14.24 - samples/sec: 7394.02 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-18 22:52:06,878 epoch 2 - iter 1008/1445 - loss 0.19645336 - time (sec): 16.46 - samples/sec: 7481.26 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 22:52:09,110 epoch 2 - iter 1152/1445 - loss 0.20134357 - time (sec): 18.70 - samples/sec: 7488.90 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-18 22:52:11,497 epoch 2 - iter 1296/1445 - loss 0.19916074 - time (sec): 21.08 - samples/sec: 7494.59 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 22:52:13,935 epoch 2 - iter 1440/1445 - loss 0.19916757 - time (sec): 23.52 - samples/sec: 7459.46 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-18 22:52:14,018 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-18 22:52:14,019 EPOCH 2 done: loss 0.1991 - lr: 0.000044
105
+ 2023-10-18 22:52:15,801 DEV : loss 0.2434382140636444 - f1-score (micro avg) 0.3074
106
+ 2023-10-18 22:52:15,815 saving best model
107
+ 2023-10-18 22:52:15,849 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-18 22:52:18,303 epoch 3 - iter 144/1445 - loss 0.16824685 - time (sec): 2.45 - samples/sec: 7641.85 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-18 22:52:20,724 epoch 3 - iter 288/1445 - loss 0.17832135 - time (sec): 4.87 - samples/sec: 7722.80 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 22:52:23,482 epoch 3 - iter 432/1445 - loss 0.17388072 - time (sec): 7.63 - samples/sec: 7228.05 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-18 22:52:25,913 epoch 3 - iter 576/1445 - loss 0.16949600 - time (sec): 10.06 - samples/sec: 7262.71 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 22:52:28,376 epoch 3 - iter 720/1445 - loss 0.17010711 - time (sec): 12.53 - samples/sec: 7214.37 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-18 22:52:30,724 epoch 3 - iter 864/1445 - loss 0.16944462 - time (sec): 14.87 - samples/sec: 7161.25 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 22:52:33,038 epoch 3 - iter 1008/1445 - loss 0.17031912 - time (sec): 17.19 - samples/sec: 7241.37 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-18 22:52:35,207 epoch 3 - iter 1152/1445 - loss 0.16944422 - time (sec): 19.36 - samples/sec: 7297.31 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 22:52:37,602 epoch 3 - iter 1296/1445 - loss 0.16674107 - time (sec): 21.75 - samples/sec: 7316.34 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 22:52:39,958 epoch 3 - iter 1440/1445 - loss 0.16647381 - time (sec): 24.11 - samples/sec: 7278.75 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-18 22:52:40,039 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-18 22:52:40,039 EPOCH 3 done: loss 0.1663 - lr: 0.000039
120
+ 2023-10-18 22:52:41,821 DEV : loss 0.21055997908115387 - f1-score (micro avg) 0.4219
121
+ 2023-10-18 22:52:41,835 saving best model
122
+ 2023-10-18 22:52:41,870 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-18 22:52:44,200 epoch 4 - iter 144/1445 - loss 0.15283862 - time (sec): 2.33 - samples/sec: 7307.47 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 22:52:46,578 epoch 4 - iter 288/1445 - loss 0.14799565 - time (sec): 4.71 - samples/sec: 7015.01 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-18 22:52:48,944 epoch 4 - iter 432/1445 - loss 0.15105169 - time (sec): 7.07 - samples/sec: 7106.38 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 22:52:51,342 epoch 4 - iter 576/1445 - loss 0.15217093 - time (sec): 9.47 - samples/sec: 7174.33 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-18 22:52:53,783 epoch 4 - iter 720/1445 - loss 0.15166536 - time (sec): 11.91 - samples/sec: 7162.93 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 22:52:56,210 epoch 4 - iter 864/1445 - loss 0.15237011 - time (sec): 14.34 - samples/sec: 7158.14 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-18 22:52:58,867 epoch 4 - iter 1008/1445 - loss 0.15079524 - time (sec): 17.00 - samples/sec: 7087.84 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 22:53:01,592 epoch 4 - iter 1152/1445 - loss 0.15204078 - time (sec): 19.72 - samples/sec: 7121.06 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 22:53:03,966 epoch 4 - iter 1296/1445 - loss 0.15103163 - time (sec): 22.10 - samples/sec: 7125.45 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-18 22:53:06,380 epoch 4 - iter 1440/1445 - loss 0.15143506 - time (sec): 24.51 - samples/sec: 7168.62 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-18 22:53:06,461 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-18 22:53:06,461 EPOCH 4 done: loss 0.1515 - lr: 0.000033
135
+ 2023-10-18 22:53:08,244 DEV : loss 0.19626548886299133 - f1-score (micro avg) 0.4869
136
+ 2023-10-18 22:53:08,258 saving best model
137
+ 2023-10-18 22:53:08,293 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-18 22:53:10,756 epoch 5 - iter 144/1445 - loss 0.14791715 - time (sec): 2.46 - samples/sec: 7246.53 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-18 22:53:13,168 epoch 5 - iter 288/1445 - loss 0.14595192 - time (sec): 4.87 - samples/sec: 7399.69 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 22:53:15,540 epoch 5 - iter 432/1445 - loss 0.14209987 - time (sec): 7.25 - samples/sec: 7414.07 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-18 22:53:17,946 epoch 5 - iter 576/1445 - loss 0.14142116 - time (sec): 9.65 - samples/sec: 7301.39 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 22:53:20,291 epoch 5 - iter 720/1445 - loss 0.13858369 - time (sec): 12.00 - samples/sec: 7226.89 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-18 22:53:22,707 epoch 5 - iter 864/1445 - loss 0.13944449 - time (sec): 14.41 - samples/sec: 7219.53 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 22:53:25,161 epoch 5 - iter 1008/1445 - loss 0.13904087 - time (sec): 16.87 - samples/sec: 7204.05 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 22:53:27,753 epoch 5 - iter 1152/1445 - loss 0.13936345 - time (sec): 19.46 - samples/sec: 7198.86 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-18 22:53:30,106 epoch 5 - iter 1296/1445 - loss 0.13877879 - time (sec): 21.81 - samples/sec: 7220.31 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 22:53:32,573 epoch 5 - iter 1440/1445 - loss 0.13778394 - time (sec): 24.28 - samples/sec: 7245.29 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-18 22:53:32,646 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-18 22:53:32,646 EPOCH 5 done: loss 0.1378 - lr: 0.000028
150
+ 2023-10-18 22:53:34,776 DEV : loss 0.186900332570076 - f1-score (micro avg) 0.5261
151
+ 2023-10-18 22:53:34,792 saving best model
152
+ 2023-10-18 22:53:34,828 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-18 22:53:37,198 epoch 6 - iter 144/1445 - loss 0.12941650 - time (sec): 2.37 - samples/sec: 6979.43 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 22:53:39,571 epoch 6 - iter 288/1445 - loss 0.12211079 - time (sec): 4.74 - samples/sec: 7141.82 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-18 22:53:41,959 epoch 6 - iter 432/1445 - loss 0.12637372 - time (sec): 7.13 - samples/sec: 7336.97 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 22:53:44,418 epoch 6 - iter 576/1445 - loss 0.12653560 - time (sec): 9.59 - samples/sec: 7368.21 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-18 22:53:46,769 epoch 6 - iter 720/1445 - loss 0.12839698 - time (sec): 11.94 - samples/sec: 7326.25 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 22:53:49,154 epoch 6 - iter 864/1445 - loss 0.12535563 - time (sec): 14.32 - samples/sec: 7325.47 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-18 22:53:51,561 epoch 6 - iter 1008/1445 - loss 0.12897091 - time (sec): 16.73 - samples/sec: 7261.16 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-18 22:53:53,981 epoch 6 - iter 1152/1445 - loss 0.12610695 - time (sec): 19.15 - samples/sec: 7266.88 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 22:53:56,366 epoch 6 - iter 1296/1445 - loss 0.12806517 - time (sec): 21.54 - samples/sec: 7280.58 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-18 22:53:58,957 epoch 6 - iter 1440/1445 - loss 0.12929665 - time (sec): 24.13 - samples/sec: 7283.06 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-18 22:53:59,044 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-18 22:53:59,044 EPOCH 6 done: loss 0.1292 - lr: 0.000022
165
+ 2023-10-18 22:54:00,808 DEV : loss 0.1867137998342514 - f1-score (micro avg) 0.5326
166
+ 2023-10-18 22:54:00,822 saving best model
167
+ 2023-10-18 22:54:00,858 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-18 22:54:03,301 epoch 7 - iter 144/1445 - loss 0.11727356 - time (sec): 2.44 - samples/sec: 6746.22 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-18 22:54:05,687 epoch 7 - iter 288/1445 - loss 0.11920637 - time (sec): 4.83 - samples/sec: 7110.68 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-18 22:54:08,078 epoch 7 - iter 432/1445 - loss 0.12142107 - time (sec): 7.22 - samples/sec: 7086.33 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-18 22:54:10,549 epoch 7 - iter 576/1445 - loss 0.12054887 - time (sec): 9.69 - samples/sec: 7176.58 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-18 22:54:12,850 epoch 7 - iter 720/1445 - loss 0.12121286 - time (sec): 11.99 - samples/sec: 7219.02 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-18 22:54:15,406 epoch 7 - iter 864/1445 - loss 0.12151057 - time (sec): 14.55 - samples/sec: 7155.32 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-18 22:54:17,870 epoch 7 - iter 1008/1445 - loss 0.12126598 - time (sec): 17.01 - samples/sec: 7193.07 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-18 22:54:20,281 epoch 7 - iter 1152/1445 - loss 0.12219795 - time (sec): 19.42 - samples/sec: 7208.87 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-18 22:54:22,749 epoch 7 - iter 1296/1445 - loss 0.12311442 - time (sec): 21.89 - samples/sec: 7217.81 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-18 22:54:25,139 epoch 7 - iter 1440/1445 - loss 0.12171338 - time (sec): 24.28 - samples/sec: 7233.22 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-18 22:54:25,219 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-18 22:54:25,220 EPOCH 7 done: loss 0.1216 - lr: 0.000017
180
+ 2023-10-18 22:54:26,988 DEV : loss 0.19099119305610657 - f1-score (micro avg) 0.5487
181
+ 2023-10-18 22:54:27,003 saving best model
182
+ 2023-10-18 22:54:27,040 ----------------------------------------------------------------------------------------------------
183
+ 2023-10-18 22:54:29,347 epoch 8 - iter 144/1445 - loss 0.13909632 - time (sec): 2.31 - samples/sec: 7149.79 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-18 22:54:31,777 epoch 8 - iter 288/1445 - loss 0.12875856 - time (sec): 4.74 - samples/sec: 7333.26 - lr: 0.000016 - momentum: 0.000000
185
+ 2023-10-18 22:54:34,165 epoch 8 - iter 432/1445 - loss 0.12665044 - time (sec): 7.13 - samples/sec: 7443.17 - lr: 0.000015 - momentum: 0.000000
186
+ 2023-10-18 22:54:36,574 epoch 8 - iter 576/1445 - loss 0.12517964 - time (sec): 9.53 - samples/sec: 7321.07 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-18 22:54:38,887 epoch 8 - iter 720/1445 - loss 0.12049045 - time (sec): 11.85 - samples/sec: 7417.55 - lr: 0.000014 - momentum: 0.000000
188
+ 2023-10-18 22:54:41,339 epoch 8 - iter 864/1445 - loss 0.11769624 - time (sec): 14.30 - samples/sec: 7392.12 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-18 22:54:43,795 epoch 8 - iter 1008/1445 - loss 0.11773878 - time (sec): 16.76 - samples/sec: 7377.68 - lr: 0.000013 - momentum: 0.000000
190
+ 2023-10-18 22:54:46,163 epoch 8 - iter 1152/1445 - loss 0.11579635 - time (sec): 19.12 - samples/sec: 7331.13 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-18 22:54:48,494 epoch 8 - iter 1296/1445 - loss 0.11660615 - time (sec): 21.45 - samples/sec: 7351.02 - lr: 0.000012 - momentum: 0.000000
192
+ 2023-10-18 22:54:50,905 epoch 8 - iter 1440/1445 - loss 0.11664721 - time (sec): 23.86 - samples/sec: 7365.31 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-18 22:54:50,980 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-18 22:54:50,980 EPOCH 8 done: loss 0.1166 - lr: 0.000011
195
+ 2023-10-18 22:54:53,066 DEV : loss 0.19956204295158386 - f1-score (micro avg) 0.5434
196
+ 2023-10-18 22:54:53,080 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-18 22:54:55,471 epoch 9 - iter 144/1445 - loss 0.11520321 - time (sec): 2.39 - samples/sec: 7521.67 - lr: 0.000011 - momentum: 0.000000
198
+ 2023-10-18 22:54:57,898 epoch 9 - iter 288/1445 - loss 0.12001827 - time (sec): 4.82 - samples/sec: 7468.77 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-18 22:55:00,238 epoch 9 - iter 432/1445 - loss 0.11044915 - time (sec): 7.16 - samples/sec: 7365.68 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-18 22:55:02,679 epoch 9 - iter 576/1445 - loss 0.10805370 - time (sec): 9.60 - samples/sec: 7325.82 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-18 22:55:05,091 epoch 9 - iter 720/1445 - loss 0.11126004 - time (sec): 12.01 - samples/sec: 7351.91 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-18 22:55:07,481 epoch 9 - iter 864/1445 - loss 0.11107034 - time (sec): 14.40 - samples/sec: 7406.58 - lr: 0.000008 - momentum: 0.000000
203
+ 2023-10-18 22:55:09,864 epoch 9 - iter 1008/1445 - loss 0.11224647 - time (sec): 16.78 - samples/sec: 7416.01 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-18 22:55:12,182 epoch 9 - iter 1152/1445 - loss 0.11351795 - time (sec): 19.10 - samples/sec: 7395.91 - lr: 0.000007 - momentum: 0.000000
205
+ 2023-10-18 22:55:14,679 epoch 9 - iter 1296/1445 - loss 0.11382066 - time (sec): 21.60 - samples/sec: 7353.71 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-18 22:55:17,000 epoch 9 - iter 1440/1445 - loss 0.11288922 - time (sec): 23.92 - samples/sec: 7345.54 - lr: 0.000006 - momentum: 0.000000
207
+ 2023-10-18 22:55:17,074 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-18 22:55:17,075 EPOCH 9 done: loss 0.1130 - lr: 0.000006
209
+ 2023-10-18 22:55:18,856 DEV : loss 0.19409048557281494 - f1-score (micro avg) 0.5636
210
+ 2023-10-18 22:55:18,870 saving best model
211
+ 2023-10-18 22:55:18,907 ----------------------------------------------------------------------------------------------------
212
+ 2023-10-18 22:55:21,246 epoch 10 - iter 144/1445 - loss 0.11919407 - time (sec): 2.34 - samples/sec: 7369.04 - lr: 0.000005 - momentum: 0.000000
213
+ 2023-10-18 22:55:23,624 epoch 10 - iter 288/1445 - loss 0.12311079 - time (sec): 4.72 - samples/sec: 7239.49 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-18 22:55:26,056 epoch 10 - iter 432/1445 - loss 0.12140389 - time (sec): 7.15 - samples/sec: 7266.09 - lr: 0.000004 - momentum: 0.000000
215
+ 2023-10-18 22:55:28,507 epoch 10 - iter 576/1445 - loss 0.11657262 - time (sec): 9.60 - samples/sec: 7407.10 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-18 22:55:30,961 epoch 10 - iter 720/1445 - loss 0.11243952 - time (sec): 12.05 - samples/sec: 7385.04 - lr: 0.000003 - momentum: 0.000000
217
+ 2023-10-18 22:55:33,205 epoch 10 - iter 864/1445 - loss 0.11354347 - time (sec): 14.30 - samples/sec: 7387.47 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-18 22:55:35,316 epoch 10 - iter 1008/1445 - loss 0.11085507 - time (sec): 16.41 - samples/sec: 7513.69 - lr: 0.000002 - momentum: 0.000000
219
+ 2023-10-18 22:55:37,805 epoch 10 - iter 1152/1445 - loss 0.10959603 - time (sec): 18.90 - samples/sec: 7503.00 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-18 22:55:40,166 epoch 10 - iter 1296/1445 - loss 0.11097144 - time (sec): 21.26 - samples/sec: 7447.61 - lr: 0.000001 - momentum: 0.000000
221
+ 2023-10-18 22:55:42,632 epoch 10 - iter 1440/1445 - loss 0.11183179 - time (sec): 23.72 - samples/sec: 7402.41 - lr: 0.000000 - momentum: 0.000000
222
+ 2023-10-18 22:55:42,711 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-18 22:55:42,712 EPOCH 10 done: loss 0.1119 - lr: 0.000000
224
+ 2023-10-18 22:55:44,486 DEV : loss 0.19939179718494415 - f1-score (micro avg) 0.5604
225
+ 2023-10-18 22:55:44,530 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-18 22:55:44,530 Loading model from best epoch ...
227
+ 2023-10-18 22:55:44,613 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
228
+ 2023-10-18 22:55:45,906
229
+ Results:
230
+ - F-score (micro) 0.5542
231
+ - F-score (macro) 0.392
232
+ - Accuracy 0.393
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ LOC 0.6227 0.6594 0.6405 458
238
+ PER 0.5196 0.4959 0.5074 482
239
+ ORG 0.5000 0.0145 0.0282 69
240
+
241
+ micro avg 0.5723 0.5372 0.5542 1009
242
+ macro avg 0.5474 0.3899 0.3920 1009
243
+ weighted avg 0.5650 0.5372 0.5351 1009
244
+
245
+ 2023-10-18 22:55:45,907 ----------------------------------------------------------------------------------------------------