Hugging Face's logo

hmbert
/
flair-icdar-fr

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
d828b44
·
1 Parent(s): 209a87a

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +239 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bc1189c2fa966bfe1c0920ce749e615d0cba4e2900ccab695efdc3ca5e79c2d
3
+ size 443311111
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 23:40:30 0.0000 0.3524 0.1243 0.7211 0.6991 0.7099 0.5696
3
+ 2 23:42:05 0.0000 0.1110 0.0963 0.6993 0.7602 0.7285 0.5905
4
+ 3 23:43:40 0.0000 0.0797 0.1172 0.7284 0.7828 0.7546 0.6234
5
+ 4 23:45:15 0.0000 0.0592 0.1438 0.7555 0.8111 0.7823 0.6572
6
+ 5 23:46:51 0.0000 0.0446 0.1670 0.7457 0.7896 0.7670 0.6421
7
+ 6 23:48:25 0.0000 0.0354 0.1907 0.7550 0.7670 0.7609 0.6331
8
+ 7 23:49:59 0.0000 0.0235 0.1984 0.7671 0.7975 0.7820 0.6595
9
+ 8 23:51:33 0.0000 0.0175 0.2155 0.7417 0.7862 0.7633 0.6382
10
+ 9 23:53:07 0.0000 0.0105 0.2331 0.7404 0.7873 0.7632 0.6379
11
+ 10 23:54:41 0.0000 0.0069 0.2377 0.7511 0.7919 0.7709 0.6470
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 23:38:56,260 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 23:38:56,261 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), 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=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 23:38:56,261 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 23:38:56,261 MultiCorpus: 7936 train + 992 dev + 992 test sentences
52
+ - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr
53
+ 2023-10-13 23:38:56,261 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 23:38:56,261 Train: 7936 sentences
55
+ 2023-10-13 23:38:56,261 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 23:38:56,261 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 23:38:56,261 Training Params:
58
+ 2023-10-13 23:38:56,261 - learning_rate: "3e-05"
59
+ 2023-10-13 23:38:56,261 - mini_batch_size: "4"
60
+ 2023-10-13 23:38:56,261 - max_epochs: "10"
61
+ 2023-10-13 23:38:56,261 - shuffle: "True"
62
+ 2023-10-13 23:38:56,261 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 23:38:56,261 Plugins:
64
+ 2023-10-13 23:38:56,261 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 23:38:56,261 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 23:38:56,261 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 23:38:56,261 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 23:38:56,262 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 23:38:56,262 Computation:
70
+ 2023-10-13 23:38:56,262 - compute on device: cuda:0
71
+ 2023-10-13 23:38:56,262 - embedding storage: none
72
+ 2023-10-13 23:38:56,262 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 23:38:56,262 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
74
+ 2023-10-13 23:38:56,262 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 23:38:56,262 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 23:39:05,623 epoch 1 - iter 198/1984 - loss 1.83762815 - time (sec): 9.36 - samples/sec: 1740.22 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 23:39:14,861 epoch 1 - iter 396/1984 - loss 1.09662191 - time (sec): 18.60 - samples/sec: 1741.17 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 23:39:23,842 epoch 1 - iter 594/1984 - loss 0.81504132 - time (sec): 27.58 - samples/sec: 1746.82 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 23:39:32,828 epoch 1 - iter 792/1984 - loss 0.66249214 - time (sec): 36.57 - samples/sec: 1765.29 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 23:39:41,985 epoch 1 - iter 990/1984 - loss 0.56311956 - time (sec): 45.72 - samples/sec: 1779.23 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 23:39:51,226 epoch 1 - iter 1188/1984 - loss 0.48540145 - time (sec): 54.96 - samples/sec: 1808.89 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 23:40:00,329 epoch 1 - iter 1386/1984 - loss 0.44028878 - time (sec): 64.07 - samples/sec: 1802.31 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 23:40:09,323 epoch 1 - iter 1584/1984 - loss 0.40258648 - time (sec): 73.06 - samples/sec: 1804.47 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 23:40:18,196 epoch 1 - iter 1782/1984 - loss 0.37540297 - time (sec): 81.93 - samples/sec: 1799.90 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 23:40:27,100 epoch 1 - iter 1980/1984 - loss 0.35246436 - time (sec): 90.84 - samples/sec: 1801.35 - lr: 0.000030 - momentum: 0.000000
86
+ 2023-10-13 23:40:27,278 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 23:40:27,278 EPOCH 1 done: loss 0.3524 - lr: 0.000030
88
+ 2023-10-13 23:40:30,422 DEV : loss 0.12433891743421555 - f1-score (micro avg) 0.7099
89
+ 2023-10-13 23:40:30,444 saving best model
90
+ 2023-10-13 23:40:30,861 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 23:40:39,812 epoch 2 - iter 198/1984 - loss 0.11828575 - time (sec): 8.95 - samples/sec: 1789.32 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 23:40:48,784 epoch 2 - iter 396/1984 - loss 0.11140177 - time (sec): 17.92 - samples/sec: 1815.27 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 23:40:58,222 epoch 2 - iter 594/1984 - loss 0.11940888 - time (sec): 27.36 - samples/sec: 1789.15 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 23:41:07,249 epoch 2 - iter 792/1984 - loss 0.11906737 - time (sec): 36.39 - samples/sec: 1799.64 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 23:41:16,257 epoch 2 - iter 990/1984 - loss 0.11891276 - time (sec): 45.39 - samples/sec: 1804.73 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 23:41:25,219 epoch 2 - iter 1188/1984 - loss 0.11640076 - time (sec): 54.36 - samples/sec: 1812.33 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 23:41:34,108 epoch 2 - iter 1386/1984 - loss 0.11635323 - time (sec): 63.25 - samples/sec: 1815.08 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 23:41:43,049 epoch 2 - iter 1584/1984 - loss 0.11619891 - time (sec): 72.19 - samples/sec: 1814.34 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 23:41:52,022 epoch 2 - iter 1782/1984 - loss 0.11338861 - time (sec): 81.16 - samples/sec: 1818.54 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 23:42:01,193 epoch 2 - iter 1980/1984 - loss 0.11087439 - time (sec): 90.33 - samples/sec: 1812.59 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 23:42:01,372 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 23:42:01,372 EPOCH 2 done: loss 0.1110 - lr: 0.000027
103
+ 2023-10-13 23:42:05,217 DEV : loss 0.09629001468420029 - f1-score (micro avg) 0.7285
104
+ 2023-10-13 23:42:05,237 saving best model
105
+ 2023-10-13 23:42:05,739 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 23:42:15,161 epoch 3 - iter 198/1984 - loss 0.07429461 - time (sec): 9.42 - samples/sec: 1699.53 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 23:42:24,281 epoch 3 - iter 396/1984 - loss 0.08110074 - time (sec): 18.54 - samples/sec: 1720.44 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 23:42:33,319 epoch 3 - iter 594/1984 - loss 0.08477110 - time (sec): 27.58 - samples/sec: 1770.13 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 23:42:42,426 epoch 3 - iter 792/1984 - loss 0.08227969 - time (sec): 36.68 - samples/sec: 1798.59 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 23:42:51,384 epoch 3 - iter 990/1984 - loss 0.08206052 - time (sec): 45.64 - samples/sec: 1800.84 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 23:43:00,378 epoch 3 - iter 1188/1984 - loss 0.08348155 - time (sec): 54.63 - samples/sec: 1794.26 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 23:43:09,338 epoch 3 - iter 1386/1984 - loss 0.08114266 - time (sec): 63.60 - samples/sec: 1796.94 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 23:43:18,462 epoch 3 - iter 1584/1984 - loss 0.07984718 - time (sec): 72.72 - samples/sec: 1803.30 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 23:43:27,624 epoch 3 - iter 1782/1984 - loss 0.07934502 - time (sec): 81.88 - samples/sec: 1801.00 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 23:43:36,624 epoch 3 - iter 1980/1984 - loss 0.07959415 - time (sec): 90.88 - samples/sec: 1802.37 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 23:43:36,802 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 23:43:36,802 EPOCH 3 done: loss 0.0797 - lr: 0.000023
118
+ 2023-10-13 23:43:40,249 DEV : loss 0.11717832088470459 - f1-score (micro avg) 0.7546
119
+ 2023-10-13 23:43:40,270 saving best model
120
+ 2023-10-13 23:43:40,823 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 23:43:50,001 epoch 4 - iter 198/1984 - loss 0.06052117 - time (sec): 9.18 - samples/sec: 1734.76 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 23:43:59,043 epoch 4 - iter 396/1984 - loss 0.06140378 - time (sec): 18.22 - samples/sec: 1796.43 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 23:44:08,039 epoch 4 - iter 594/1984 - loss 0.06052478 - time (sec): 27.21 - samples/sec: 1754.30 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 23:44:17,139 epoch 4 - iter 792/1984 - loss 0.06090929 - time (sec): 36.31 - samples/sec: 1772.51 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 23:44:26,199 epoch 4 - iter 990/1984 - loss 0.05940225 - time (sec): 45.37 - samples/sec: 1784.17 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 23:44:35,410 epoch 4 - iter 1188/1984 - loss 0.06144572 - time (sec): 54.59 - samples/sec: 1792.61 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 23:44:44,471 epoch 4 - iter 1386/1984 - loss 0.06104930 - time (sec): 63.65 - samples/sec: 1790.11 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 23:44:53,448 epoch 4 - iter 1584/1984 - loss 0.06021919 - time (sec): 72.62 - samples/sec: 1787.03 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 23:45:02,466 epoch 4 - iter 1782/1984 - loss 0.06016900 - time (sec): 81.64 - samples/sec: 1792.86 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 23:45:11,679 epoch 4 - iter 1980/1984 - loss 0.05925545 - time (sec): 90.85 - samples/sec: 1801.73 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 23:45:11,872 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 23:45:11,872 EPOCH 4 done: loss 0.0592 - lr: 0.000020
133
+ 2023-10-13 23:45:15,405 DEV : loss 0.14380605518817902 - f1-score (micro avg) 0.7823
134
+ 2023-10-13 23:45:15,440 saving best model
135
+ 2023-10-13 23:45:15,946 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 23:45:25,143 epoch 5 - iter 198/1984 - loss 0.04087458 - time (sec): 9.19 - samples/sec: 1756.29 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 23:45:34,337 epoch 5 - iter 396/1984 - loss 0.04482892 - time (sec): 18.39 - samples/sec: 1786.25 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 23:45:43,527 epoch 5 - iter 594/1984 - loss 0.04311401 - time (sec): 27.58 - samples/sec: 1811.77 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 23:45:52,597 epoch 5 - iter 792/1984 - loss 0.04281423 - time (sec): 36.65 - samples/sec: 1791.80 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 23:46:01,560 epoch 5 - iter 990/1984 - loss 0.04332734 - time (sec): 45.61 - samples/sec: 1786.28 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 23:46:10,615 epoch 5 - iter 1188/1984 - loss 0.04358208 - time (sec): 54.66 - samples/sec: 1794.86 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 23:46:19,677 epoch 5 - iter 1386/1984 - loss 0.04379144 - time (sec): 63.73 - samples/sec: 1803.16 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 23:46:28,892 epoch 5 - iter 1584/1984 - loss 0.04545313 - time (sec): 72.94 - samples/sec: 1811.13 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 23:46:37,793 epoch 5 - iter 1782/1984 - loss 0.04375927 - time (sec): 81.84 - samples/sec: 1807.89 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 23:46:46,890 epoch 5 - iter 1980/1984 - loss 0.04461810 - time (sec): 90.94 - samples/sec: 1798.77 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 23:46:47,084 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 23:46:47,084 EPOCH 5 done: loss 0.0446 - lr: 0.000017
148
+ 2023-10-13 23:46:51,086 DEV : loss 0.16696855425834656 - f1-score (micro avg) 0.767
149
+ 2023-10-13 23:46:51,110 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 23:47:00,477 epoch 6 - iter 198/1984 - loss 0.03505539 - time (sec): 9.37 - samples/sec: 1863.68 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-13 23:47:09,450 epoch 6 - iter 396/1984 - loss 0.03251886 - time (sec): 18.34 - samples/sec: 1813.90 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 23:47:18,382 epoch 6 - iter 594/1984 - loss 0.03280510 - time (sec): 27.27 - samples/sec: 1791.04 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 23:47:27,447 epoch 6 - iter 792/1984 - loss 0.03472134 - time (sec): 36.34 - samples/sec: 1798.71 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-13 23:47:36,364 epoch 6 - iter 990/1984 - loss 0.03368279 - time (sec): 45.25 - samples/sec: 1793.01 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 23:47:45,255 epoch 6 - iter 1188/1984 - loss 0.03396626 - time (sec): 54.14 - samples/sec: 1792.49 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 23:47:54,494 epoch 6 - iter 1386/1984 - loss 0.03365918 - time (sec): 63.38 - samples/sec: 1800.85 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-13 23:48:03,472 epoch 6 - iter 1584/1984 - loss 0.03440385 - time (sec): 72.36 - samples/sec: 1803.11 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 23:48:12,439 epoch 6 - iter 1782/1984 - loss 0.03479304 - time (sec): 81.33 - samples/sec: 1808.13 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 23:48:21,422 epoch 6 - iter 1980/1984 - loss 0.03544213 - time (sec): 90.31 - samples/sec: 1813.02 - lr: 0.000013 - momentum: 0.000000
160
+ 2023-10-13 23:48:21,597 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 23:48:21,598 EPOCH 6 done: loss 0.0354 - lr: 0.000013
162
+ 2023-10-13 23:48:24,988 DEV : loss 0.1906966120004654 - f1-score (micro avg) 0.7609
163
+ 2023-10-13 23:48:25,009 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-13 23:48:34,032 epoch 7 - iter 198/1984 - loss 0.02239552 - time (sec): 9.02 - samples/sec: 1854.40 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-13 23:48:42,982 epoch 7 - iter 396/1984 - loss 0.01908052 - time (sec): 17.97 - samples/sec: 1843.91 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 23:48:52,026 epoch 7 - iter 594/1984 - loss 0.01846812 - time (sec): 27.02 - samples/sec: 1843.30 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-13 23:49:01,113 epoch 7 - iter 792/1984 - loss 0.02010717 - time (sec): 36.10 - samples/sec: 1803.01 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 23:49:10,095 epoch 7 - iter 990/1984 - loss 0.02248072 - time (sec): 45.08 - samples/sec: 1819.55 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 23:49:18,978 epoch 7 - iter 1188/1984 - loss 0.02304749 - time (sec): 53.97 - samples/sec: 1817.48 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-13 23:49:27,935 epoch 7 - iter 1386/1984 - loss 0.02228094 - time (sec): 62.93 - samples/sec: 1812.85 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 23:49:36,927 epoch 7 - iter 1584/1984 - loss 0.02350682 - time (sec): 71.92 - samples/sec: 1811.32 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 23:49:46,117 epoch 7 - iter 1782/1984 - loss 0.02341870 - time (sec): 81.11 - samples/sec: 1810.88 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-13 23:49:55,199 epoch 7 - iter 1980/1984 - loss 0.02353248 - time (sec): 90.19 - samples/sec: 1815.61 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 23:49:55,377 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-13 23:49:55,377 EPOCH 7 done: loss 0.0235 - lr: 0.000010
176
+ 2023-10-13 23:49:59,310 DEV : loss 0.19835640490055084 - f1-score (micro avg) 0.782
177
+ 2023-10-13 23:49:59,331 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-13 23:50:08,784 epoch 8 - iter 198/1984 - loss 0.02230710 - time (sec): 9.45 - samples/sec: 1803.36 - lr: 0.000010 - momentum: 0.000000
179
+ 2023-10-13 23:50:17,765 epoch 8 - iter 396/1984 - loss 0.01940484 - time (sec): 18.43 - samples/sec: 1809.43 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-13 23:50:26,817 epoch 8 - iter 594/1984 - loss 0.01764565 - time (sec): 27.48 - samples/sec: 1836.45 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-13 23:50:35,737 epoch 8 - iter 792/1984 - loss 0.01686537 - time (sec): 36.40 - samples/sec: 1833.82 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 23:50:44,795 epoch 8 - iter 990/1984 - loss 0.01829213 - time (sec): 45.46 - samples/sec: 1805.63 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-13 23:50:53,724 epoch 8 - iter 1188/1984 - loss 0.01820113 - time (sec): 54.39 - samples/sec: 1809.96 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-13 23:51:02,869 epoch 8 - iter 1386/1984 - loss 0.01748894 - time (sec): 63.54 - samples/sec: 1807.49 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 23:51:12,333 epoch 8 - iter 1584/1984 - loss 0.01719619 - time (sec): 73.00 - samples/sec: 1800.67 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-13 23:51:21,277 epoch 8 - iter 1782/1984 - loss 0.01734332 - time (sec): 81.94 - samples/sec: 1807.45 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-13 23:51:30,188 epoch 8 - iter 1980/1984 - loss 0.01756418 - time (sec): 90.86 - samples/sec: 1801.14 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 23:51:30,370 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-13 23:51:30,370 EPOCH 8 done: loss 0.0175 - lr: 0.000007
190
+ 2023-10-13 23:51:33,748 DEV : loss 0.215502068400383 - f1-score (micro avg) 0.7633
191
+ 2023-10-13 23:51:33,769 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-13 23:51:42,760 epoch 9 - iter 198/1984 - loss 0.01149768 - time (sec): 8.99 - samples/sec: 1769.82 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-13 23:51:51,819 epoch 9 - iter 396/1984 - loss 0.01515882 - time (sec): 18.05 - samples/sec: 1787.98 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-13 23:52:00,844 epoch 9 - iter 594/1984 - loss 0.01337974 - time (sec): 27.07 - samples/sec: 1824.64 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 23:52:09,839 epoch 9 - iter 792/1984 - loss 0.01205560 - time (sec): 36.07 - samples/sec: 1828.37 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-13 23:52:18,833 epoch 9 - iter 990/1984 - loss 0.01052937 - time (sec): 45.06 - samples/sec: 1821.80 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-13 23:52:27,846 epoch 9 - iter 1188/1984 - loss 0.01105230 - time (sec): 54.08 - samples/sec: 1822.13 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 23:52:36,854 epoch 9 - iter 1386/1984 - loss 0.01084377 - time (sec): 63.08 - samples/sec: 1815.25 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-13 23:52:45,813 epoch 9 - iter 1584/1984 - loss 0.01116629 - time (sec): 72.04 - samples/sec: 1817.09 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-13 23:52:54,838 epoch 9 - iter 1782/1984 - loss 0.01094512 - time (sec): 81.07 - samples/sec: 1812.73 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 23:53:03,779 epoch 9 - iter 1980/1984 - loss 0.01048321 - time (sec): 90.01 - samples/sec: 1818.01 - lr: 0.000003 - momentum: 0.000000
202
+ 2023-10-13 23:53:03,957 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-13 23:53:03,957 EPOCH 9 done: loss 0.0105 - lr: 0.000003
204
+ 2023-10-13 23:53:07,359 DEV : loss 0.2330678254365921 - f1-score (micro avg) 0.7632
205
+ 2023-10-13 23:53:07,381 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 23:53:16,538 epoch 10 - iter 198/1984 - loss 0.00727112 - time (sec): 9.16 - samples/sec: 1873.57 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-13 23:53:25,529 epoch 10 - iter 396/1984 - loss 0.00644925 - time (sec): 18.15 - samples/sec: 1829.60 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-13 23:53:34,573 epoch 10 - iter 594/1984 - loss 0.00644003 - time (sec): 27.19 - samples/sec: 1831.35 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-13 23:53:44,140 epoch 10 - iter 792/1984 - loss 0.00614650 - time (sec): 36.76 - samples/sec: 1815.49 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-13 23:53:53,201 epoch 10 - iter 990/1984 - loss 0.00665805 - time (sec): 45.82 - samples/sec: 1833.66 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-13 23:54:02,072 epoch 10 - iter 1188/1984 - loss 0.00708536 - time (sec): 54.69 - samples/sec: 1829.89 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-13 23:54:10,915 epoch 10 - iter 1386/1984 - loss 0.00771984 - time (sec): 63.53 - samples/sec: 1817.53 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-13 23:54:19,803 epoch 10 - iter 1584/1984 - loss 0.00781777 - time (sec): 72.42 - samples/sec: 1807.47 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-13 23:54:28,689 epoch 10 - iter 1782/1984 - loss 0.00737069 - time (sec): 81.31 - samples/sec: 1806.15 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-13 23:54:38,294 epoch 10 - iter 1980/1984 - loss 0.00694992 - time (sec): 90.91 - samples/sec: 1800.46 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-13 23:54:38,470 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-13 23:54:38,470 EPOCH 10 done: loss 0.0069 - lr: 0.000000
218
+ 2023-10-13 23:54:41,942 DEV : loss 0.23772144317626953 - f1-score (micro avg) 0.7709
219
+ 2023-10-13 23:54:42,395 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 23:54:42,396 Loading model from best epoch ...
221
+ 2023-10-13 23:54:43,833 SequenceTagger predicts: Dictionary with 13 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG
222
+ 2023-10-13 23:54:47,114
223
+ Results:
224
+ - F-score (micro) 0.7789
225
+ - F-score (macro) 0.6828
226
+ - Accuracy 0.6588
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ LOC 0.8215 0.8641 0.8423 655
232
+ PER 0.6963 0.8430 0.7627 223
233
+ ORG 0.4951 0.4016 0.4435 127
234
+
235
+ micro avg 0.7580 0.8010 0.7789 1005
236
+ macro avg 0.6710 0.7029 0.6828 1005
237
+ weighted avg 0.7525 0.8010 0.7742 1005
238
+
239
+ 2023-10-13 23:54:47,115 ----------------------------------------------------------------------------------------------------