Hugging Face's logo

stefan-it
/
hmbench-icdar-fr-hmbert-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
fca9cec
•
1 Parent(s): 99d6731

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 +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f83b40cd4a4a7e026d57483142f9ff5aec2037f21a8485fba08127a2a34a4227
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 21:11:27 0.0000 0.3157 0.1070 0.6255 0.7387 0.6774 0.5415
3
+ 2 21:13:02 0.0000 0.1166 0.0982 0.6640 0.7466 0.7029 0.5670
4
+ 3 21:14:37 0.0000 0.0890 0.1266 0.6846 0.7907 0.7339 0.6031
5
+ 4 21:16:12 0.0000 0.0668 0.1627 0.7301 0.7557 0.7426 0.6112
6
+ 5 21:17:48 0.0000 0.0536 0.1772 0.7413 0.7715 0.7561 0.6268
7
+ 6 21:19:23 0.0000 0.0401 0.1878 0.7402 0.7477 0.7440 0.6160
8
+ 7 21:21:00 0.0000 0.0282 0.1914 0.7648 0.7613 0.7630 0.6361
9
+ 8 21:22:33 0.0000 0.0175 0.2060 0.7424 0.8020 0.7711 0.6481
10
+ 9 21:24:08 0.0000 0.0127 0.2049 0.7540 0.7941 0.7736 0.6488
11
+ 10 21:25:45 0.0000 0.0086 0.2193 0.7548 0.7941 0.7740 0.6488
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 21:09:52,051 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 21:09:52,052 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 21:09:52,052 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 21:09:52,052 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 21:09:52,052 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 21:09:52,052 Train: 7936 sentences
55
+ 2023-10-13 21:09:52,052 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 21:09:52,052 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 21:09:52,052 Training Params:
58
+ 2023-10-13 21:09:52,053 - learning_rate: "5e-05"
59
+ 2023-10-13 21:09:52,053 - mini_batch_size: "4"
60
+ 2023-10-13 21:09:52,053 - max_epochs: "10"
61
+ 2023-10-13 21:09:52,053 - shuffle: "True"
62
+ 2023-10-13 21:09:52,053 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 21:09:52,053 Plugins:
64
+ 2023-10-13 21:09:52,053 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 21:09:52,053 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 21:09:52,053 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 21:09:52,053 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 21:09:52,053 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 21:09:52,053 Computation:
70
+ 2023-10-13 21:09:52,053 - compute on device: cuda:0
71
+ 2023-10-13 21:09:52,053 - embedding storage: none
72
+ 2023-10-13 21:09:52,053 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 21:09:52,053 Model training base path: "hmbench-icdar/fr-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 21:09:52,053 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 21:09:52,053 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 21:10:01,654 epoch 1 - iter 198/1984 - loss 1.57314828 - time (sec): 9.60 - samples/sec: 1674.91 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 21:10:10,891 epoch 1 - iter 396/1984 - loss 0.94482932 - time (sec): 18.84 - samples/sec: 1728.91 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 21:10:19,877 epoch 1 - iter 594/1984 - loss 0.70656946 - time (sec): 27.82 - samples/sec: 1767.52 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 21:10:28,806 epoch 1 - iter 792/1984 - loss 0.57589195 - time (sec): 36.75 - samples/sec: 1776.73 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 21:10:37,770 epoch 1 - iter 990/1984 - loss 0.49394510 - time (sec): 45.72 - samples/sec: 1780.76 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-13 21:10:47,231 epoch 1 - iter 1188/1984 - loss 0.43440653 - time (sec): 55.18 - samples/sec: 1768.08 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-13 21:10:56,769 epoch 1 - iter 1386/1984 - loss 0.39123991 - time (sec): 64.71 - samples/sec: 1772.12 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-13 21:11:05,879 epoch 1 - iter 1584/1984 - loss 0.35692182 - time (sec): 73.82 - samples/sec: 1790.27 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-13 21:11:14,766 epoch 1 - iter 1782/1984 - loss 0.33500315 - time (sec): 82.71 - samples/sec: 1790.47 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-13 21:11:23,785 epoch 1 - iter 1980/1984 - loss 0.31600489 - time (sec): 91.73 - samples/sec: 1785.44 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-13 21:11:23,964 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 21:11:23,964 EPOCH 1 done: loss 0.3157 - lr: 0.000050
88
+ 2023-10-13 21:11:27,089 DEV : loss 0.10700166970491409 - f1-score (micro avg) 0.6774
89
+ 2023-10-13 21:11:27,109 saving best model
90
+ 2023-10-13 21:11:27,560 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 21:11:36,750 epoch 2 - iter 198/1984 - loss 0.12449949 - time (sec): 9.19 - samples/sec: 1878.49 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 21:11:45,799 epoch 2 - iter 396/1984 - loss 0.12255206 - time (sec): 18.24 - samples/sec: 1777.92 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 21:11:55,488 epoch 2 - iter 594/1984 - loss 0.12029581 - time (sec): 27.93 - samples/sec: 1784.54 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 21:12:04,857 epoch 2 - iter 792/1984 - loss 0.11861062 - time (sec): 37.29 - samples/sec: 1736.16 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 21:12:14,075 epoch 2 - iter 990/1984 - loss 0.11960110 - time (sec): 46.51 - samples/sec: 1766.04 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 21:12:22,965 epoch 2 - iter 1188/1984 - loss 0.11657540 - time (sec): 55.40 - samples/sec: 1770.76 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 21:12:32,062 epoch 2 - iter 1386/1984 - loss 0.11794534 - time (sec): 64.50 - samples/sec: 1776.69 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 21:12:41,040 epoch 2 - iter 1584/1984 - loss 0.11799208 - time (sec): 73.48 - samples/sec: 1776.65 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 21:12:49,960 epoch 2 - iter 1782/1984 - loss 0.11734119 - time (sec): 82.40 - samples/sec: 1787.75 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 21:12:58,919 epoch 2 - iter 1980/1984 - loss 0.11668880 - time (sec): 91.36 - samples/sec: 1792.51 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-13 21:12:59,093 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 21:12:59,093 EPOCH 2 done: loss 0.1166 - lr: 0.000044
103
+ 2023-10-13 21:13:02,923 DEV : loss 0.098160520195961 - f1-score (micro avg) 0.7029
104
+ 2023-10-13 21:13:02,942 saving best model
105
+ 2023-10-13 21:13:03,474 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 21:13:12,412 epoch 3 - iter 198/1984 - loss 0.08773465 - time (sec): 8.94 - samples/sec: 1833.04 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 21:13:21,418 epoch 3 - iter 396/1984 - loss 0.08439184 - time (sec): 17.94 - samples/sec: 1776.93 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 21:13:30,440 epoch 3 - iter 594/1984 - loss 0.07868581 - time (sec): 26.96 - samples/sec: 1833.42 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 21:13:39,685 epoch 3 - iter 792/1984 - loss 0.08531933 - time (sec): 36.21 - samples/sec: 1840.58 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 21:13:48,778 epoch 3 - iter 990/1984 - loss 0.08514713 - time (sec): 45.30 - samples/sec: 1828.82 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 21:13:57,734 epoch 3 - iter 1188/1984 - loss 0.08825157 - time (sec): 54.26 - samples/sec: 1825.18 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 21:14:06,673 epoch 3 - iter 1386/1984 - loss 0.08814664 - time (sec): 63.20 - samples/sec: 1819.58 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 21:14:15,704 epoch 3 - iter 1584/1984 - loss 0.09009066 - time (sec): 72.23 - samples/sec: 1820.88 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 21:14:24,715 epoch 3 - iter 1782/1984 - loss 0.09006858 - time (sec): 81.24 - samples/sec: 1818.73 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-13 21:14:33,667 epoch 3 - iter 1980/1984 - loss 0.08914040 - time (sec): 90.19 - samples/sec: 1813.41 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 21:14:33,845 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 21:14:33,845 EPOCH 3 done: loss 0.0890 - lr: 0.000039
118
+ 2023-10-13 21:14:37,406 DEV : loss 0.12662376463413239 - f1-score (micro avg) 0.7339
119
+ 2023-10-13 21:14:37,432 saving best model
120
+ 2023-10-13 21:14:38,036 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 21:14:47,082 epoch 4 - iter 198/1984 - loss 0.06364157 - time (sec): 9.04 - samples/sec: 1828.28 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 21:14:56,152 epoch 4 - iter 396/1984 - loss 0.06757552 - time (sec): 18.11 - samples/sec: 1835.62 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 21:15:05,034 epoch 4 - iter 594/1984 - loss 0.06841129 - time (sec): 26.99 - samples/sec: 1817.44 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 21:15:13,994 epoch 4 - iter 792/1984 - loss 0.06652070 - time (sec): 35.95 - samples/sec: 1809.83 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 21:15:23,002 epoch 4 - iter 990/1984 - loss 0.06676259 - time (sec): 44.96 - samples/sec: 1810.97 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 21:15:32,008 epoch 4 - iter 1188/1984 - loss 0.06542120 - time (sec): 53.97 - samples/sec: 1810.27 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 21:15:40,984 epoch 4 - iter 1386/1984 - loss 0.06788585 - time (sec): 62.94 - samples/sec: 1810.85 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 21:15:50,127 epoch 4 - iter 1584/1984 - loss 0.06753735 - time (sec): 72.09 - samples/sec: 1802.82 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-13 21:15:59,268 epoch 4 - iter 1782/1984 - loss 0.06658891 - time (sec): 81.23 - samples/sec: 1804.20 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 21:16:08,240 epoch 4 - iter 1980/1984 - loss 0.06689595 - time (sec): 90.20 - samples/sec: 1815.32 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 21:16:08,414 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 21:16:08,414 EPOCH 4 done: loss 0.0668 - lr: 0.000033
133
+ 2023-10-13 21:16:12,009 DEV : loss 0.1626797765493393 - f1-score (micro avg) 0.7426
134
+ 2023-10-13 21:16:12,038 saving best model
135
+ 2023-10-13 21:16:12,616 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 21:16:22,166 epoch 5 - iter 198/1984 - loss 0.05707626 - time (sec): 9.55 - samples/sec: 1742.71 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 21:16:31,599 epoch 5 - iter 396/1984 - loss 0.05057017 - time (sec): 18.98 - samples/sec: 1736.15 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 21:16:40,701 epoch 5 - iter 594/1984 - loss 0.05284113 - time (sec): 28.08 - samples/sec: 1754.35 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 21:16:49,956 epoch 5 - iter 792/1984 - loss 0.05196859 - time (sec): 37.34 - samples/sec: 1785.68 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 21:16:58,899 epoch 5 - iter 990/1984 - loss 0.05288056 - time (sec): 46.28 - samples/sec: 1797.84 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 21:17:07,821 epoch 5 - iter 1188/1984 - loss 0.05233510 - time (sec): 55.20 - samples/sec: 1797.48 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 21:17:16,772 epoch 5 - iter 1386/1984 - loss 0.05315803 - time (sec): 64.15 - samples/sec: 1794.32 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-13 21:17:25,950 epoch 5 - iter 1584/1984 - loss 0.05266700 - time (sec): 73.33 - samples/sec: 1794.36 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 21:17:34,933 epoch 5 - iter 1782/1984 - loss 0.05326372 - time (sec): 82.31 - samples/sec: 1798.69 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 21:17:43,886 epoch 5 - iter 1980/1984 - loss 0.05366528 - time (sec): 91.27 - samples/sec: 1792.47 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 21:17:44,081 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 21:17:44,081 EPOCH 5 done: loss 0.0536 - lr: 0.000028
148
+ 2023-10-13 21:17:47,992 DEV : loss 0.17723220586776733 - f1-score (micro avg) 0.7561
149
+ 2023-10-13 21:17:48,015 saving best model
150
+ 2023-10-13 21:17:48,548 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 21:17:57,694 epoch 6 - iter 198/1984 - loss 0.03763551 - time (sec): 9.15 - samples/sec: 1813.48 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 21:18:06,904 epoch 6 - iter 396/1984 - loss 0.03893849 - time (sec): 18.36 - samples/sec: 1842.25 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-13 21:18:16,141 epoch 6 - iter 594/1984 - loss 0.03776879 - time (sec): 27.59 - samples/sec: 1800.77 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 21:18:25,473 epoch 6 - iter 792/1984 - loss 0.03719490 - time (sec): 36.92 - samples/sec: 1775.51 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-13 21:18:34,661 epoch 6 - iter 990/1984 - loss 0.03762218 - time (sec): 46.11 - samples/sec: 1776.83 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-13 21:18:43,620 epoch 6 - iter 1188/1984 - loss 0.03873105 - time (sec): 55.07 - samples/sec: 1786.34 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-13 21:18:52,599 epoch 6 - iter 1386/1984 - loss 0.03856198 - time (sec): 64.05 - samples/sec: 1797.77 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-13 21:19:01,520 epoch 6 - iter 1584/1984 - loss 0.03903961 - time (sec): 72.97 - samples/sec: 1801.11 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 21:19:10,502 epoch 6 - iter 1782/1984 - loss 0.03926235 - time (sec): 81.95 - samples/sec: 1798.82 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-13 21:19:19,517 epoch 6 - iter 1980/1984 - loss 0.04014236 - time (sec): 90.97 - samples/sec: 1799.22 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-13 21:19:19,698 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 21:19:19,698 EPOCH 6 done: loss 0.0401 - lr: 0.000022
163
+ 2023-10-13 21:19:23,200 DEV : loss 0.18782225251197815 - f1-score (micro avg) 0.744
164
+ 2023-10-13 21:19:23,224 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 21:19:32,531 epoch 7 - iter 198/1984 - loss 0.02824745 - time (sec): 9.31 - samples/sec: 1651.36 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-13 21:19:41,932 epoch 7 - iter 396/1984 - loss 0.02833595 - time (sec): 18.71 - samples/sec: 1721.59 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 21:19:51,512 epoch 7 - iter 594/1984 - loss 0.02650201 - time (sec): 28.29 - samples/sec: 1689.25 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-13 21:20:00,933 epoch 7 - iter 792/1984 - loss 0.02830249 - time (sec): 37.71 - samples/sec: 1696.26 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-13 21:20:09,940 epoch 7 - iter 990/1984 - loss 0.02699457 - time (sec): 46.71 - samples/sec: 1737.12 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-13 21:20:19,637 epoch 7 - iter 1188/1984 - loss 0.02713766 - time (sec): 56.41 - samples/sec: 1745.60 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-13 21:20:29,015 epoch 7 - iter 1386/1984 - loss 0.02807107 - time (sec): 65.79 - samples/sec: 1727.94 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 21:20:38,025 epoch 7 - iter 1584/1984 - loss 0.02793388 - time (sec): 74.80 - samples/sec: 1747.11 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-13 21:20:47,096 epoch 7 - iter 1782/1984 - loss 0.02878022 - time (sec): 83.87 - samples/sec: 1753.11 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 21:20:55,978 epoch 7 - iter 1980/1984 - loss 0.02830615 - time (sec): 92.75 - samples/sec: 1763.80 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-13 21:20:56,162 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 21:20:56,162 EPOCH 7 done: loss 0.0282 - lr: 0.000017
177
+ 2023-10-13 21:21:00,009 DEV : loss 0.19144612550735474 - f1-score (micro avg) 0.763
178
+ 2023-10-13 21:21:00,029 saving best model
179
+ 2023-10-13 21:21:00,591 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 21:21:09,922 epoch 8 - iter 198/1984 - loss 0.01890035 - time (sec): 9.33 - samples/sec: 1751.85 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-13 21:21:19,057 epoch 8 - iter 396/1984 - loss 0.01767485 - time (sec): 18.46 - samples/sec: 1785.14 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-13 21:21:27,952 epoch 8 - iter 594/1984 - loss 0.01621751 - time (sec): 27.36 - samples/sec: 1785.22 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-13 21:21:36,767 epoch 8 - iter 792/1984 - loss 0.01561299 - time (sec): 36.17 - samples/sec: 1819.33 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-13 21:21:45,342 epoch 8 - iter 990/1984 - loss 0.01638503 - time (sec): 44.75 - samples/sec: 1829.74 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-13 21:21:53,833 epoch 8 - iter 1188/1984 - loss 0.01763387 - time (sec): 53.24 - samples/sec: 1827.41 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-13 21:22:02,464 epoch 8 - iter 1386/1984 - loss 0.01795526 - time (sec): 61.87 - samples/sec: 1842.78 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-13 21:22:11,253 epoch 8 - iter 1584/1984 - loss 0.01774552 - time (sec): 70.66 - samples/sec: 1862.31 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-13 21:22:20,490 epoch 8 - iter 1782/1984 - loss 0.01753201 - time (sec): 79.89 - samples/sec: 1845.71 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-13 21:22:29,666 epoch 8 - iter 1980/1984 - loss 0.01755699 - time (sec): 89.07 - samples/sec: 1838.26 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-13 21:22:29,843 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 21:22:29,843 EPOCH 8 done: loss 0.0175 - lr: 0.000011
192
+ 2023-10-13 21:22:33,369 DEV : loss 0.2059580534696579 - f1-score (micro avg) 0.7711
193
+ 2023-10-13 21:22:33,395 saving best model
194
+ 2023-10-13 21:22:33,947 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-13 21:22:43,129 epoch 9 - iter 198/1984 - loss 0.01401159 - time (sec): 9.18 - samples/sec: 1824.43 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-13 21:22:52,178 epoch 9 - iter 396/1984 - loss 0.01102370 - time (sec): 18.23 - samples/sec: 1798.64 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-13 21:23:01,192 epoch 9 - iter 594/1984 - loss 0.01127156 - time (sec): 27.24 - samples/sec: 1785.58 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-13 21:23:10,348 epoch 9 - iter 792/1984 - loss 0.01140865 - time (sec): 36.40 - samples/sec: 1807.20 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-13 21:23:19,348 epoch 9 - iter 990/1984 - loss 0.01159091 - time (sec): 45.40 - samples/sec: 1817.85 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-13 21:23:28,275 epoch 9 - iter 1188/1984 - loss 0.01135423 - time (sec): 54.32 - samples/sec: 1805.71 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-13 21:23:37,355 epoch 9 - iter 1386/1984 - loss 0.01161526 - time (sec): 63.40 - samples/sec: 1800.54 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-13 21:23:46,647 epoch 9 - iter 1584/1984 - loss 0.01193952 - time (sec): 72.70 - samples/sec: 1802.01 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-13 21:23:56,078 epoch 9 - iter 1782/1984 - loss 0.01265391 - time (sec): 82.13 - samples/sec: 1800.11 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-13 21:24:05,126 epoch 9 - iter 1980/1984 - loss 0.01277214 - time (sec): 91.18 - samples/sec: 1794.10 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-13 21:24:05,313 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 21:24:05,313 EPOCH 9 done: loss 0.0127 - lr: 0.000006
207
+ 2023-10-13 21:24:08,821 DEV : loss 0.2048816680908203 - f1-score (micro avg) 0.7736
208
+ 2023-10-13 21:24:08,849 saving best model
209
+ 2023-10-13 21:24:09,365 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-13 21:24:18,894 epoch 10 - iter 198/1984 - loss 0.01189187 - time (sec): 9.52 - samples/sec: 1789.41 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-13 21:24:28,197 epoch 10 - iter 396/1984 - loss 0.01127133 - time (sec): 18.83 - samples/sec: 1740.55 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-13 21:24:37,540 epoch 10 - iter 594/1984 - loss 0.01116046 - time (sec): 28.17 - samples/sec: 1732.33 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-13 21:24:46,777 epoch 10 - iter 792/1984 - loss 0.01063014 - time (sec): 37.41 - samples/sec: 1749.55 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-13 21:24:56,075 epoch 10 - iter 990/1984 - loss 0.01067083 - time (sec): 46.71 - samples/sec: 1744.53 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-13 21:25:05,141 epoch 10 - iter 1188/1984 - loss 0.00975194 - time (sec): 55.77 - samples/sec: 1756.59 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-13 21:25:14,121 epoch 10 - iter 1386/1984 - loss 0.00942246 - time (sec): 64.75 - samples/sec: 1765.55 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-13 21:25:23,112 epoch 10 - iter 1584/1984 - loss 0.00913427 - time (sec): 73.74 - samples/sec: 1775.53 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 21:25:32,155 epoch 10 - iter 1782/1984 - loss 0.00900070 - time (sec): 82.79 - samples/sec: 1787.74 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-13 21:25:41,053 epoch 10 - iter 1980/1984 - loss 0.00866710 - time (sec): 91.68 - samples/sec: 1784.89 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-13 21:25:41,229 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-13 21:25:41,229 EPOCH 10 done: loss 0.0086 - lr: 0.000000
222
+ 2023-10-13 21:25:45,158 DEV : loss 0.21929599344730377 - f1-score (micro avg) 0.774
223
+ 2023-10-13 21:25:45,188 saving best model
224
+ 2023-10-13 21:25:46,137 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-13 21:25:46,138 Loading model from best epoch ...
226
+ 2023-10-13 21:25:47,640 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
227
+ 2023-10-13 21:25:50,920
228
+ Results:
229
+ - F-score (micro) 0.7904
230
+ - F-score (macro) 0.7146
231
+ - Accuracy 0.6747
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.8228 0.8580 0.8401 655
237
+ PER 0.7312 0.8296 0.7773 223
238
+ ORG 0.5941 0.4724 0.5263 127
239
+
240
+ micro avg 0.7782 0.8030 0.7904 1005
241
+ macro avg 0.7160 0.7200 0.7146 1005
242
+ weighted avg 0.7736 0.8030 0.7865 1005
243
+
244
+ 2023-10-13 21:25:50,920 ----------------------------------------------------------------------------------------------------