Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
cd935fd
•
1 Parent(s): f001068

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.1697543574.4aef72135bc5.1113.5 +3 -0
  5. test.tsv +0 -0
  6. training.log +237 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7511c759fa3aeb9c82f40fa456b48e80471a9ffdd8126573871104e5b97425c2
3
+ size 440941957
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 11:56:51 0.0000 0.2669 0.1179 0.5754 0.4451 0.5019 0.3368
3
+ 2 12:00:37 0.0000 0.1063 0.1570 0.5153 0.8078 0.6292 0.4716
4
+ 3 12:04:26 0.0000 0.0853 0.2051 0.5385 0.7197 0.6161 0.4575
5
+ 4 12:08:18 0.0000 0.0634 0.2212 0.5229 0.7574 0.6187 0.4591
6
+ 5 12:12:14 0.0000 0.0447 0.2751 0.5412 0.7883 0.6418 0.4828
7
+ 6 12:16:06 0.0000 0.0337 0.3224 0.5494 0.7323 0.6278 0.4655
8
+ 7 12:19:51 0.0000 0.0202 0.3175 0.5696 0.6979 0.6272 0.4664
9
+ 8 12:23:48 0.0000 0.0148 0.3656 0.5721 0.7803 0.6602 0.4985
10
+ 9 12:27:50 0.0000 0.0077 0.4163 0.5656 0.7551 0.6467 0.4846
11
+ 10 12:31:47 0.0000 0.0046 0.4362 0.5647 0.7689 0.6512 0.4898
runs/events.out.tfevents.1697543574.4aef72135bc5.1113.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d322420d90691ad2631ae64feb21dde46c4cc6fd8ca6c913ab52a0f12174a0
3
+ size 2030580
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 11:52:54,786 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 11:52:54,787 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
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): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
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): ElectraSelfOutput(
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): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
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
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 11:52:54,787 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 11:52:54,787 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
48
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
49
+ 2023-10-17 11:52:54,787 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 11:52:54,787 Train: 14465 sentences
51
+ 2023-10-17 11:52:54,788 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 11:52:54,788 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 11:52:54,788 Training Params:
54
+ 2023-10-17 11:52:54,788 - learning_rate: "5e-05"
55
+ 2023-10-17 11:52:54,788 - mini_batch_size: "4"
56
+ 2023-10-17 11:52:54,788 - max_epochs: "10"
57
+ 2023-10-17 11:52:54,788 - shuffle: "True"
58
+ 2023-10-17 11:52:54,788 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 11:52:54,788 Plugins:
60
+ 2023-10-17 11:52:54,788 - TensorboardLogger
61
+ 2023-10-17 11:52:54,788 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 11:52:54,788 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 11:52:54,788 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 11:52:54,788 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 11:52:54,788 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 11:52:54,788 Computation:
67
+ 2023-10-17 11:52:54,789 - compute on device: cuda:0
68
+ 2023-10-17 11:52:54,789 - embedding storage: none
69
+ 2023-10-17 11:52:54,789 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 11:52:54,789 Model training base path: "hmbench-letemps/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 11:52:54,789 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 11:52:54,789 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 11:52:54,789 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 11:53:17,101 epoch 1 - iter 361/3617 - loss 1.45041553 - time (sec): 22.31 - samples/sec: 1698.14 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 11:53:38,886 epoch 1 - iter 722/3617 - loss 0.83716082 - time (sec): 44.10 - samples/sec: 1686.06 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 11:54:02,640 epoch 1 - iter 1083/3617 - loss 0.59781487 - time (sec): 67.85 - samples/sec: 1681.62 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 11:54:24,936 epoch 1 - iter 1444/3617 - loss 0.48149327 - time (sec): 90.15 - samples/sec: 1694.00 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 11:54:47,775 epoch 1 - iter 1805/3617 - loss 0.41319463 - time (sec): 112.98 - samples/sec: 1690.70 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 11:55:11,378 epoch 1 - iter 2166/3617 - loss 0.36558875 - time (sec): 136.59 - samples/sec: 1672.75 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 11:55:35,040 epoch 1 - iter 2527/3617 - loss 0.32938220 - time (sec): 160.25 - samples/sec: 1663.32 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 11:55:59,195 epoch 1 - iter 2888/3617 - loss 0.30249835 - time (sec): 184.40 - samples/sec: 1658.74 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 11:56:22,092 epoch 1 - iter 3249/3617 - loss 0.28225761 - time (sec): 207.30 - samples/sec: 1657.19 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 11:56:45,459 epoch 1 - iter 3610/3617 - loss 0.26717410 - time (sec): 230.67 - samples/sec: 1644.02 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 11:56:45,909 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 11:56:45,909 EPOCH 1 done: loss 0.2669 - lr: 0.000050
86
+ 2023-10-17 11:56:51,334 DEV : loss 0.11786916851997375 - f1-score (micro avg) 0.5019
87
+ 2023-10-17 11:56:51,374 saving best model
88
+ 2023-10-17 11:56:51,877 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 11:57:15,292 epoch 2 - iter 361/3617 - loss 0.10557221 - time (sec): 23.41 - samples/sec: 1662.15 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 11:57:37,011 epoch 2 - iter 722/3617 - loss 0.10278944 - time (sec): 45.13 - samples/sec: 1710.38 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 11:57:58,661 epoch 2 - iter 1083/3617 - loss 0.10655278 - time (sec): 66.78 - samples/sec: 1709.09 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 11:58:21,263 epoch 2 - iter 1444/3617 - loss 0.10643025 - time (sec): 89.38 - samples/sec: 1696.68 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 11:58:44,442 epoch 2 - iter 1805/3617 - loss 0.10457147 - time (sec): 112.56 - samples/sec: 1674.98 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 11:59:07,714 epoch 2 - iter 2166/3617 - loss 0.10556253 - time (sec): 135.84 - samples/sec: 1671.06 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 11:59:30,682 epoch 2 - iter 2527/3617 - loss 0.10440273 - time (sec): 158.80 - samples/sec: 1673.80 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 11:59:51,173 epoch 2 - iter 2888/3617 - loss 0.10398260 - time (sec): 179.29 - samples/sec: 1692.95 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 12:00:09,116 epoch 2 - iter 3249/3617 - loss 0.10460700 - time (sec): 197.24 - samples/sec: 1736.35 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 12:00:30,262 epoch 2 - iter 3610/3617 - loss 0.10618003 - time (sec): 218.38 - samples/sec: 1736.86 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 12:00:30,682 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 12:00:30,682 EPOCH 2 done: loss 0.1063 - lr: 0.000044
101
+ 2023-10-17 12:00:37,743 DEV : loss 0.15698249638080597 - f1-score (micro avg) 0.6292
102
+ 2023-10-17 12:00:37,792 saving best model
103
+ 2023-10-17 12:00:38,379 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 12:01:00,850 epoch 3 - iter 361/3617 - loss 0.08022559 - time (sec): 22.47 - samples/sec: 1636.31 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 12:01:23,625 epoch 3 - iter 722/3617 - loss 0.08069320 - time (sec): 45.24 - samples/sec: 1663.23 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 12:01:46,101 epoch 3 - iter 1083/3617 - loss 0.08181083 - time (sec): 67.72 - samples/sec: 1672.77 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 12:02:09,383 epoch 3 - iter 1444/3617 - loss 0.08325852 - time (sec): 91.00 - samples/sec: 1661.25 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 12:02:27,763 epoch 3 - iter 1805/3617 - loss 0.08237466 - time (sec): 109.38 - samples/sec: 1726.56 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 12:02:49,091 epoch 3 - iter 2166/3617 - loss 0.08389650 - time (sec): 130.71 - samples/sec: 1745.30 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 12:03:11,251 epoch 3 - iter 2527/3617 - loss 0.08517465 - time (sec): 152.87 - samples/sec: 1731.56 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 12:03:33,655 epoch 3 - iter 2888/3617 - loss 0.08551924 - time (sec): 175.27 - samples/sec: 1728.77 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 12:03:56,927 epoch 3 - iter 3249/3617 - loss 0.08551615 - time (sec): 198.55 - samples/sec: 1722.72 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 12:04:19,219 epoch 3 - iter 3610/3617 - loss 0.08533098 - time (sec): 220.84 - samples/sec: 1717.15 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 12:04:19,653 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 12:04:19,654 EPOCH 3 done: loss 0.0853 - lr: 0.000039
116
+ 2023-10-17 12:04:26,008 DEV : loss 0.20511414110660553 - f1-score (micro avg) 0.6161
117
+ 2023-10-17 12:04:26,049 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 12:04:49,116 epoch 4 - iter 361/3617 - loss 0.05873537 - time (sec): 23.07 - samples/sec: 1674.62 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 12:05:12,376 epoch 4 - iter 722/3617 - loss 0.06004159 - time (sec): 46.33 - samples/sec: 1645.73 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 12:05:35,066 epoch 4 - iter 1083/3617 - loss 0.06324927 - time (sec): 69.02 - samples/sec: 1673.37 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 12:05:57,755 epoch 4 - iter 1444/3617 - loss 0.06295022 - time (sec): 91.70 - samples/sec: 1671.02 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 12:06:20,466 epoch 4 - iter 1805/3617 - loss 0.06317630 - time (sec): 114.42 - samples/sec: 1668.82 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 12:06:42,695 epoch 4 - iter 2166/3617 - loss 0.06379107 - time (sec): 136.64 - samples/sec: 1673.67 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 12:07:04,646 epoch 4 - iter 2527/3617 - loss 0.06397835 - time (sec): 158.60 - samples/sec: 1681.56 - lr: 0.000035 - momentum: 0.000000
125
+ 2023-10-17 12:07:27,971 epoch 4 - iter 2888/3617 - loss 0.06348311 - time (sec): 181.92 - samples/sec: 1678.47 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 12:07:49,326 epoch 4 - iter 3249/3617 - loss 0.06347814 - time (sec): 203.28 - samples/sec: 1686.73 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 12:08:11,036 epoch 4 - iter 3610/3617 - loss 0.06347373 - time (sec): 224.98 - samples/sec: 1686.43 - lr: 0.000033 - momentum: 0.000000
128
+ 2023-10-17 12:08:11,436 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 12:08:11,436 EPOCH 4 done: loss 0.0634 - lr: 0.000033
130
+ 2023-10-17 12:08:18,597 DEV : loss 0.22120679914951324 - f1-score (micro avg) 0.6187
131
+ 2023-10-17 12:08:18,639 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-17 12:08:42,405 epoch 5 - iter 361/3617 - loss 0.03776153 - time (sec): 23.77 - samples/sec: 1596.80 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-17 12:09:05,646 epoch 5 - iter 722/3617 - loss 0.04135391 - time (sec): 47.01 - samples/sec: 1629.07 - lr: 0.000032 - momentum: 0.000000
134
+ 2023-10-17 12:09:28,421 epoch 5 - iter 1083/3617 - loss 0.04270991 - time (sec): 69.78 - samples/sec: 1637.87 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 12:09:51,769 epoch 5 - iter 1444/3617 - loss 0.04260540 - time (sec): 93.13 - samples/sec: 1635.70 - lr: 0.000031 - momentum: 0.000000
136
+ 2023-10-17 12:10:14,299 epoch 5 - iter 1805/3617 - loss 0.04110131 - time (sec): 115.66 - samples/sec: 1656.86 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 12:10:36,976 epoch 5 - iter 2166/3617 - loss 0.04177018 - time (sec): 138.34 - samples/sec: 1668.53 - lr: 0.000030 - momentum: 0.000000
138
+ 2023-10-17 12:10:59,264 epoch 5 - iter 2527/3617 - loss 0.04324074 - time (sec): 160.62 - samples/sec: 1663.73 - lr: 0.000029 - momentum: 0.000000
139
+ 2023-10-17 12:11:21,101 epoch 5 - iter 2888/3617 - loss 0.04411956 - time (sec): 182.46 - samples/sec: 1658.59 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 12:11:45,148 epoch 5 - iter 3249/3617 - loss 0.04348395 - time (sec): 206.51 - samples/sec: 1652.71 - lr: 0.000028 - momentum: 0.000000
141
+ 2023-10-17 12:12:07,783 epoch 5 - iter 3610/3617 - loss 0.04478114 - time (sec): 229.14 - samples/sec: 1654.40 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 12:12:08,198 ----------------------------------------------------------------------------------------------------
143
+ 2023-10-17 12:12:08,198 EPOCH 5 done: loss 0.0447 - lr: 0.000028
144
+ 2023-10-17 12:12:14,607 DEV : loss 0.2750839591026306 - f1-score (micro avg) 0.6418
145
+ 2023-10-17 12:12:14,652 saving best model
146
+ 2023-10-17 12:12:15,246 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 12:12:37,546 epoch 6 - iter 361/3617 - loss 0.02896062 - time (sec): 22.30 - samples/sec: 1678.63 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 12:13:01,122 epoch 6 - iter 722/3617 - loss 0.02877240 - time (sec): 45.87 - samples/sec: 1629.00 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 12:13:23,419 epoch 6 - iter 1083/3617 - loss 0.03088311 - time (sec): 68.17 - samples/sec: 1654.59 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 12:13:45,707 epoch 6 - iter 1444/3617 - loss 0.03181763 - time (sec): 90.46 - samples/sec: 1672.21 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 12:14:07,684 epoch 6 - iter 1805/3617 - loss 0.03280478 - time (sec): 112.44 - samples/sec: 1689.30 - lr: 0.000025 - momentum: 0.000000
152
+ 2023-10-17 12:14:30,091 epoch 6 - iter 2166/3617 - loss 0.03257395 - time (sec): 134.84 - samples/sec: 1691.26 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 12:14:52,451 epoch 6 - iter 2527/3617 - loss 0.03273840 - time (sec): 157.20 - samples/sec: 1693.80 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 12:15:16,751 epoch 6 - iter 2888/3617 - loss 0.03337305 - time (sec): 181.50 - samples/sec: 1675.04 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 12:15:39,289 epoch 6 - iter 3249/3617 - loss 0.03410165 - time (sec): 204.04 - samples/sec: 1671.99 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 12:15:59,015 epoch 6 - iter 3610/3617 - loss 0.03367272 - time (sec): 223.77 - samples/sec: 1695.44 - lr: 0.000022 - momentum: 0.000000
157
+ 2023-10-17 12:15:59,460 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 12:15:59,460 EPOCH 6 done: loss 0.0337 - lr: 0.000022
159
+ 2023-10-17 12:16:06,723 DEV : loss 0.3224092423915863 - f1-score (micro avg) 0.6278
160
+ 2023-10-17 12:16:06,764 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 12:16:30,012 epoch 7 - iter 361/3617 - loss 0.01207785 - time (sec): 23.25 - samples/sec: 1632.13 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 12:16:52,430 epoch 7 - iter 722/3617 - loss 0.01588108 - time (sec): 45.66 - samples/sec: 1649.57 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 12:17:14,472 epoch 7 - iter 1083/3617 - loss 0.01914681 - time (sec): 67.71 - samples/sec: 1671.24 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 12:17:38,387 epoch 7 - iter 1444/3617 - loss 0.02093559 - time (sec): 91.62 - samples/sec: 1648.96 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 12:18:00,039 epoch 7 - iter 1805/3617 - loss 0.02030467 - time (sec): 113.27 - samples/sec: 1670.47 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 12:18:22,176 epoch 7 - iter 2166/3617 - loss 0.02042856 - time (sec): 135.41 - samples/sec: 1675.92 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 12:18:45,119 epoch 7 - iter 2527/3617 - loss 0.01975550 - time (sec): 158.35 - samples/sec: 1676.74 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 12:19:04,588 epoch 7 - iter 2888/3617 - loss 0.01949421 - time (sec): 177.82 - samples/sec: 1705.58 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 12:19:22,591 epoch 7 - iter 3249/3617 - loss 0.01975215 - time (sec): 195.82 - samples/sec: 1746.76 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 12:19:44,496 epoch 7 - iter 3610/3617 - loss 0.02006605 - time (sec): 217.73 - samples/sec: 1742.14 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 12:19:44,901 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 12:19:44,901 EPOCH 7 done: loss 0.0202 - lr: 0.000017
173
+ 2023-10-17 12:19:51,251 DEV : loss 0.317545086145401 - f1-score (micro avg) 0.6272
174
+ 2023-10-17 12:19:51,295 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 12:20:13,563 epoch 8 - iter 361/3617 - loss 0.01412422 - time (sec): 22.27 - samples/sec: 1693.14 - lr: 0.000016 - momentum: 0.000000
176
+ 2023-10-17 12:20:37,743 epoch 8 - iter 722/3617 - loss 0.01808065 - time (sec): 46.45 - samples/sec: 1612.50 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 12:21:02,137 epoch 8 - iter 1083/3617 - loss 0.01681718 - time (sec): 70.84 - samples/sec: 1590.05 - lr: 0.000015 - momentum: 0.000000
178
+ 2023-10-17 12:21:26,146 epoch 8 - iter 1444/3617 - loss 0.01601246 - time (sec): 94.85 - samples/sec: 1600.06 - lr: 0.000014 - momentum: 0.000000
179
+ 2023-10-17 12:21:49,292 epoch 8 - iter 1805/3617 - loss 0.01568364 - time (sec): 117.99 - samples/sec: 1600.39 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 12:22:11,848 epoch 8 - iter 2166/3617 - loss 0.01635340 - time (sec): 140.55 - samples/sec: 1609.35 - lr: 0.000013 - momentum: 0.000000
181
+ 2023-10-17 12:22:33,797 epoch 8 - iter 2527/3617 - loss 0.01630735 - time (sec): 162.50 - samples/sec: 1622.79 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 12:22:55,815 epoch 8 - iter 2888/3617 - loss 0.01515567 - time (sec): 184.52 - samples/sec: 1637.90 - lr: 0.000012 - momentum: 0.000000
183
+ 2023-10-17 12:23:18,342 epoch 8 - iter 3249/3617 - loss 0.01483412 - time (sec): 207.05 - samples/sec: 1648.57 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 12:23:41,314 epoch 8 - iter 3610/3617 - loss 0.01486930 - time (sec): 230.02 - samples/sec: 1648.51 - lr: 0.000011 - momentum: 0.000000
185
+ 2023-10-17 12:23:41,781 ----------------------------------------------------------------------------------------------------
186
+ 2023-10-17 12:23:41,781 EPOCH 8 done: loss 0.0148 - lr: 0.000011
187
+ 2023-10-17 12:23:48,164 DEV : loss 0.3655739724636078 - f1-score (micro avg) 0.6602
188
+ 2023-10-17 12:23:48,207 saving best model
189
+ 2023-10-17 12:23:48,840 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 12:24:11,655 epoch 9 - iter 361/3617 - loss 0.00915400 - time (sec): 22.81 - samples/sec: 1667.62 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-17 12:24:34,394 epoch 9 - iter 722/3617 - loss 0.00828080 - time (sec): 45.55 - samples/sec: 1634.29 - lr: 0.000010 - momentum: 0.000000
192
+ 2023-10-17 12:24:57,398 epoch 9 - iter 1083/3617 - loss 0.00838778 - time (sec): 68.56 - samples/sec: 1624.06 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-17 12:25:21,466 epoch 9 - iter 1444/3617 - loss 0.00854920 - time (sec): 92.62 - samples/sec: 1609.74 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-17 12:25:44,800 epoch 9 - iter 1805/3617 - loss 0.00847143 - time (sec): 115.96 - samples/sec: 1621.53 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-17 12:26:07,965 epoch 9 - iter 2166/3617 - loss 0.00871744 - time (sec): 139.12 - samples/sec: 1625.29 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 12:26:31,239 epoch 9 - iter 2527/3617 - loss 0.00823885 - time (sec): 162.40 - samples/sec: 1627.58 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-17 12:26:55,849 epoch 9 - iter 2888/3617 - loss 0.00773025 - time (sec): 187.01 - samples/sec: 1618.47 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 12:27:19,397 epoch 9 - iter 3249/3617 - loss 0.00760834 - time (sec): 210.55 - samples/sec: 1614.92 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-17 12:27:43,113 epoch 9 - iter 3610/3617 - loss 0.00769799 - time (sec): 234.27 - samples/sec: 1618.48 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 12:27:43,552 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-17 12:27:43,552 EPOCH 9 done: loss 0.0077 - lr: 0.000006
202
+ 2023-10-17 12:27:49,962 DEV : loss 0.4163112938404083 - f1-score (micro avg) 0.6467
203
+ 2023-10-17 12:27:50,004 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 12:28:13,013 epoch 10 - iter 361/3617 - loss 0.00413246 - time (sec): 23.01 - samples/sec: 1593.63 - lr: 0.000005 - momentum: 0.000000
205
+ 2023-10-17 12:28:35,587 epoch 10 - iter 722/3617 - loss 0.00334843 - time (sec): 45.58 - samples/sec: 1657.68 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-17 12:28:58,768 epoch 10 - iter 1083/3617 - loss 0.00444223 - time (sec): 68.76 - samples/sec: 1625.52 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 12:29:22,388 epoch 10 - iter 1444/3617 - loss 0.00421888 - time (sec): 92.38 - samples/sec: 1628.53 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 12:29:45,256 epoch 10 - iter 1805/3617 - loss 0.00399761 - time (sec): 115.25 - samples/sec: 1631.71 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 12:30:07,935 epoch 10 - iter 2166/3617 - loss 0.00472994 - time (sec): 137.93 - samples/sec: 1641.01 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 12:30:31,147 epoch 10 - iter 2527/3617 - loss 0.00456748 - time (sec): 161.14 - samples/sec: 1631.95 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 12:30:54,698 epoch 10 - iter 2888/3617 - loss 0.00474495 - time (sec): 184.69 - samples/sec: 1636.72 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 12:31:16,709 epoch 10 - iter 3249/3617 - loss 0.00463207 - time (sec): 206.70 - samples/sec: 1652.97 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 12:31:40,217 epoch 10 - iter 3610/3617 - loss 0.00465381 - time (sec): 230.21 - samples/sec: 1647.46 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-17 12:31:40,665 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-17 12:31:40,665 EPOCH 10 done: loss 0.0046 - lr: 0.000000
216
+ 2023-10-17 12:31:47,136 DEV : loss 0.43618330359458923 - f1-score (micro avg) 0.6512
217
+ 2023-10-17 12:31:48,461 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 12:31:48,463 Loading model from best epoch ...
219
+ 2023-10-17 12:31:50,256 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org
220
+ 2023-10-17 12:31:58,239
221
+ Results:
222
+ - F-score (micro) 0.6485
223
+ - F-score (macro) 0.4908
224
+ - Accuracy 0.4915
225
+
226
+ By class:
227
+ precision recall f1-score support
228
+
229
+ loc 0.6662 0.7733 0.7157 591
230
+ pers 0.5293 0.7339 0.6150 357
231
+ org 0.2353 0.1013 0.1416 79
232
+
233
+ micro avg 0.5984 0.7079 0.6485 1027
234
+ macro avg 0.4769 0.5361 0.4908 1027
235
+ weighted avg 0.5855 0.7079 0.6366 1027
236
+
237
+ 2023-10-17 12:31:58,239 ----------------------------------------------------------------------------------------------------