Hugging Face's logo

stefan-it
/
hmbench-icdar-fr-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
70e96e2
•
1 Parent(s): 747ba3b

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.1697550173.bce904bcef33.2023.13 +3 -0
  5. test.tsv +0 -0
  6. training.log +242 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352e14d7e32ee48be574ebd0c2363ae08c8fa65684ab4328c63ff43e19763baa
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 13:44:26 0.0000 0.3635 0.1107 0.7003 0.7296 0.7147 0.5790
3
+ 2 13:46:02 0.0000 0.1188 0.0929 0.7670 0.7262 0.7461 0.6068
4
+ 3 13:47:38 0.0000 0.0899 0.1153 0.7562 0.7545 0.7554 0.6275
5
+ 4 13:49:12 0.0000 0.0716 0.1697 0.7395 0.7738 0.7562 0.6258
6
+ 5 13:50:48 0.0000 0.0548 0.1719 0.7323 0.7862 0.7583 0.6330
7
+ 6 13:52:25 0.0000 0.0414 0.1980 0.7230 0.8088 0.7635 0.6367
8
+ 7 13:54:02 0.0000 0.0285 0.2168 0.7320 0.7817 0.7560 0.6265
9
+ 8 13:55:38 0.0000 0.0203 0.2282 0.7503 0.7885 0.7689 0.6418
10
+ 9 13:57:13 0.0000 0.0130 0.2394 0.7524 0.7907 0.7711 0.6466
11
+ 10 13:58:48 0.0000 0.0088 0.2471 0.7603 0.7964 0.7779 0.6537
runs/events.out.tfevents.1697550173.bce904bcef33.2023.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8943877c62dc625315b74ff334733df6fa013406b776bc73ceef378a3d84c92d
3
+ size 1108164
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 13:42:53,754 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 13:42:53,755 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 13:42:53,755 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 13:42:53,755 MultiCorpus: 7936 train + 992 dev + 992 test sentences
48
+ - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr
49
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 13:42:53,756 Train: 7936 sentences
51
+ 2023-10-17 13:42:53,756 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 13:42:53,756 Training Params:
54
+ 2023-10-17 13:42:53,756 - learning_rate: "5e-05"
55
+ 2023-10-17 13:42:53,756 - mini_batch_size: "4"
56
+ 2023-10-17 13:42:53,756 - max_epochs: "10"
57
+ 2023-10-17 13:42:53,756 - shuffle: "True"
58
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 13:42:53,756 Plugins:
60
+ 2023-10-17 13:42:53,756 - TensorboardLogger
61
+ 2023-10-17 13:42:53,756 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 13:42:53,756 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 13:42:53,756 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 13:42:53,756 Computation:
67
+ 2023-10-17 13:42:53,756 - compute on device: cuda:0
68
+ 2023-10-17 13:42:53,756 - embedding storage: none
69
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 13:42:53,756 Model training base path: "hmbench-icdar/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
71
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 13:42:53,756 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 13:42:53,756 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 13:43:02,902 epoch 1 - iter 198/1984 - loss 1.99194816 - time (sec): 9.14 - samples/sec: 1812.16 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 13:43:12,040 epoch 1 - iter 396/1984 - loss 1.12529108 - time (sec): 18.28 - samples/sec: 1834.45 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 13:43:20,571 epoch 1 - iter 594/1984 - loss 0.84075243 - time (sec): 26.81 - samples/sec: 1828.97 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 13:43:29,636 epoch 1 - iter 792/1984 - loss 0.67948072 - time (sec): 35.88 - samples/sec: 1809.73 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 13:43:38,961 epoch 1 - iter 990/1984 - loss 0.56666412 - time (sec): 45.20 - samples/sec: 1828.99 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 13:43:47,711 epoch 1 - iter 1188/1984 - loss 0.50179248 - time (sec): 53.95 - samples/sec: 1829.62 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 13:43:56,331 epoch 1 - iter 1386/1984 - loss 0.45691609 - time (sec): 62.57 - samples/sec: 1836.93 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 13:44:05,242 epoch 1 - iter 1584/1984 - loss 0.41865425 - time (sec): 71.48 - samples/sec: 1841.02 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 13:44:14,524 epoch 1 - iter 1782/1984 - loss 0.38769661 - time (sec): 80.77 - samples/sec: 1834.44 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 13:44:23,569 epoch 1 - iter 1980/1984 - loss 0.36361201 - time (sec): 89.81 - samples/sec: 1822.66 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 13:44:23,744 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 13:44:23,744 EPOCH 1 done: loss 0.3635 - lr: 0.000050
86
+ 2023-10-17 13:44:26,902 DEV : loss 0.1107097640633583 - f1-score (micro avg) 0.7147
87
+ 2023-10-17 13:44:26,923 saving best model
88
+ 2023-10-17 13:44:27,399 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 13:44:36,392 epoch 2 - iter 198/1984 - loss 0.12198282 - time (sec): 8.99 - samples/sec: 1816.59 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 13:44:45,686 epoch 2 - iter 396/1984 - loss 0.12288858 - time (sec): 18.29 - samples/sec: 1802.37 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 13:44:54,485 epoch 2 - iter 594/1984 - loss 0.12158637 - time (sec): 27.08 - samples/sec: 1790.77 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 13:45:03,453 epoch 2 - iter 792/1984 - loss 0.12378321 - time (sec): 36.05 - samples/sec: 1793.41 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 13:45:12,572 epoch 2 - iter 990/1984 - loss 0.11981922 - time (sec): 45.17 - samples/sec: 1793.52 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 13:45:21,725 epoch 2 - iter 1188/1984 - loss 0.11892503 - time (sec): 54.32 - samples/sec: 1795.43 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 13:45:30,864 epoch 2 - iter 1386/1984 - loss 0.11995066 - time (sec): 63.46 - samples/sec: 1807.05 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 13:45:40,092 epoch 2 - iter 1584/1984 - loss 0.11971087 - time (sec): 72.69 - samples/sec: 1801.71 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 13:45:49,162 epoch 2 - iter 1782/1984 - loss 0.11939199 - time (sec): 81.76 - samples/sec: 1797.41 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 13:45:58,300 epoch 2 - iter 1980/1984 - loss 0.11867051 - time (sec): 90.90 - samples/sec: 1802.10 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 13:45:58,474 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 13:45:58,474 EPOCH 2 done: loss 0.1188 - lr: 0.000044
101
+ 2023-10-17 13:46:02,349 DEV : loss 0.09292253851890564 - f1-score (micro avg) 0.7461
102
+ 2023-10-17 13:46:02,372 saving best model
103
+ 2023-10-17 13:46:02,884 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 13:46:12,137 epoch 3 - iter 198/1984 - loss 0.08093006 - time (sec): 9.25 - samples/sec: 1833.94 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 13:46:21,419 epoch 3 - iter 396/1984 - loss 0.08776510 - time (sec): 18.53 - samples/sec: 1800.42 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 13:46:30,417 epoch 3 - iter 594/1984 - loss 0.08770434 - time (sec): 27.53 - samples/sec: 1795.44 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 13:46:39,552 epoch 3 - iter 792/1984 - loss 0.08713512 - time (sec): 36.67 - samples/sec: 1797.16 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 13:46:48,582 epoch 3 - iter 990/1984 - loss 0.08915958 - time (sec): 45.70 - samples/sec: 1808.80 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 13:46:57,705 epoch 3 - iter 1188/1984 - loss 0.08975126 - time (sec): 54.82 - samples/sec: 1817.72 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 13:47:06,969 epoch 3 - iter 1386/1984 - loss 0.08933047 - time (sec): 64.08 - samples/sec: 1822.52 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 13:47:16,293 epoch 3 - iter 1584/1984 - loss 0.08968171 - time (sec): 73.41 - samples/sec: 1814.20 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 13:47:25,592 epoch 3 - iter 1782/1984 - loss 0.09022258 - time (sec): 82.71 - samples/sec: 1798.16 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 13:47:34,674 epoch 3 - iter 1980/1984 - loss 0.08989172 - time (sec): 91.79 - samples/sec: 1783.16 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 13:47:34,856 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 13:47:34,856 EPOCH 3 done: loss 0.0899 - lr: 0.000039
116
+ 2023-10-17 13:47:38,254 DEV : loss 0.11529310792684555 - f1-score (micro avg) 0.7554
117
+ 2023-10-17 13:47:38,275 saving best model
118
+ 2023-10-17 13:47:38,842 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 13:47:47,509 epoch 4 - iter 198/1984 - loss 0.05901225 - time (sec): 8.66 - samples/sec: 1941.15 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 13:47:56,529 epoch 4 - iter 396/1984 - loss 0.07172775 - time (sec): 17.68 - samples/sec: 1856.82 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 13:48:05,245 epoch 4 - iter 594/1984 - loss 0.06965845 - time (sec): 26.40 - samples/sec: 1845.67 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 13:48:13,933 epoch 4 - iter 792/1984 - loss 0.07214150 - time (sec): 35.09 - samples/sec: 1873.43 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 13:48:22,554 epoch 4 - iter 990/1984 - loss 0.07156799 - time (sec): 43.71 - samples/sec: 1878.28 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 13:48:31,704 epoch 4 - iter 1188/1984 - loss 0.07472710 - time (sec): 52.86 - samples/sec: 1874.11 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 13:48:40,821 epoch 4 - iter 1386/1984 - loss 0.07315463 - time (sec): 61.97 - samples/sec: 1855.64 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 13:48:49,969 epoch 4 - iter 1584/1984 - loss 0.07446253 - time (sec): 71.12 - samples/sec: 1846.18 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 13:48:59,484 epoch 4 - iter 1782/1984 - loss 0.07318315 - time (sec): 80.64 - samples/sec: 1826.73 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 13:49:09,059 epoch 4 - iter 1980/1984 - loss 0.07161599 - time (sec): 90.21 - samples/sec: 1815.30 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 13:49:09,239 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 13:49:09,239 EPOCH 4 done: loss 0.0716 - lr: 0.000033
131
+ 2023-10-17 13:49:12,748 DEV : loss 0.16965167224407196 - f1-score (micro avg) 0.7562
132
+ 2023-10-17 13:49:12,770 saving best model
133
+ 2023-10-17 13:49:13,358 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 13:49:22,504 epoch 5 - iter 198/1984 - loss 0.05142115 - time (sec): 9.14 - samples/sec: 1744.82 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 13:49:31,639 epoch 5 - iter 396/1984 - loss 0.05326253 - time (sec): 18.28 - samples/sec: 1783.51 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 13:49:40,726 epoch 5 - iter 594/1984 - loss 0.05234995 - time (sec): 27.36 - samples/sec: 1766.40 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 13:49:49,869 epoch 5 - iter 792/1984 - loss 0.05493024 - time (sec): 36.51 - samples/sec: 1766.69 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 13:49:59,222 epoch 5 - iter 990/1984 - loss 0.05547255 - time (sec): 45.86 - samples/sec: 1768.21 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 13:50:08,703 epoch 5 - iter 1188/1984 - loss 0.05535415 - time (sec): 55.34 - samples/sec: 1775.28 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 13:50:17,849 epoch 5 - iter 1386/1984 - loss 0.05553716 - time (sec): 64.49 - samples/sec: 1780.41 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 13:50:27,041 epoch 5 - iter 1584/1984 - loss 0.05438664 - time (sec): 73.68 - samples/sec: 1785.59 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 13:50:36,058 epoch 5 - iter 1782/1984 - loss 0.05420342 - time (sec): 82.70 - samples/sec: 1785.78 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 13:50:45,233 epoch 5 - iter 1980/1984 - loss 0.05491134 - time (sec): 91.87 - samples/sec: 1780.76 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 13:50:45,422 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 13:50:45,423 EPOCH 5 done: loss 0.0548 - lr: 0.000028
146
+ 2023-10-17 13:50:48,854 DEV : loss 0.17186634242534637 - f1-score (micro avg) 0.7583
147
+ 2023-10-17 13:50:48,875 saving best model
148
+ 2023-10-17 13:50:49,394 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 13:50:58,709 epoch 6 - iter 198/1984 - loss 0.04210687 - time (sec): 9.31 - samples/sec: 1797.63 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 13:51:07,945 epoch 6 - iter 396/1984 - loss 0.04558327 - time (sec): 18.55 - samples/sec: 1786.69 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 13:51:17,296 epoch 6 - iter 594/1984 - loss 0.04411621 - time (sec): 27.90 - samples/sec: 1776.05 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 13:51:26,833 epoch 6 - iter 792/1984 - loss 0.04189826 - time (sec): 37.44 - samples/sec: 1766.81 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 13:51:35,758 epoch 6 - iter 990/1984 - loss 0.04186020 - time (sec): 46.36 - samples/sec: 1790.47 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 13:51:44,892 epoch 6 - iter 1188/1984 - loss 0.04179555 - time (sec): 55.50 - samples/sec: 1784.39 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 13:51:54,014 epoch 6 - iter 1386/1984 - loss 0.04062803 - time (sec): 64.62 - samples/sec: 1802.35 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 13:52:03,187 epoch 6 - iter 1584/1984 - loss 0.04047753 - time (sec): 73.79 - samples/sec: 1794.79 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 13:52:12,464 epoch 6 - iter 1782/1984 - loss 0.04096866 - time (sec): 83.07 - samples/sec: 1783.58 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 13:52:21,511 epoch 6 - iter 1980/1984 - loss 0.04137447 - time (sec): 92.11 - samples/sec: 1776.94 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 13:52:21,692 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 13:52:21,692 EPOCH 6 done: loss 0.0414 - lr: 0.000022
161
+ 2023-10-17 13:52:25,752 DEV : loss 0.1979617029428482 - f1-score (micro avg) 0.7635
162
+ 2023-10-17 13:52:25,775 saving best model
163
+ 2023-10-17 13:52:26,295 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 13:52:35,522 epoch 7 - iter 198/1984 - loss 0.02932924 - time (sec): 9.22 - samples/sec: 1697.08 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-17 13:52:45,099 epoch 7 - iter 396/1984 - loss 0.02557373 - time (sec): 18.80 - samples/sec: 1741.96 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 13:52:54,288 epoch 7 - iter 594/1984 - loss 0.02664735 - time (sec): 27.99 - samples/sec: 1753.83 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-17 13:53:03,396 epoch 7 - iter 792/1984 - loss 0.02794794 - time (sec): 37.10 - samples/sec: 1758.17 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-17 13:53:12,526 epoch 7 - iter 990/1984 - loss 0.02878967 - time (sec): 46.23 - samples/sec: 1767.18 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 13:53:21,604 epoch 7 - iter 1188/1984 - loss 0.02864416 - time (sec): 55.30 - samples/sec: 1761.33 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-17 13:53:30,974 epoch 7 - iter 1386/1984 - loss 0.02877632 - time (sec): 64.67 - samples/sec: 1751.38 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 13:53:40,189 epoch 7 - iter 1584/1984 - loss 0.02875581 - time (sec): 73.89 - samples/sec: 1754.20 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-17 13:53:49,370 epoch 7 - iter 1782/1984 - loss 0.02874451 - time (sec): 83.07 - samples/sec: 1755.94 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 13:53:58,828 epoch 7 - iter 1980/1984 - loss 0.02854042 - time (sec): 92.53 - samples/sec: 1768.83 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-17 13:53:59,013 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 13:53:59,014 EPOCH 7 done: loss 0.0285 - lr: 0.000017
176
+ 2023-10-17 13:54:02,405 DEV : loss 0.21675720810890198 - f1-score (micro avg) 0.756
177
+ 2023-10-17 13:54:02,426 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-17 13:54:11,532 epoch 8 - iter 198/1984 - loss 0.02131513 - time (sec): 9.10 - samples/sec: 1755.79 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 13:54:20,688 epoch 8 - iter 396/1984 - loss 0.02216696 - time (sec): 18.26 - samples/sec: 1771.05 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-17 13:54:29,689 epoch 8 - iter 594/1984 - loss 0.02326467 - time (sec): 27.26 - samples/sec: 1759.32 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-17 13:54:38,755 epoch 8 - iter 792/1984 - loss 0.02241368 - time (sec): 36.33 - samples/sec: 1763.98 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 13:54:47,967 epoch 8 - iter 990/1984 - loss 0.02005196 - time (sec): 45.54 - samples/sec: 1771.30 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-17 13:54:57,291 epoch 8 - iter 1188/1984 - loss 0.01961340 - time (sec): 54.86 - samples/sec: 1775.08 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 13:55:06,861 epoch 8 - iter 1386/1984 - loss 0.02145710 - time (sec): 64.43 - samples/sec: 1753.37 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-17 13:55:16,241 epoch 8 - iter 1584/1984 - loss 0.02064329 - time (sec): 73.81 - samples/sec: 1762.80 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 13:55:25,486 epoch 8 - iter 1782/1984 - loss 0.01981026 - time (sec): 83.06 - samples/sec: 1766.73 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-17 13:55:34,752 epoch 8 - iter 1980/1984 - loss 0.02031700 - time (sec): 92.32 - samples/sec: 1772.93 - lr: 0.000011 - momentum: 0.000000
188
+ 2023-10-17 13:55:34,925 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 13:55:34,925 EPOCH 8 done: loss 0.0203 - lr: 0.000011
190
+ 2023-10-17 13:55:38,336 DEV : loss 0.22816428542137146 - f1-score (micro avg) 0.7689
191
+ 2023-10-17 13:55:38,358 saving best model
192
+ 2023-10-17 13:55:38,938 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 13:55:47,982 epoch 9 - iter 198/1984 - loss 0.01192882 - time (sec): 9.04 - samples/sec: 1734.20 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-17 13:55:56,918 epoch 9 - iter 396/1984 - loss 0.01286841 - time (sec): 17.97 - samples/sec: 1798.99 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-17 13:56:05,849 epoch 9 - iter 594/1984 - loss 0.01438189 - time (sec): 26.91 - samples/sec: 1772.52 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 13:56:14,942 epoch 9 - iter 792/1984 - loss 0.01318238 - time (sec): 36.00 - samples/sec: 1770.21 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-17 13:56:24,030 epoch 9 - iter 990/1984 - loss 0.01351039 - time (sec): 45.09 - samples/sec: 1778.59 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 13:56:32,852 epoch 9 - iter 1188/1984 - loss 0.01319278 - time (sec): 53.91 - samples/sec: 1793.12 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-17 13:56:41,731 epoch 9 - iter 1386/1984 - loss 0.01309930 - time (sec): 62.79 - samples/sec: 1811.55 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 13:56:51,161 epoch 9 - iter 1584/1984 - loss 0.01255843 - time (sec): 72.22 - samples/sec: 1810.15 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-17 13:57:00,359 epoch 9 - iter 1782/1984 - loss 0.01307612 - time (sec): 81.42 - samples/sec: 1803.41 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 13:57:09,450 epoch 9 - iter 1980/1984 - loss 0.01305751 - time (sec): 90.51 - samples/sec: 1807.63 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-17 13:57:09,640 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 13:57:09,640 EPOCH 9 done: loss 0.0130 - lr: 0.000006
205
+ 2023-10-17 13:57:13,058 DEV : loss 0.23943665623664856 - f1-score (micro avg) 0.7711
206
+ 2023-10-17 13:57:13,081 saving best model
207
+ 2023-10-17 13:57:13,702 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-17 13:57:22,874 epoch 10 - iter 198/1984 - loss 0.00790504 - time (sec): 9.17 - samples/sec: 1775.44 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-17 13:57:32,117 epoch 10 - iter 396/1984 - loss 0.00810567 - time (sec): 18.41 - samples/sec: 1819.26 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-17 13:57:41,199 epoch 10 - iter 594/1984 - loss 0.00780535 - time (sec): 27.49 - samples/sec: 1803.46 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-17 13:57:50,230 epoch 10 - iter 792/1984 - loss 0.00784589 - time (sec): 36.53 - samples/sec: 1788.64 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 13:57:59,203 epoch 10 - iter 990/1984 - loss 0.00744212 - time (sec): 45.50 - samples/sec: 1799.38 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-17 13:58:08,284 epoch 10 - iter 1188/1984 - loss 0.00828425 - time (sec): 54.58 - samples/sec: 1802.08 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 13:58:17,328 epoch 10 - iter 1386/1984 - loss 0.00823271 - time (sec): 63.62 - samples/sec: 1805.08 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-17 13:58:26,441 epoch 10 - iter 1584/1984 - loss 0.00807062 - time (sec): 72.74 - samples/sec: 1805.28 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 13:58:35,408 epoch 10 - iter 1782/1984 - loss 0.00842240 - time (sec): 81.70 - samples/sec: 1803.89 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-17 13:58:44,477 epoch 10 - iter 1980/1984 - loss 0.00880008 - time (sec): 90.77 - samples/sec: 1803.88 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-17 13:58:44,651 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 13:58:44,651 EPOCH 10 done: loss 0.0088 - lr: 0.000000
220
+ 2023-10-17 13:58:48,192 DEV : loss 0.2471495419740677 - f1-score (micro avg) 0.7779
221
+ 2023-10-17 13:58:48,221 saving best model
222
+ 2023-10-17 13:58:49,148 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-17 13:58:49,150 Loading model from best epoch ...
224
+ 2023-10-17 13:58:51,929 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
225
+ 2023-10-17 13:58:54,795
226
+ Results:
227
+ - F-score (micro) 0.7672
228
+ - F-score (macro) 0.6813
229
+ - Accuracy 0.653
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ LOC 0.8318 0.8382 0.8350 655
235
+ PER 0.6811 0.7758 0.7254 223
236
+ ORG 0.5043 0.4646 0.4836 127
237
+
238
+ micro avg 0.7575 0.7771 0.7672 1005
239
+ macro avg 0.6724 0.6928 0.6813 1005
240
+ weighted avg 0.7570 0.7771 0.7663 1005
241
+
242
+ 2023-10-17 13:58:54,795 ----------------------------------------------------------------------------------------------------