Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
1851430
·
1 Parent(s): b1198b2

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.1697567561.4c6324b99746.1390.17 +3 -0
  5. test.tsv +0 -0
  6. training.log +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11cfd393b1c0653bfc223b55a251dd7f704c33830ab2461de467968a846ce79
3
+ size 440966725
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 18:33:32 0.0000 0.6633 0.1745 0.6645 0.5528 0.6035 0.4475
3
+ 2 18:34:29 0.0000 0.1448 0.1311 0.7118 0.7475 0.7292 0.5901
4
+ 3 18:35:28 0.0000 0.0896 0.1342 0.7477 0.7553 0.7515 0.6161
5
+ 4 18:36:26 0.0000 0.0564 0.1650 0.7805 0.7592 0.7697 0.6430
6
+ 5 18:37:22 0.0000 0.0343 0.1769 0.7785 0.7803 0.7794 0.6561
7
+ 6 18:38:19 0.0000 0.0209 0.2170 0.7931 0.7701 0.7814 0.6558
8
+ 7 18:39:14 0.0000 0.0132 0.2289 0.7896 0.7834 0.7865 0.6640
9
+ 8 18:40:10 0.0000 0.0100 0.2463 0.7862 0.7764 0.7813 0.6563
10
+ 9 18:41:05 0.0000 0.0045 0.2428 0.7883 0.7889 0.7886 0.6656
11
+ 10 18:42:01 0.0000 0.0048 0.2444 0.7953 0.7928 0.7940 0.6706
runs/events.out.tfevents.1697567561.4c6324b99746.1390.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aac2c7c3855580ceee07287d9043dc30c1d9aa0b236e0b7ecf84542ba017e6f
3
+ size 253592
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 18:32:41,025 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 18:32:41,027 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=21, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 18:32:41,028 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 18:32:41,028 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
48
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
49
+ 2023-10-17 18:32:41,028 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 18:32:41,028 Train: 3575 sentences
51
+ 2023-10-17 18:32:41,028 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 18:32:41,028 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 18:32:41,028 Training Params:
54
+ 2023-10-17 18:32:41,028 - learning_rate: "5e-05"
55
+ 2023-10-17 18:32:41,028 - mini_batch_size: "8"
56
+ 2023-10-17 18:32:41,028 - max_epochs: "10"
57
+ 2023-10-17 18:32:41,029 - shuffle: "True"
58
+ 2023-10-17 18:32:41,029 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 18:32:41,029 Plugins:
60
+ 2023-10-17 18:32:41,029 - TensorboardLogger
61
+ 2023-10-17 18:32:41,029 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 18:32:41,029 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 18:32:41,029 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 18:32:41,029 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 18:32:41,029 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 18:32:41,029 Computation:
67
+ 2023-10-17 18:32:41,029 - compute on device: cuda:0
68
+ 2023-10-17 18:32:41,029 - embedding storage: none
69
+ 2023-10-17 18:32:41,029 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 18:32:41,029 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
71
+ 2023-10-17 18:32:41,029 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 18:32:41,030 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 18:32:41,030 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 18:32:45,281 epoch 1 - iter 44/447 - loss 3.28319391 - time (sec): 4.25 - samples/sec: 1909.75 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 18:32:49,847 epoch 1 - iter 88/447 - loss 2.16729802 - time (sec): 8.82 - samples/sec: 1871.58 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 18:32:54,474 epoch 1 - iter 132/447 - loss 1.58472566 - time (sec): 13.44 - samples/sec: 1867.59 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 18:32:59,143 epoch 1 - iter 176/447 - loss 1.28290411 - time (sec): 18.11 - samples/sec: 1824.30 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 18:33:03,625 epoch 1 - iter 220/447 - loss 1.09679775 - time (sec): 22.59 - samples/sec: 1828.99 - lr: 0.000024 - momentum: 0.000000
79
+ 2023-10-17 18:33:07,987 epoch 1 - iter 264/447 - loss 0.98249636 - time (sec): 26.96 - samples/sec: 1845.66 - lr: 0.000029 - momentum: 0.000000
80
+ 2023-10-17 18:33:12,161 epoch 1 - iter 308/447 - loss 0.88418366 - time (sec): 31.13 - samples/sec: 1860.65 - lr: 0.000034 - momentum: 0.000000
81
+ 2023-10-17 18:33:16,473 epoch 1 - iter 352/447 - loss 0.79838079 - time (sec): 35.44 - samples/sec: 1883.13 - lr: 0.000039 - momentum: 0.000000
82
+ 2023-10-17 18:33:20,636 epoch 1 - iter 396/447 - loss 0.72651329 - time (sec): 39.60 - samples/sec: 1918.58 - lr: 0.000044 - momentum: 0.000000
83
+ 2023-10-17 18:33:25,125 epoch 1 - iter 440/447 - loss 0.67193639 - time (sec): 44.09 - samples/sec: 1930.31 - lr: 0.000049 - momentum: 0.000000
84
+ 2023-10-17 18:33:25,762 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 18:33:25,763 EPOCH 1 done: loss 0.6633 - lr: 0.000049
86
+ 2023-10-17 18:33:32,386 DEV : loss 0.1744980365037918 - f1-score (micro avg) 0.6035
87
+ 2023-10-17 18:33:32,445 saving best model
88
+ 2023-10-17 18:33:33,042 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 18:33:37,924 epoch 2 - iter 44/447 - loss 0.17779822 - time (sec): 4.88 - samples/sec: 2036.36 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 18:33:42,693 epoch 2 - iter 88/447 - loss 0.18081454 - time (sec): 9.65 - samples/sec: 1902.25 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 18:33:46,869 epoch 2 - iter 132/447 - loss 0.17033044 - time (sec): 13.82 - samples/sec: 1895.20 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 18:33:51,250 epoch 2 - iter 176/447 - loss 0.16248166 - time (sec): 18.21 - samples/sec: 1910.43 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 18:33:55,643 epoch 2 - iter 220/447 - loss 0.15837240 - time (sec): 22.60 - samples/sec: 1891.36 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 18:34:00,068 epoch 2 - iter 264/447 - loss 0.15761608 - time (sec): 27.02 - samples/sec: 1921.87 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 18:34:04,112 epoch 2 - iter 308/447 - loss 0.15372266 - time (sec): 31.07 - samples/sec: 1939.68 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 18:34:08,523 epoch 2 - iter 352/447 - loss 0.14866787 - time (sec): 35.48 - samples/sec: 1938.18 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 18:34:12,905 epoch 2 - iter 396/447 - loss 0.14808787 - time (sec): 39.86 - samples/sec: 1928.10 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 18:34:17,054 epoch 2 - iter 440/447 - loss 0.14534280 - time (sec): 44.01 - samples/sec: 1937.36 - lr: 0.000045 - momentum: 0.000000
99
+ 2023-10-17 18:34:17,696 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 18:34:17,696 EPOCH 2 done: loss 0.1448 - lr: 0.000045
101
+ 2023-10-17 18:34:29,558 DEV : loss 0.1310628205537796 - f1-score (micro avg) 0.7292
102
+ 2023-10-17 18:34:29,614 saving best model
103
+ 2023-10-17 18:34:31,054 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 18:34:35,742 epoch 3 - iter 44/447 - loss 0.09348001 - time (sec): 4.68 - samples/sec: 1807.17 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 18:34:40,331 epoch 3 - iter 88/447 - loss 0.09261690 - time (sec): 9.27 - samples/sec: 1785.80 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 18:34:44,948 epoch 3 - iter 132/447 - loss 0.08918888 - time (sec): 13.89 - samples/sec: 1849.68 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 18:34:49,456 epoch 3 - iter 176/447 - loss 0.08598151 - time (sec): 18.40 - samples/sec: 1851.63 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 18:34:54,018 epoch 3 - iter 220/447 - loss 0.09004317 - time (sec): 22.96 - samples/sec: 1851.86 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 18:34:58,752 epoch 3 - iter 264/447 - loss 0.08930716 - time (sec): 27.69 - samples/sec: 1881.64 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 18:35:02,714 epoch 3 - iter 308/447 - loss 0.08984280 - time (sec): 31.66 - samples/sec: 1900.59 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 18:35:06,959 epoch 3 - iter 352/447 - loss 0.09017038 - time (sec): 35.90 - samples/sec: 1900.69 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 18:35:11,651 epoch 3 - iter 396/447 - loss 0.08914909 - time (sec): 40.59 - samples/sec: 1886.73 - lr: 0.000040 - momentum: 0.000000
113
+ 2023-10-17 18:35:16,362 epoch 3 - iter 440/447 - loss 0.09020947 - time (sec): 45.30 - samples/sec: 1879.93 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 18:35:17,046 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 18:35:17,046 EPOCH 3 done: loss 0.0896 - lr: 0.000039
116
+ 2023-10-17 18:35:28,443 DEV : loss 0.13421297073364258 - f1-score (micro avg) 0.7515
117
+ 2023-10-17 18:35:28,500 saving best model
118
+ 2023-10-17 18:35:29,985 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 18:35:34,305 epoch 4 - iter 44/447 - loss 0.04624539 - time (sec): 4.31 - samples/sec: 1728.30 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 18:35:38,772 epoch 4 - iter 88/447 - loss 0.04440189 - time (sec): 8.78 - samples/sec: 1851.77 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 18:35:43,463 epoch 4 - iter 132/447 - loss 0.05384950 - time (sec): 13.47 - samples/sec: 1910.60 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 18:35:47,579 epoch 4 - iter 176/447 - loss 0.05588999 - time (sec): 17.58 - samples/sec: 1957.95 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 18:35:51,671 epoch 4 - iter 220/447 - loss 0.05836835 - time (sec): 21.68 - samples/sec: 1974.46 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 18:35:56,069 epoch 4 - iter 264/447 - loss 0.05627529 - time (sec): 26.07 - samples/sec: 1969.72 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 18:36:00,754 epoch 4 - iter 308/447 - loss 0.05990380 - time (sec): 30.76 - samples/sec: 1945.81 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 18:36:05,256 epoch 4 - iter 352/447 - loss 0.05894391 - time (sec): 35.26 - samples/sec: 1941.97 - lr: 0.000035 - momentum: 0.000000
127
+ 2023-10-17 18:36:09,723 epoch 4 - iter 396/447 - loss 0.05734348 - time (sec): 39.73 - samples/sec: 1941.59 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 18:36:14,112 epoch 4 - iter 440/447 - loss 0.05645626 - time (sec): 44.12 - samples/sec: 1937.81 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 18:36:14,760 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 18:36:14,761 EPOCH 4 done: loss 0.0564 - lr: 0.000033
131
+ 2023-10-17 18:36:26,224 DEV : loss 0.16498109698295593 - f1-score (micro avg) 0.7697
132
+ 2023-10-17 18:36:26,284 saving best model
133
+ 2023-10-17 18:36:27,687 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 18:36:31,851 epoch 5 - iter 44/447 - loss 0.02199943 - time (sec): 4.16 - samples/sec: 2052.74 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 18:36:36,000 epoch 5 - iter 88/447 - loss 0.03388540 - time (sec): 8.31 - samples/sec: 2049.75 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 18:36:40,377 epoch 5 - iter 132/447 - loss 0.03279965 - time (sec): 12.69 - samples/sec: 2086.55 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 18:36:44,397 epoch 5 - iter 176/447 - loss 0.03416884 - time (sec): 16.71 - samples/sec: 2081.94 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 18:36:48,272 epoch 5 - iter 220/447 - loss 0.03457991 - time (sec): 20.58 - samples/sec: 2068.03 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 18:36:52,516 epoch 5 - iter 264/447 - loss 0.03419096 - time (sec): 24.82 - samples/sec: 2056.72 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 18:36:56,737 epoch 5 - iter 308/447 - loss 0.03362099 - time (sec): 29.04 - samples/sec: 2050.86 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-17 18:37:00,804 epoch 5 - iter 352/447 - loss 0.03318720 - time (sec): 33.11 - samples/sec: 2041.25 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 18:37:04,979 epoch 5 - iter 396/447 - loss 0.03273012 - time (sec): 37.29 - samples/sec: 2029.72 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 18:37:09,434 epoch 5 - iter 440/447 - loss 0.03445776 - time (sec): 41.74 - samples/sec: 2021.35 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 18:37:10,503 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 18:37:10,503 EPOCH 5 done: loss 0.0343 - lr: 0.000028
146
+ 2023-10-17 18:37:22,287 DEV : loss 0.1768861711025238 - f1-score (micro avg) 0.7794
147
+ 2023-10-17 18:37:22,350 saving best model
148
+ 2023-10-17 18:37:23,824 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 18:37:28,237 epoch 6 - iter 44/447 - loss 0.01272213 - time (sec): 4.41 - samples/sec: 2169.06 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 18:37:32,518 epoch 6 - iter 88/447 - loss 0.01539498 - time (sec): 8.69 - samples/sec: 2037.92 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 18:37:37,101 epoch 6 - iter 132/447 - loss 0.01851038 - time (sec): 13.27 - samples/sec: 1935.72 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 18:37:41,284 epoch 6 - iter 176/447 - loss 0.01975938 - time (sec): 17.46 - samples/sec: 1936.02 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 18:37:45,549 epoch 6 - iter 220/447 - loss 0.02077733 - time (sec): 21.72 - samples/sec: 1930.62 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 18:37:49,663 epoch 6 - iter 264/447 - loss 0.02148132 - time (sec): 25.84 - samples/sec: 1965.90 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-17 18:37:53,750 epoch 6 - iter 308/447 - loss 0.02125641 - time (sec): 29.92 - samples/sec: 1979.97 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 18:37:58,443 epoch 6 - iter 352/447 - loss 0.02171037 - time (sec): 34.62 - samples/sec: 1966.41 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 18:38:03,472 epoch 6 - iter 396/447 - loss 0.02173515 - time (sec): 39.64 - samples/sec: 1954.12 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 18:38:07,761 epoch 6 - iter 440/447 - loss 0.02098498 - time (sec): 43.93 - samples/sec: 1946.46 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 18:38:08,414 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 18:38:08,415 EPOCH 6 done: loss 0.0209 - lr: 0.000022
161
+ 2023-10-17 18:38:19,003 DEV : loss 0.21698522567749023 - f1-score (micro avg) 0.7814
162
+ 2023-10-17 18:38:19,057 saving best model
163
+ 2023-10-17 18:38:20,481 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 18:38:24,541 epoch 7 - iter 44/447 - loss 0.00663934 - time (sec): 4.06 - samples/sec: 2150.22 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-17 18:38:28,549 epoch 7 - iter 88/447 - loss 0.00916382 - time (sec): 8.06 - samples/sec: 2101.54 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 18:38:32,548 epoch 7 - iter 132/447 - loss 0.00862219 - time (sec): 12.06 - samples/sec: 2083.10 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-17 18:38:36,714 epoch 7 - iter 176/447 - loss 0.01076391 - time (sec): 16.23 - samples/sec: 2075.89 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-17 18:38:40,916 epoch 7 - iter 220/447 - loss 0.01133687 - time (sec): 20.43 - samples/sec: 2056.94 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-17 18:38:45,009 epoch 7 - iter 264/447 - loss 0.01169682 - time (sec): 24.52 - samples/sec: 2045.15 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-17 18:38:49,616 epoch 7 - iter 308/447 - loss 0.01149309 - time (sec): 29.13 - samples/sec: 2017.06 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 18:38:53,734 epoch 7 - iter 352/447 - loss 0.01240281 - time (sec): 33.25 - samples/sec: 2000.31 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-17 18:38:58,381 epoch 7 - iter 396/447 - loss 0.01335837 - time (sec): 37.90 - samples/sec: 2020.64 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 18:39:02,568 epoch 7 - iter 440/447 - loss 0.01332056 - time (sec): 42.08 - samples/sec: 2020.03 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-17 18:39:03,195 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 18:39:03,196 EPOCH 7 done: loss 0.0132 - lr: 0.000017
176
+ 2023-10-17 18:39:13,976 DEV : loss 0.2289014309644699 - f1-score (micro avg) 0.7865
177
+ 2023-10-17 18:39:14,038 saving best model
178
+ 2023-10-17 18:39:15,456 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-17 18:39:19,748 epoch 8 - iter 44/447 - loss 0.00757963 - time (sec): 4.29 - samples/sec: 1852.38 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-17 18:39:24,373 epoch 8 - iter 88/447 - loss 0.01028323 - time (sec): 8.91 - samples/sec: 1853.54 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-17 18:39:29,308 epoch 8 - iter 132/447 - loss 0.00833315 - time (sec): 13.85 - samples/sec: 1933.16 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-17 18:39:33,329 epoch 8 - iter 176/447 - loss 0.00791567 - time (sec): 17.87 - samples/sec: 1929.69 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-17 18:39:37,380 epoch 8 - iter 220/447 - loss 0.00938211 - time (sec): 21.92 - samples/sec: 1952.84 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-17 18:39:41,533 epoch 8 - iter 264/447 - loss 0.00986939 - time (sec): 26.07 - samples/sec: 1959.68 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-17 18:39:45,823 epoch 8 - iter 308/447 - loss 0.01043189 - time (sec): 30.36 - samples/sec: 1980.94 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-17 18:39:50,183 epoch 8 - iter 352/447 - loss 0.01072671 - time (sec): 34.72 - samples/sec: 1972.90 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-17 18:39:54,559 epoch 8 - iter 396/447 - loss 0.01039982 - time (sec): 39.10 - samples/sec: 1951.97 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-17 18:39:59,113 epoch 8 - iter 440/447 - loss 0.01008795 - time (sec): 43.65 - samples/sec: 1957.71 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-17 18:39:59,749 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 18:39:59,749 EPOCH 8 done: loss 0.0100 - lr: 0.000011
191
+ 2023-10-17 18:40:10,771 DEV : loss 0.24633415043354034 - f1-score (micro avg) 0.7813
192
+ 2023-10-17 18:40:10,826 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 18:40:14,890 epoch 9 - iter 44/447 - loss 0.00587764 - time (sec): 4.06 - samples/sec: 1932.48 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-17 18:40:18,943 epoch 9 - iter 88/447 - loss 0.00574376 - time (sec): 8.11 - samples/sec: 2002.18 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-17 18:40:23,087 epoch 9 - iter 132/447 - loss 0.00498408 - time (sec): 12.26 - samples/sec: 2009.48 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-17 18:40:27,716 epoch 9 - iter 176/447 - loss 0.00542873 - time (sec): 16.89 - samples/sec: 2019.96 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-17 18:40:31,791 epoch 9 - iter 220/447 - loss 0.00462645 - time (sec): 20.96 - samples/sec: 1989.58 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 18:40:35,880 epoch 9 - iter 264/447 - loss 0.00439777 - time (sec): 25.05 - samples/sec: 1988.43 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-17 18:40:40,307 epoch 9 - iter 308/447 - loss 0.00454180 - time (sec): 29.48 - samples/sec: 1972.83 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 18:40:44,975 epoch 9 - iter 352/447 - loss 0.00448785 - time (sec): 34.15 - samples/sec: 1973.74 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-17 18:40:49,421 epoch 9 - iter 396/447 - loss 0.00445712 - time (sec): 38.59 - samples/sec: 1983.69 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 18:40:53,474 epoch 9 - iter 440/447 - loss 0.00457860 - time (sec): 42.65 - samples/sec: 2001.83 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-17 18:40:54,093 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 18:40:54,093 EPOCH 9 done: loss 0.0045 - lr: 0.000006
205
+ 2023-10-17 18:41:05,718 DEV : loss 0.2427874058485031 - f1-score (micro avg) 0.7886
206
+ 2023-10-17 18:41:05,781 saving best model
207
+ 2023-10-17 18:41:07,280 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-17 18:41:11,725 epoch 10 - iter 44/447 - loss 0.00160514 - time (sec): 4.44 - samples/sec: 2042.33 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-17 18:41:16,229 epoch 10 - iter 88/447 - loss 0.00319179 - time (sec): 8.94 - samples/sec: 2118.49 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-17 18:41:20,172 epoch 10 - iter 132/447 - loss 0.00275824 - time (sec): 12.89 - samples/sec: 2119.39 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-17 18:41:23,939 epoch 10 - iter 176/447 - loss 0.00498494 - time (sec): 16.65 - samples/sec: 2156.62 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 18:41:27,774 epoch 10 - iter 220/447 - loss 0.00437952 - time (sec): 20.49 - samples/sec: 2147.41 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-17 18:41:31,811 epoch 10 - iter 264/447 - loss 0.00435338 - time (sec): 24.53 - samples/sec: 2135.63 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 18:41:36,331 epoch 10 - iter 308/447 - loss 0.00540662 - time (sec): 29.05 - samples/sec: 2079.00 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-17 18:41:40,384 epoch 10 - iter 352/447 - loss 0.00523384 - time (sec): 33.10 - samples/sec: 2059.89 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 18:41:44,730 epoch 10 - iter 396/447 - loss 0.00489409 - time (sec): 37.45 - samples/sec: 2042.80 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-17 18:41:48,878 epoch 10 - iter 440/447 - loss 0.00484791 - time (sec): 41.59 - samples/sec: 2047.20 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-17 18:41:49,568 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 18:41:49,568 EPOCH 10 done: loss 0.0048 - lr: 0.000000
220
+ 2023-10-17 18:42:01,233 DEV : loss 0.24444200098514557 - f1-score (micro avg) 0.794
221
+ 2023-10-17 18:42:01,295 saving best model
222
+ 2023-10-17 18:42:03,304 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-17 18:42:03,306 Loading model from best epoch ...
224
+ 2023-10-17 18:42:05,494 SequenceTagger predicts: Dictionary with 21 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, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
225
+ 2023-10-17 18:42:11,511
226
+ Results:
227
+ - F-score (micro) 0.7688
228
+ - F-score (macro) 0.6973
229
+ - Accuracy 0.6446
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8431 0.8658 0.8543 596
235
+ pers 0.7048 0.7958 0.7475 333
236
+ org 0.5075 0.5152 0.5113 132
237
+ prod 0.6731 0.5303 0.5932 66
238
+ time 0.7647 0.7959 0.7800 49
239
+
240
+ micro avg 0.7535 0.7849 0.7688 1176
241
+ macro avg 0.6986 0.7006 0.6973 1176
242
+ weighted avg 0.7535 0.7849 0.7678 1176
243
+
244
+ 2023-10-17 18:42:11,511 ----------------------------------------------------------------------------------------------------