Hugging Face's logo

hmteams
/
flair-hipe-2022-hipe2020-de

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
e1b6c7e
•
1 Parent(s): bfe8e4a

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.1697561232.4c6324b99746.1390.8 +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:df75363ec21b83a5b4761bde0861571d07df98b8a940fd56caa896c075b787ae
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 16:48:01 0.0000 0.8052 0.1861 0.6556 0.5880 0.6200 0.4585
3
+ 2 16:48:55 0.0000 0.1564 0.1185 0.7141 0.6873 0.7004 0.5546
4
+ 3 16:49:50 0.0000 0.0831 0.1610 0.7641 0.7115 0.7368 0.6019
5
+ 4 16:50:44 0.0000 0.0537 0.1712 0.7857 0.7623 0.7738 0.6440
6
+ 5 16:51:39 0.0000 0.0315 0.1702 0.7553 0.8014 0.7777 0.6508
7
+ 6 16:52:35 0.0000 0.0230 0.1998 0.8110 0.7952 0.8030 0.6821
8
+ 7 16:53:30 0.0000 0.0135 0.2047 0.7845 0.7998 0.7921 0.6691
9
+ 8 16:54:25 0.0000 0.0088 0.2188 0.7850 0.8194 0.8018 0.6841
10
+ 9 16:55:20 0.0000 0.0065 0.2287 0.8047 0.8084 0.8066 0.6880
11
+ 10 16:56:15 0.0000 0.0048 0.2345 0.8031 0.8069 0.8050 0.6853
runs/events.out.tfevents.1697561232.4c6324b99746.1390.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f914a6f47018c99bc5ef388d428ea2f3cde33e1db0cbe0403f83ad7e4721ae5
3
+ size 253592
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 16:47:12,055 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 16:47:12,057 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 16:47:12,057 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 16:47:12,057 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 16:47:12,057 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 16:47:12,057 Train: 3575 sentences
51
+ 2023-10-17 16:47:12,057 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 16:47:12,057 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 16:47:12,058 Training Params:
54
+ 2023-10-17 16:47:12,058 - learning_rate: "3e-05"
55
+ 2023-10-17 16:47:12,058 - mini_batch_size: "8"
56
+ 2023-10-17 16:47:12,058 - max_epochs: "10"
57
+ 2023-10-17 16:47:12,058 - shuffle: "True"
58
+ 2023-10-17 16:47:12,058 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 16:47:12,058 Plugins:
60
+ 2023-10-17 16:47:12,058 - TensorboardLogger
61
+ 2023-10-17 16:47:12,058 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 16:47:12,058 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 16:47:12,058 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 16:47:12,058 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 16:47:12,058 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 16:47:12,059 Computation:
67
+ 2023-10-17 16:47:12,059 - compute on device: cuda:0
68
+ 2023-10-17 16:47:12,059 - embedding storage: none
69
+ 2023-10-17 16:47:12,059 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 16:47:12,059 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
71
+ 2023-10-17 16:47:12,059 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 16:47:12,059 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 16:47:12,059 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 16:47:16,186 epoch 1 - iter 44/447 - loss 3.49661378 - time (sec): 4.13 - samples/sec: 1872.19 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 16:47:20,660 epoch 1 - iter 88/447 - loss 2.61631042 - time (sec): 8.60 - samples/sec: 1956.66 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 16:47:24,936 epoch 1 - iter 132/447 - loss 1.93352666 - time (sec): 12.88 - samples/sec: 1984.67 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 16:47:28,939 epoch 1 - iter 176/447 - loss 1.57530896 - time (sec): 16.88 - samples/sec: 2000.58 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 16:47:33,220 epoch 1 - iter 220/447 - loss 1.34725282 - time (sec): 21.16 - samples/sec: 1996.09 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 16:47:37,715 epoch 1 - iter 264/447 - loss 1.15393413 - time (sec): 25.65 - samples/sec: 2022.57 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 16:47:41,873 epoch 1 - iter 308/447 - loss 1.04226944 - time (sec): 29.81 - samples/sec: 2024.30 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 16:47:45,852 epoch 1 - iter 352/447 - loss 0.95292814 - time (sec): 33.79 - samples/sec: 2021.95 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 16:47:50,370 epoch 1 - iter 396/447 - loss 0.87278568 - time (sec): 38.31 - samples/sec: 2013.81 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 16:47:54,446 epoch 1 - iter 440/447 - loss 0.81583916 - time (sec): 42.39 - samples/sec: 2007.91 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-17 16:47:55,074 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 16:47:55,075 EPOCH 1 done: loss 0.8052 - lr: 0.000029
86
+ 2023-10-17 16:48:01,442 DEV : loss 0.18609091639518738 - f1-score (micro avg) 0.62
87
+ 2023-10-17 16:48:01,495 saving best model
88
+ 2023-10-17 16:48:02,032 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 16:48:06,103 epoch 2 - iter 44/447 - loss 0.17646139 - time (sec): 4.07 - samples/sec: 2094.88 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 16:48:10,127 epoch 2 - iter 88/447 - loss 0.17558676 - time (sec): 8.09 - samples/sec: 2086.39 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 16:48:14,170 epoch 2 - iter 132/447 - loss 0.16683960 - time (sec): 12.14 - samples/sec: 2026.77 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 16:48:18,156 epoch 2 - iter 176/447 - loss 0.16952362 - time (sec): 16.12 - samples/sec: 1992.29 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 16:48:22,496 epoch 2 - iter 220/447 - loss 0.16761727 - time (sec): 20.46 - samples/sec: 2027.06 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 16:48:26,893 epoch 2 - iter 264/447 - loss 0.17109456 - time (sec): 24.86 - samples/sec: 2038.35 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 16:48:30,902 epoch 2 - iter 308/447 - loss 0.17214782 - time (sec): 28.87 - samples/sec: 2044.42 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 16:48:35,157 epoch 2 - iter 352/447 - loss 0.16542676 - time (sec): 33.12 - samples/sec: 2051.24 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 16:48:39,571 epoch 2 - iter 396/447 - loss 0.15856207 - time (sec): 37.54 - samples/sec: 2060.57 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 16:48:43,542 epoch 2 - iter 440/447 - loss 0.15666011 - time (sec): 41.51 - samples/sec: 2055.00 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 16:48:44,156 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 16:48:44,156 EPOCH 2 done: loss 0.1564 - lr: 0.000027
101
+ 2023-10-17 16:48:55,101 DEV : loss 0.11850441992282867 - f1-score (micro avg) 0.7004
102
+ 2023-10-17 16:48:55,153 saving best model
103
+ 2023-10-17 16:48:56,532 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 16:49:00,603 epoch 3 - iter 44/447 - loss 0.08474878 - time (sec): 4.07 - samples/sec: 2113.03 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 16:49:04,693 epoch 3 - iter 88/447 - loss 0.08245773 - time (sec): 8.16 - samples/sec: 2090.39 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 16:49:09,017 epoch 3 - iter 132/447 - loss 0.08517300 - time (sec): 12.48 - samples/sec: 2086.23 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 16:49:13,016 epoch 3 - iter 176/447 - loss 0.08575584 - time (sec): 16.48 - samples/sec: 2062.81 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 16:49:17,520 epoch 3 - iter 220/447 - loss 0.08751252 - time (sec): 20.98 - samples/sec: 2038.05 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 16:49:22,077 epoch 3 - iter 264/447 - loss 0.08907774 - time (sec): 25.54 - samples/sec: 2025.88 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 16:49:26,176 epoch 3 - iter 308/447 - loss 0.08626226 - time (sec): 29.64 - samples/sec: 2027.47 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 16:49:30,200 epoch 3 - iter 352/447 - loss 0.08544823 - time (sec): 33.66 - samples/sec: 2036.17 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 16:49:34,477 epoch 3 - iter 396/447 - loss 0.08472916 - time (sec): 37.94 - samples/sec: 2041.16 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 16:49:38,389 epoch 3 - iter 440/447 - loss 0.08337869 - time (sec): 41.85 - samples/sec: 2039.72 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 16:49:39,011 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 16:49:39,011 EPOCH 3 done: loss 0.0831 - lr: 0.000023
116
+ 2023-10-17 16:49:50,287 DEV : loss 0.16098077595233917 - f1-score (micro avg) 0.7368
117
+ 2023-10-17 16:49:50,342 saving best model
118
+ 2023-10-17 16:49:51,747 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 16:49:56,121 epoch 4 - iter 44/447 - loss 0.06080484 - time (sec): 4.37 - samples/sec: 2053.56 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 16:50:00,102 epoch 4 - iter 88/447 - loss 0.05047837 - time (sec): 8.35 - samples/sec: 2073.72 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 16:50:04,214 epoch 4 - iter 132/447 - loss 0.04822910 - time (sec): 12.46 - samples/sec: 2078.43 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 16:50:08,227 epoch 4 - iter 176/447 - loss 0.05146065 - time (sec): 16.48 - samples/sec: 2067.12 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 16:50:12,222 epoch 4 - iter 220/447 - loss 0.05457535 - time (sec): 20.47 - samples/sec: 2081.48 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 16:50:16,289 epoch 4 - iter 264/447 - loss 0.05684864 - time (sec): 24.54 - samples/sec: 2089.74 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 16:50:20,515 epoch 4 - iter 308/447 - loss 0.05629000 - time (sec): 28.76 - samples/sec: 2067.32 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 16:50:24,525 epoch 4 - iter 352/447 - loss 0.05515985 - time (sec): 32.77 - samples/sec: 2058.16 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 16:50:29,074 epoch 4 - iter 396/447 - loss 0.05406735 - time (sec): 37.32 - samples/sec: 2059.09 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 16:50:33,156 epoch 4 - iter 440/447 - loss 0.05404876 - time (sec): 41.40 - samples/sec: 2055.53 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 16:50:33,828 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 16:50:33,829 EPOCH 4 done: loss 0.0537 - lr: 0.000020
131
+ 2023-10-17 16:50:44,774 DEV : loss 0.17118440568447113 - f1-score (micro avg) 0.7738
132
+ 2023-10-17 16:50:44,823 saving best model
133
+ 2023-10-17 16:50:46,179 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 16:50:50,043 epoch 5 - iter 44/447 - loss 0.02823819 - time (sec): 3.86 - samples/sec: 2125.42 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-17 16:50:54,046 epoch 5 - iter 88/447 - loss 0.02974272 - time (sec): 7.86 - samples/sec: 2178.10 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 16:50:58,481 epoch 5 - iter 132/447 - loss 0.03274366 - time (sec): 12.30 - samples/sec: 2173.97 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 16:51:02,421 epoch 5 - iter 176/447 - loss 0.03126456 - time (sec): 16.24 - samples/sec: 2120.29 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-17 16:51:06,701 epoch 5 - iter 220/447 - loss 0.02862125 - time (sec): 20.52 - samples/sec: 2123.83 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 16:51:10,991 epoch 5 - iter 264/447 - loss 0.02862398 - time (sec): 24.81 - samples/sec: 2103.31 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 16:51:15,112 epoch 5 - iter 308/447 - loss 0.02844421 - time (sec): 28.93 - samples/sec: 2083.75 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-17 16:51:19,138 epoch 5 - iter 352/447 - loss 0.02956228 - time (sec): 32.96 - samples/sec: 2071.76 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 16:51:23,488 epoch 5 - iter 396/447 - loss 0.03284724 - time (sec): 37.31 - samples/sec: 2064.00 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 16:51:27,485 epoch 5 - iter 440/447 - loss 0.03180610 - time (sec): 41.30 - samples/sec: 2062.28 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-17 16:51:28,153 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 16:51:28,154 EPOCH 5 done: loss 0.0315 - lr: 0.000017
146
+ 2023-10-17 16:51:39,205 DEV : loss 0.17024928331375122 - f1-score (micro avg) 0.7777
147
+ 2023-10-17 16:51:39,267 saving best model
148
+ 2023-10-17 16:51:40,718 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 16:51:45,030 epoch 6 - iter 44/447 - loss 0.02203100 - time (sec): 4.31 - samples/sec: 2041.04 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 16:51:49,781 epoch 6 - iter 88/447 - loss 0.01920241 - time (sec): 9.06 - samples/sec: 2020.90 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 16:51:54,204 epoch 6 - iter 132/447 - loss 0.02226912 - time (sec): 13.48 - samples/sec: 1979.81 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-17 16:51:58,231 epoch 6 - iter 176/447 - loss 0.02378920 - time (sec): 17.51 - samples/sec: 1959.27 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 16:52:02,125 epoch 6 - iter 220/447 - loss 0.02333195 - time (sec): 21.40 - samples/sec: 1932.28 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 16:52:06,311 epoch 6 - iter 264/447 - loss 0.02310408 - time (sec): 25.59 - samples/sec: 1946.29 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-17 16:52:10,568 epoch 6 - iter 308/447 - loss 0.02234226 - time (sec): 29.85 - samples/sec: 1981.40 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 16:52:14,740 epoch 6 - iter 352/447 - loss 0.02289841 - time (sec): 34.02 - samples/sec: 1984.53 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 16:52:19,543 epoch 6 - iter 396/447 - loss 0.02189250 - time (sec): 38.82 - samples/sec: 1986.59 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-17 16:52:23,522 epoch 6 - iter 440/447 - loss 0.02187698 - time (sec): 42.80 - samples/sec: 1997.83 - lr: 0.000013 - momentum: 0.000000
159
+ 2023-10-17 16:52:24,166 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 16:52:24,167 EPOCH 6 done: loss 0.0230 - lr: 0.000013
161
+ 2023-10-17 16:52:34,982 DEV : loss 0.19983802735805511 - f1-score (micro avg) 0.803
162
+ 2023-10-17 16:52:35,059 saving best model
163
+ 2023-10-17 16:52:36,497 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 16:52:40,921 epoch 7 - iter 44/447 - loss 0.00850187 - time (sec): 4.42 - samples/sec: 2092.53 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-17 16:52:45,097 epoch 7 - iter 88/447 - loss 0.01184907 - time (sec): 8.60 - samples/sec: 2003.34 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-17 16:52:49,559 epoch 7 - iter 132/447 - loss 0.01008429 - time (sec): 13.06 - samples/sec: 1983.15 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 16:52:53,577 epoch 7 - iter 176/447 - loss 0.01116324 - time (sec): 17.08 - samples/sec: 1978.81 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-17 16:52:57,658 epoch 7 - iter 220/447 - loss 0.01311415 - time (sec): 21.16 - samples/sec: 1975.15 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-17 16:53:01,902 epoch 7 - iter 264/447 - loss 0.01472328 - time (sec): 25.40 - samples/sec: 1967.29 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 16:53:06,100 epoch 7 - iter 308/447 - loss 0.01385064 - time (sec): 29.60 - samples/sec: 1977.81 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-17 16:53:10,128 epoch 7 - iter 352/447 - loss 0.01331558 - time (sec): 33.63 - samples/sec: 1999.23 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-17 16:53:14,178 epoch 7 - iter 396/447 - loss 0.01397777 - time (sec): 37.68 - samples/sec: 2010.39 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-17 16:53:18,463 epoch 7 - iter 440/447 - loss 0.01368698 - time (sec): 41.96 - samples/sec: 2027.17 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-17 16:53:19,188 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 16:53:19,188 EPOCH 7 done: loss 0.0135 - lr: 0.000010
176
+ 2023-10-17 16:53:30,279 DEV : loss 0.20469656586647034 - f1-score (micro avg) 0.7921
177
+ 2023-10-17 16:53:30,335 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-17 16:53:34,480 epoch 8 - iter 44/447 - loss 0.00313666 - time (sec): 4.14 - samples/sec: 2080.39 - lr: 0.000010 - momentum: 0.000000
179
+ 2023-10-17 16:53:38,581 epoch 8 - iter 88/447 - loss 0.00502648 - time (sec): 8.24 - samples/sec: 2049.56 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 16:53:42,753 epoch 8 - iter 132/447 - loss 0.00740875 - time (sec): 12.42 - samples/sec: 2062.49 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-17 16:53:47,062 epoch 8 - iter 176/447 - loss 0.00859745 - time (sec): 16.73 - samples/sec: 2020.65 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-17 16:53:51,256 epoch 8 - iter 220/447 - loss 0.00798549 - time (sec): 20.92 - samples/sec: 2006.40 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 16:53:55,572 epoch 8 - iter 264/447 - loss 0.00781959 - time (sec): 25.23 - samples/sec: 2015.40 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-17 16:53:59,928 epoch 8 - iter 308/447 - loss 0.00794785 - time (sec): 29.59 - samples/sec: 2008.36 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-17 16:54:04,317 epoch 8 - iter 352/447 - loss 0.00872736 - time (sec): 33.98 - samples/sec: 1991.41 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 16:54:08,671 epoch 8 - iter 396/447 - loss 0.00928899 - time (sec): 38.33 - samples/sec: 1991.38 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-17 16:54:13,050 epoch 8 - iter 440/447 - loss 0.00882367 - time (sec): 42.71 - samples/sec: 1995.01 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-17 16:54:13,689 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 16:54:13,689 EPOCH 8 done: loss 0.0088 - lr: 0.000007
190
+ 2023-10-17 16:54:25,266 DEV : loss 0.21882730722427368 - f1-score (micro avg) 0.8018
191
+ 2023-10-17 16:54:25,341 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-17 16:54:29,957 epoch 9 - iter 44/447 - loss 0.00911349 - time (sec): 4.61 - samples/sec: 1939.98 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 16:54:34,629 epoch 9 - iter 88/447 - loss 0.00622748 - time (sec): 9.28 - samples/sec: 2044.19 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 16:54:38,713 epoch 9 - iter 132/447 - loss 0.00477911 - time (sec): 13.37 - samples/sec: 2033.90 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-17 16:54:43,037 epoch 9 - iter 176/447 - loss 0.00545796 - time (sec): 17.69 - samples/sec: 1994.09 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 16:54:47,439 epoch 9 - iter 220/447 - loss 0.00514891 - time (sec): 22.09 - samples/sec: 2000.95 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 16:54:51,898 epoch 9 - iter 264/447 - loss 0.00530463 - time (sec): 26.55 - samples/sec: 1997.43 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-17 16:54:56,171 epoch 9 - iter 308/447 - loss 0.00519452 - time (sec): 30.83 - samples/sec: 1989.09 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 16:55:00,230 epoch 9 - iter 352/447 - loss 0.00567824 - time (sec): 34.89 - samples/sec: 1984.82 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 16:55:04,392 epoch 9 - iter 396/447 - loss 0.00625861 - time (sec): 39.05 - samples/sec: 1978.66 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-17 16:55:08,577 epoch 9 - iter 440/447 - loss 0.00656770 - time (sec): 43.23 - samples/sec: 1975.09 - lr: 0.000003 - momentum: 0.000000
202
+ 2023-10-17 16:55:09,189 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 16:55:09,190 EPOCH 9 done: loss 0.0065 - lr: 0.000003
204
+ 2023-10-17 16:55:20,752 DEV : loss 0.22874712944030762 - f1-score (micro avg) 0.8066
205
+ 2023-10-17 16:55:20,817 saving best model
206
+ 2023-10-17 16:55:22,230 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 16:55:26,626 epoch 10 - iter 44/447 - loss 0.00173260 - time (sec): 4.39 - samples/sec: 1946.13 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 16:55:30,957 epoch 10 - iter 88/447 - loss 0.00259927 - time (sec): 8.72 - samples/sec: 1922.78 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 16:55:34,844 epoch 10 - iter 132/447 - loss 0.00371022 - time (sec): 12.61 - samples/sec: 1951.89 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 16:55:39,216 epoch 10 - iter 176/447 - loss 0.00343244 - time (sec): 16.98 - samples/sec: 1973.14 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 16:55:43,550 epoch 10 - iter 220/447 - loss 0.00410654 - time (sec): 21.31 - samples/sec: 1982.22 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 16:55:48,037 epoch 10 - iter 264/447 - loss 0.00468622 - time (sec): 25.80 - samples/sec: 1992.41 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 16:55:51,992 epoch 10 - iter 308/447 - loss 0.00492962 - time (sec): 29.76 - samples/sec: 1994.33 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 16:55:56,019 epoch 10 - iter 352/447 - loss 0.00498152 - time (sec): 33.78 - samples/sec: 2022.40 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 16:55:59,943 epoch 10 - iter 396/447 - loss 0.00514324 - time (sec): 37.71 - samples/sec: 2033.47 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-17 16:56:04,083 epoch 10 - iter 440/447 - loss 0.00486802 - time (sec): 41.85 - samples/sec: 2035.70 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 16:56:04,730 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 16:56:04,731 EPOCH 10 done: loss 0.0048 - lr: 0.000000
219
+ 2023-10-17 16:56:15,689 DEV : loss 0.23447194695472717 - f1-score (micro avg) 0.805
220
+ 2023-10-17 16:56:16,295 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-17 16:56:16,298 Loading model from best epoch ...
222
+ 2023-10-17 16:56:19,028 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
223
+ 2023-10-17 16:56:25,007
224
+ Results:
225
+ - F-score (micro) 0.7627
226
+ - F-score (macro) 0.6747
227
+ - Accuracy 0.6391
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.8617 0.8574 0.8595 596
233
+ pers 0.7067 0.7958 0.7486 333
234
+ org 0.4667 0.5833 0.5185 132
235
+ prod 0.5965 0.5152 0.5528 66
236
+ time 0.6939 0.6939 0.6939 49
237
+
238
+ micro avg 0.7433 0.7832 0.7627 1176
239
+ macro avg 0.6651 0.6891 0.6747 1176
240
+ weighted avg 0.7516 0.7832 0.7657 1176
241
+
242
+ 2023-10-17 16:56:25,007 ----------------------------------------------------------------------------------------------------