Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
1461c38
·
1 Parent(s): dda6310

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.1697559497.4c6324b99746.1390.6 +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 sha256:0c309377fd8e28e7a5bdda1cf2bef1bb6eb22b69d49e175ddd13c562ea45abc4
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 16:19:35 0.0000 0.7328 0.1595 0.6364 0.6255 0.6309 0.4728
3
+ 2 16:20:59 0.0000 0.1539 0.1810 0.7449 0.6849 0.7136 0.5707
4
+ 3 16:22:24 0.0000 0.0879 0.1748 0.7365 0.7670 0.7514 0.6205
5
+ 4 16:23:48 0.0000 0.0531 0.1793 0.7806 0.7873 0.7840 0.6647
6
+ 5 16:25:13 0.0000 0.0362 0.1936 0.7759 0.7795 0.7777 0.6533
7
+ 6 16:26:36 0.0000 0.0214 0.2107 0.7794 0.7873 0.7834 0.6616
8
+ 7 16:27:58 0.0000 0.0151 0.2255 0.7877 0.7920 0.7899 0.6718
9
+ 8 16:29:23 0.0000 0.0103 0.2575 0.7864 0.7858 0.7861 0.6656
10
+ 9 16:30:47 0.0000 0.0067 0.2568 0.7926 0.7889 0.7908 0.6687
11
+ 10 16:32:11 0.0000 0.0039 0.2455 0.7874 0.8022 0.7947 0.6746
runs/events.out.tfevents.1697559497.4c6324b99746.1390.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a46e4424a92928110784470d160130068f9cb927e480fc3df51dfe3090921a
3
+ size 502124
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 16:18:17,473 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 16:18:17,475 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 16:18:17,475 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 16:18:17,475 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 16:18:17,475 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 16:18:17,475 Train: 3575 sentences
51
+ 2023-10-17 16:18:17,475 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 16:18:17,475 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 16:18:17,475 Training Params:
54
+ 2023-10-17 16:18:17,476 - learning_rate: "3e-05"
55
+ 2023-10-17 16:18:17,476 - mini_batch_size: "4"
56
+ 2023-10-17 16:18:17,476 - max_epochs: "10"
57
+ 2023-10-17 16:18:17,476 - shuffle: "True"
58
+ 2023-10-17 16:18:17,476 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 16:18:17,476 Plugins:
60
+ 2023-10-17 16:18:17,476 - TensorboardLogger
61
+ 2023-10-17 16:18:17,476 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 16:18:17,476 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 16:18:17,476 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 16:18:17,476 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 16:18:17,476 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 16:18:17,476 Computation:
67
+ 2023-10-17 16:18:17,476 - compute on device: cuda:0
68
+ 2023-10-17 16:18:17,476 - embedding storage: none
69
+ 2023-10-17 16:18:17,477 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 16:18:17,477 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 16:18:17,477 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 16:18:17,477 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 16:18:17,477 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 16:18:24,576 epoch 1 - iter 89/894 - loss 3.49098594 - time (sec): 7.10 - samples/sec: 1258.54 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 16:18:31,595 epoch 1 - iter 178/894 - loss 2.32366876 - time (sec): 14.12 - samples/sec: 1228.67 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 16:18:38,525 epoch 1 - iter 267/894 - loss 1.75529411 - time (sec): 21.05 - samples/sec: 1189.14 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 16:18:45,733 epoch 1 - iter 356/894 - loss 1.39116171 - time (sec): 28.25 - samples/sec: 1225.66 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 16:18:52,748 epoch 1 - iter 445/894 - loss 1.18927583 - time (sec): 35.27 - samples/sec: 1221.71 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 16:18:59,818 epoch 1 - iter 534/894 - loss 1.04847785 - time (sec): 42.34 - samples/sec: 1221.03 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 16:19:06,763 epoch 1 - iter 623/894 - loss 0.94878418 - time (sec): 49.28 - samples/sec: 1209.92 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 16:19:13,830 epoch 1 - iter 712/894 - loss 0.86276987 - time (sec): 56.35 - samples/sec: 1215.14 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 16:19:21,649 epoch 1 - iter 801/894 - loss 0.79019396 - time (sec): 64.17 - samples/sec: 1213.93 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 16:19:29,090 epoch 1 - iter 890/894 - loss 0.73480438 - time (sec): 71.61 - samples/sec: 1204.46 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 16:19:29,405 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 16:19:29,405 EPOCH 1 done: loss 0.7328 - lr: 0.000030
86
+ 2023-10-17 16:19:35,528 DEV : loss 0.15951120853424072 - f1-score (micro avg) 0.6309
87
+ 2023-10-17 16:19:35,586 saving best model
88
+ 2023-10-17 16:19:36,204 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 16:19:43,596 epoch 2 - iter 89/894 - loss 0.18396528 - time (sec): 7.39 - samples/sec: 1147.58 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 16:19:51,344 epoch 2 - iter 178/894 - loss 0.18794022 - time (sec): 15.14 - samples/sec: 1189.48 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 16:19:58,283 epoch 2 - iter 267/894 - loss 0.18661222 - time (sec): 22.08 - samples/sec: 1186.51 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 16:20:05,472 epoch 2 - iter 356/894 - loss 0.17708364 - time (sec): 29.26 - samples/sec: 1209.78 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 16:20:12,475 epoch 2 - iter 445/894 - loss 0.17032159 - time (sec): 36.27 - samples/sec: 1215.16 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 16:20:19,668 epoch 2 - iter 534/894 - loss 0.16365282 - time (sec): 43.46 - samples/sec: 1197.59 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 16:20:26,799 epoch 2 - iter 623/894 - loss 0.16022299 - time (sec): 50.59 - samples/sec: 1207.36 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 16:20:33,843 epoch 2 - iter 712/894 - loss 0.15724052 - time (sec): 57.64 - samples/sec: 1220.13 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 16:20:40,997 epoch 2 - iter 801/894 - loss 0.15532819 - time (sec): 64.79 - samples/sec: 1210.62 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 16:20:48,054 epoch 2 - iter 890/894 - loss 0.15430259 - time (sec): 71.85 - samples/sec: 1201.25 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 16:20:48,368 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 16:20:48,368 EPOCH 2 done: loss 0.1539 - lr: 0.000027
101
+ 2023-10-17 16:20:59,492 DEV : loss 0.1809595227241516 - f1-score (micro avg) 0.7136
102
+ 2023-10-17 16:20:59,549 saving best model
103
+ 2023-10-17 16:21:00,966 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 16:21:08,129 epoch 3 - iter 89/894 - loss 0.09331837 - time (sec): 7.16 - samples/sec: 1124.91 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 16:21:15,444 epoch 3 - iter 178/894 - loss 0.08405150 - time (sec): 14.47 - samples/sec: 1159.98 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 16:21:23,055 epoch 3 - iter 267/894 - loss 0.07605411 - time (sec): 22.08 - samples/sec: 1167.85 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 16:21:30,524 epoch 3 - iter 356/894 - loss 0.07990159 - time (sec): 29.55 - samples/sec: 1152.16 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 16:21:37,586 epoch 3 - iter 445/894 - loss 0.07898967 - time (sec): 36.61 - samples/sec: 1180.95 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 16:21:44,567 epoch 3 - iter 534/894 - loss 0.08478162 - time (sec): 43.60 - samples/sec: 1180.53 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 16:21:51,598 epoch 3 - iter 623/894 - loss 0.08323998 - time (sec): 50.63 - samples/sec: 1194.00 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 16:21:58,523 epoch 3 - iter 712/894 - loss 0.08445594 - time (sec): 57.55 - samples/sec: 1198.00 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 16:22:05,473 epoch 3 - iter 801/894 - loss 0.08776340 - time (sec): 64.50 - samples/sec: 1199.14 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 16:22:12,539 epoch 3 - iter 890/894 - loss 0.08785018 - time (sec): 71.57 - samples/sec: 1204.47 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 16:22:12,841 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 16:22:12,841 EPOCH 3 done: loss 0.0879 - lr: 0.000023
116
+ 2023-10-17 16:22:24,398 DEV : loss 0.17476926743984222 - f1-score (micro avg) 0.7514
117
+ 2023-10-17 16:22:24,459 saving best model
118
+ 2023-10-17 16:22:25,882 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 16:22:32,762 epoch 4 - iter 89/894 - loss 0.04063277 - time (sec): 6.88 - samples/sec: 1393.61 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 16:22:39,858 epoch 4 - iter 178/894 - loss 0.04513127 - time (sec): 13.97 - samples/sec: 1366.56 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 16:22:46,759 epoch 4 - iter 267/894 - loss 0.04728134 - time (sec): 20.87 - samples/sec: 1302.78 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 16:22:53,633 epoch 4 - iter 356/894 - loss 0.04603510 - time (sec): 27.75 - samples/sec: 1262.38 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 16:23:00,593 epoch 4 - iter 445/894 - loss 0.04807142 - time (sec): 34.71 - samples/sec: 1253.87 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 16:23:07,910 epoch 4 - iter 534/894 - loss 0.04880179 - time (sec): 42.02 - samples/sec: 1245.02 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 16:23:15,036 epoch 4 - iter 623/894 - loss 0.04793107 - time (sec): 49.15 - samples/sec: 1233.15 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 16:23:22,257 epoch 4 - iter 712/894 - loss 0.04983695 - time (sec): 56.37 - samples/sec: 1230.64 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 16:23:29,415 epoch 4 - iter 801/894 - loss 0.05080398 - time (sec): 63.53 - samples/sec: 1225.07 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 16:23:36,701 epoch 4 - iter 890/894 - loss 0.05295316 - time (sec): 70.81 - samples/sec: 1216.37 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 16:23:37,026 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 16:23:37,026 EPOCH 4 done: loss 0.0531 - lr: 0.000020
131
+ 2023-10-17 16:23:48,561 DEV : loss 0.1792767345905304 - f1-score (micro avg) 0.784
132
+ 2023-10-17 16:23:48,621 saving best model
133
+ 2023-10-17 16:23:50,016 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 16:23:57,097 epoch 5 - iter 89/894 - loss 0.03003141 - time (sec): 7.08 - samples/sec: 1184.99 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-17 16:24:04,339 epoch 5 - iter 178/894 - loss 0.03386181 - time (sec): 14.32 - samples/sec: 1258.85 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 16:24:11,294 epoch 5 - iter 267/894 - loss 0.03450992 - time (sec): 21.27 - samples/sec: 1259.13 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 16:24:18,300 epoch 5 - iter 356/894 - loss 0.03581250 - time (sec): 28.28 - samples/sec: 1242.93 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-17 16:24:25,225 epoch 5 - iter 445/894 - loss 0.03969636 - time (sec): 35.21 - samples/sec: 1227.42 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 16:24:32,350 epoch 5 - iter 534/894 - loss 0.04027827 - time (sec): 42.33 - samples/sec: 1233.12 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 16:24:39,848 epoch 5 - iter 623/894 - loss 0.04050683 - time (sec): 49.83 - samples/sec: 1217.98 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-17 16:24:46,961 epoch 5 - iter 712/894 - loss 0.03821864 - time (sec): 56.94 - samples/sec: 1224.89 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 16:24:54,046 epoch 5 - iter 801/894 - loss 0.03790059 - time (sec): 64.03 - samples/sec: 1216.47 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 16:25:01,137 epoch 5 - iter 890/894 - loss 0.03627111 - time (sec): 71.12 - samples/sec: 1213.26 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-17 16:25:01,446 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 16:25:01,447 EPOCH 5 done: loss 0.0362 - lr: 0.000017
146
+ 2023-10-17 16:25:13,187 DEV : loss 0.1935582309961319 - f1-score (micro avg) 0.7777
147
+ 2023-10-17 16:25:13,243 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 16:25:20,221 epoch 6 - iter 89/894 - loss 0.03711638 - time (sec): 6.98 - samples/sec: 1275.39 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-17 16:25:27,241 epoch 6 - iter 178/894 - loss 0.02750927 - time (sec): 14.00 - samples/sec: 1256.60 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 16:25:33,829 epoch 6 - iter 267/894 - loss 0.02860102 - time (sec): 20.58 - samples/sec: 1256.66 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 16:25:40,054 epoch 6 - iter 356/894 - loss 0.03148660 - time (sec): 26.81 - samples/sec: 1277.67 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-17 16:25:46,934 epoch 6 - iter 445/894 - loss 0.02760601 - time (sec): 33.69 - samples/sec: 1276.12 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 16:25:54,136 epoch 6 - iter 534/894 - loss 0.02699126 - time (sec): 40.89 - samples/sec: 1251.24 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 16:26:01,914 epoch 6 - iter 623/894 - loss 0.02489164 - time (sec): 48.67 - samples/sec: 1215.02 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-17 16:26:10,004 epoch 6 - iter 712/894 - loss 0.02413339 - time (sec): 56.76 - samples/sec: 1201.89 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 16:26:17,118 epoch 6 - iter 801/894 - loss 0.02224205 - time (sec): 63.87 - samples/sec: 1199.72 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 16:26:24,447 epoch 6 - iter 890/894 - loss 0.02153523 - time (sec): 71.20 - samples/sec: 1210.61 - lr: 0.000013 - momentum: 0.000000
158
+ 2023-10-17 16:26:24,756 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 16:26:24,757 EPOCH 6 done: loss 0.0214 - lr: 0.000013
160
+ 2023-10-17 16:26:36,294 DEV : loss 0.21073873341083527 - f1-score (micro avg) 0.7834
161
+ 2023-10-17 16:26:36,351 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-17 16:26:43,526 epoch 7 - iter 89/894 - loss 0.01344321 - time (sec): 7.17 - samples/sec: 1213.35 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-17 16:26:50,431 epoch 7 - iter 178/894 - loss 0.00956923 - time (sec): 14.08 - samples/sec: 1167.69 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-17 16:26:57,578 epoch 7 - iter 267/894 - loss 0.01112114 - time (sec): 21.22 - samples/sec: 1178.79 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-17 16:27:04,765 epoch 7 - iter 356/894 - loss 0.01197922 - time (sec): 28.41 - samples/sec: 1200.39 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-17 16:27:11,688 epoch 7 - iter 445/894 - loss 0.01450837 - time (sec): 35.33 - samples/sec: 1208.76 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 16:27:18,436 epoch 7 - iter 534/894 - loss 0.01471580 - time (sec): 42.08 - samples/sec: 1226.69 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-17 16:27:25,406 epoch 7 - iter 623/894 - loss 0.01479523 - time (sec): 49.05 - samples/sec: 1226.52 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-17 16:27:32,663 epoch 7 - iter 712/894 - loss 0.01445821 - time (sec): 56.31 - samples/sec: 1231.00 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 16:27:39,657 epoch 7 - iter 801/894 - loss 0.01556922 - time (sec): 63.30 - samples/sec: 1234.27 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-17 16:27:46,756 epoch 7 - iter 890/894 - loss 0.01512635 - time (sec): 70.40 - samples/sec: 1222.90 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-17 16:27:47,082 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-17 16:27:47,082 EPOCH 7 done: loss 0.0151 - lr: 0.000010
174
+ 2023-10-17 16:27:58,328 DEV : loss 0.22550107538700104 - f1-score (micro avg) 0.7899
175
+ 2023-10-17 16:27:58,394 saving best model
176
+ 2023-10-17 16:27:59,799 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 16:28:06,882 epoch 8 - iter 89/894 - loss 0.00735787 - time (sec): 7.08 - samples/sec: 1243.80 - lr: 0.000010 - momentum: 0.000000
178
+ 2023-10-17 16:28:13,927 epoch 8 - iter 178/894 - loss 0.01365307 - time (sec): 14.12 - samples/sec: 1205.85 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-17 16:28:21,045 epoch 8 - iter 267/894 - loss 0.01185970 - time (sec): 21.24 - samples/sec: 1194.91 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 16:28:28,164 epoch 8 - iter 356/894 - loss 0.01188072 - time (sec): 28.36 - samples/sec: 1184.91 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-17 16:28:35,573 epoch 8 - iter 445/894 - loss 0.01063050 - time (sec): 35.77 - samples/sec: 1219.19 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-17 16:28:43,036 epoch 8 - iter 534/894 - loss 0.01071909 - time (sec): 43.23 - samples/sec: 1214.11 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 16:28:50,128 epoch 8 - iter 623/894 - loss 0.00992864 - time (sec): 50.32 - samples/sec: 1224.89 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-17 16:28:57,943 epoch 8 - iter 712/894 - loss 0.00975064 - time (sec): 58.14 - samples/sec: 1198.00 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-17 16:29:05,257 epoch 8 - iter 801/894 - loss 0.01030314 - time (sec): 65.45 - samples/sec: 1192.10 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 16:29:12,309 epoch 8 - iter 890/894 - loss 0.01034406 - time (sec): 72.50 - samples/sec: 1190.39 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-17 16:29:12,613 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 16:29:12,613 EPOCH 8 done: loss 0.0103 - lr: 0.000007
189
+ 2023-10-17 16:29:23,870 DEV : loss 0.2575424909591675 - f1-score (micro avg) 0.7861
190
+ 2023-10-17 16:29:23,936 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-17 16:29:31,056 epoch 9 - iter 89/894 - loss 0.00456394 - time (sec): 7.12 - samples/sec: 1194.27 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-17 16:29:37,954 epoch 9 - iter 178/894 - loss 0.01007170 - time (sec): 14.02 - samples/sec: 1222.45 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 16:29:44,870 epoch 9 - iter 267/894 - loss 0.01043709 - time (sec): 20.93 - samples/sec: 1187.76 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 16:29:51,939 epoch 9 - iter 356/894 - loss 0.00821020 - time (sec): 28.00 - samples/sec: 1208.05 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-17 16:29:59,410 epoch 9 - iter 445/894 - loss 0.00750055 - time (sec): 35.47 - samples/sec: 1203.33 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 16:30:06,520 epoch 9 - iter 534/894 - loss 0.00728371 - time (sec): 42.58 - samples/sec: 1212.36 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 16:30:13,357 epoch 9 - iter 623/894 - loss 0.00665355 - time (sec): 49.42 - samples/sec: 1215.10 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-17 16:30:20,354 epoch 9 - iter 712/894 - loss 0.00712338 - time (sec): 56.41 - samples/sec: 1218.78 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 16:30:27,700 epoch 9 - iter 801/894 - loss 0.00673904 - time (sec): 63.76 - samples/sec: 1217.94 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 16:30:34,836 epoch 9 - iter 890/894 - loss 0.00673433 - time (sec): 70.90 - samples/sec: 1216.48 - lr: 0.000003 - momentum: 0.000000
201
+ 2023-10-17 16:30:35,144 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-17 16:30:35,144 EPOCH 9 done: loss 0.0067 - lr: 0.000003
203
+ 2023-10-17 16:30:46,951 DEV : loss 0.2568037509918213 - f1-score (micro avg) 0.7908
204
+ 2023-10-17 16:30:47,017 saving best model
205
+ 2023-10-17 16:30:48,440 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-17 16:30:55,777 epoch 10 - iter 89/894 - loss 0.00138104 - time (sec): 7.33 - samples/sec: 1254.10 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-17 16:31:02,774 epoch 10 - iter 178/894 - loss 0.00366289 - time (sec): 14.33 - samples/sec: 1208.69 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 16:31:09,867 epoch 10 - iter 267/894 - loss 0.00365606 - time (sec): 21.42 - samples/sec: 1185.24 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 16:31:16,830 epoch 10 - iter 356/894 - loss 0.00343159 - time (sec): 28.39 - samples/sec: 1198.61 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 16:31:23,966 epoch 10 - iter 445/894 - loss 0.00426874 - time (sec): 35.52 - samples/sec: 1202.62 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 16:31:31,313 epoch 10 - iter 534/894 - loss 0.00431619 - time (sec): 42.87 - samples/sec: 1218.53 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 16:31:38,177 epoch 10 - iter 623/894 - loss 0.00428653 - time (sec): 49.73 - samples/sec: 1204.91 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 16:31:45,304 epoch 10 - iter 712/894 - loss 0.00426761 - time (sec): 56.86 - samples/sec: 1208.58 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 16:31:52,251 epoch 10 - iter 801/894 - loss 0.00417570 - time (sec): 63.81 - samples/sec: 1205.29 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 16:31:59,363 epoch 10 - iter 890/894 - loss 0.00387118 - time (sec): 70.92 - samples/sec: 1214.02 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-17 16:31:59,677 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-17 16:31:59,677 EPOCH 10 done: loss 0.0039 - lr: 0.000000
218
+ 2023-10-17 16:32:11,414 DEV : loss 0.24554787576198578 - f1-score (micro avg) 0.7947
219
+ 2023-10-17 16:32:11,470 saving best model
220
+ 2023-10-17 16:32:13,374 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-17 16:32:13,376 Loading model from best epoch ...
222
+ 2023-10-17 16:32:15,657 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 16:32:21,664
224
+ Results:
225
+ - F-score (micro) 0.7665
226
+ - F-score (macro) 0.6658
227
+ - Accuracy 0.6401
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.8478 0.8691 0.8583 596
233
+ pers 0.7116 0.8078 0.7567 333
234
+ org 0.5207 0.4773 0.4980 132
235
+ prod 0.5849 0.4697 0.5210 66
236
+ time 0.7174 0.6735 0.6947 49
237
+
238
+ micro avg 0.7560 0.7772 0.7665 1176
239
+ macro avg 0.6765 0.6595 0.6658 1176
240
+ weighted avg 0.7523 0.7772 0.7634 1176
241
+
242
+ 2023-10-17 16:32:21,665 ----------------------------------------------------------------------------------------------------