Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
6726f0c
·
1 Parent(s): 4258539

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.1697557475.4c6324b99746.1390.3 +3 -0
  5. test.tsv +0 -0
  6. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939c5d442f032f53891001d48e2982edc3a674d15ef2647d0af54909143b81bb
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 15:45:52 0.0000 0.6525 0.1838 0.5544 0.6052 0.5787 0.4227
3
+ 2 15:47:17 0.0000 0.1579 0.1433 0.7063 0.7107 0.7085 0.5728
4
+ 3 15:48:43 0.0000 0.0991 0.1510 0.7081 0.7357 0.7216 0.5819
5
+ 4 15:50:07 0.0000 0.0649 0.1875 0.7667 0.7529 0.7598 0.6315
6
+ 5 15:51:31 0.0000 0.0465 0.2248 0.7849 0.7647 0.7747 0.6481
7
+ 6 15:52:54 0.0000 0.0297 0.2363 0.7816 0.7553 0.7682 0.6423
8
+ 7 15:54:17 0.0000 0.0163 0.2253 0.7861 0.7756 0.7808 0.6578
9
+ 8 15:55:39 0.0000 0.0136 0.2593 0.7780 0.7725 0.7752 0.6487
10
+ 9 15:57:00 0.0000 0.0057 0.2765 0.7844 0.7850 0.7847 0.6623
11
+ 10 15:58:25 0.0000 0.0034 0.2744 0.7935 0.7873 0.7904 0.6704
runs/events.out.tfevents.1697557475.4c6324b99746.1390.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab6968adc8038a13efa0924c1ff567e042b1624203a20af58c10e828807bb5ab
3
+ size 502124
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 15:44:35,152 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 15:44:35,154 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 15:44:35,154 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 15:44:35,155 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 15:44:35,155 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 15:44:35,155 Train: 3575 sentences
51
+ 2023-10-17 15:44:35,155 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 15:44:35,155 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 15:44:35,155 Training Params:
54
+ 2023-10-17 15:44:35,155 - learning_rate: "5e-05"
55
+ 2023-10-17 15:44:35,155 - mini_batch_size: "4"
56
+ 2023-10-17 15:44:35,155 - max_epochs: "10"
57
+ 2023-10-17 15:44:35,155 - shuffle: "True"
58
+ 2023-10-17 15:44:35,156 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 15:44:35,156 Plugins:
60
+ 2023-10-17 15:44:35,156 - TensorboardLogger
61
+ 2023-10-17 15:44:35,156 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 15:44:35,156 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 15:44:35,156 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 15:44:35,156 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 15:44:35,156 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 15:44:35,156 Computation:
67
+ 2023-10-17 15:44:35,156 - compute on device: cuda:0
68
+ 2023-10-17 15:44:35,156 - embedding storage: none
69
+ 2023-10-17 15:44:35,156 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 15:44:35,156 Model training base path: "hmbench-hipe2020/de-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
71
+ 2023-10-17 15:44:35,156 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 15:44:35,156 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 15:44:35,157 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 15:44:42,344 epoch 1 - iter 89/894 - loss 2.91539600 - time (sec): 7.19 - samples/sec: 1246.80 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 15:44:49,272 epoch 1 - iter 178/894 - loss 1.80464316 - time (sec): 14.11 - samples/sec: 1222.26 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 15:44:56,189 epoch 1 - iter 267/894 - loss 1.36782446 - time (sec): 21.03 - samples/sec: 1228.23 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 15:45:03,113 epoch 1 - iter 356/894 - loss 1.10936834 - time (sec): 27.96 - samples/sec: 1247.79 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 15:45:10,564 epoch 1 - iter 445/894 - loss 0.93995891 - time (sec): 35.41 - samples/sec: 1236.66 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 15:45:17,587 epoch 1 - iter 534/894 - loss 0.90914551 - time (sec): 42.43 - samples/sec: 1232.63 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 15:45:24,470 epoch 1 - iter 623/894 - loss 0.83544821 - time (sec): 49.31 - samples/sec: 1231.63 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 15:45:31,417 epoch 1 - iter 712/894 - loss 0.76823309 - time (sec): 56.26 - samples/sec: 1224.39 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 15:45:38,609 epoch 1 - iter 801/894 - loss 0.70255786 - time (sec): 63.45 - samples/sec: 1234.50 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 15:45:45,502 epoch 1 - iter 890/894 - loss 0.65383812 - time (sec): 70.34 - samples/sec: 1225.86 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 15:45:45,802 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 15:45:45,802 EPOCH 1 done: loss 0.6525 - lr: 0.000050
86
+ 2023-10-17 15:45:52,567 DEV : loss 0.18383200466632843 - f1-score (micro avg) 0.5787
87
+ 2023-10-17 15:45:52,644 saving best model
88
+ 2023-10-17 15:45:53,292 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 15:46:00,489 epoch 2 - iter 89/894 - loss 0.23639322 - time (sec): 7.19 - samples/sec: 1197.73 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 15:46:08,042 epoch 2 - iter 178/894 - loss 0.20566560 - time (sec): 14.75 - samples/sec: 1141.12 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 15:46:15,151 epoch 2 - iter 267/894 - loss 0.20004145 - time (sec): 21.85 - samples/sec: 1156.49 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 15:46:22,373 epoch 2 - iter 356/894 - loss 0.18486982 - time (sec): 29.08 - samples/sec: 1166.08 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 15:46:29,598 epoch 2 - iter 445/894 - loss 0.17676887 - time (sec): 36.30 - samples/sec: 1166.69 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 15:46:36,817 epoch 2 - iter 534/894 - loss 0.17708823 - time (sec): 43.52 - samples/sec: 1184.92 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 15:46:44,026 epoch 2 - iter 623/894 - loss 0.17121058 - time (sec): 50.73 - samples/sec: 1188.24 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 15:46:51,313 epoch 2 - iter 712/894 - loss 0.16652271 - time (sec): 58.02 - samples/sec: 1195.63 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 15:46:58,497 epoch 2 - iter 801/894 - loss 0.16303052 - time (sec): 65.20 - samples/sec: 1184.14 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 15:47:05,835 epoch 2 - iter 890/894 - loss 0.15787277 - time (sec): 72.54 - samples/sec: 1188.83 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 15:47:06,145 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 15:47:06,146 EPOCH 2 done: loss 0.1579 - lr: 0.000044
101
+ 2023-10-17 15:47:17,287 DEV : loss 0.14334321022033691 - f1-score (micro avg) 0.7085
102
+ 2023-10-17 15:47:17,354 saving best model
103
+ 2023-10-17 15:47:18,820 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 15:47:26,280 epoch 3 - iter 89/894 - loss 0.07813350 - time (sec): 7.46 - samples/sec: 1282.70 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 15:47:33,860 epoch 3 - iter 178/894 - loss 0.09913616 - time (sec): 15.04 - samples/sec: 1249.92 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 15:47:41,689 epoch 3 - iter 267/894 - loss 0.10793971 - time (sec): 22.86 - samples/sec: 1173.68 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 15:47:49,341 epoch 3 - iter 356/894 - loss 0.10704836 - time (sec): 30.52 - samples/sec: 1139.29 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 15:47:56,425 epoch 3 - iter 445/894 - loss 0.10184390 - time (sec): 37.60 - samples/sec: 1144.76 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 15:48:03,494 epoch 3 - iter 534/894 - loss 0.10054332 - time (sec): 44.67 - samples/sec: 1143.14 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 15:48:10,617 epoch 3 - iter 623/894 - loss 0.09942243 - time (sec): 51.79 - samples/sec: 1145.24 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 15:48:17,781 epoch 3 - iter 712/894 - loss 0.10174860 - time (sec): 58.96 - samples/sec: 1161.79 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 15:48:24,921 epoch 3 - iter 801/894 - loss 0.10063278 - time (sec): 66.10 - samples/sec: 1171.38 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 15:48:32,239 epoch 3 - iter 890/894 - loss 0.09898124 - time (sec): 73.42 - samples/sec: 1174.64 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 15:48:32,558 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 15:48:32,559 EPOCH 3 done: loss 0.0991 - lr: 0.000039
116
+ 2023-10-17 15:48:43,839 DEV : loss 0.1510310173034668 - f1-score (micro avg) 0.7216
117
+ 2023-10-17 15:48:43,898 saving best model
118
+ 2023-10-17 15:48:45,360 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 15:48:52,496 epoch 4 - iter 89/894 - loss 0.07471403 - time (sec): 7.13 - samples/sec: 1171.78 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 15:48:59,548 epoch 4 - iter 178/894 - loss 0.07152783 - time (sec): 14.18 - samples/sec: 1174.20 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 15:49:06,441 epoch 4 - iter 267/894 - loss 0.06660839 - time (sec): 21.08 - samples/sec: 1147.78 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 15:49:13,392 epoch 4 - iter 356/894 - loss 0.06963329 - time (sec): 28.03 - samples/sec: 1179.18 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 15:49:20,860 epoch 4 - iter 445/894 - loss 0.07210417 - time (sec): 35.50 - samples/sec: 1226.25 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 15:49:27,936 epoch 4 - iter 534/894 - loss 0.06863732 - time (sec): 42.57 - samples/sec: 1214.14 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 15:49:34,875 epoch 4 - iter 623/894 - loss 0.06728191 - time (sec): 49.51 - samples/sec: 1222.35 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 15:49:41,896 epoch 4 - iter 712/894 - loss 0.06607071 - time (sec): 56.53 - samples/sec: 1227.05 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 15:49:49,075 epoch 4 - iter 801/894 - loss 0.06540782 - time (sec): 63.71 - samples/sec: 1219.84 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 15:49:56,132 epoch 4 - iter 890/894 - loss 0.06487201 - time (sec): 70.77 - samples/sec: 1218.20 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 15:49:56,434 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 15:49:56,435 EPOCH 4 done: loss 0.0649 - lr: 0.000033
131
+ 2023-10-17 15:50:07,665 DEV : loss 0.18753261864185333 - f1-score (micro avg) 0.7598
132
+ 2023-10-17 15:50:07,723 saving best model
133
+ 2023-10-17 15:50:09,202 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 15:50:16,314 epoch 5 - iter 89/894 - loss 0.04554912 - time (sec): 7.11 - samples/sec: 1258.23 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 15:50:23,393 epoch 5 - iter 178/894 - loss 0.04649557 - time (sec): 14.19 - samples/sec: 1242.98 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 15:50:30,683 epoch 5 - iter 267/894 - loss 0.04140939 - time (sec): 21.48 - samples/sec: 1238.00 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 15:50:37,854 epoch 5 - iter 356/894 - loss 0.04138492 - time (sec): 28.65 - samples/sec: 1204.31 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 15:50:45,123 epoch 5 - iter 445/894 - loss 0.05411284 - time (sec): 35.92 - samples/sec: 1222.37 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 15:50:52,169 epoch 5 - iter 534/894 - loss 0.05080553 - time (sec): 42.96 - samples/sec: 1211.48 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 15:50:59,144 epoch 5 - iter 623/894 - loss 0.04833544 - time (sec): 49.94 - samples/sec: 1212.08 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 15:51:06,093 epoch 5 - iter 712/894 - loss 0.04820027 - time (sec): 56.89 - samples/sec: 1215.38 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 15:51:13,045 epoch 5 - iter 801/894 - loss 0.04783057 - time (sec): 63.84 - samples/sec: 1215.05 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 15:51:19,921 epoch 5 - iter 890/894 - loss 0.04664670 - time (sec): 70.71 - samples/sec: 1220.16 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 15:51:20,217 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 15:51:20,217 EPOCH 5 done: loss 0.0465 - lr: 0.000028
146
+ 2023-10-17 15:51:31,594 DEV : loss 0.22483567893505096 - f1-score (micro avg) 0.7747
147
+ 2023-10-17 15:51:31,657 saving best model
148
+ 2023-10-17 15:51:33,125 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 15:51:40,106 epoch 6 - iter 89/894 - loss 0.02224176 - time (sec): 6.98 - samples/sec: 1197.71 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 15:51:47,068 epoch 6 - iter 178/894 - loss 0.02790633 - time (sec): 13.94 - samples/sec: 1212.37 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 15:51:53,957 epoch 6 - iter 267/894 - loss 0.03349122 - time (sec): 20.83 - samples/sec: 1237.02 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 15:52:00,898 epoch 6 - iter 356/894 - loss 0.03376256 - time (sec): 27.77 - samples/sec: 1243.48 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 15:52:07,970 epoch 6 - iter 445/894 - loss 0.03080036 - time (sec): 34.84 - samples/sec: 1250.73 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 15:52:14,857 epoch 6 - iter 534/894 - loss 0.03219363 - time (sec): 41.73 - samples/sec: 1230.66 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 15:52:22,139 epoch 6 - iter 623/894 - loss 0.03300328 - time (sec): 49.01 - samples/sec: 1246.28 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 15:52:29,253 epoch 6 - iter 712/894 - loss 0.03197960 - time (sec): 56.12 - samples/sec: 1241.63 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 15:52:36,303 epoch 6 - iter 801/894 - loss 0.03059184 - time (sec): 63.17 - samples/sec: 1237.76 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 15:52:43,298 epoch 6 - iter 890/894 - loss 0.02966133 - time (sec): 70.17 - samples/sec: 1228.24 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 15:52:43,613 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 15:52:43,613 EPOCH 6 done: loss 0.0297 - lr: 0.000022
161
+ 2023-10-17 15:52:54,626 DEV : loss 0.23626892268657684 - f1-score (micro avg) 0.7682
162
+ 2023-10-17 15:52:54,688 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-17 15:53:01,842 epoch 7 - iter 89/894 - loss 0.01453486 - time (sec): 7.15 - samples/sec: 1341.37 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-17 15:53:08,799 epoch 7 - iter 178/894 - loss 0.01426282 - time (sec): 14.11 - samples/sec: 1278.77 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 15:53:16,409 epoch 7 - iter 267/894 - loss 0.01170213 - time (sec): 21.72 - samples/sec: 1236.79 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 15:53:23,894 epoch 7 - iter 356/894 - loss 0.01502251 - time (sec): 29.20 - samples/sec: 1246.83 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-17 15:53:30,914 epoch 7 - iter 445/894 - loss 0.01592358 - time (sec): 36.22 - samples/sec: 1241.76 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-17 15:53:37,929 epoch 7 - iter 534/894 - loss 0.01506050 - time (sec): 43.24 - samples/sec: 1227.46 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 15:53:44,802 epoch 7 - iter 623/894 - loss 0.01569285 - time (sec): 50.11 - samples/sec: 1225.12 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 15:53:51,714 epoch 7 - iter 712/894 - loss 0.01598849 - time (sec): 57.02 - samples/sec: 1229.78 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 15:53:58,543 epoch 7 - iter 801/894 - loss 0.01505426 - time (sec): 63.85 - samples/sec: 1225.65 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 15:54:05,377 epoch 7 - iter 890/894 - loss 0.01634400 - time (sec): 70.69 - samples/sec: 1219.04 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 15:54:05,690 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-17 15:54:05,690 EPOCH 7 done: loss 0.0163 - lr: 0.000017
175
+ 2023-10-17 15:54:17,064 DEV : loss 0.2253272533416748 - f1-score (micro avg) 0.7808
176
+ 2023-10-17 15:54:17,123 saving best model
177
+ 2023-10-17 15:54:18,629 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-17 15:54:25,480 epoch 8 - iter 89/894 - loss 0.01251303 - time (sec): 6.85 - samples/sec: 1215.36 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 15:54:32,319 epoch 8 - iter 178/894 - loss 0.01211563 - time (sec): 13.69 - samples/sec: 1204.97 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-17 15:54:39,189 epoch 8 - iter 267/894 - loss 0.01317594 - time (sec): 20.56 - samples/sec: 1191.22 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-17 15:54:46,270 epoch 8 - iter 356/894 - loss 0.01525423 - time (sec): 27.64 - samples/sec: 1207.62 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 15:54:53,283 epoch 8 - iter 445/894 - loss 0.01504989 - time (sec): 34.65 - samples/sec: 1219.32 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-17 15:55:00,195 epoch 8 - iter 534/894 - loss 0.01361242 - time (sec): 41.56 - samples/sec: 1214.36 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 15:55:07,127 epoch 8 - iter 623/894 - loss 0.01464410 - time (sec): 48.49 - samples/sec: 1212.03 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-17 15:55:13,952 epoch 8 - iter 712/894 - loss 0.01438402 - time (sec): 55.32 - samples/sec: 1213.86 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 15:55:20,917 epoch 8 - iter 801/894 - loss 0.01467751 - time (sec): 62.28 - samples/sec: 1230.73 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-17 15:55:27,954 epoch 8 - iter 890/894 - loss 0.01365605 - time (sec): 69.32 - samples/sec: 1244.28 - lr: 0.000011 - momentum: 0.000000
188
+ 2023-10-17 15:55:28,260 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 15:55:28,260 EPOCH 8 done: loss 0.0136 - lr: 0.000011
190
+ 2023-10-17 15:55:39,303 DEV : loss 0.25934016704559326 - f1-score (micro avg) 0.7752
191
+ 2023-10-17 15:55:39,365 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-17 15:55:46,115 epoch 9 - iter 89/894 - loss 0.00235891 - time (sec): 6.75 - samples/sec: 1149.86 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-17 15:55:52,881 epoch 9 - iter 178/894 - loss 0.00468143 - time (sec): 13.51 - samples/sec: 1194.17 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-17 15:55:59,717 epoch 9 - iter 267/894 - loss 0.00575664 - time (sec): 20.35 - samples/sec: 1207.81 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-17 15:56:06,612 epoch 9 - iter 356/894 - loss 0.00558437 - time (sec): 27.25 - samples/sec: 1214.75 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 15:56:14,079 epoch 9 - iter 445/894 - loss 0.00553854 - time (sec): 34.71 - samples/sec: 1250.09 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 15:56:21,118 epoch 9 - iter 534/894 - loss 0.00506110 - time (sec): 41.75 - samples/sec: 1259.30 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 15:56:28,035 epoch 9 - iter 623/894 - loss 0.00692322 - time (sec): 48.67 - samples/sec: 1247.83 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 15:56:35,176 epoch 9 - iter 712/894 - loss 0.00657232 - time (sec): 55.81 - samples/sec: 1232.76 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 15:56:42,129 epoch 9 - iter 801/894 - loss 0.00603686 - time (sec): 62.76 - samples/sec: 1233.58 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 15:56:49,231 epoch 9 - iter 890/894 - loss 0.00573165 - time (sec): 69.86 - samples/sec: 1231.63 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 15:56:49,545 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 15:56:49,545 EPOCH 9 done: loss 0.0057 - lr: 0.000006
204
+ 2023-10-17 15:57:00,913 DEV : loss 0.27651283144950867 - f1-score (micro avg) 0.7847
205
+ 2023-10-17 15:57:00,980 saving best model
206
+ 2023-10-17 15:57:02,455 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 15:57:09,482 epoch 10 - iter 89/894 - loss 0.00371495 - time (sec): 7.02 - samples/sec: 1226.07 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-17 15:57:16,473 epoch 10 - iter 178/894 - loss 0.00299072 - time (sec): 14.01 - samples/sec: 1198.78 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-17 15:57:23,793 epoch 10 - iter 267/894 - loss 0.00302717 - time (sec): 21.33 - samples/sec: 1246.43 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-17 15:57:30,750 epoch 10 - iter 356/894 - loss 0.00372958 - time (sec): 28.29 - samples/sec: 1216.31 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 15:57:37,742 epoch 10 - iter 445/894 - loss 0.00318995 - time (sec): 35.28 - samples/sec: 1229.18 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 15:57:44,789 epoch 10 - iter 534/894 - loss 0.00338575 - time (sec): 42.33 - samples/sec: 1235.47 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 15:57:51,733 epoch 10 - iter 623/894 - loss 0.00351432 - time (sec): 49.27 - samples/sec: 1229.50 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 15:57:59,331 epoch 10 - iter 712/894 - loss 0.00332563 - time (sec): 56.87 - samples/sec: 1223.36 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 15:58:06,294 epoch 10 - iter 801/894 - loss 0.00327091 - time (sec): 63.83 - samples/sec: 1212.54 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 15:58:13,380 epoch 10 - iter 890/894 - loss 0.00345596 - time (sec): 70.92 - samples/sec: 1216.40 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 15:58:13,697 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 15:58:13,698 EPOCH 10 done: loss 0.0034 - lr: 0.000000
219
+ 2023-10-17 15:58:25,218 DEV : loss 0.27436527609825134 - f1-score (micro avg) 0.7904
220
+ 2023-10-17 15:58:25,278 saving best model
221
+ 2023-10-17 15:58:27,359 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-17 15:58:27,361 Loading model from best epoch ...
223
+ 2023-10-17 15:58:30,392 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
224
+ 2023-10-17 15:58:36,273
225
+ Results:
226
+ - F-score (micro) 0.7748
227
+ - F-score (macro) 0.675
228
+ - Accuracy 0.6531
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ loc 0.8648 0.8909 0.8777 596
234
+ pers 0.7072 0.7688 0.7367 333
235
+ org 0.5462 0.4924 0.5179 132
236
+ prod 0.6444 0.4394 0.5225 66
237
+ time 0.7059 0.7347 0.7200 49
238
+
239
+ micro avg 0.7699 0.7798 0.7748 1176
240
+ macro avg 0.6937 0.6652 0.6750 1176
241
+ weighted avg 0.7654 0.7798 0.7709 1176
242
+
243
+ 2023-10-17 15:58:36,273 ----------------------------------------------------------------------------------------------------