Hugging Face's logo

stefan-it
/
hmbench-topres19th-en-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
42f3775
·
1 Parent(s): 44e22dc

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.1697540414.4c6324b99746.1159.7 +3 -0
  5. test.tsv +0 -0
  6. training.log +237 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9b549fb0bba7c8affe9743b7ab2c51bb20095e9f8d643a3984bfad524f7b10
3
+ size 440942021
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 11:01:33 0.0000 0.3490 0.0567 0.7419 0.7764 0.7588 0.6323
3
+ 2 11:02:54 0.0000 0.0807 0.0535 0.7555 0.7300 0.7425 0.6223
4
+ 3 11:04:11 0.0000 0.0490 0.0773 0.7176 0.7932 0.7535 0.6184
5
+ 4 11:05:27 0.0000 0.0386 0.1029 0.7407 0.7595 0.7500 0.6164
6
+ 5 11:06:48 0.0000 0.0239 0.1020 0.7510 0.8017 0.7755 0.6485
7
+ 6 11:08:09 0.0000 0.0175 0.1065 0.7579 0.8059 0.7812 0.6564
8
+ 7 11:09:29 0.0000 0.0109 0.1156 0.7884 0.8017 0.7950 0.6786
9
+ 8 11:10:47 0.0000 0.0076 0.1203 0.7924 0.7890 0.7907 0.6679
10
+ 9 11:12:04 0.0000 0.0044 0.1235 0.7640 0.8059 0.7844 0.6632
11
+ 10 11:13:23 0.0000 0.0029 0.1283 0.7689 0.8143 0.7910 0.6748
runs/events.out.tfevents.1697540414.4c6324b99746.1159.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c953da7d7ea03ca5729b1b5080b3e872e357b2f9ae5c62f34326ebf67083b55
3
+ size 434848
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 11:00:14,315 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 11:00:14,316 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
6
+ (word_embeddings): Embedding(32001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): ElectraSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 11:00:14,317 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 11:00:14,317 MultiCorpus: 6183 train + 680 dev + 2113 test sentences
48
+ - NER_HIPE_2022 Corpus: 6183 train + 680 dev + 2113 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/topres19th/en/with_doc_seperator
49
+ 2023-10-17 11:00:14,317 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 11:00:14,317 Train: 6183 sentences
51
+ 2023-10-17 11:00:14,317 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 11:00:14,317 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 11:00:14,317 Training Params:
54
+ 2023-10-17 11:00:14,317 - learning_rate: "5e-05"
55
+ 2023-10-17 11:00:14,317 - mini_batch_size: "8"
56
+ 2023-10-17 11:00:14,317 - max_epochs: "10"
57
+ 2023-10-17 11:00:14,317 - shuffle: "True"
58
+ 2023-10-17 11:00:14,317 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 11:00:14,318 Plugins:
60
+ 2023-10-17 11:00:14,318 - TensorboardLogger
61
+ 2023-10-17 11:00:14,318 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 11:00:14,318 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 11:00:14,318 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 11:00:14,318 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 11:00:14,318 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 11:00:14,318 Computation:
67
+ 2023-10-17 11:00:14,318 - compute on device: cuda:0
68
+ 2023-10-17 11:00:14,318 - embedding storage: none
69
+ 2023-10-17 11:00:14,318 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 11:00:14,318 Model training base path: "hmbench-topres19th/en-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 11:00:14,318 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 11:00:14,318 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 11:00:14,318 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 11:00:21,885 epoch 1 - iter 77/773 - loss 2.45093293 - time (sec): 7.56 - samples/sec: 1493.76 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 11:00:29,944 epoch 1 - iter 154/773 - loss 1.24837000 - time (sec): 15.62 - samples/sec: 1587.57 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 11:00:37,607 epoch 1 - iter 231/773 - loss 0.88720878 - time (sec): 23.29 - samples/sec: 1621.94 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 11:00:45,319 epoch 1 - iter 308/773 - loss 0.69711197 - time (sec): 31.00 - samples/sec: 1630.66 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 11:00:52,416 epoch 1 - iter 385/773 - loss 0.58170860 - time (sec): 38.10 - samples/sec: 1662.22 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 11:00:59,813 epoch 1 - iter 462/773 - loss 0.50112244 - time (sec): 45.49 - samples/sec: 1674.06 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 11:01:07,113 epoch 1 - iter 539/773 - loss 0.44948369 - time (sec): 52.79 - samples/sec: 1657.75 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 11:01:14,963 epoch 1 - iter 616/773 - loss 0.40797204 - time (sec): 60.64 - samples/sec: 1645.26 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 11:01:22,928 epoch 1 - iter 693/773 - loss 0.37438356 - time (sec): 68.61 - samples/sec: 1637.73 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 11:01:30,630 epoch 1 - iter 770/773 - loss 0.34972134 - time (sec): 76.31 - samples/sec: 1623.90 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 11:01:30,909 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 11:01:30,910 EPOCH 1 done: loss 0.3490 - lr: 0.000050
86
+ 2023-10-17 11:01:33,275 DEV : loss 0.05666542798280716 - f1-score (micro avg) 0.7588
87
+ 2023-10-17 11:01:33,307 saving best model
88
+ 2023-10-17 11:01:33,850 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 11:01:41,159 epoch 2 - iter 77/773 - loss 0.10595151 - time (sec): 7.31 - samples/sec: 1665.95 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 11:01:48,833 epoch 2 - iter 154/773 - loss 0.09841306 - time (sec): 14.98 - samples/sec: 1681.95 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 11:01:56,463 epoch 2 - iter 231/773 - loss 0.09574344 - time (sec): 22.61 - samples/sec: 1633.46 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 11:02:04,412 epoch 2 - iter 308/773 - loss 0.09169926 - time (sec): 30.56 - samples/sec: 1613.33 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 11:02:12,560 epoch 2 - iter 385/773 - loss 0.08863266 - time (sec): 38.71 - samples/sec: 1583.60 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 11:02:20,339 epoch 2 - iter 462/773 - loss 0.08698644 - time (sec): 46.49 - samples/sec: 1577.22 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 11:02:28,249 epoch 2 - iter 539/773 - loss 0.08349280 - time (sec): 54.40 - samples/sec: 1581.51 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 11:02:35,216 epoch 2 - iter 616/773 - loss 0.08431562 - time (sec): 61.36 - samples/sec: 1604.20 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 11:02:42,366 epoch 2 - iter 693/773 - loss 0.08313786 - time (sec): 68.51 - samples/sec: 1621.52 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 11:02:50,101 epoch 2 - iter 770/773 - loss 0.08075274 - time (sec): 76.25 - samples/sec: 1625.77 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 11:02:50,377 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 11:02:50,377 EPOCH 2 done: loss 0.0807 - lr: 0.000044
101
+ 2023-10-17 11:02:54,039 DEV : loss 0.05350477248430252 - f1-score (micro avg) 0.7425
102
+ 2023-10-17 11:02:54,072 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-17 11:03:01,603 epoch 3 - iter 77/773 - loss 0.05640998 - time (sec): 7.53 - samples/sec: 1560.20 - lr: 0.000044 - momentum: 0.000000
104
+ 2023-10-17 11:03:09,509 epoch 3 - iter 154/773 - loss 0.05629241 - time (sec): 15.43 - samples/sec: 1659.98 - lr: 0.000043 - momentum: 0.000000
105
+ 2023-10-17 11:03:17,025 epoch 3 - iter 231/773 - loss 0.05247215 - time (sec): 22.95 - samples/sec: 1689.23 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 11:03:23,846 epoch 3 - iter 308/773 - loss 0.05112877 - time (sec): 29.77 - samples/sec: 1690.16 - lr: 0.000042 - momentum: 0.000000
107
+ 2023-10-17 11:03:30,759 epoch 3 - iter 385/773 - loss 0.05111415 - time (sec): 36.68 - samples/sec: 1697.84 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 11:03:37,744 epoch 3 - iter 462/773 - loss 0.05066311 - time (sec): 43.67 - samples/sec: 1718.06 - lr: 0.000041 - momentum: 0.000000
109
+ 2023-10-17 11:03:44,762 epoch 3 - iter 539/773 - loss 0.04970420 - time (sec): 50.69 - samples/sec: 1718.08 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 11:03:52,179 epoch 3 - iter 616/773 - loss 0.05056488 - time (sec): 58.10 - samples/sec: 1711.20 - lr: 0.000040 - momentum: 0.000000
111
+ 2023-10-17 11:04:00,191 epoch 3 - iter 693/773 - loss 0.04984793 - time (sec): 66.12 - samples/sec: 1698.05 - lr: 0.000039 - momentum: 0.000000
112
+ 2023-10-17 11:04:07,775 epoch 3 - iter 770/773 - loss 0.04912347 - time (sec): 73.70 - samples/sec: 1681.26 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 11:04:08,068 ----------------------------------------------------------------------------------------------------
114
+ 2023-10-17 11:04:08,069 EPOCH 3 done: loss 0.0490 - lr: 0.000039
115
+ 2023-10-17 11:04:11,130 DEV : loss 0.07729422301054001 - f1-score (micro avg) 0.7535
116
+ 2023-10-17 11:04:11,162 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-17 11:04:18,431 epoch 4 - iter 77/773 - loss 0.04152581 - time (sec): 7.27 - samples/sec: 1784.91 - lr: 0.000038 - momentum: 0.000000
118
+ 2023-10-17 11:04:25,836 epoch 4 - iter 154/773 - loss 0.04153601 - time (sec): 14.67 - samples/sec: 1725.78 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 11:04:33,460 epoch 4 - iter 231/773 - loss 0.03745722 - time (sec): 22.30 - samples/sec: 1670.11 - lr: 0.000037 - momentum: 0.000000
120
+ 2023-10-17 11:04:40,594 epoch 4 - iter 308/773 - loss 0.03833193 - time (sec): 29.43 - samples/sec: 1674.11 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 11:04:48,298 epoch 4 - iter 385/773 - loss 0.03751315 - time (sec): 37.13 - samples/sec: 1673.41 - lr: 0.000036 - momentum: 0.000000
122
+ 2023-10-17 11:04:55,464 epoch 4 - iter 462/773 - loss 0.04103089 - time (sec): 44.30 - samples/sec: 1679.69 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 11:05:02,532 epoch 4 - iter 539/773 - loss 0.04171505 - time (sec): 51.37 - samples/sec: 1686.35 - lr: 0.000035 - momentum: 0.000000
124
+ 2023-10-17 11:05:09,597 epoch 4 - iter 616/773 - loss 0.04053471 - time (sec): 58.43 - samples/sec: 1704.07 - lr: 0.000034 - momentum: 0.000000
125
+ 2023-10-17 11:05:16,908 epoch 4 - iter 693/773 - loss 0.04085799 - time (sec): 65.74 - samples/sec: 1703.30 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 11:05:23,845 epoch 4 - iter 770/773 - loss 0.03858981 - time (sec): 72.68 - samples/sec: 1703.53 - lr: 0.000033 - momentum: 0.000000
127
+ 2023-10-17 11:05:24,115 ----------------------------------------------------------------------------------------------------
128
+ 2023-10-17 11:05:24,115 EPOCH 4 done: loss 0.0386 - lr: 0.000033
129
+ 2023-10-17 11:05:27,335 DEV : loss 0.10291995108127594 - f1-score (micro avg) 0.75
130
+ 2023-10-17 11:05:27,368 ----------------------------------------------------------------------------------------------------
131
+ 2023-10-17 11:05:34,468 epoch 5 - iter 77/773 - loss 0.02121432 - time (sec): 7.10 - samples/sec: 1722.34 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-17 11:05:41,809 epoch 5 - iter 154/773 - loss 0.02173581 - time (sec): 14.44 - samples/sec: 1656.77 - lr: 0.000032 - momentum: 0.000000
133
+ 2023-10-17 11:05:49,386 epoch 5 - iter 231/773 - loss 0.02284222 - time (sec): 22.02 - samples/sec: 1623.47 - lr: 0.000032 - momentum: 0.000000
134
+ 2023-10-17 11:05:57,449 epoch 5 - iter 308/773 - loss 0.02224722 - time (sec): 30.08 - samples/sec: 1599.93 - lr: 0.000031 - momentum: 0.000000
135
+ 2023-10-17 11:06:05,538 epoch 5 - iter 385/773 - loss 0.02315292 - time (sec): 38.17 - samples/sec: 1584.64 - lr: 0.000031 - momentum: 0.000000
136
+ 2023-10-17 11:06:13,313 epoch 5 - iter 462/773 - loss 0.02280264 - time (sec): 45.94 - samples/sec: 1586.27 - lr: 0.000030 - momentum: 0.000000
137
+ 2023-10-17 11:06:21,346 epoch 5 - iter 539/773 - loss 0.02222341 - time (sec): 53.98 - samples/sec: 1605.57 - lr: 0.000029 - momentum: 0.000000
138
+ 2023-10-17 11:06:29,147 epoch 5 - iter 616/773 - loss 0.02225636 - time (sec): 61.78 - samples/sec: 1604.81 - lr: 0.000029 - momentum: 0.000000
139
+ 2023-10-17 11:06:36,844 epoch 5 - iter 693/773 - loss 0.02247422 - time (sec): 69.47 - samples/sec: 1598.18 - lr: 0.000028 - momentum: 0.000000
140
+ 2023-10-17 11:06:44,690 epoch 5 - iter 770/773 - loss 0.02385905 - time (sec): 77.32 - samples/sec: 1601.97 - lr: 0.000028 - momentum: 0.000000
141
+ 2023-10-17 11:06:44,982 ----------------------------------------------------------------------------------------------------
142
+ 2023-10-17 11:06:44,983 EPOCH 5 done: loss 0.0239 - lr: 0.000028
143
+ 2023-10-17 11:06:47,973 DEV : loss 0.10200614482164383 - f1-score (micro avg) 0.7755
144
+ 2023-10-17 11:06:48,006 saving best model
145
+ 2023-10-17 11:06:49,423 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-17 11:06:57,017 epoch 6 - iter 77/773 - loss 0.02265088 - time (sec): 7.59 - samples/sec: 1636.48 - lr: 0.000027 - momentum: 0.000000
147
+ 2023-10-17 11:07:04,370 epoch 6 - iter 154/773 - loss 0.01754504 - time (sec): 14.94 - samples/sec: 1670.67 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 11:07:11,949 epoch 6 - iter 231/773 - loss 0.02091300 - time (sec): 22.52 - samples/sec: 1669.32 - lr: 0.000026 - momentum: 0.000000
149
+ 2023-10-17 11:07:19,655 epoch 6 - iter 308/773 - loss 0.02004128 - time (sec): 30.23 - samples/sec: 1659.22 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 11:07:27,169 epoch 6 - iter 385/773 - loss 0.01990145 - time (sec): 37.74 - samples/sec: 1647.46 - lr: 0.000025 - momentum: 0.000000
151
+ 2023-10-17 11:07:34,917 epoch 6 - iter 462/773 - loss 0.01815685 - time (sec): 45.49 - samples/sec: 1638.47 - lr: 0.000024 - momentum: 0.000000
152
+ 2023-10-17 11:07:42,565 epoch 6 - iter 539/773 - loss 0.01761772 - time (sec): 53.14 - samples/sec: 1653.33 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 11:07:50,486 epoch 6 - iter 616/773 - loss 0.01780920 - time (sec): 61.06 - samples/sec: 1629.64 - lr: 0.000023 - momentum: 0.000000
154
+ 2023-10-17 11:07:58,505 epoch 6 - iter 693/773 - loss 0.01725283 - time (sec): 69.08 - samples/sec: 1615.06 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 11:08:06,220 epoch 6 - iter 770/773 - loss 0.01731812 - time (sec): 76.79 - samples/sec: 1612.45 - lr: 0.000022 - momentum: 0.000000
156
+ 2023-10-17 11:08:06,512 ----------------------------------------------------------------------------------------------------
157
+ 2023-10-17 11:08:06,513 EPOCH 6 done: loss 0.0175 - lr: 0.000022
158
+ 2023-10-17 11:08:09,372 DEV : loss 0.1064695492386818 - f1-score (micro avg) 0.7812
159
+ 2023-10-17 11:08:09,402 saving best model
160
+ 2023-10-17 11:08:10,827 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 11:08:19,013 epoch 7 - iter 77/773 - loss 0.00823321 - time (sec): 8.18 - samples/sec: 1534.57 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 11:08:27,207 epoch 7 - iter 154/773 - loss 0.00771650 - time (sec): 16.38 - samples/sec: 1596.41 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 11:08:34,794 epoch 7 - iter 231/773 - loss 0.00743188 - time (sec): 23.96 - samples/sec: 1601.35 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 11:08:42,358 epoch 7 - iter 308/773 - loss 0.00932527 - time (sec): 31.53 - samples/sec: 1601.51 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 11:08:49,801 epoch 7 - iter 385/773 - loss 0.01044298 - time (sec): 38.97 - samples/sec: 1607.78 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 11:08:57,085 epoch 7 - iter 462/773 - loss 0.01033137 - time (sec): 46.25 - samples/sec: 1603.80 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 11:09:04,079 epoch 7 - iter 539/773 - loss 0.01077934 - time (sec): 53.25 - samples/sec: 1616.94 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 11:09:10,970 epoch 7 - iter 616/773 - loss 0.01030466 - time (sec): 60.14 - samples/sec: 1644.61 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 11:09:18,516 epoch 7 - iter 693/773 - loss 0.01069559 - time (sec): 67.68 - samples/sec: 1651.42 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 11:09:26,294 epoch 7 - iter 770/773 - loss 0.01086256 - time (sec): 75.46 - samples/sec: 1642.31 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 11:09:26,580 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 11:09:26,580 EPOCH 7 done: loss 0.0109 - lr: 0.000017
173
+ 2023-10-17 11:09:29,687 DEV : loss 0.1156071275472641 - f1-score (micro avg) 0.795
174
+ 2023-10-17 11:09:29,716 saving best model
175
+ 2023-10-17 11:09:30,324 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 11:09:37,985 epoch 8 - iter 77/773 - loss 0.00730225 - time (sec): 7.66 - samples/sec: 1614.48 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 11:09:45,493 epoch 8 - iter 154/773 - loss 0.00623081 - time (sec): 15.17 - samples/sec: 1667.90 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 11:09:52,733 epoch 8 - iter 231/773 - loss 0.00556449 - time (sec): 22.41 - samples/sec: 1656.66 - lr: 0.000015 - momentum: 0.000000
179
+ 2023-10-17 11:10:00,021 epoch 8 - iter 308/773 - loss 0.00601470 - time (sec): 29.69 - samples/sec: 1667.09 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 11:10:07,775 epoch 8 - iter 385/773 - loss 0.00628428 - time (sec): 37.45 - samples/sec: 1664.34 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 11:10:14,899 epoch 8 - iter 462/773 - loss 0.00605850 - time (sec): 44.57 - samples/sec: 1683.47 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 11:10:22,424 epoch 8 - iter 539/773 - loss 0.00700050 - time (sec): 52.10 - samples/sec: 1672.76 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 11:10:29,379 epoch 8 - iter 616/773 - loss 0.00759703 - time (sec): 59.05 - samples/sec: 1679.44 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 11:10:36,671 epoch 8 - iter 693/773 - loss 0.00788866 - time (sec): 66.35 - samples/sec: 1683.27 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 11:10:43,865 epoch 8 - iter 770/773 - loss 0.00753285 - time (sec): 73.54 - samples/sec: 1682.46 - lr: 0.000011 - momentum: 0.000000
186
+ 2023-10-17 11:10:44,140 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 11:10:44,141 EPOCH 8 done: loss 0.0076 - lr: 0.000011
188
+ 2023-10-17 11:10:47,005 DEV : loss 0.12029711902141571 - f1-score (micro avg) 0.7907
189
+ 2023-10-17 11:10:47,036 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 11:10:55,094 epoch 9 - iter 77/773 - loss 0.00421926 - time (sec): 8.06 - samples/sec: 1520.59 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-17 11:11:02,690 epoch 9 - iter 154/773 - loss 0.00644406 - time (sec): 15.65 - samples/sec: 1544.60 - lr: 0.000010 - momentum: 0.000000
192
+ 2023-10-17 11:11:10,046 epoch 9 - iter 231/773 - loss 0.00582051 - time (sec): 23.01 - samples/sec: 1641.13 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-17 11:11:17,664 epoch 9 - iter 308/773 - loss 0.00577635 - time (sec): 30.63 - samples/sec: 1616.34 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-17 11:11:24,755 epoch 9 - iter 385/773 - loss 0.00505832 - time (sec): 37.72 - samples/sec: 1630.49 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-17 11:11:31,696 epoch 9 - iter 462/773 - loss 0.00461600 - time (sec): 44.66 - samples/sec: 1643.56 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 11:11:38,576 epoch 9 - iter 539/773 - loss 0.00451370 - time (sec): 51.54 - samples/sec: 1659.27 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-17 11:11:45,934 epoch 9 - iter 616/773 - loss 0.00431455 - time (sec): 58.90 - samples/sec: 1685.41 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 11:11:53,167 epoch 9 - iter 693/773 - loss 0.00441306 - time (sec): 66.13 - samples/sec: 1680.31 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-17 11:12:00,970 epoch 9 - iter 770/773 - loss 0.00435539 - time (sec): 73.93 - samples/sec: 1677.04 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 11:12:01,228 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-17 11:12:01,228 EPOCH 9 done: loss 0.0044 - lr: 0.000006
202
+ 2023-10-17 11:12:04,174 DEV : loss 0.12349887937307358 - f1-score (micro avg) 0.7844
203
+ 2023-10-17 11:12:04,207 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 11:12:11,747 epoch 10 - iter 77/773 - loss 0.00455782 - time (sec): 7.54 - samples/sec: 1732.92 - lr: 0.000005 - momentum: 0.000000
205
+ 2023-10-17 11:12:19,108 epoch 10 - iter 154/773 - loss 0.00420301 - time (sec): 14.90 - samples/sec: 1648.39 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-17 11:12:26,608 epoch 10 - iter 231/773 - loss 0.00367766 - time (sec): 22.40 - samples/sec: 1622.02 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 11:12:33,675 epoch 10 - iter 308/773 - loss 0.00347476 - time (sec): 29.47 - samples/sec: 1663.99 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 11:12:41,045 epoch 10 - iter 385/773 - loss 0.00326384 - time (sec): 36.84 - samples/sec: 1660.68 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 11:12:49,048 epoch 10 - iter 462/773 - loss 0.00312465 - time (sec): 44.84 - samples/sec: 1633.05 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 11:12:57,102 epoch 10 - iter 539/773 - loss 0.00324546 - time (sec): 52.89 - samples/sec: 1628.44 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 11:13:05,165 epoch 10 - iter 616/773 - loss 0.00279880 - time (sec): 60.96 - samples/sec: 1644.46 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 11:13:12,609 epoch 10 - iter 693/773 - loss 0.00267431 - time (sec): 68.40 - samples/sec: 1634.31 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 11:13:20,306 epoch 10 - iter 770/773 - loss 0.00286368 - time (sec): 76.10 - samples/sec: 1628.24 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-17 11:13:20,580 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-17 11:13:20,581 EPOCH 10 done: loss 0.0029 - lr: 0.000000
216
+ 2023-10-17 11:13:23,848 DEV : loss 0.12833575904369354 - f1-score (micro avg) 0.791
217
+ 2023-10-17 11:13:24,507 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 11:13:24,509 Loading model from best epoch ...
219
+ 2023-10-17 11:13:27,115 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-BUILDING, B-BUILDING, E-BUILDING, I-BUILDING, S-STREET, B-STREET, E-STREET, I-STREET
220
+ 2023-10-17 11:13:36,470
221
+ Results:
222
+ - F-score (micro) 0.8191
223
+ - F-score (macro) 0.7465
224
+ - Accuracy 0.7116
225
+
226
+ By class:
227
+ precision recall f1-score support
228
+
229
+ LOC 0.8524 0.8668 0.8595 946
230
+ BUILDING 0.6506 0.5838 0.6154 185
231
+ STREET 0.8478 0.6964 0.7647 56
232
+
233
+ micro avg 0.8237 0.8147 0.8191 1187
234
+ macro avg 0.7836 0.7157 0.7465 1187
235
+ weighted avg 0.8207 0.8147 0.8170 1187
236
+
237
+ 2023-10-17 11:13:36,470 ----------------------------------------------------------------------------------------------------