Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert_tiny-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
90b7512
·
1 Parent(s): 943d9a4

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.1697652746.46dc0c540dd0.2878.12 +3 -0
  5. test.tsv +0 -0
  6. training.log +247 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eedb108b8ae8a0819db9721052005ad4e1037584cecf17f03d464629df3d384
3
+ size 19050210
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 18:12:42 0.0000 1.8338 0.4582 0.0000 0.0000 0.0000 0.0000
3
+ 2 18:13:02 0.0000 0.5047 0.3485 0.2452 0.0602 0.0967 0.0515
4
+ 3 18:13:21 0.0000 0.4159 0.3227 0.3372 0.2260 0.2706 0.1629
5
+ 4 18:13:40 0.0000 0.3762 0.3212 0.3431 0.2651 0.2991 0.1833
6
+ 5 18:13:59 0.0000 0.3544 0.3080 0.3222 0.3096 0.3158 0.1982
7
+ 6 18:14:18 0.0000 0.3365 0.3021 0.3431 0.3010 0.3207 0.1999
8
+ 7 18:14:37 0.0000 0.3228 0.3085 0.3595 0.3081 0.3318 0.2090
9
+ 8 18:14:57 0.0000 0.3121 0.3047 0.3480 0.3213 0.3341 0.2110
10
+ 9 18:15:16 0.0000 0.3060 0.3093 0.3553 0.3073 0.3296 0.2070
11
+ 10 18:15:36 0.0000 0.3003 0.3070 0.3529 0.3190 0.3351 0.2116
runs/events.out.tfevents.1697652746.46dc0c540dd0.2878.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6247d27485dbef41b9e0f2c4f20bd12b86922b11f12e2165b521a134c904493b
3
+ size 502124
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 18:12:26,648 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 18:12:26,648 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-18 18:12:26,648 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 18:12:26,648 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
52
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
53
+ 2023-10-18 18:12:26,648 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 18:12:26,648 Train: 3575 sentences
55
+ 2023-10-18 18:12:26,648 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 18:12:26,648 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 18:12:26,648 Training Params:
58
+ 2023-10-18 18:12:26,648 - learning_rate: "3e-05"
59
+ 2023-10-18 18:12:26,648 - mini_batch_size: "4"
60
+ 2023-10-18 18:12:26,648 - max_epochs: "10"
61
+ 2023-10-18 18:12:26,648 - shuffle: "True"
62
+ 2023-10-18 18:12:26,648 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 18:12:26,649 Plugins:
64
+ 2023-10-18 18:12:26,649 - TensorboardLogger
65
+ 2023-10-18 18:12:26,649 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 18:12:26,649 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 18:12:26,649 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 18:12:26,649 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 18:12:26,649 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 18:12:26,649 Computation:
71
+ 2023-10-18 18:12:26,649 - compute on device: cuda:0
72
+ 2023-10-18 18:12:26,649 - embedding storage: none
73
+ 2023-10-18 18:12:26,649 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 18:12:26,649 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-18 18:12:26,649 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 18:12:26,649 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 18:12:26,649 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 18:12:28,063 epoch 1 - iter 89/894 - loss 4.30065895 - time (sec): 1.41 - samples/sec: 5863.68 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-18 18:12:29,477 epoch 1 - iter 178/894 - loss 4.05118813 - time (sec): 2.83 - samples/sec: 5957.89 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-18 18:12:30,886 epoch 1 - iter 267/894 - loss 3.74797971 - time (sec): 4.24 - samples/sec: 6281.29 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-18 18:12:32,265 epoch 1 - iter 356/894 - loss 3.35481920 - time (sec): 5.62 - samples/sec: 6340.56 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-18 18:12:33,666 epoch 1 - iter 445/894 - loss 2.91699777 - time (sec): 7.02 - samples/sec: 6417.64 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-18 18:12:35,047 epoch 1 - iter 534/894 - loss 2.58442281 - time (sec): 8.40 - samples/sec: 6383.78 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-18 18:12:36,429 epoch 1 - iter 623/894 - loss 2.32823076 - time (sec): 9.78 - samples/sec: 6307.91 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-18 18:12:37,798 epoch 1 - iter 712/894 - loss 2.12806775 - time (sec): 11.15 - samples/sec: 6264.38 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-18 18:12:39,182 epoch 1 - iter 801/894 - loss 1.97667733 - time (sec): 12.53 - samples/sec: 6194.87 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-18 18:12:40,561 epoch 1 - iter 890/894 - loss 1.83834318 - time (sec): 13.91 - samples/sec: 6197.81 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-18 18:12:40,624 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 18:12:40,625 EPOCH 1 done: loss 1.8338 - lr: 0.000030
90
+ 2023-10-18 18:12:42,893 DEV : loss 0.4581781327724457 - f1-score (micro avg) 0.0
91
+ 2023-10-18 18:12:42,916 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 18:12:44,292 epoch 2 - iter 89/894 - loss 0.59867823 - time (sec): 1.38 - samples/sec: 6435.72 - lr: 0.000030 - momentum: 0.000000
93
+ 2023-10-18 18:12:45,665 epoch 2 - iter 178/894 - loss 0.57480149 - time (sec): 2.75 - samples/sec: 6269.54 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-18 18:12:47,021 epoch 2 - iter 267/894 - loss 0.56770059 - time (sec): 4.10 - samples/sec: 6239.82 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-18 18:12:48,401 epoch 2 - iter 356/894 - loss 0.56163379 - time (sec): 5.49 - samples/sec: 6187.91 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-18 18:12:49,776 epoch 2 - iter 445/894 - loss 0.54920126 - time (sec): 6.86 - samples/sec: 6175.95 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-18 18:12:51,155 epoch 2 - iter 534/894 - loss 0.54336327 - time (sec): 8.24 - samples/sec: 6073.43 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-18 18:12:52,540 epoch 2 - iter 623/894 - loss 0.53277504 - time (sec): 9.62 - samples/sec: 6109.68 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-18 18:12:53,993 epoch 2 - iter 712/894 - loss 0.51554670 - time (sec): 11.08 - samples/sec: 6207.01 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-18 18:12:55,391 epoch 2 - iter 801/894 - loss 0.51151749 - time (sec): 12.47 - samples/sec: 6234.99 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-18 18:12:56,802 epoch 2 - iter 890/894 - loss 0.50365857 - time (sec): 13.89 - samples/sec: 6205.94 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-18 18:12:56,873 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 18:12:56,874 EPOCH 2 done: loss 0.5047 - lr: 0.000027
104
+ 2023-10-18 18:13:02,051 DEV : loss 0.34852492809295654 - f1-score (micro avg) 0.0967
105
+ 2023-10-18 18:13:02,074 saving best model
106
+ 2023-10-18 18:13:02,108 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 18:13:03,520 epoch 3 - iter 89/894 - loss 0.42103620 - time (sec): 1.41 - samples/sec: 6298.51 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-18 18:13:04,895 epoch 3 - iter 178/894 - loss 0.40181846 - time (sec): 2.79 - samples/sec: 6186.38 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-18 18:13:06,296 epoch 3 - iter 267/894 - loss 0.41796152 - time (sec): 4.19 - samples/sec: 6196.39 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-18 18:13:07,671 epoch 3 - iter 356/894 - loss 0.42404257 - time (sec): 5.56 - samples/sec: 6124.96 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-18 18:13:09,042 epoch 3 - iter 445/894 - loss 0.41948278 - time (sec): 6.93 - samples/sec: 6176.89 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-18 18:13:10,487 epoch 3 - iter 534/894 - loss 0.41394295 - time (sec): 8.38 - samples/sec: 6298.19 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-18 18:13:11,914 epoch 3 - iter 623/894 - loss 0.42265535 - time (sec): 9.81 - samples/sec: 6275.67 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-18 18:13:13,303 epoch 3 - iter 712/894 - loss 0.41519781 - time (sec): 11.20 - samples/sec: 6238.64 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-18 18:13:14,686 epoch 3 - iter 801/894 - loss 0.41634385 - time (sec): 12.58 - samples/sec: 6174.11 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-18 18:13:16,059 epoch 3 - iter 890/894 - loss 0.41644892 - time (sec): 13.95 - samples/sec: 6174.42 - lr: 0.000023 - momentum: 0.000000
117
+ 2023-10-18 18:13:16,119 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 18:13:16,119 EPOCH 3 done: loss 0.4159 - lr: 0.000023
119
+ 2023-10-18 18:13:21,342 DEV : loss 0.32269880175590515 - f1-score (micro avg) 0.2706
120
+ 2023-10-18 18:13:21,366 saving best model
121
+ 2023-10-18 18:13:21,403 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 18:13:22,790 epoch 4 - iter 89/894 - loss 0.35650452 - time (sec): 1.39 - samples/sec: 5576.49 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-18 18:13:24,169 epoch 4 - iter 178/894 - loss 0.37533141 - time (sec): 2.77 - samples/sec: 5757.37 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-18 18:13:25,573 epoch 4 - iter 267/894 - loss 0.40715939 - time (sec): 4.17 - samples/sec: 5835.06 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-18 18:13:26,968 epoch 4 - iter 356/894 - loss 0.40776949 - time (sec): 5.56 - samples/sec: 5922.05 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-18 18:13:28,396 epoch 4 - iter 445/894 - loss 0.39118533 - time (sec): 6.99 - samples/sec: 6059.11 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-18 18:13:29,766 epoch 4 - iter 534/894 - loss 0.38025983 - time (sec): 8.36 - samples/sec: 6110.48 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-18 18:13:31,206 epoch 4 - iter 623/894 - loss 0.37519774 - time (sec): 9.80 - samples/sec: 6187.68 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-18 18:13:32,610 epoch 4 - iter 712/894 - loss 0.37572856 - time (sec): 11.21 - samples/sec: 6218.96 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-18 18:13:33,990 epoch 4 - iter 801/894 - loss 0.37183429 - time (sec): 12.59 - samples/sec: 6197.42 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-18 18:13:35,366 epoch 4 - iter 890/894 - loss 0.37518355 - time (sec): 13.96 - samples/sec: 6178.59 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-18 18:13:35,422 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 18:13:35,422 EPOCH 4 done: loss 0.3762 - lr: 0.000020
134
+ 2023-10-18 18:13:40,338 DEV : loss 0.32122358679771423 - f1-score (micro avg) 0.2991
135
+ 2023-10-18 18:13:40,361 saving best model
136
+ 2023-10-18 18:13:40,395 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 18:13:41,655 epoch 5 - iter 89/894 - loss 0.37027438 - time (sec): 1.26 - samples/sec: 7062.84 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-18 18:13:42,917 epoch 5 - iter 178/894 - loss 0.34873801 - time (sec): 2.52 - samples/sec: 6657.06 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-18 18:13:44,643 epoch 5 - iter 267/894 - loss 0.34681192 - time (sec): 4.25 - samples/sec: 6165.03 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-18 18:13:46,029 epoch 5 - iter 356/894 - loss 0.35184385 - time (sec): 5.63 - samples/sec: 6206.58 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-18 18:13:47,434 epoch 5 - iter 445/894 - loss 0.34721870 - time (sec): 7.04 - samples/sec: 6219.04 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-18 18:13:48,822 epoch 5 - iter 534/894 - loss 0.34945722 - time (sec): 8.43 - samples/sec: 6192.10 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-18 18:13:50,180 epoch 5 - iter 623/894 - loss 0.35630689 - time (sec): 9.78 - samples/sec: 6119.76 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-18 18:13:51,574 epoch 5 - iter 712/894 - loss 0.35521245 - time (sec): 11.18 - samples/sec: 6089.61 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-18 18:13:52,948 epoch 5 - iter 801/894 - loss 0.35160330 - time (sec): 12.55 - samples/sec: 6080.81 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-18 18:13:54,243 epoch 5 - iter 890/894 - loss 0.35440492 - time (sec): 13.85 - samples/sec: 6232.31 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-18 18:13:54,305 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 18:13:54,305 EPOCH 5 done: loss 0.3544 - lr: 0.000017
149
+ 2023-10-18 18:13:59,306 DEV : loss 0.3080124258995056 - f1-score (micro avg) 0.3158
150
+ 2023-10-18 18:13:59,331 saving best model
151
+ 2023-10-18 18:13:59,364 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 18:14:00,783 epoch 6 - iter 89/894 - loss 0.33467325 - time (sec): 1.42 - samples/sec: 5601.86 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-18 18:14:02,208 epoch 6 - iter 178/894 - loss 0.30810723 - time (sec): 2.84 - samples/sec: 6105.34 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-18 18:14:03,625 epoch 6 - iter 267/894 - loss 0.30292506 - time (sec): 4.26 - samples/sec: 5918.09 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-18 18:14:05,038 epoch 6 - iter 356/894 - loss 0.32078430 - time (sec): 5.67 - samples/sec: 6105.76 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-18 18:14:06,396 epoch 6 - iter 445/894 - loss 0.32374234 - time (sec): 7.03 - samples/sec: 6237.92 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-18 18:14:07,777 epoch 6 - iter 534/894 - loss 0.32865529 - time (sec): 8.41 - samples/sec: 6183.14 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-18 18:14:09,178 epoch 6 - iter 623/894 - loss 0.32702913 - time (sec): 9.81 - samples/sec: 6127.61 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-18 18:14:10,596 epoch 6 - iter 712/894 - loss 0.32725480 - time (sec): 11.23 - samples/sec: 6209.99 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-18 18:14:11,856 epoch 6 - iter 801/894 - loss 0.32393042 - time (sec): 12.49 - samples/sec: 6227.81 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-18 18:14:13,084 epoch 6 - iter 890/894 - loss 0.33649160 - time (sec): 13.72 - samples/sec: 6284.34 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-18 18:14:13,135 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 18:14:13,135 EPOCH 6 done: loss 0.3365 - lr: 0.000013
164
+ 2023-10-18 18:14:18,439 DEV : loss 0.3021206855773926 - f1-score (micro avg) 0.3207
165
+ 2023-10-18 18:14:18,464 saving best model
166
+ 2023-10-18 18:14:18,496 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 18:14:19,958 epoch 7 - iter 89/894 - loss 0.26960562 - time (sec): 1.46 - samples/sec: 6365.87 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-18 18:14:21,346 epoch 7 - iter 178/894 - loss 0.30468972 - time (sec): 2.85 - samples/sec: 6151.31 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-18 18:14:22,767 epoch 7 - iter 267/894 - loss 0.33313252 - time (sec): 4.27 - samples/sec: 6407.92 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-18 18:14:24,187 epoch 7 - iter 356/894 - loss 0.33431427 - time (sec): 5.69 - samples/sec: 6344.58 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-18 18:14:25,577 epoch 7 - iter 445/894 - loss 0.33591565 - time (sec): 7.08 - samples/sec: 6302.37 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-18 18:14:26,922 epoch 7 - iter 534/894 - loss 0.33295271 - time (sec): 8.43 - samples/sec: 6245.70 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-18 18:14:28,331 epoch 7 - iter 623/894 - loss 0.32496234 - time (sec): 9.83 - samples/sec: 6181.53 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-18 18:14:29,748 epoch 7 - iter 712/894 - loss 0.32501740 - time (sec): 11.25 - samples/sec: 6160.77 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-18 18:14:31,133 epoch 7 - iter 801/894 - loss 0.31957759 - time (sec): 12.64 - samples/sec: 6170.46 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-18 18:14:32,480 epoch 7 - iter 890/894 - loss 0.32210478 - time (sec): 13.98 - samples/sec: 6164.55 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-18 18:14:32,542 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 18:14:32,543 EPOCH 7 done: loss 0.3228 - lr: 0.000010
179
+ 2023-10-18 18:14:37,838 DEV : loss 0.30848488211631775 - f1-score (micro avg) 0.3318
180
+ 2023-10-18 18:14:37,863 saving best model
181
+ 2023-10-18 18:14:37,897 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-18 18:14:39,315 epoch 8 - iter 89/894 - loss 0.31380512 - time (sec): 1.42 - samples/sec: 6724.19 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-18 18:14:40,788 epoch 8 - iter 178/894 - loss 0.30161176 - time (sec): 2.89 - samples/sec: 6165.41 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-18 18:14:42,187 epoch 8 - iter 267/894 - loss 0.31408641 - time (sec): 4.29 - samples/sec: 6172.07 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-18 18:14:43,636 epoch 8 - iter 356/894 - loss 0.32273847 - time (sec): 5.74 - samples/sec: 6020.27 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-18 18:14:45,011 epoch 8 - iter 445/894 - loss 0.32694106 - time (sec): 7.11 - samples/sec: 6034.66 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-18 18:14:46,388 epoch 8 - iter 534/894 - loss 0.32254045 - time (sec): 8.49 - samples/sec: 6039.39 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-18 18:14:47,761 epoch 8 - iter 623/894 - loss 0.31843528 - time (sec): 9.86 - samples/sec: 6009.62 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-18 18:14:49,180 epoch 8 - iter 712/894 - loss 0.31741782 - time (sec): 11.28 - samples/sec: 6032.12 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-18 18:14:50,555 epoch 8 - iter 801/894 - loss 0.31067949 - time (sec): 12.66 - samples/sec: 6049.15 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-18 18:14:51,967 epoch 8 - iter 890/894 - loss 0.31317693 - time (sec): 14.07 - samples/sec: 6118.58 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-18 18:14:52,032 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-18 18:14:52,032 EPOCH 8 done: loss 0.3121 - lr: 0.000007
194
+ 2023-10-18 18:14:57,331 DEV : loss 0.304724782705307 - f1-score (micro avg) 0.3341
195
+ 2023-10-18 18:14:57,355 saving best model
196
+ 2023-10-18 18:14:57,395 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-18 18:14:58,774 epoch 9 - iter 89/894 - loss 0.28201030 - time (sec): 1.38 - samples/sec: 5974.75 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-18 18:15:00,149 epoch 9 - iter 178/894 - loss 0.30076729 - time (sec): 2.75 - samples/sec: 5684.88 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-18 18:15:01,567 epoch 9 - iter 267/894 - loss 0.29425291 - time (sec): 4.17 - samples/sec: 5863.62 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-18 18:15:03,049 epoch 9 - iter 356/894 - loss 0.30464495 - time (sec): 5.65 - samples/sec: 5799.05 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-18 18:15:04,519 epoch 9 - iter 445/894 - loss 0.30458727 - time (sec): 7.12 - samples/sec: 5906.97 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-18 18:15:05,921 epoch 9 - iter 534/894 - loss 0.30462622 - time (sec): 8.53 - samples/sec: 6011.64 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-18 18:15:07,339 epoch 9 - iter 623/894 - loss 0.29970434 - time (sec): 9.94 - samples/sec: 6014.50 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-18 18:15:08,843 epoch 9 - iter 712/894 - loss 0.29994186 - time (sec): 11.45 - samples/sec: 5930.13 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-18 18:15:10,270 epoch 9 - iter 801/894 - loss 0.30270378 - time (sec): 12.87 - samples/sec: 6023.83 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-18 18:15:11,655 epoch 9 - iter 890/894 - loss 0.30548739 - time (sec): 14.26 - samples/sec: 6053.64 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-18 18:15:11,717 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-18 18:15:11,717 EPOCH 9 done: loss 0.3060 - lr: 0.000003
209
+ 2023-10-18 18:15:16,672 DEV : loss 0.3093281090259552 - f1-score (micro avg) 0.3296
210
+ 2023-10-18 18:15:16,697 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-18 18:15:18,092 epoch 10 - iter 89/894 - loss 0.35217359 - time (sec): 1.39 - samples/sec: 5946.91 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-18 18:15:19,482 epoch 10 - iter 178/894 - loss 0.32604035 - time (sec): 2.78 - samples/sec: 5919.61 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-18 18:15:20,873 epoch 10 - iter 267/894 - loss 0.30390326 - time (sec): 4.18 - samples/sec: 6002.65 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-18 18:15:22,239 epoch 10 - iter 356/894 - loss 0.29975890 - time (sec): 5.54 - samples/sec: 5978.58 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-18 18:15:23,593 epoch 10 - iter 445/894 - loss 0.30706171 - time (sec): 6.90 - samples/sec: 5917.41 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-18 18:15:25,047 epoch 10 - iter 534/894 - loss 0.29824962 - time (sec): 8.35 - samples/sec: 5945.27 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 18:15:26,410 epoch 10 - iter 623/894 - loss 0.29881777 - time (sec): 9.71 - samples/sec: 5970.96 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 18:15:28,198 epoch 10 - iter 712/894 - loss 0.30115841 - time (sec): 11.50 - samples/sec: 5963.76 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 18:15:29,602 epoch 10 - iter 801/894 - loss 0.30301864 - time (sec): 12.90 - samples/sec: 5967.88 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 18:15:31,020 epoch 10 - iter 890/894 - loss 0.30007494 - time (sec): 14.32 - samples/sec: 6006.28 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-18 18:15:31,082 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-18 18:15:31,082 EPOCH 10 done: loss 0.3003 - lr: 0.000000
223
+ 2023-10-18 18:15:36,037 DEV : loss 0.30702558159828186 - f1-score (micro avg) 0.3351
224
+ 2023-10-18 18:15:36,062 saving best model
225
+ 2023-10-18 18:15:36,125 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-18 18:15:36,126 Loading model from best epoch ...
227
+ 2023-10-18 18:15:36,208 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
228
+ 2023-10-18 18:15:38,533
229
+ Results:
230
+ - F-score (micro) 0.3319
231
+ - F-score (macro) 0.1314
232
+ - Accuracy 0.2091
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ loc 0.4859 0.5503 0.5161 596
238
+ pers 0.1228 0.1652 0.1408 333
239
+ org 0.0000 0.0000 0.0000 132
240
+ prod 0.0000 0.0000 0.0000 66
241
+ time 0.0000 0.0000 0.0000 49
242
+
243
+ micro avg 0.3383 0.3257 0.3319 1176
244
+ macro avg 0.1217 0.1431 0.1314 1176
245
+ weighted avg 0.2810 0.3257 0.3015 1176
246
+
247
+ 2023-10-18 18:15:38,533 ----------------------------------------------------------------------------------------------------