Hugging Face's logo

hmbert-tiny
/
flair-hipe-2022-hipe2020-de

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files
xet
Metrics Community
1
stefan-it commited on
Commit
b1f715a
·
1 Parent(s): 352ab22

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.1697651507.46dc0c540dd0.2878.5 +3 -0
  5. test.tsv +0 -0
  6. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a3237298ea6d99a7a7210f857ee28237dc101442b879e4ccd6ed3498d256990
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 17:52:03 0.0000 1.1875 0.3862 0.0000 0.0000 0.0000 0.0000
3
+ 2 17:52:22 0.0000 0.4526 0.3269 0.3661 0.2330 0.2848 0.1726
4
+ 3 17:52:41 0.0000 0.3781 0.3309 0.4383 0.2807 0.3422 0.2133
5
+ 4 17:53:01 0.0000 0.3335 0.2942 0.3898 0.3401 0.3633 0.2321
6
+ 5 17:53:20 0.0000 0.3014 0.3075 0.4138 0.3229 0.3628 0.2333
7
+ 6 17:53:39 0.0000 0.2759 0.2959 0.3964 0.3651 0.3801 0.2480
8
+ 7 17:53:59 0.0000 0.2602 0.2992 0.3949 0.3776 0.3861 0.2543
9
+ 8 17:54:18 0.0000 0.2481 0.3005 0.4246 0.3745 0.3980 0.2633
10
+ 9 17:54:37 0.0000 0.2396 0.2993 0.4065 0.3894 0.3978 0.2646
11
+ 10 17:54:57 0.0000 0.2369 0.3009 0.4086 0.3862 0.3971 0.2637
runs/events.out.tfevents.1697651507.46dc0c540dd0.2878.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34f31d069ba100973bd4c3dc63219c2a9dfca413bc3b965107d15e63375aefad
3
+ size 502124
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 17:51:47,354 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 17:51:47,354 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 17:51:47,354 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 17:51:47,354 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 17:51:47,354 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 17:51:47,354 Train: 3575 sentences
55
+ 2023-10-18 17:51:47,354 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 17:51:47,354 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 17:51:47,354 Training Params:
58
+ 2023-10-18 17:51:47,355 - learning_rate: "5e-05"
59
+ 2023-10-18 17:51:47,355 - mini_batch_size: "4"
60
+ 2023-10-18 17:51:47,355 - max_epochs: "10"
61
+ 2023-10-18 17:51:47,355 - shuffle: "True"
62
+ 2023-10-18 17:51:47,355 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 17:51:47,355 Plugins:
64
+ 2023-10-18 17:51:47,355 - TensorboardLogger
65
+ 2023-10-18 17:51:47,355 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 17:51:47,355 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 17:51:47,355 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 17:51:47,355 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 17:51:47,355 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 17:51:47,355 Computation:
71
+ 2023-10-18 17:51:47,355 - compute on device: cuda:0
72
+ 2023-10-18 17:51:47,355 - embedding storage: none
73
+ 2023-10-18 17:51:47,355 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 17:51:47,355 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-18 17:51:47,355 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 17:51:47,355 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 17:51:47,355 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 17:51:48,543 epoch 1 - iter 89/894 - loss 3.15511888 - time (sec): 1.19 - samples/sec: 7651.58 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 17:51:49,821 epoch 1 - iter 178/894 - loss 2.80037201 - time (sec): 2.47 - samples/sec: 7645.46 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 17:51:51,177 epoch 1 - iter 267/894 - loss 2.47260416 - time (sec): 3.82 - samples/sec: 6949.16 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 17:51:52,559 epoch 1 - iter 356/894 - loss 2.10896505 - time (sec): 5.20 - samples/sec: 6568.91 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 17:51:53,949 epoch 1 - iter 445/894 - loss 1.83239594 - time (sec): 6.59 - samples/sec: 6413.69 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-18 17:51:55,393 epoch 1 - iter 534/894 - loss 1.63156121 - time (sec): 8.04 - samples/sec: 6332.03 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-18 17:51:56,861 epoch 1 - iter 623/894 - loss 1.45542562 - time (sec): 9.51 - samples/sec: 6423.68 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-18 17:51:58,227 epoch 1 - iter 712/894 - loss 1.33899230 - time (sec): 10.87 - samples/sec: 6400.13 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-18 17:51:59,651 epoch 1 - iter 801/894 - loss 1.25186435 - time (sec): 12.30 - samples/sec: 6339.08 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-18 17:52:01,030 epoch 1 - iter 890/894 - loss 1.18860703 - time (sec): 13.67 - samples/sec: 6310.36 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-18 17:52:01,090 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 17:52:01,090 EPOCH 1 done: loss 1.1875 - lr: 0.000050
90
+ 2023-10-18 17:52:03,341 DEV : loss 0.3861956000328064 - f1-score (micro avg) 0.0
91
+ 2023-10-18 17:52:03,366 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 17:52:04,722 epoch 2 - iter 89/894 - loss 0.46859686 - time (sec): 1.36 - samples/sec: 6233.38 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-18 17:52:06,106 epoch 2 - iter 178/894 - loss 0.48826135 - time (sec): 2.74 - samples/sec: 6366.22 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 17:52:07,448 epoch 2 - iter 267/894 - loss 0.47572411 - time (sec): 4.08 - samples/sec: 6180.80 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-18 17:52:08,844 epoch 2 - iter 356/894 - loss 0.47148961 - time (sec): 5.48 - samples/sec: 6084.52 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 17:52:10,261 epoch 2 - iter 445/894 - loss 0.46961239 - time (sec): 6.89 - samples/sec: 6246.17 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-18 17:52:11,623 epoch 2 - iter 534/894 - loss 0.46231896 - time (sec): 8.26 - samples/sec: 6237.81 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 17:52:13,056 epoch 2 - iter 623/894 - loss 0.46322114 - time (sec): 9.69 - samples/sec: 6365.55 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-18 17:52:14,389 epoch 2 - iter 712/894 - loss 0.45970767 - time (sec): 11.02 - samples/sec: 6278.75 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 17:52:15,768 epoch 2 - iter 801/894 - loss 0.45510621 - time (sec): 12.40 - samples/sec: 6268.29 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-18 17:52:17,137 epoch 2 - iter 890/894 - loss 0.45141144 - time (sec): 13.77 - samples/sec: 6265.98 - lr: 0.000044 - momentum: 0.000000
102
+ 2023-10-18 17:52:17,191 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 17:52:17,191 EPOCH 2 done: loss 0.4526 - lr: 0.000044
104
+ 2023-10-18 17:52:22,463 DEV : loss 0.3269258439540863 - f1-score (micro avg) 0.2848
105
+ 2023-10-18 17:52:22,490 saving best model
106
+ 2023-10-18 17:52:22,526 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 17:52:23,961 epoch 3 - iter 89/894 - loss 0.42146752 - time (sec): 1.43 - samples/sec: 6369.86 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-18 17:52:25,413 epoch 3 - iter 178/894 - loss 0.41385378 - time (sec): 2.89 - samples/sec: 6155.04 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-18 17:52:26,812 epoch 3 - iter 267/894 - loss 0.39703685 - time (sec): 4.29 - samples/sec: 6193.72 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 17:52:28,162 epoch 3 - iter 356/894 - loss 0.40727453 - time (sec): 5.64 - samples/sec: 6079.29 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-18 17:52:29,517 epoch 3 - iter 445/894 - loss 0.39317668 - time (sec): 6.99 - samples/sec: 6060.54 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 17:52:30,907 epoch 3 - iter 534/894 - loss 0.39255571 - time (sec): 8.38 - samples/sec: 6086.50 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-18 17:52:32,257 epoch 3 - iter 623/894 - loss 0.38537576 - time (sec): 9.73 - samples/sec: 6120.95 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 17:52:33,603 epoch 3 - iter 712/894 - loss 0.38546544 - time (sec): 11.08 - samples/sec: 6197.79 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-18 17:52:35,022 epoch 3 - iter 801/894 - loss 0.37977830 - time (sec): 12.50 - samples/sec: 6220.92 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-18 17:52:36,393 epoch 3 - iter 890/894 - loss 0.37792977 - time (sec): 13.87 - samples/sec: 6217.99 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 17:52:36,454 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 17:52:36,454 EPOCH 3 done: loss 0.3781 - lr: 0.000039
119
+ 2023-10-18 17:52:41,761 DEV : loss 0.33094078302383423 - f1-score (micro avg) 0.3422
120
+ 2023-10-18 17:52:41,787 saving best model
121
+ 2023-10-18 17:52:41,826 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 17:52:43,299 epoch 4 - iter 89/894 - loss 0.36629004 - time (sec): 1.47 - samples/sec: 5534.51 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-18 17:52:44,808 epoch 4 - iter 178/894 - loss 0.33855096 - time (sec): 2.98 - samples/sec: 6134.47 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 17:52:46,217 epoch 4 - iter 267/894 - loss 0.33721312 - time (sec): 4.39 - samples/sec: 6122.15 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-18 17:52:47,629 epoch 4 - iter 356/894 - loss 0.34572340 - time (sec): 5.80 - samples/sec: 6140.01 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 17:52:49,067 epoch 4 - iter 445/894 - loss 0.33658431 - time (sec): 7.24 - samples/sec: 6141.39 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-18 17:52:50,434 epoch 4 - iter 534/894 - loss 0.33650082 - time (sec): 8.61 - samples/sec: 6133.57 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 17:52:51,821 epoch 4 - iter 623/894 - loss 0.33284655 - time (sec): 9.99 - samples/sec: 6131.40 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-18 17:52:53,229 epoch 4 - iter 712/894 - loss 0.33587300 - time (sec): 11.40 - samples/sec: 6117.26 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-18 17:52:54,614 epoch 4 - iter 801/894 - loss 0.33537409 - time (sec): 12.79 - samples/sec: 6083.85 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 17:52:56,013 epoch 4 - iter 890/894 - loss 0.33482722 - time (sec): 14.19 - samples/sec: 6073.37 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-18 17:52:56,079 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 17:52:56,079 EPOCH 4 done: loss 0.3335 - lr: 0.000033
134
+ 2023-10-18 17:53:01,130 DEV : loss 0.2942203879356384 - f1-score (micro avg) 0.3633
135
+ 2023-10-18 17:53:01,157 saving best model
136
+ 2023-10-18 17:53:01,197 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 17:53:02,724 epoch 5 - iter 89/894 - loss 0.32299854 - time (sec): 1.53 - samples/sec: 5726.16 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-18 17:53:04,138 epoch 5 - iter 178/894 - loss 0.29471132 - time (sec): 2.94 - samples/sec: 6180.01 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-18 17:53:05,500 epoch 5 - iter 267/894 - loss 0.30092530 - time (sec): 4.30 - samples/sec: 6008.61 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 17:53:06,897 epoch 5 - iter 356/894 - loss 0.29863113 - time (sec): 5.70 - samples/sec: 6060.52 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-18 17:53:08,305 epoch 5 - iter 445/894 - loss 0.30227620 - time (sec): 7.11 - samples/sec: 5986.26 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 17:53:09,673 epoch 5 - iter 534/894 - loss 0.30941454 - time (sec): 8.48 - samples/sec: 5982.95 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-18 17:53:11,395 epoch 5 - iter 623/894 - loss 0.30942619 - time (sec): 10.20 - samples/sec: 5877.15 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-18 17:53:12,804 epoch 5 - iter 712/894 - loss 0.31087058 - time (sec): 11.61 - samples/sec: 5970.10 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 17:53:14,197 epoch 5 - iter 801/894 - loss 0.30816482 - time (sec): 13.00 - samples/sec: 5989.37 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-18 17:53:15,554 epoch 5 - iter 890/894 - loss 0.30195323 - time (sec): 14.36 - samples/sec: 6006.69 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 17:53:15,615 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 17:53:15,615 EPOCH 5 done: loss 0.3014 - lr: 0.000028
149
+ 2023-10-18 17:53:20,620 DEV : loss 0.30749502778053284 - f1-score (micro avg) 0.3628
150
+ 2023-10-18 17:53:20,646 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-18 17:53:22,067 epoch 6 - iter 89/894 - loss 0.28575379 - time (sec): 1.42 - samples/sec: 6046.45 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-18 17:53:23,422 epoch 6 - iter 178/894 - loss 0.27960058 - time (sec): 2.78 - samples/sec: 5968.25 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-18 17:53:24,818 epoch 6 - iter 267/894 - loss 0.26798805 - time (sec): 4.17 - samples/sec: 5811.20 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-18 17:53:26,205 epoch 6 - iter 356/894 - loss 0.28685018 - time (sec): 5.56 - samples/sec: 5849.95 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-18 17:53:27,592 epoch 6 - iter 445/894 - loss 0.28493924 - time (sec): 6.95 - samples/sec: 5887.50 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-18 17:53:29,034 epoch 6 - iter 534/894 - loss 0.29289459 - time (sec): 8.39 - samples/sec: 6068.56 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-18 17:53:30,425 epoch 6 - iter 623/894 - loss 0.28609675 - time (sec): 9.78 - samples/sec: 6099.55 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-18 17:53:31,825 epoch 6 - iter 712/894 - loss 0.27834340 - time (sec): 11.18 - samples/sec: 6125.73 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-18 17:53:33,251 epoch 6 - iter 801/894 - loss 0.27981318 - time (sec): 12.60 - samples/sec: 6170.26 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-18 17:53:34,537 epoch 6 - iter 890/894 - loss 0.27587057 - time (sec): 13.89 - samples/sec: 6206.85 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-18 17:53:34,592 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-18 17:53:34,592 EPOCH 6 done: loss 0.2759 - lr: 0.000022
163
+ 2023-10-18 17:53:39,941 DEV : loss 0.2958523631095886 - f1-score (micro avg) 0.3801
164
+ 2023-10-18 17:53:39,967 saving best model
165
+ 2023-10-18 17:53:40,004 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-18 17:53:41,290 epoch 7 - iter 89/894 - loss 0.25107818 - time (sec): 1.29 - samples/sec: 6966.43 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-18 17:53:42,673 epoch 7 - iter 178/894 - loss 0.26751214 - time (sec): 2.67 - samples/sec: 6486.38 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-18 17:53:44,052 epoch 7 - iter 267/894 - loss 0.26367724 - time (sec): 4.05 - samples/sec: 6364.62 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-18 17:53:45,431 epoch 7 - iter 356/894 - loss 0.26557215 - time (sec): 5.43 - samples/sec: 6229.57 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-18 17:53:46,936 epoch 7 - iter 445/894 - loss 0.25680326 - time (sec): 6.93 - samples/sec: 6101.11 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-18 17:53:48,357 epoch 7 - iter 534/894 - loss 0.25808523 - time (sec): 8.35 - samples/sec: 6174.89 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-18 17:53:49,803 epoch 7 - iter 623/894 - loss 0.26017038 - time (sec): 9.80 - samples/sec: 6166.19 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-18 17:53:51,177 epoch 7 - iter 712/894 - loss 0.26202742 - time (sec): 11.17 - samples/sec: 6238.15 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-18 17:53:52,566 epoch 7 - iter 801/894 - loss 0.26124153 - time (sec): 12.56 - samples/sec: 6242.21 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-18 17:53:53,941 epoch 7 - iter 890/894 - loss 0.25949025 - time (sec): 13.94 - samples/sec: 6186.49 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-18 17:53:54,000 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-18 17:53:54,000 EPOCH 7 done: loss 0.2602 - lr: 0.000017
178
+ 2023-10-18 17:53:59,392 DEV : loss 0.29916736483573914 - f1-score (micro avg) 0.3861
179
+ 2023-10-18 17:53:59,420 saving best model
180
+ 2023-10-18 17:53:59,462 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-18 17:54:00,850 epoch 8 - iter 89/894 - loss 0.28048937 - time (sec): 1.39 - samples/sec: 6383.64 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-18 17:54:02,245 epoch 8 - iter 178/894 - loss 0.26462728 - time (sec): 2.78 - samples/sec: 6586.99 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-18 17:54:03,619 epoch 8 - iter 267/894 - loss 0.26224666 - time (sec): 4.16 - samples/sec: 6344.89 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-18 17:54:05,047 epoch 8 - iter 356/894 - loss 0.25592339 - time (sec): 5.58 - samples/sec: 6308.85 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-18 17:54:06,456 epoch 8 - iter 445/894 - loss 0.24937114 - time (sec): 6.99 - samples/sec: 6381.76 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-18 17:54:07,811 epoch 8 - iter 534/894 - loss 0.24766456 - time (sec): 8.35 - samples/sec: 6353.10 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-18 17:54:09,183 epoch 8 - iter 623/894 - loss 0.25014946 - time (sec): 9.72 - samples/sec: 6266.67 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-18 17:54:10,616 epoch 8 - iter 712/894 - loss 0.24560857 - time (sec): 11.15 - samples/sec: 6296.58 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-18 17:54:12,031 epoch 8 - iter 801/894 - loss 0.25300894 - time (sec): 12.57 - samples/sec: 6242.10 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-18 17:54:13,396 epoch 8 - iter 890/894 - loss 0.24861475 - time (sec): 13.93 - samples/sec: 6181.84 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-18 17:54:13,454 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-18 17:54:13,454 EPOCH 8 done: loss 0.2481 - lr: 0.000011
193
+ 2023-10-18 17:54:18,827 DEV : loss 0.3004680871963501 - f1-score (micro avg) 0.398
194
+ 2023-10-18 17:54:18,853 saving best model
195
+ 2023-10-18 17:54:18,893 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-18 17:54:20,299 epoch 9 - iter 89/894 - loss 0.18561501 - time (sec): 1.41 - samples/sec: 6001.06 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-18 17:54:21,683 epoch 9 - iter 178/894 - loss 0.21725744 - time (sec): 2.79 - samples/sec: 5961.01 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-18 17:54:23,101 epoch 9 - iter 267/894 - loss 0.22441472 - time (sec): 4.21 - samples/sec: 6224.00 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-18 17:54:24,487 epoch 9 - iter 356/894 - loss 0.23638987 - time (sec): 5.59 - samples/sec: 6324.92 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-18 17:54:25,859 epoch 9 - iter 445/894 - loss 0.23826232 - time (sec): 6.97 - samples/sec: 6205.80 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-18 17:54:27,231 epoch 9 - iter 534/894 - loss 0.23872170 - time (sec): 8.34 - samples/sec: 6188.22 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-18 17:54:28,611 epoch 9 - iter 623/894 - loss 0.23973153 - time (sec): 9.72 - samples/sec: 6203.64 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-18 17:54:29,994 epoch 9 - iter 712/894 - loss 0.23340771 - time (sec): 11.10 - samples/sec: 6298.23 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-18 17:54:31,367 epoch 9 - iter 801/894 - loss 0.23972144 - time (sec): 12.47 - samples/sec: 6249.30 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-18 17:54:32,776 epoch 9 - iter 890/894 - loss 0.24028937 - time (sec): 13.88 - samples/sec: 6208.28 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-18 17:54:32,837 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-18 17:54:32,837 EPOCH 9 done: loss 0.2396 - lr: 0.000006
208
+ 2023-10-18 17:54:37,940 DEV : loss 0.29927825927734375 - f1-score (micro avg) 0.3978
209
+ 2023-10-18 17:54:37,969 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-18 17:54:39,383 epoch 10 - iter 89/894 - loss 0.23021562 - time (sec): 1.41 - samples/sec: 6946.18 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-18 17:54:40,731 epoch 10 - iter 178/894 - loss 0.23527595 - time (sec): 2.76 - samples/sec: 6556.86 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-18 17:54:42,095 epoch 10 - iter 267/894 - loss 0.22389138 - time (sec): 4.13 - samples/sec: 6417.79 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-18 17:54:43,542 epoch 10 - iter 356/894 - loss 0.23573274 - time (sec): 5.57 - samples/sec: 6372.62 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-18 17:54:44,896 epoch 10 - iter 445/894 - loss 0.23234303 - time (sec): 6.93 - samples/sec: 6222.73 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-18 17:54:46,283 epoch 10 - iter 534/894 - loss 0.23247333 - time (sec): 8.31 - samples/sec: 6296.22 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-18 17:54:47,678 epoch 10 - iter 623/894 - loss 0.24172654 - time (sec): 9.71 - samples/sec: 6374.96 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-18 17:54:49,076 epoch 10 - iter 712/894 - loss 0.24388043 - time (sec): 11.11 - samples/sec: 6272.26 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 17:54:50,370 epoch 10 - iter 801/894 - loss 0.23766827 - time (sec): 12.40 - samples/sec: 6290.49 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 17:54:51,731 epoch 10 - iter 890/894 - loss 0.23736563 - time (sec): 13.76 - samples/sec: 6236.95 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 17:54:51,808 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-18 17:54:51,809 EPOCH 10 done: loss 0.2369 - lr: 0.000000
222
+ 2023-10-18 17:54:57,262 DEV : loss 0.30093932151794434 - f1-score (micro avg) 0.3971
223
+ 2023-10-18 17:54:57,319 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 17:54:57,320 Loading model from best epoch ...
225
+ 2023-10-18 17:54:57,400 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
226
+ 2023-10-18 17:54:59,821
227
+ Results:
228
+ - F-score (micro) 0.4054
229
+ - F-score (macro) 0.207
230
+ - Accuracy 0.2654
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.5597 0.5822 0.5707 596
236
+ pers 0.2388 0.3213 0.2740 333
237
+ org 0.0000 0.0000 0.0000 132
238
+ time 0.2286 0.1633 0.1905 49
239
+ prod 0.0000 0.0000 0.0000 66
240
+
241
+ micro avg 0.4189 0.3929 0.4054 1176
242
+ macro avg 0.2054 0.2134 0.2070 1176
243
+ weighted avg 0.3608 0.3929 0.3748 1176
244
+
245
+ 2023-10-18 17:54:59,821 ----------------------------------------------------------------------------------------------------