Hugging Face's logo

stefan-it
/
hmbench-newseye-de-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
f4e3d0d
•
1 Parent(s): 7011030

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +239 -0
training.log ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 19:56:58,111 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 19:56:58,112 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 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): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
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): BertSelfOutput(
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): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
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
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 19:56:58,112 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences
52
+ - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator
53
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 19:56:58,112 Train: 20847 sentences
55
+ 2023-10-25 19:56:58,112 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 19:56:58,112 Training Params:
58
+ 2023-10-25 19:56:58,112 - learning_rate: "5e-05"
59
+ 2023-10-25 19:56:58,112 - mini_batch_size: "4"
60
+ 2023-10-25 19:56:58,112 - max_epochs: "10"
61
+ 2023-10-25 19:56:58,112 - shuffle: "True"
62
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 19:56:58,112 Plugins:
64
+ 2023-10-25 19:56:58,112 - TensorboardLogger
65
+ 2023-10-25 19:56:58,112 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 19:56:58,112 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 19:56:58,112 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 19:56:58,112 Computation:
71
+ 2023-10-25 19:56:58,112 - compute on device: cuda:0
72
+ 2023-10-25 19:56:58,112 - embedding storage: none
73
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 19:56:58,112 Model training base path: "hmbench-newseye/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-25 19:56:58,112 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 19:56:58,113 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 19:56:58,113 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 19:57:20,386 epoch 1 - iter 521/5212 - loss 1.08348570 - time (sec): 22.27 - samples/sec: 1626.00 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-25 19:57:42,372 epoch 1 - iter 1042/5212 - loss 0.70758840 - time (sec): 44.26 - samples/sec: 1663.56 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-25 19:58:04,781 epoch 1 - iter 1563/5212 - loss 0.55092863 - time (sec): 66.67 - samples/sec: 1681.34 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-25 19:58:26,646 epoch 1 - iter 2084/5212 - loss 0.47203657 - time (sec): 88.53 - samples/sec: 1679.64 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-25 19:58:48,297 epoch 1 - iter 2605/5212 - loss 0.42902220 - time (sec): 110.18 - samples/sec: 1665.66 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-25 19:59:10,349 epoch 1 - iter 3126/5212 - loss 0.39940587 - time (sec): 132.24 - samples/sec: 1653.17 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-25 19:59:32,713 epoch 1 - iter 3647/5212 - loss 0.37156643 - time (sec): 154.60 - samples/sec: 1673.93 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-25 19:59:54,575 epoch 1 - iter 4168/5212 - loss 0.34705201 - time (sec): 176.46 - samples/sec: 1679.91 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-25 20:00:16,906 epoch 1 - iter 4689/5212 - loss 0.33147071 - time (sec): 198.79 - samples/sec: 1670.29 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-25 20:00:39,372 epoch 1 - iter 5210/5212 - loss 0.32226811 - time (sec): 221.26 - samples/sec: 1659.98 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-25 20:00:39,451 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 20:00:39,451 EPOCH 1 done: loss 0.3222 - lr: 0.000050
90
+ 2023-10-25 20:00:43,129 DEV : loss 0.11420618742704391 - f1-score (micro avg) 0.2931
91
+ 2023-10-25 20:00:43,155 saving best model
92
+ 2023-10-25 20:00:43,631 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 20:01:05,416 epoch 2 - iter 521/5212 - loss 0.18552954 - time (sec): 21.78 - samples/sec: 1681.53 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-25 20:01:27,647 epoch 2 - iter 1042/5212 - loss 0.17954476 - time (sec): 44.01 - samples/sec: 1655.99 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 20:01:49,727 epoch 2 - iter 1563/5212 - loss 0.18022652 - time (sec): 66.09 - samples/sec: 1672.98 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 20:02:11,870 epoch 2 - iter 2084/5212 - loss 0.18252575 - time (sec): 88.24 - samples/sec: 1672.56 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 20:02:34,162 epoch 2 - iter 2605/5212 - loss 0.18537995 - time (sec): 110.53 - samples/sec: 1660.49 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 20:02:56,495 epoch 2 - iter 3126/5212 - loss 0.18574013 - time (sec): 132.86 - samples/sec: 1670.44 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 20:03:18,676 epoch 2 - iter 3647/5212 - loss 0.21371016 - time (sec): 155.04 - samples/sec: 1663.40 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 20:03:40,512 epoch 2 - iter 4168/5212 - loss 0.22735133 - time (sec): 176.88 - samples/sec: 1654.56 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 20:04:02,042 epoch 2 - iter 4689/5212 - loss 0.26232838 - time (sec): 198.41 - samples/sec: 1658.91 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 20:04:23,713 epoch 2 - iter 5210/5212 - loss 0.29428995 - time (sec): 220.08 - samples/sec: 1669.05 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-25 20:04:23,796 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 20:04:23,796 EPOCH 2 done: loss 0.2942 - lr: 0.000044
105
+ 2023-10-25 20:04:30,604 DEV : loss 0.21574755012989044 - f1-score (micro avg) 0.0
106
+ 2023-10-25 20:04:30,629 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-25 20:04:52,387 epoch 3 - iter 521/5212 - loss 0.61023887 - time (sec): 21.76 - samples/sec: 1676.40 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-25 20:05:14,600 epoch 3 - iter 1042/5212 - loss 0.56119949 - time (sec): 43.97 - samples/sec: 1730.25 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-25 20:05:36,372 epoch 3 - iter 1563/5212 - loss 0.56421056 - time (sec): 65.74 - samples/sec: 1717.45 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 20:05:58,622 epoch 3 - iter 2084/5212 - loss 0.57799536 - time (sec): 87.99 - samples/sec: 1690.37 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-25 20:06:20,339 epoch 3 - iter 2605/5212 - loss 0.57725572 - time (sec): 109.71 - samples/sec: 1690.27 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 20:06:42,574 epoch 3 - iter 3126/5212 - loss 0.57924881 - time (sec): 131.94 - samples/sec: 1666.46 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-25 20:07:04,690 epoch 3 - iter 3647/5212 - loss 0.58468851 - time (sec): 154.06 - samples/sec: 1662.21 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 20:07:27,168 epoch 3 - iter 4168/5212 - loss 0.58359992 - time (sec): 176.54 - samples/sec: 1672.35 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-25 20:07:48,934 epoch 3 - iter 4689/5212 - loss 0.58385727 - time (sec): 198.30 - samples/sec: 1661.25 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-25 20:08:10,931 epoch 3 - iter 5210/5212 - loss 0.57967064 - time (sec): 220.30 - samples/sec: 1667.45 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-25 20:08:11,008 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-25 20:08:11,008 EPOCH 3 done: loss 0.5798 - lr: 0.000039
119
+ 2023-10-25 20:08:17,809 DEV : loss 0.22797180712223053 - f1-score (micro avg) 0.0
120
+ 2023-10-25 20:08:17,834 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-25 20:08:39,704 epoch 4 - iter 521/5212 - loss 0.53509142 - time (sec): 21.87 - samples/sec: 1670.95 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-25 20:09:01,224 epoch 4 - iter 1042/5212 - loss 0.57089598 - time (sec): 43.39 - samples/sec: 1769.02 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-25 20:09:23,217 epoch 4 - iter 1563/5212 - loss 0.56098897 - time (sec): 65.38 - samples/sec: 1736.26 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-25 20:09:45,468 epoch 4 - iter 2084/5212 - loss 0.56792280 - time (sec): 87.63 - samples/sec: 1733.55 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-25 20:10:07,654 epoch 4 - iter 2605/5212 - loss 0.55856576 - time (sec): 109.82 - samples/sec: 1732.46 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-25 20:10:29,680 epoch 4 - iter 3126/5212 - loss 0.55882546 - time (sec): 131.84 - samples/sec: 1704.50 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-25 20:10:51,853 epoch 4 - iter 3647/5212 - loss 0.56106127 - time (sec): 154.02 - samples/sec: 1706.01 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-25 20:11:13,676 epoch 4 - iter 4168/5212 - loss 0.55614039 - time (sec): 175.84 - samples/sec: 1698.08 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-25 20:11:35,559 epoch 4 - iter 4689/5212 - loss 0.55568875 - time (sec): 197.72 - samples/sec: 1687.66 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-25 20:11:57,314 epoch 4 - iter 5210/5212 - loss 0.56143141 - time (sec): 219.48 - samples/sec: 1673.89 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-25 20:11:57,394 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-25 20:11:57,394 EPOCH 4 done: loss 0.5614 - lr: 0.000033
133
+ 2023-10-25 20:12:04,213 DEV : loss 0.22103846073150635 - f1-score (micro avg) 0.0
134
+ 2023-10-25 20:12:04,238 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-25 20:12:26,199 epoch 5 - iter 521/5212 - loss 0.59690938 - time (sec): 21.96 - samples/sec: 1651.61 - lr: 0.000033 - momentum: 0.000000
136
+ 2023-10-25 20:12:47,893 epoch 5 - iter 1042/5212 - loss 0.57083926 - time (sec): 43.65 - samples/sec: 1634.39 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-25 20:13:09,967 epoch 5 - iter 1563/5212 - loss 0.55181100 - time (sec): 65.73 - samples/sec: 1668.56 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-25 20:13:32,378 epoch 5 - iter 2084/5212 - loss 0.55381084 - time (sec): 88.14 - samples/sec: 1674.65 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-25 20:13:54,700 epoch 5 - iter 2605/5212 - loss 0.55370422 - time (sec): 110.46 - samples/sec: 1669.48 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-25 20:14:16,931 epoch 5 - iter 3126/5212 - loss 0.55580912 - time (sec): 132.69 - samples/sec: 1670.75 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-25 20:14:39,010 epoch 5 - iter 3647/5212 - loss 0.55361204 - time (sec): 154.77 - samples/sec: 1648.30 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-25 20:15:01,019 epoch 5 - iter 4168/5212 - loss 0.55662199 - time (sec): 176.78 - samples/sec: 1657.09 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-25 20:15:23,088 epoch 5 - iter 4689/5212 - loss 0.54917164 - time (sec): 198.85 - samples/sec: 1654.63 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-25 20:15:45,019 epoch 5 - iter 5210/5212 - loss 0.54696535 - time (sec): 220.78 - samples/sec: 1664.02 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-25 20:15:45,098 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-25 20:15:45,098 EPOCH 5 done: loss 0.5469 - lr: 0.000028
147
+ 2023-10-25 20:15:51,857 DEV : loss 0.2455786168575287 - f1-score (micro avg) 0.0
148
+ 2023-10-25 20:15:51,883 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 20:16:14,379 epoch 6 - iter 521/5212 - loss 0.57254029 - time (sec): 22.49 - samples/sec: 1691.82 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-25 20:16:36,220 epoch 6 - iter 1042/5212 - loss 0.52755461 - time (sec): 44.34 - samples/sec: 1655.77 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-25 20:16:58,010 epoch 6 - iter 1563/5212 - loss 0.53602606 - time (sec): 66.13 - samples/sec: 1643.95 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-25 20:17:20,136 epoch 6 - iter 2084/5212 - loss 0.53959820 - time (sec): 88.25 - samples/sec: 1666.58 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-25 20:17:41,835 epoch 6 - iter 2605/5212 - loss 0.54382641 - time (sec): 109.95 - samples/sec: 1658.66 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-25 20:18:04,025 epoch 6 - iter 3126/5212 - loss 0.54769962 - time (sec): 132.14 - samples/sec: 1669.15 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-25 20:18:25,736 epoch 6 - iter 3647/5212 - loss 0.54874941 - time (sec): 153.85 - samples/sec: 1658.88 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-25 20:18:47,563 epoch 6 - iter 4168/5212 - loss 0.54164387 - time (sec): 175.68 - samples/sec: 1663.19 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-25 20:19:09,794 epoch 6 - iter 4689/5212 - loss 0.53460429 - time (sec): 197.91 - samples/sec: 1668.66 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-25 20:19:32,171 epoch 6 - iter 5210/5212 - loss 0.53273458 - time (sec): 220.29 - samples/sec: 1667.76 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-25 20:19:32,256 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-25 20:19:32,256 EPOCH 6 done: loss 0.5327 - lr: 0.000022
161
+ 2023-10-25 20:19:39,076 DEV : loss 0.24423913657665253 - f1-score (micro avg) 0.0
162
+ 2023-10-25 20:19:39,103 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 20:20:01,010 epoch 7 - iter 521/5212 - loss 0.52293661 - time (sec): 21.91 - samples/sec: 1654.87 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-25 20:20:22,981 epoch 7 - iter 1042/5212 - loss 0.55864614 - time (sec): 43.88 - samples/sec: 1685.68 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-25 20:20:44,977 epoch 7 - iter 1563/5212 - loss 0.54801286 - time (sec): 65.87 - samples/sec: 1687.51 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-25 20:21:07,465 epoch 7 - iter 2084/5212 - loss 0.52281712 - time (sec): 88.36 - samples/sec: 1697.53 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-25 20:21:29,412 epoch 7 - iter 2605/5212 - loss 0.52541212 - time (sec): 110.31 - samples/sec: 1686.47 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-25 20:21:50,941 epoch 7 - iter 3126/5212 - loss 0.52460589 - time (sec): 131.84 - samples/sec: 1702.56 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-25 20:22:12,842 epoch 7 - iter 3647/5212 - loss 0.52696389 - time (sec): 153.74 - samples/sec: 1706.10 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-25 20:22:34,666 epoch 7 - iter 4168/5212 - loss 0.52978826 - time (sec): 175.56 - samples/sec: 1703.61 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-25 20:22:56,241 epoch 7 - iter 4689/5212 - loss 0.53279906 - time (sec): 197.14 - samples/sec: 1687.62 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-25 20:23:18,267 epoch 7 - iter 5210/5212 - loss 0.53320841 - time (sec): 219.16 - samples/sec: 1676.23 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-25 20:23:18,343 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-25 20:23:18,343 EPOCH 7 done: loss 0.5332 - lr: 0.000017
175
+ 2023-10-25 20:23:24,491 DEV : loss 0.24582862854003906 - f1-score (micro avg) 0.0
176
+ 2023-10-25 20:23:24,518 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-25 20:23:46,181 epoch 8 - iter 521/5212 - loss 0.51997984 - time (sec): 21.66 - samples/sec: 1675.53 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-25 20:24:08,717 epoch 8 - iter 1042/5212 - loss 0.50827131 - time (sec): 44.20 - samples/sec: 1632.62 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-25 20:24:30,464 epoch 8 - iter 1563/5212 - loss 0.52442736 - time (sec): 65.94 - samples/sec: 1655.07 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-25 20:24:52,677 epoch 8 - iter 2084/5212 - loss 0.53205725 - time (sec): 88.16 - samples/sec: 1627.91 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-25 20:25:14,585 epoch 8 - iter 2605/5212 - loss 0.52219100 - time (sec): 110.06 - samples/sec: 1645.61 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-25 20:25:36,027 epoch 8 - iter 3126/5212 - loss 0.53222967 - time (sec): 131.51 - samples/sec: 1636.67 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-25 20:25:58,145 epoch 8 - iter 3647/5212 - loss 0.53929555 - time (sec): 153.63 - samples/sec: 1646.93 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-25 20:26:20,446 epoch 8 - iter 4168/5212 - loss 0.54041489 - time (sec): 175.93 - samples/sec: 1649.90 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-25 20:26:42,442 epoch 8 - iter 4689/5212 - loss 0.53637281 - time (sec): 197.92 - samples/sec: 1667.54 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-25 20:27:04,221 epoch 8 - iter 5210/5212 - loss 0.53009907 - time (sec): 219.70 - samples/sec: 1671.95 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-25 20:27:04,313 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-25 20:27:04,314 EPOCH 8 done: loss 0.5301 - lr: 0.000011
189
+ 2023-10-25 20:27:10,440 DEV : loss 0.2523580491542816 - f1-score (micro avg) 0.0
190
+ 2023-10-25 20:27:10,466 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-25 20:27:32,371 epoch 9 - iter 521/5212 - loss 0.52508937 - time (sec): 21.90 - samples/sec: 1695.81 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-25 20:27:54,597 epoch 9 - iter 1042/5212 - loss 0.54085716 - time (sec): 44.13 - samples/sec: 1626.44 - lr: 0.000010 - momentum: 0.000000
193
+ 2023-10-25 20:28:16,737 epoch 9 - iter 1563/5212 - loss 0.54010812 - time (sec): 66.27 - samples/sec: 1656.38 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-25 20:28:39,178 epoch 9 - iter 2084/5212 - loss 0.54472189 - time (sec): 88.71 - samples/sec: 1642.16 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-25 20:29:01,052 epoch 9 - iter 2605/5212 - loss 0.54518847 - time (sec): 110.58 - samples/sec: 1633.86 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-25 20:29:23,296 epoch 9 - iter 3126/5212 - loss 0.54101988 - time (sec): 132.83 - samples/sec: 1638.13 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-25 20:29:45,113 epoch 9 - iter 3647/5212 - loss 0.53936286 - time (sec): 154.65 - samples/sec: 1632.42 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-25 20:30:07,429 epoch 9 - iter 4168/5212 - loss 0.53352108 - time (sec): 176.96 - samples/sec: 1649.12 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-25 20:30:29,902 epoch 9 - iter 4689/5212 - loss 0.53176607 - time (sec): 199.43 - samples/sec: 1661.49 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-25 20:30:52,350 epoch 9 - iter 5210/5212 - loss 0.52897509 - time (sec): 221.88 - samples/sec: 1655.79 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-25 20:30:52,435 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-25 20:30:52,435 EPOCH 9 done: loss 0.5289 - lr: 0.000006
203
+ 2023-10-25 20:30:58,598 DEV : loss 0.26791492104530334 - f1-score (micro avg) 0.0
204
+ 2023-10-25 20:30:58,624 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-25 20:31:20,588 epoch 10 - iter 521/5212 - loss 0.48688069 - time (sec): 21.96 - samples/sec: 1689.43 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-25 20:31:42,505 epoch 10 - iter 1042/5212 - loss 0.52394542 - time (sec): 43.88 - samples/sec: 1671.09 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-25 20:32:04,555 epoch 10 - iter 1563/5212 - loss 0.54120385 - time (sec): 65.93 - samples/sec: 1662.55 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-25 20:32:26,521 epoch 10 - iter 2084/5212 - loss 0.54119260 - time (sec): 87.90 - samples/sec: 1654.95 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-25 20:32:48,533 epoch 10 - iter 2605/5212 - loss 0.53504612 - time (sec): 109.91 - samples/sec: 1653.51 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-25 20:33:09,946 epoch 10 - iter 3126/5212 - loss 0.54141693 - time (sec): 131.32 - samples/sec: 1638.10 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-25 20:33:31,270 epoch 10 - iter 3647/5212 - loss 0.53472820 - time (sec): 152.64 - samples/sec: 1649.26 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-25 20:33:53,359 epoch 10 - iter 4168/5212 - loss 0.53331190 - time (sec): 174.73 - samples/sec: 1649.47 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-25 20:34:15,455 epoch 10 - iter 4689/5212 - loss 0.52669984 - time (sec): 196.83 - samples/sec: 1667.97 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-25 20:34:37,198 epoch 10 - iter 5210/5212 - loss 0.52741026 - time (sec): 218.57 - samples/sec: 1680.12 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-25 20:34:37,280 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-25 20:34:37,280 EPOCH 10 done: loss 0.5273 - lr: 0.000000
217
+ 2023-10-25 20:34:44,070 DEV : loss 0.26033899188041687 - f1-score (micro avg) 0.0
218
+ 2023-10-25 20:34:44,436 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-25 20:34:44,437 Loading model from best epoch ...
220
+ 2023-10-25 20:34:46,052 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
221
+ 2023-10-25 20:34:55,751
222
+ Results:
223
+ - F-score (micro) 0.3206
224
+ - F-score (macro) 0.1588
225
+ - Accuracy 0.1914
226
+
227
+ By class:
228
+ precision recall f1-score support
229
+
230
+ LOC 0.4903 0.4580 0.4736 1214
231
+ PER 0.1940 0.1126 0.1425 808
232
+ ORG 0.0588 0.0113 0.0190 353
233
+ HumanProd 0.0000 0.0000 0.0000 15
234
+
235
+ micro avg 0.3896 0.2724 0.3206 2390
236
+ macro avg 0.1858 0.1455 0.1588 2390
237
+ weighted avg 0.3233 0.2724 0.2916 2390
238
+
239
+ 2023-10-25 20:34:55,751 ----------------------------------------------------------------------------------------------------