Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs8-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
988531e
•
1 Parent(s): 4bb02bc

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 15:45:20,702 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 15:45:20,703 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=25, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-23 15:45:20,703 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 15:45:20,703 MultiCorpus: 1100 train + 206 dev + 240 test sentences
52
+ - NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
53
+ 2023-10-23 15:45:20,703 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 15:45:20,703 Train: 1100 sentences
55
+ 2023-10-23 15:45:20,703 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 15:45:20,704 Training Params:
58
+ 2023-10-23 15:45:20,704 - learning_rate: "3e-05"
59
+ 2023-10-23 15:45:20,704 - mini_batch_size: "8"
60
+ 2023-10-23 15:45:20,704 - max_epochs: "10"
61
+ 2023-10-23 15:45:20,704 - shuffle: "True"
62
+ 2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 15:45:20,704 Plugins:
64
+ 2023-10-23 15:45:20,704 - TensorboardLogger
65
+ 2023-10-23 15:45:20,704 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 15:45:20,704 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 15:45:20,704 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 15:45:20,704 Computation:
71
+ 2023-10-23 15:45:20,704 - compute on device: cuda:0
72
+ 2023-10-23 15:45:20,704 - embedding storage: none
73
+ 2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 15:45:20,704 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 15:45:20,704 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 15:45:20,704 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 15:45:21,458 epoch 1 - iter 13/138 - loss 3.19724143 - time (sec): 0.75 - samples/sec: 2797.24 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-23 15:45:22,219 epoch 1 - iter 26/138 - loss 2.76719642 - time (sec): 1.51 - samples/sec: 2812.76 - lr: 0.000005 - momentum: 0.000000
80
+ 2023-10-23 15:45:22,939 epoch 1 - iter 39/138 - loss 2.27990881 - time (sec): 2.23 - samples/sec: 2769.62 - lr: 0.000008 - momentum: 0.000000
81
+ 2023-10-23 15:45:23,707 epoch 1 - iter 52/138 - loss 1.87919582 - time (sec): 3.00 - samples/sec: 2883.32 - lr: 0.000011 - momentum: 0.000000
82
+ 2023-10-23 15:45:24,444 epoch 1 - iter 65/138 - loss 1.68296880 - time (sec): 3.74 - samples/sec: 2837.09 - lr: 0.000014 - momentum: 0.000000
83
+ 2023-10-23 15:45:25,198 epoch 1 - iter 78/138 - loss 1.47784903 - time (sec): 4.49 - samples/sec: 2858.47 - lr: 0.000017 - momentum: 0.000000
84
+ 2023-10-23 15:45:25,974 epoch 1 - iter 91/138 - loss 1.33890195 - time (sec): 5.27 - samples/sec: 2799.70 - lr: 0.000020 - momentum: 0.000000
85
+ 2023-10-23 15:45:26,758 epoch 1 - iter 104/138 - loss 1.19646330 - time (sec): 6.05 - samples/sec: 2862.84 - lr: 0.000022 - momentum: 0.000000
86
+ 2023-10-23 15:45:27,491 epoch 1 - iter 117/138 - loss 1.09649998 - time (sec): 6.79 - samples/sec: 2869.11 - lr: 0.000025 - momentum: 0.000000
87
+ 2023-10-23 15:45:28,210 epoch 1 - iter 130/138 - loss 1.02207775 - time (sec): 7.50 - samples/sec: 2888.81 - lr: 0.000028 - momentum: 0.000000
88
+ 2023-10-23 15:45:28,673 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 15:45:28,673 EPOCH 1 done: loss 0.9842 - lr: 0.000028
90
+ 2023-10-23 15:45:29,262 DEV : loss 0.2637031376361847 - f1-score (micro avg) 0.6608
91
+ 2023-10-23 15:45:29,268 saving best model
92
+ 2023-10-23 15:45:29,668 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 15:45:30,399 epoch 2 - iter 13/138 - loss 0.28211232 - time (sec): 0.73 - samples/sec: 2905.37 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-23 15:45:31,138 epoch 2 - iter 26/138 - loss 0.23645117 - time (sec): 1.47 - samples/sec: 3020.01 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-23 15:45:31,865 epoch 2 - iter 39/138 - loss 0.22703358 - time (sec): 2.20 - samples/sec: 3079.58 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-23 15:45:32,595 epoch 2 - iter 52/138 - loss 0.20824501 - time (sec): 2.93 - samples/sec: 3097.73 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-23 15:45:33,325 epoch 2 - iter 65/138 - loss 0.20724269 - time (sec): 3.66 - samples/sec: 3049.60 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-23 15:45:34,054 epoch 2 - iter 78/138 - loss 0.19916937 - time (sec): 4.38 - samples/sec: 3051.76 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-23 15:45:34,793 epoch 2 - iter 91/138 - loss 0.19649440 - time (sec): 5.12 - samples/sec: 3032.09 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-23 15:45:35,531 epoch 2 - iter 104/138 - loss 0.19268046 - time (sec): 5.86 - samples/sec: 3006.97 - lr: 0.000028 - momentum: 0.000000
101
+ 2023-10-23 15:45:36,270 epoch 2 - iter 117/138 - loss 0.18827503 - time (sec): 6.60 - samples/sec: 2961.56 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-23 15:45:36,989 epoch 2 - iter 130/138 - loss 0.18348349 - time (sec): 7.32 - samples/sec: 2951.24 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-23 15:45:37,429 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 15:45:37,429 EPOCH 2 done: loss 0.1787 - lr: 0.000027
105
+ 2023-10-23 15:45:37,959 DEV : loss 0.11417855322360992 - f1-score (micro avg) 0.8383
106
+ 2023-10-23 15:45:37,965 saving best model
107
+ 2023-10-23 15:45:38,486 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 15:45:39,203 epoch 3 - iter 13/138 - loss 0.10319665 - time (sec): 0.72 - samples/sec: 2882.11 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-23 15:45:39,918 epoch 3 - iter 26/138 - loss 0.12345856 - time (sec): 1.43 - samples/sec: 2842.55 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-23 15:45:40,633 epoch 3 - iter 39/138 - loss 0.10479944 - time (sec): 2.15 - samples/sec: 2931.77 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-23 15:45:41,366 epoch 3 - iter 52/138 - loss 0.09914611 - time (sec): 2.88 - samples/sec: 2899.42 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-23 15:45:42,091 epoch 3 - iter 65/138 - loss 0.09899777 - time (sec): 3.60 - samples/sec: 2853.25 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-23 15:45:42,825 epoch 3 - iter 78/138 - loss 0.09442590 - time (sec): 4.34 - samples/sec: 2890.44 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-23 15:45:43,552 epoch 3 - iter 91/138 - loss 0.09932234 - time (sec): 5.06 - samples/sec: 2903.82 - lr: 0.000025 - momentum: 0.000000
115
+ 2023-10-23 15:45:44,285 epoch 3 - iter 104/138 - loss 0.09677320 - time (sec): 5.80 - samples/sec: 2914.91 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-23 15:45:45,028 epoch 3 - iter 117/138 - loss 0.09735892 - time (sec): 6.54 - samples/sec: 2929.20 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-23 15:45:45,787 epoch 3 - iter 130/138 - loss 0.09842761 - time (sec): 7.30 - samples/sec: 2957.18 - lr: 0.000024 - momentum: 0.000000
118
+ 2023-10-23 15:45:46,248 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 15:45:46,248 EPOCH 3 done: loss 0.0976 - lr: 0.000024
120
+ 2023-10-23 15:45:46,785 DEV : loss 0.11052478104829788 - f1-score (micro avg) 0.8561
121
+ 2023-10-23 15:45:46,791 saving best model
122
+ 2023-10-23 15:45:47,338 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 15:45:48,055 epoch 4 - iter 13/138 - loss 0.05429172 - time (sec): 0.72 - samples/sec: 3108.04 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-23 15:45:48,769 epoch 4 - iter 26/138 - loss 0.06880590 - time (sec): 1.43 - samples/sec: 2926.31 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-23 15:45:49,509 epoch 4 - iter 39/138 - loss 0.06536197 - time (sec): 2.17 - samples/sec: 2878.70 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-23 15:45:50,329 epoch 4 - iter 52/138 - loss 0.06633934 - time (sec): 2.99 - samples/sec: 2785.88 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-23 15:45:51,093 epoch 4 - iter 65/138 - loss 0.05923637 - time (sec): 3.75 - samples/sec: 2732.95 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-23 15:45:51,893 epoch 4 - iter 78/138 - loss 0.06130330 - time (sec): 4.55 - samples/sec: 2740.28 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-23 15:45:52,664 epoch 4 - iter 91/138 - loss 0.06339566 - time (sec): 5.32 - samples/sec: 2772.24 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-23 15:45:53,410 epoch 4 - iter 104/138 - loss 0.06287406 - time (sec): 6.07 - samples/sec: 2804.47 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-23 15:45:54,195 epoch 4 - iter 117/138 - loss 0.06738814 - time (sec): 6.86 - samples/sec: 2815.45 - lr: 0.000021 - momentum: 0.000000
132
+ 2023-10-23 15:45:54,976 epoch 4 - iter 130/138 - loss 0.06977085 - time (sec): 7.64 - samples/sec: 2801.72 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-23 15:45:55,461 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 15:45:55,462 EPOCH 4 done: loss 0.0682 - lr: 0.000020
135
+ 2023-10-23 15:45:56,002 DEV : loss 0.12191484868526459 - f1-score (micro avg) 0.8525
136
+ 2023-10-23 15:45:56,008 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-23 15:45:56,772 epoch 5 - iter 13/138 - loss 0.05204482 - time (sec): 0.76 - samples/sec: 2725.06 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-23 15:45:57,535 epoch 5 - iter 26/138 - loss 0.04270482 - time (sec): 1.53 - samples/sec: 2765.10 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-23 15:45:58,316 epoch 5 - iter 39/138 - loss 0.05189148 - time (sec): 2.31 - samples/sec: 2775.05 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-23 15:45:59,077 epoch 5 - iter 52/138 - loss 0.05066165 - time (sec): 3.07 - samples/sec: 2810.13 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-23 15:45:59,823 epoch 5 - iter 65/138 - loss 0.04849827 - time (sec): 3.81 - samples/sec: 2810.73 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-23 15:46:00,558 epoch 5 - iter 78/138 - loss 0.05075800 - time (sec): 4.55 - samples/sec: 2872.86 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-23 15:46:01,281 epoch 5 - iter 91/138 - loss 0.05255442 - time (sec): 5.27 - samples/sec: 2855.43 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-23 15:46:02,021 epoch 5 - iter 104/138 - loss 0.05109410 - time (sec): 6.01 - samples/sec: 2826.82 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-23 15:46:02,759 epoch 5 - iter 117/138 - loss 0.05205831 - time (sec): 6.75 - samples/sec: 2876.34 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-23 15:46:03,501 epoch 5 - iter 130/138 - loss 0.05049339 - time (sec): 7.49 - samples/sec: 2884.60 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-23 15:46:03,952 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-23 15:46:03,952 EPOCH 5 done: loss 0.0485 - lr: 0.000017
149
+ 2023-10-23 15:46:04,497 DEV : loss 0.13699379563331604 - f1-score (micro avg) 0.8779
150
+ 2023-10-23 15:46:04,503 saving best model
151
+ 2023-10-23 15:46:05,045 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-23 15:46:05,792 epoch 6 - iter 13/138 - loss 0.02970998 - time (sec): 0.74 - samples/sec: 2833.02 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-23 15:46:06,563 epoch 6 - iter 26/138 - loss 0.04688615 - time (sec): 1.51 - samples/sec: 2901.61 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-23 15:46:07,321 epoch 6 - iter 39/138 - loss 0.04223240 - time (sec): 2.27 - samples/sec: 2860.93 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-23 15:46:08,072 epoch 6 - iter 52/138 - loss 0.03535856 - time (sec): 3.02 - samples/sec: 2838.96 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-23 15:46:08,804 epoch 6 - iter 65/138 - loss 0.03293734 - time (sec): 3.75 - samples/sec: 2851.14 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-23 15:46:09,564 epoch 6 - iter 78/138 - loss 0.03132917 - time (sec): 4.51 - samples/sec: 2937.99 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-23 15:46:10,329 epoch 6 - iter 91/138 - loss 0.03035412 - time (sec): 5.28 - samples/sec: 2925.95 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-23 15:46:11,059 epoch 6 - iter 104/138 - loss 0.03635085 - time (sec): 6.01 - samples/sec: 2897.63 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-23 15:46:11,799 epoch 6 - iter 117/138 - loss 0.03792811 - time (sec): 6.75 - samples/sec: 2906.81 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-23 15:46:12,534 epoch 6 - iter 130/138 - loss 0.03734866 - time (sec): 7.48 - samples/sec: 2868.22 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-23 15:46:12,987 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-23 15:46:12,988 EPOCH 6 done: loss 0.0372 - lr: 0.000014
164
+ 2023-10-23 15:46:13,519 DEV : loss 0.139994814991951 - f1-score (micro avg) 0.8785
165
+ 2023-10-23 15:46:13,524 saving best model
166
+ 2023-10-23 15:46:14,054 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-23 15:46:14,817 epoch 7 - iter 13/138 - loss 0.00842643 - time (sec): 0.76 - samples/sec: 2797.23 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-23 15:46:15,575 epoch 7 - iter 26/138 - loss 0.01783786 - time (sec): 1.52 - samples/sec: 2846.49 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-23 15:46:16,341 epoch 7 - iter 39/138 - loss 0.04117613 - time (sec): 2.28 - samples/sec: 2841.39 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-23 15:46:17,120 epoch 7 - iter 52/138 - loss 0.03560924 - time (sec): 3.06 - samples/sec: 2927.84 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-23 15:46:17,877 epoch 7 - iter 65/138 - loss 0.03352044 - time (sec): 3.82 - samples/sec: 2870.05 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-23 15:46:18,622 epoch 7 - iter 78/138 - loss 0.03277726 - time (sec): 4.56 - samples/sec: 2886.77 - lr: 0.000012 - momentum: 0.000000
173
+ 2023-10-23 15:46:19,352 epoch 7 - iter 91/138 - loss 0.03439841 - time (sec): 5.29 - samples/sec: 2866.31 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-23 15:46:20,108 epoch 7 - iter 104/138 - loss 0.03154978 - time (sec): 6.05 - samples/sec: 2891.32 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-23 15:46:20,868 epoch 7 - iter 117/138 - loss 0.03023976 - time (sec): 6.81 - samples/sec: 2891.55 - lr: 0.000011 - momentum: 0.000000
176
+ 2023-10-23 15:46:21,610 epoch 7 - iter 130/138 - loss 0.02991660 - time (sec): 7.55 - samples/sec: 2868.59 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-23 15:46:22,079 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-23 15:46:22,079 EPOCH 7 done: loss 0.0299 - lr: 0.000010
179
+ 2023-10-23 15:46:22,617 DEV : loss 0.14777213335037231 - f1-score (micro avg) 0.897
180
+ 2023-10-23 15:46:22,623 saving best model
181
+ 2023-10-23 15:46:23,152 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-23 15:46:23,905 epoch 8 - iter 13/138 - loss 0.00644670 - time (sec): 0.75 - samples/sec: 2716.21 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-23 15:46:24,659 epoch 8 - iter 26/138 - loss 0.01964341 - time (sec): 1.50 - samples/sec: 2951.47 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-23 15:46:25,389 epoch 8 - iter 39/138 - loss 0.01628448 - time (sec): 2.23 - samples/sec: 2947.00 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-23 15:46:26,144 epoch 8 - iter 52/138 - loss 0.02420344 - time (sec): 2.99 - samples/sec: 2926.35 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-23 15:46:26,896 epoch 8 - iter 65/138 - loss 0.02319288 - time (sec): 3.74 - samples/sec: 2863.46 - lr: 0.000009 - momentum: 0.000000
187
+ 2023-10-23 15:46:27,676 epoch 8 - iter 78/138 - loss 0.02179369 - time (sec): 4.52 - samples/sec: 2866.48 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-23 15:46:28,411 epoch 8 - iter 91/138 - loss 0.02597878 - time (sec): 5.26 - samples/sec: 2886.46 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-23 15:46:29,155 epoch 8 - iter 104/138 - loss 0.02487449 - time (sec): 6.00 - samples/sec: 2852.95 - lr: 0.000008 - momentum: 0.000000
190
+ 2023-10-23 15:46:29,879 epoch 8 - iter 117/138 - loss 0.02372089 - time (sec): 6.72 - samples/sec: 2861.21 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-23 15:46:30,603 epoch 8 - iter 130/138 - loss 0.02257563 - time (sec): 7.45 - samples/sec: 2886.61 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-23 15:46:31,039 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-23 15:46:31,039 EPOCH 8 done: loss 0.0222 - lr: 0.000007
194
+ 2023-10-23 15:46:31,571 DEV : loss 0.15574227273464203 - f1-score (micro avg) 0.8838
195
+ 2023-10-23 15:46:31,577 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-23 15:46:32,300 epoch 9 - iter 13/138 - loss 0.00660491 - time (sec): 0.72 - samples/sec: 2887.41 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-23 15:46:33,022 epoch 9 - iter 26/138 - loss 0.01041455 - time (sec): 1.44 - samples/sec: 2851.88 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-23 15:46:33,740 epoch 9 - iter 39/138 - loss 0.01005111 - time (sec): 2.16 - samples/sec: 2913.14 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-23 15:46:34,486 epoch 9 - iter 52/138 - loss 0.01334769 - time (sec): 2.91 - samples/sec: 2895.30 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-23 15:46:35,204 epoch 9 - iter 65/138 - loss 0.01186627 - time (sec): 3.63 - samples/sec: 2936.89 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-23 15:46:35,960 epoch 9 - iter 78/138 - loss 0.01168564 - time (sec): 4.38 - samples/sec: 2939.27 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-23 15:46:36,703 epoch 9 - iter 91/138 - loss 0.01330314 - time (sec): 5.13 - samples/sec: 2952.30 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-23 15:46:37,441 epoch 9 - iter 104/138 - loss 0.01202213 - time (sec): 5.86 - samples/sec: 2950.18 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-23 15:46:38,187 epoch 9 - iter 117/138 - loss 0.01286806 - time (sec): 6.61 - samples/sec: 2935.01 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-23 15:46:38,919 epoch 9 - iter 130/138 - loss 0.01425818 - time (sec): 7.34 - samples/sec: 2935.17 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-23 15:46:39,337 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-23 15:46:39,337 EPOCH 9 done: loss 0.0178 - lr: 0.000004
208
+ 2023-10-23 15:46:39,872 DEV : loss 0.16283106803894043 - f1-score (micro avg) 0.8916
209
+ 2023-10-23 15:46:39,877 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-23 15:46:40,602 epoch 10 - iter 13/138 - loss 0.00433738 - time (sec): 0.72 - samples/sec: 2968.37 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-23 15:46:41,333 epoch 10 - iter 26/138 - loss 0.00331970 - time (sec): 1.45 - samples/sec: 2916.40 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-23 15:46:42,080 epoch 10 - iter 39/138 - loss 0.00840588 - time (sec): 2.20 - samples/sec: 3008.39 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-23 15:46:42,816 epoch 10 - iter 52/138 - loss 0.00903499 - time (sec): 2.94 - samples/sec: 2948.34 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-23 15:46:43,536 epoch 10 - iter 65/138 - loss 0.01232935 - time (sec): 3.66 - samples/sec: 2906.92 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-23 15:46:44,266 epoch 10 - iter 78/138 - loss 0.01223517 - time (sec): 4.39 - samples/sec: 2933.48 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-23 15:46:44,999 epoch 10 - iter 91/138 - loss 0.01251053 - time (sec): 5.12 - samples/sec: 2922.86 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-23 15:46:45,750 epoch 10 - iter 104/138 - loss 0.01268933 - time (sec): 5.87 - samples/sec: 2919.33 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 15:46:46,455 epoch 10 - iter 117/138 - loss 0.01157601 - time (sec): 6.58 - samples/sec: 2928.72 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 15:46:47,182 epoch 10 - iter 130/138 - loss 0.01176484 - time (sec): 7.30 - samples/sec: 2944.52 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-23 15:46:47,618 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-23 15:46:47,619 EPOCH 10 done: loss 0.0140 - lr: 0.000000
222
+ 2023-10-23 15:46:48,151 DEV : loss 0.16455598175525665 - f1-score (micro avg) 0.8926
223
+ 2023-10-23 15:46:48,549 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-23 15:46:48,550 Loading model from best epoch ...
225
+ 2023-10-23 15:46:50,228 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
226
+ 2023-10-23 15:46:50,881
227
+ Results:
228
+ - F-score (micro) 0.9084
229
+ - F-score (macro) 0.8767
230
+ - Accuracy 0.8382
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ scope 0.8771 0.8920 0.8845 176
236
+ pers 0.9542 0.9766 0.9653 128
237
+ work 0.8986 0.8378 0.8671 74
238
+ object 1.0000 1.0000 1.0000 2
239
+ loc 1.0000 0.5000 0.6667 2
240
+
241
+ micro avg 0.9084 0.9084 0.9084 382
242
+ macro avg 0.9460 0.8413 0.8767 382
243
+ weighted avg 0.9084 0.9084 0.9077 382
244
+
245
+ 2023-10-23 15:46:50,881 ----------------------------------------------------------------------------------------------------