Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
c203c44
•
1 Parent(s): b3dfa31

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 15:16:32,401 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 15:16:32,402 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 15:16:32,402 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 15:16:32,402 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 15:16:32,402 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 15:16:32,402 Train: 1100 sentences
55
+ 2023-10-23 15:16:32,402 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 15:16:32,402 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 15:16:32,402 Training Params:
58
+ 2023-10-23 15:16:32,402 - learning_rate: "3e-05"
59
+ 2023-10-23 15:16:32,402 - mini_batch_size: "8"
60
+ 2023-10-23 15:16:32,402 - max_epochs: "10"
61
+ 2023-10-23 15:16:32,402 - shuffle: "True"
62
+ 2023-10-23 15:16:32,402 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 15:16:32,402 Plugins:
64
+ 2023-10-23 15:16:32,402 - TensorboardLogger
65
+ 2023-10-23 15:16:32,402 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 15:16:32,402 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 15:16:32,402 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 15:16:32,402 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 15:16:32,402 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 15:16:32,402 Computation:
71
+ 2023-10-23 15:16:32,403 - compute on device: cuda:0
72
+ 2023-10-23 15:16:32,403 - embedding storage: none
73
+ 2023-10-23 15:16:32,403 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 15:16:32,403 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-23 15:16:32,403 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 15:16:32,403 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 15:16:32,403 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 15:16:33,137 epoch 1 - iter 13/138 - loss 3.15159757 - time (sec): 0.73 - samples/sec: 2692.78 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-23 15:16:33,852 epoch 1 - iter 26/138 - loss 2.67852230 - time (sec): 1.45 - samples/sec: 2784.94 - lr: 0.000005 - momentum: 0.000000
80
+ 2023-10-23 15:16:34,566 epoch 1 - iter 39/138 - loss 2.14776296 - time (sec): 2.16 - samples/sec: 2808.56 - lr: 0.000008 - momentum: 0.000000
81
+ 2023-10-23 15:16:35,288 epoch 1 - iter 52/138 - loss 1.83383780 - time (sec): 2.88 - samples/sec: 2863.16 - lr: 0.000011 - momentum: 0.000000
82
+ 2023-10-23 15:16:36,020 epoch 1 - iter 65/138 - loss 1.63570418 - time (sec): 3.62 - samples/sec: 2907.46 - lr: 0.000014 - momentum: 0.000000
83
+ 2023-10-23 15:16:36,734 epoch 1 - iter 78/138 - loss 1.46280230 - time (sec): 4.33 - samples/sec: 2940.51 - lr: 0.000017 - momentum: 0.000000
84
+ 2023-10-23 15:16:37,454 epoch 1 - iter 91/138 - loss 1.33109959 - time (sec): 5.05 - samples/sec: 2983.52 - lr: 0.000020 - momentum: 0.000000
85
+ 2023-10-23 15:16:38,176 epoch 1 - iter 104/138 - loss 1.20350822 - time (sec): 5.77 - samples/sec: 2999.94 - lr: 0.000022 - momentum: 0.000000
86
+ 2023-10-23 15:16:38,898 epoch 1 - iter 117/138 - loss 1.11281855 - time (sec): 6.49 - samples/sec: 2978.31 - lr: 0.000025 - momentum: 0.000000
87
+ 2023-10-23 15:16:39,638 epoch 1 - iter 130/138 - loss 1.03805511 - time (sec): 7.23 - samples/sec: 2961.58 - lr: 0.000028 - momentum: 0.000000
88
+ 2023-10-23 15:16:40,079 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 15:16:40,080 EPOCH 1 done: loss 0.9909 - lr: 0.000028
90
+ 2023-10-23 15:16:40,669 DEV : loss 0.22412429749965668 - f1-score (micro avg) 0.6792
91
+ 2023-10-23 15:16:40,676 saving best model
92
+ 2023-10-23 15:16:41,080 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 15:16:41,793 epoch 2 - iter 13/138 - loss 0.24804051 - time (sec): 0.71 - samples/sec: 2686.47 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-23 15:16:42,514 epoch 2 - iter 26/138 - loss 0.23545181 - time (sec): 1.43 - samples/sec: 2779.59 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-23 15:16:43,229 epoch 2 - iter 39/138 - loss 0.21049432 - time (sec): 2.15 - samples/sec: 2793.50 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-23 15:16:43,957 epoch 2 - iter 52/138 - loss 0.20175587 - time (sec): 2.88 - samples/sec: 2947.97 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-23 15:16:44,673 epoch 2 - iter 65/138 - loss 0.20299641 - time (sec): 3.59 - samples/sec: 2967.39 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-23 15:16:45,386 epoch 2 - iter 78/138 - loss 0.19313653 - time (sec): 4.31 - samples/sec: 2987.45 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-23 15:16:46,104 epoch 2 - iter 91/138 - loss 0.18964022 - time (sec): 5.02 - samples/sec: 3007.03 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-23 15:16:46,828 epoch 2 - iter 104/138 - loss 0.18816331 - time (sec): 5.75 - samples/sec: 3029.58 - lr: 0.000028 - momentum: 0.000000
101
+ 2023-10-23 15:16:47,543 epoch 2 - iter 117/138 - loss 0.18594547 - time (sec): 6.46 - samples/sec: 2989.39 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-23 15:16:48,277 epoch 2 - iter 130/138 - loss 0.17966663 - time (sec): 7.20 - samples/sec: 3000.49 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-23 15:16:48,712 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 15:16:48,712 EPOCH 2 done: loss 0.1812 - lr: 0.000027
105
+ 2023-10-23 15:16:49,252 DEV : loss 0.1470060795545578 - f1-score (micro avg) 0.7971
106
+ 2023-10-23 15:16:49,258 saving best model
107
+ 2023-10-23 15:16:49,808 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 15:16:50,535 epoch 3 - iter 13/138 - loss 0.10254962 - time (sec): 0.72 - samples/sec: 2872.39 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-23 15:16:51,290 epoch 3 - iter 26/138 - loss 0.08340266 - time (sec): 1.48 - samples/sec: 2954.54 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-23 15:16:52,023 epoch 3 - iter 39/138 - loss 0.08449978 - time (sec): 2.21 - samples/sec: 2969.42 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-23 15:16:52,747 epoch 3 - iter 52/138 - loss 0.10374305 - time (sec): 2.94 - samples/sec: 3076.64 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-23 15:16:53,460 epoch 3 - iter 65/138 - loss 0.11185432 - time (sec): 3.65 - samples/sec: 3036.17 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-23 15:16:54,167 epoch 3 - iter 78/138 - loss 0.10775174 - time (sec): 4.36 - samples/sec: 3045.18 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-23 15:16:54,884 epoch 3 - iter 91/138 - loss 0.10101946 - time (sec): 5.07 - samples/sec: 3024.98 - lr: 0.000025 - momentum: 0.000000
115
+ 2023-10-23 15:16:55,581 epoch 3 - iter 104/138 - loss 0.09734678 - time (sec): 5.77 - samples/sec: 3013.53 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-23 15:16:56,314 epoch 3 - iter 117/138 - loss 0.09793904 - time (sec): 6.50 - samples/sec: 3019.20 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-23 15:16:57,021 epoch 3 - iter 130/138 - loss 0.09585714 - time (sec): 7.21 - samples/sec: 2996.49 - lr: 0.000024 - momentum: 0.000000
118
+ 2023-10-23 15:16:57,474 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 15:16:57,474 EPOCH 3 done: loss 0.0957 - lr: 0.000024
120
+ 2023-10-23 15:16:58,020 DEV : loss 0.11253706365823746 - f1-score (micro avg) 0.8547
121
+ 2023-10-23 15:16:58,026 saving best model
122
+ 2023-10-23 15:16:58,568 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 15:16:59,292 epoch 4 - iter 13/138 - loss 0.06217316 - time (sec): 0.72 - samples/sec: 2519.38 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-23 15:17:00,019 epoch 4 - iter 26/138 - loss 0.06300866 - time (sec): 1.45 - samples/sec: 2692.98 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-23 15:17:00,736 epoch 4 - iter 39/138 - loss 0.07147369 - time (sec): 2.16 - samples/sec: 2729.52 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-23 15:17:01,466 epoch 4 - iter 52/138 - loss 0.06737408 - time (sec): 2.89 - samples/sec: 2796.37 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-23 15:17:02,186 epoch 4 - iter 65/138 - loss 0.06990664 - time (sec): 3.61 - samples/sec: 2842.86 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-23 15:17:02,930 epoch 4 - iter 78/138 - loss 0.07046978 - time (sec): 4.36 - samples/sec: 2904.66 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-23 15:17:03,634 epoch 4 - iter 91/138 - loss 0.06853393 - time (sec): 5.06 - samples/sec: 2914.90 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-23 15:17:04,341 epoch 4 - iter 104/138 - loss 0.06819464 - time (sec): 5.77 - samples/sec: 2898.53 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-23 15:17:05,053 epoch 4 - iter 117/138 - loss 0.06414598 - time (sec): 6.48 - samples/sec: 2921.20 - lr: 0.000021 - momentum: 0.000000
132
+ 2023-10-23 15:17:05,780 epoch 4 - iter 130/138 - loss 0.06705376 - time (sec): 7.21 - samples/sec: 2979.25 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-23 15:17:06,236 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 15:17:06,236 EPOCH 4 done: loss 0.0655 - lr: 0.000020
135
+ 2023-10-23 15:17:06,778 DEV : loss 0.13936196267604828 - f1-score (micro avg) 0.8592
136
+ 2023-10-23 15:17:06,784 saving best model
137
+ 2023-10-23 15:17:07,323 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-23 15:17:08,038 epoch 5 - iter 13/138 - loss 0.04804955 - time (sec): 0.71 - samples/sec: 2830.23 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-23 15:17:08,767 epoch 5 - iter 26/138 - loss 0.05093135 - time (sec): 1.44 - samples/sec: 2981.81 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-23 15:17:09,489 epoch 5 - iter 39/138 - loss 0.04714132 - time (sec): 2.16 - samples/sec: 2993.12 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-23 15:17:10,217 epoch 5 - iter 52/138 - loss 0.05285373 - time (sec): 2.89 - samples/sec: 2985.73 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-23 15:17:10,928 epoch 5 - iter 65/138 - loss 0.05440381 - time (sec): 3.60 - samples/sec: 3017.20 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-23 15:17:11,649 epoch 5 - iter 78/138 - loss 0.05418822 - time (sec): 4.32 - samples/sec: 2997.09 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-23 15:17:12,353 epoch 5 - iter 91/138 - loss 0.05224433 - time (sec): 5.03 - samples/sec: 2983.07 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-23 15:17:13,061 epoch 5 - iter 104/138 - loss 0.05437088 - time (sec): 5.73 - samples/sec: 2995.34 - lr: 0.000018 - momentum: 0.000000
146
+ 2023-10-23 15:17:13,764 epoch 5 - iter 117/138 - loss 0.05484615 - time (sec): 6.44 - samples/sec: 2965.19 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-23 15:17:14,489 epoch 5 - iter 130/138 - loss 0.05218539 - time (sec): 7.16 - samples/sec: 2993.41 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-23 15:17:14,936 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-23 15:17:14,936 EPOCH 5 done: loss 0.0502 - lr: 0.000017
150
+ 2023-10-23 15:17:15,471 DEV : loss 0.14914952218532562 - f1-score (micro avg) 0.8753
151
+ 2023-10-23 15:17:15,477 saving best model
152
+ 2023-10-23 15:17:16,007 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-23 15:17:16,753 epoch 6 - iter 13/138 - loss 0.05269582 - time (sec): 0.74 - samples/sec: 2751.04 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-23 15:17:17,463 epoch 6 - iter 26/138 - loss 0.03792950 - time (sec): 1.45 - samples/sec: 2825.37 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-23 15:17:18,194 epoch 6 - iter 39/138 - loss 0.04085549 - time (sec): 2.19 - samples/sec: 2857.81 - lr: 0.000016 - momentum: 0.000000
156
+ 2023-10-23 15:17:18,947 epoch 6 - iter 52/138 - loss 0.04828210 - time (sec): 2.94 - samples/sec: 2941.90 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-23 15:17:19,696 epoch 6 - iter 65/138 - loss 0.04326092 - time (sec): 3.69 - samples/sec: 2937.00 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-23 15:17:20,475 epoch 6 - iter 78/138 - loss 0.03745468 - time (sec): 4.47 - samples/sec: 2967.33 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-23 15:17:21,221 epoch 6 - iter 91/138 - loss 0.03999567 - time (sec): 5.21 - samples/sec: 2925.48 - lr: 0.000015 - momentum: 0.000000
160
+ 2023-10-23 15:17:21,946 epoch 6 - iter 104/138 - loss 0.04285950 - time (sec): 5.94 - samples/sec: 2920.50 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-23 15:17:22,708 epoch 6 - iter 117/138 - loss 0.04247360 - time (sec): 6.70 - samples/sec: 2913.04 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-23 15:17:23,455 epoch 6 - iter 130/138 - loss 0.03914589 - time (sec): 7.45 - samples/sec: 2885.35 - lr: 0.000014 - momentum: 0.000000
163
+ 2023-10-23 15:17:23,885 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-23 15:17:23,885 EPOCH 6 done: loss 0.0385 - lr: 0.000014
165
+ 2023-10-23 15:17:24,421 DEV : loss 0.1594824641942978 - f1-score (micro avg) 0.8738
166
+ 2023-10-23 15:17:24,427 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-23 15:17:25,168 epoch 7 - iter 13/138 - loss 0.02623740 - time (sec): 0.74 - samples/sec: 3269.55 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-23 15:17:25,877 epoch 7 - iter 26/138 - loss 0.04124979 - time (sec): 1.45 - samples/sec: 3085.37 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-23 15:17:26,585 epoch 7 - iter 39/138 - loss 0.03804665 - time (sec): 2.16 - samples/sec: 2902.57 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-23 15:17:27,303 epoch 7 - iter 52/138 - loss 0.03995093 - time (sec): 2.87 - samples/sec: 2976.43 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-23 15:17:28,015 epoch 7 - iter 65/138 - loss 0.04712794 - time (sec): 3.59 - samples/sec: 2961.99 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-23 15:17:28,733 epoch 7 - iter 78/138 - loss 0.04381189 - time (sec): 4.30 - samples/sec: 2982.05 - lr: 0.000012 - momentum: 0.000000
173
+ 2023-10-23 15:17:29,453 epoch 7 - iter 91/138 - loss 0.03775627 - time (sec): 5.02 - samples/sec: 2978.04 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-23 15:17:30,158 epoch 7 - iter 104/138 - loss 0.03752184 - time (sec): 5.73 - samples/sec: 2987.02 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-23 15:17:30,883 epoch 7 - iter 117/138 - loss 0.03570110 - time (sec): 6.45 - samples/sec: 2985.97 - lr: 0.000011 - momentum: 0.000000
176
+ 2023-10-23 15:17:31,596 epoch 7 - iter 130/138 - loss 0.03405070 - time (sec): 7.17 - samples/sec: 2986.70 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-23 15:17:32,045 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-23 15:17:32,045 EPOCH 7 done: loss 0.0325 - lr: 0.000010
179
+ 2023-10-23 15:17:32,580 DEV : loss 0.16084513068199158 - f1-score (micro avg) 0.8675
180
+ 2023-10-23 15:17:32,586 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-23 15:17:33,312 epoch 8 - iter 13/138 - loss 0.01655083 - time (sec): 0.72 - samples/sec: 2704.01 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-23 15:17:34,042 epoch 8 - iter 26/138 - loss 0.01496619 - time (sec): 1.46 - samples/sec: 2798.56 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-23 15:17:34,768 epoch 8 - iter 39/138 - loss 0.01279914 - time (sec): 2.18 - samples/sec: 2893.30 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-23 15:17:35,477 epoch 8 - iter 52/138 - loss 0.01008931 - time (sec): 2.89 - samples/sec: 2851.61 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-23 15:17:36,190 epoch 8 - iter 65/138 - loss 0.01497003 - time (sec): 3.60 - samples/sec: 2874.20 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-23 15:17:36,934 epoch 8 - iter 78/138 - loss 0.01761736 - time (sec): 4.35 - samples/sec: 2890.33 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-23 15:17:37,641 epoch 8 - iter 91/138 - loss 0.01899735 - time (sec): 5.05 - samples/sec: 2897.82 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-23 15:17:38,366 epoch 8 - iter 104/138 - loss 0.02359081 - time (sec): 5.78 - samples/sec: 2924.38 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-23 15:17:39,091 epoch 8 - iter 117/138 - loss 0.02409698 - time (sec): 6.50 - samples/sec: 2926.25 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-23 15:17:39,834 epoch 8 - iter 130/138 - loss 0.02490566 - time (sec): 7.25 - samples/sec: 2972.13 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-23 15:17:40,272 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-23 15:17:40,273 EPOCH 8 done: loss 0.0236 - lr: 0.000007
193
+ 2023-10-23 15:17:40,811 DEV : loss 0.16172528266906738 - f1-score (micro avg) 0.8667
194
+ 2023-10-23 15:17:40,817 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-23 15:17:41,528 epoch 9 - iter 13/138 - loss 0.03973560 - time (sec): 0.71 - samples/sec: 2844.60 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-23 15:17:42,282 epoch 9 - iter 26/138 - loss 0.03323065 - time (sec): 1.46 - samples/sec: 3021.85 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-23 15:17:43,017 epoch 9 - iter 39/138 - loss 0.02535528 - time (sec): 2.20 - samples/sec: 3054.90 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-23 15:17:43,739 epoch 9 - iter 52/138 - loss 0.02347053 - time (sec): 2.92 - samples/sec: 3017.28 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-23 15:17:44,455 epoch 9 - iter 65/138 - loss 0.02281061 - time (sec): 3.64 - samples/sec: 3031.58 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-23 15:17:45,173 epoch 9 - iter 78/138 - loss 0.01958166 - time (sec): 4.35 - samples/sec: 2967.46 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-23 15:17:45,885 epoch 9 - iter 91/138 - loss 0.01809992 - time (sec): 5.07 - samples/sec: 2975.33 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-23 15:17:46,621 epoch 9 - iter 104/138 - loss 0.01706841 - time (sec): 5.80 - samples/sec: 2976.16 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-23 15:17:47,348 epoch 9 - iter 117/138 - loss 0.01708119 - time (sec): 6.53 - samples/sec: 2962.05 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-23 15:17:48,078 epoch 9 - iter 130/138 - loss 0.01655074 - time (sec): 7.26 - samples/sec: 2981.61 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-23 15:17:48,532 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-23 15:17:48,532 EPOCH 9 done: loss 0.0180 - lr: 0.000004
207
+ 2023-10-23 15:17:49,069 DEV : loss 0.16817787289619446 - f1-score (micro avg) 0.8691
208
+ 2023-10-23 15:17:49,075 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-23 15:17:49,834 epoch 10 - iter 13/138 - loss 0.00406144 - time (sec): 0.76 - samples/sec: 2881.69 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-23 15:17:50,565 epoch 10 - iter 26/138 - loss 0.00650983 - time (sec): 1.49 - samples/sec: 2847.69 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-23 15:17:51,310 epoch 10 - iter 39/138 - loss 0.00724709 - time (sec): 2.23 - samples/sec: 2781.17 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-23 15:17:52,044 epoch 10 - iter 52/138 - loss 0.00703865 - time (sec): 2.97 - samples/sec: 2785.27 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-23 15:17:52,756 epoch 10 - iter 65/138 - loss 0.00744279 - time (sec): 3.68 - samples/sec: 2798.43 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-23 15:17:53,482 epoch 10 - iter 78/138 - loss 0.00654534 - time (sec): 4.41 - samples/sec: 2809.67 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-23 15:17:54,188 epoch 10 - iter 91/138 - loss 0.00764440 - time (sec): 5.11 - samples/sec: 2893.26 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-23 15:17:54,928 epoch 10 - iter 104/138 - loss 0.00702711 - time (sec): 5.85 - samples/sec: 2846.16 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-23 15:17:55,643 epoch 10 - iter 117/138 - loss 0.00776517 - time (sec): 6.57 - samples/sec: 2876.84 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 15:17:56,348 epoch 10 - iter 130/138 - loss 0.01220343 - time (sec): 7.27 - samples/sec: 2929.84 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-23 15:17:56,783 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-23 15:17:56,783 EPOCH 10 done: loss 0.0129 - lr: 0.000000
221
+ 2023-10-23 15:17:57,332 DEV : loss 0.16879194974899292 - f1-score (micro avg) 0.8764
222
+ 2023-10-23 15:17:57,338 saving best model
223
+ 2023-10-23 15:17:58,296 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-23 15:17:58,297 Loading model from best epoch ...
225
+ 2023-10-23 15:18:00,117 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 15:18:00,793
227
+ Results:
228
+ - F-score (micro) 0.9009
229
+ - F-score (macro) 0.7686
230
+ - Accuracy 0.8297
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ scope 0.8977 0.8977 0.8977 176
236
+ pers 0.9918 0.9453 0.9680 128
237
+ work 0.8108 0.8108 0.8108 74
238
+ object 0.5000 0.5000 0.5000 2
239
+ loc 1.0000 0.5000 0.6667 2
240
+
241
+ micro avg 0.9093 0.8927 0.9009 382
242
+ macro avg 0.8401 0.7308 0.7686 382
243
+ weighted avg 0.9109 0.8927 0.9011 382
244
+
245
+ 2023-10-23 15:18:00,793 ----------------------------------------------------------------------------------------------------