Hugging Face's logo

hmbert-64k
/
flair-hipe-2022-ajmc-en

Token Classification
Flair
PyTorch
TensorBoard
English
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
624de1e
•
1 Parent(s): 39aaf42

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +248 -0
training.log ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 18:41:45,091 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 18:41:45,092 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 18:41:45,092 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 18:41:45,092 MultiCorpus: 1214 train + 266 dev + 251 test sentences
52
+ - NER_HIPE_2022 Corpus: 1214 train + 266 dev + 251 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/en/with_doc_seperator
53
+ 2023-10-23 18:41:45,092 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 18:41:45,093 Train: 1214 sentences
55
+ 2023-10-23 18:41:45,093 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 18:41:45,093 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 18:41:45,093 Training Params:
58
+ 2023-10-23 18:41:45,093 - learning_rate: "3e-05"
59
+ 2023-10-23 18:41:45,093 - mini_batch_size: "4"
60
+ 2023-10-23 18:41:45,093 - max_epochs: "10"
61
+ 2023-10-23 18:41:45,093 - shuffle: "True"
62
+ 2023-10-23 18:41:45,093 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 18:41:45,093 Plugins:
64
+ 2023-10-23 18:41:45,093 - TensorboardLogger
65
+ 2023-10-23 18:41:45,093 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 18:41:45,093 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 18:41:45,093 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 18:41:45,093 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 18:41:45,093 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 18:41:45,093 Computation:
71
+ 2023-10-23 18:41:45,093 - compute on device: cuda:0
72
+ 2023-10-23 18:41:45,093 - embedding storage: none
73
+ 2023-10-23 18:41:45,093 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 18:41:45,093 Model training base path: "hmbench-ajmc/en-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-23 18:41:45,093 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 18:41:45,093 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 18:41:45,093 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 18:41:46,953 epoch 1 - iter 30/304 - loss 3.15357505 - time (sec): 1.86 - samples/sec: 1851.87 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-23 18:41:48,302 epoch 1 - iter 60/304 - loss 2.36000192 - time (sec): 3.21 - samples/sec: 2046.32 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-23 18:41:49,812 epoch 1 - iter 90/304 - loss 1.83211545 - time (sec): 4.72 - samples/sec: 2037.14 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-23 18:41:51,437 epoch 1 - iter 120/304 - loss 1.54637991 - time (sec): 6.34 - samples/sec: 1977.90 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-23 18:41:53,048 epoch 1 - iter 150/304 - loss 1.33358728 - time (sec): 7.95 - samples/sec: 1952.51 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-23 18:41:54,706 epoch 1 - iter 180/304 - loss 1.16893708 - time (sec): 9.61 - samples/sec: 1953.49 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-23 18:41:56,248 epoch 1 - iter 210/304 - loss 1.03890310 - time (sec): 11.15 - samples/sec: 1956.96 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-23 18:41:57,863 epoch 1 - iter 240/304 - loss 0.93849684 - time (sec): 12.77 - samples/sec: 1932.04 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-23 18:41:59,478 epoch 1 - iter 270/304 - loss 0.85855528 - time (sec): 14.38 - samples/sec: 1930.24 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-23 18:42:01,088 epoch 1 - iter 300/304 - loss 0.78745823 - time (sec): 15.99 - samples/sec: 1922.00 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-23 18:42:01,301 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 18:42:01,302 EPOCH 1 done: loss 0.7825 - lr: 0.000030
90
+ 2023-10-23 18:42:02,163 DEV : loss 0.17122632265090942 - f1-score (micro avg) 0.6378
91
+ 2023-10-23 18:42:02,172 saving best model
92
+ 2023-10-23 18:42:02,639 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 18:42:04,241 epoch 2 - iter 30/304 - loss 0.16461256 - time (sec): 1.60 - samples/sec: 1871.36 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-23 18:42:05,853 epoch 2 - iter 60/304 - loss 0.17202265 - time (sec): 3.21 - samples/sec: 1820.19 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-23 18:42:07,476 epoch 2 - iter 90/304 - loss 0.17172785 - time (sec): 4.84 - samples/sec: 1853.53 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-23 18:42:09,098 epoch 2 - iter 120/304 - loss 0.16591034 - time (sec): 6.46 - samples/sec: 1862.68 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-23 18:42:10,710 epoch 2 - iter 150/304 - loss 0.15967805 - time (sec): 8.07 - samples/sec: 1865.46 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-23 18:42:12,327 epoch 2 - iter 180/304 - loss 0.15117997 - time (sec): 9.69 - samples/sec: 1858.06 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-23 18:42:13,929 epoch 2 - iter 210/304 - loss 0.14443417 - time (sec): 11.29 - samples/sec: 1860.92 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-23 18:42:15,553 epoch 2 - iter 240/304 - loss 0.13660870 - time (sec): 12.91 - samples/sec: 1883.04 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-23 18:42:17,168 epoch 2 - iter 270/304 - loss 0.13344760 - time (sec): 14.53 - samples/sec: 1887.78 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-23 18:42:18,759 epoch 2 - iter 300/304 - loss 0.13430576 - time (sec): 16.12 - samples/sec: 1898.61 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-23 18:42:18,970 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 18:42:18,970 EPOCH 2 done: loss 0.1338 - lr: 0.000027
105
+ 2023-10-23 18:42:19,867 DEV : loss 0.12917864322662354 - f1-score (micro avg) 0.7897
106
+ 2023-10-23 18:42:19,875 saving best model
107
+ 2023-10-23 18:42:20,494 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 18:42:22,100 epoch 3 - iter 30/304 - loss 0.07447068 - time (sec): 1.60 - samples/sec: 2014.00 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-23 18:42:23,712 epoch 3 - iter 60/304 - loss 0.07214026 - time (sec): 3.22 - samples/sec: 1879.74 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-23 18:42:25,316 epoch 3 - iter 90/304 - loss 0.06916445 - time (sec): 4.82 - samples/sec: 1857.51 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-23 18:42:26,920 epoch 3 - iter 120/304 - loss 0.07514555 - time (sec): 6.42 - samples/sec: 1824.16 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-23 18:42:28,527 epoch 3 - iter 150/304 - loss 0.07376503 - time (sec): 8.03 - samples/sec: 1860.71 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-23 18:42:30,115 epoch 3 - iter 180/304 - loss 0.07485776 - time (sec): 9.62 - samples/sec: 1863.75 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-23 18:42:31,658 epoch 3 - iter 210/304 - loss 0.08140956 - time (sec): 11.16 - samples/sec: 1895.56 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-23 18:42:33,254 epoch 3 - iter 240/304 - loss 0.08170940 - time (sec): 12.76 - samples/sec: 1897.40 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-23 18:42:34,862 epoch 3 - iter 270/304 - loss 0.08251059 - time (sec): 14.37 - samples/sec: 1907.90 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-23 18:42:36,483 epoch 3 - iter 300/304 - loss 0.08118098 - time (sec): 15.99 - samples/sec: 1912.18 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-23 18:42:36,688 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 18:42:36,688 EPOCH 3 done: loss 0.0807 - lr: 0.000023
120
+ 2023-10-23 18:42:37,626 DEV : loss 0.1632656306028366 - f1-score (micro avg) 0.7976
121
+ 2023-10-23 18:42:37,633 saving best model
122
+ 2023-10-23 18:42:38,224 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 18:42:39,805 epoch 4 - iter 30/304 - loss 0.07437738 - time (sec): 1.58 - samples/sec: 2027.00 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-23 18:42:41,410 epoch 4 - iter 60/304 - loss 0.06433723 - time (sec): 3.18 - samples/sec: 1968.33 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-23 18:42:43,019 epoch 4 - iter 90/304 - loss 0.06492611 - time (sec): 4.79 - samples/sec: 2018.50 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-23 18:42:44,608 epoch 4 - iter 120/304 - loss 0.06014683 - time (sec): 6.38 - samples/sec: 1969.83 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-23 18:42:46,203 epoch 4 - iter 150/304 - loss 0.06363062 - time (sec): 7.98 - samples/sec: 1931.18 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-23 18:42:47,761 epoch 4 - iter 180/304 - loss 0.06608947 - time (sec): 9.53 - samples/sec: 1935.19 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-23 18:42:49,360 epoch 4 - iter 210/304 - loss 0.06318501 - time (sec): 11.13 - samples/sec: 1933.30 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-23 18:42:50,907 epoch 4 - iter 240/304 - loss 0.06084353 - time (sec): 12.68 - samples/sec: 1938.15 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-23 18:42:52,489 epoch 4 - iter 270/304 - loss 0.05801282 - time (sec): 14.26 - samples/sec: 1942.20 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-23 18:42:54,105 epoch 4 - iter 300/304 - loss 0.05979266 - time (sec): 15.88 - samples/sec: 1931.84 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-23 18:42:54,319 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 18:42:54,320 EPOCH 4 done: loss 0.0592 - lr: 0.000020
135
+ 2023-10-23 18:42:55,191 DEV : loss 0.19565072655677795 - f1-score (micro avg) 0.7945
136
+ 2023-10-23 18:42:55,198 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-23 18:42:56,821 epoch 5 - iter 30/304 - loss 0.07629438 - time (sec): 1.62 - samples/sec: 1985.19 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-23 18:42:58,452 epoch 5 - iter 60/304 - loss 0.06584847 - time (sec): 3.25 - samples/sec: 1967.62 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-23 18:42:59,920 epoch 5 - iter 90/304 - loss 0.06645514 - time (sec): 4.72 - samples/sec: 2005.47 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-23 18:43:01,174 epoch 5 - iter 120/304 - loss 0.06106677 - time (sec): 5.97 - samples/sec: 2041.54 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-23 18:43:02,441 epoch 5 - iter 150/304 - loss 0.05684249 - time (sec): 7.24 - samples/sec: 2118.68 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-23 18:43:03,698 epoch 5 - iter 180/304 - loss 0.04992630 - time (sec): 8.50 - samples/sec: 2164.49 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-23 18:43:04,955 epoch 5 - iter 210/304 - loss 0.04768756 - time (sec): 9.76 - samples/sec: 2217.14 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-23 18:43:06,208 epoch 5 - iter 240/304 - loss 0.04739891 - time (sec): 11.01 - samples/sec: 2253.22 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-23 18:43:07,468 epoch 5 - iter 270/304 - loss 0.04743295 - time (sec): 12.27 - samples/sec: 2248.91 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-23 18:43:08,721 epoch 5 - iter 300/304 - loss 0.04437326 - time (sec): 13.52 - samples/sec: 2257.12 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-23 18:43:08,890 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-23 18:43:08,890 EPOCH 5 done: loss 0.0449 - lr: 0.000017
149
+ 2023-10-23 18:43:09,746 DEV : loss 0.20239944756031036 - f1-score (micro avg) 0.8224
150
+ 2023-10-23 18:43:09,754 saving best model
151
+ 2023-10-23 18:43:10,376 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-23 18:43:11,909 epoch 6 - iter 30/304 - loss 0.02754479 - time (sec): 1.53 - samples/sec: 1982.77 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-23 18:43:13,524 epoch 6 - iter 60/304 - loss 0.02883878 - time (sec): 3.15 - samples/sec: 1883.50 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-23 18:43:15,118 epoch 6 - iter 90/304 - loss 0.02965682 - time (sec): 4.74 - samples/sec: 1911.75 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-23 18:43:16,698 epoch 6 - iter 120/304 - loss 0.03433798 - time (sec): 6.32 - samples/sec: 1916.86 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-23 18:43:18,289 epoch 6 - iter 150/304 - loss 0.03330524 - time (sec): 7.91 - samples/sec: 1934.35 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-23 18:43:19,894 epoch 6 - iter 180/304 - loss 0.02900939 - time (sec): 9.52 - samples/sec: 1940.06 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-23 18:43:21,512 epoch 6 - iter 210/304 - loss 0.02849291 - time (sec): 11.13 - samples/sec: 1938.92 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-23 18:43:23,111 epoch 6 - iter 240/304 - loss 0.02600130 - time (sec): 12.73 - samples/sec: 1949.33 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-23 18:43:24,708 epoch 6 - iter 270/304 - loss 0.02678085 - time (sec): 14.33 - samples/sec: 1937.82 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-23 18:43:26,302 epoch 6 - iter 300/304 - loss 0.02733155 - time (sec): 15.92 - samples/sec: 1924.64 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-23 18:43:26,514 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-23 18:43:26,515 EPOCH 6 done: loss 0.0273 - lr: 0.000013
164
+ 2023-10-23 18:43:27,403 DEV : loss 0.21934179961681366 - f1-score (micro avg) 0.8298
165
+ 2023-10-23 18:43:27,410 saving best model
166
+ 2023-10-23 18:43:28,235 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-23 18:43:29,841 epoch 7 - iter 30/304 - loss 0.01397302 - time (sec): 1.60 - samples/sec: 1936.59 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-23 18:43:31,455 epoch 7 - iter 60/304 - loss 0.01915468 - time (sec): 3.22 - samples/sec: 1915.21 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-23 18:43:33,055 epoch 7 - iter 90/304 - loss 0.01762276 - time (sec): 4.82 - samples/sec: 1873.86 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-23 18:43:34,677 epoch 7 - iter 120/304 - loss 0.01645907 - time (sec): 6.44 - samples/sec: 1959.36 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-23 18:43:36,291 epoch 7 - iter 150/304 - loss 0.01542218 - time (sec): 8.05 - samples/sec: 1952.32 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-23 18:43:37,897 epoch 7 - iter 180/304 - loss 0.01713716 - time (sec): 9.66 - samples/sec: 1920.18 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-23 18:43:39,511 epoch 7 - iter 210/304 - loss 0.01820963 - time (sec): 11.27 - samples/sec: 1922.96 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-23 18:43:41,127 epoch 7 - iter 240/304 - loss 0.02198012 - time (sec): 12.89 - samples/sec: 1906.65 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-23 18:43:42,739 epoch 7 - iter 270/304 - loss 0.02216705 - time (sec): 14.50 - samples/sec: 1889.30 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-23 18:43:44,356 epoch 7 - iter 300/304 - loss 0.02285418 - time (sec): 16.12 - samples/sec: 1901.87 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-23 18:43:44,571 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-23 18:43:44,571 EPOCH 7 done: loss 0.0226 - lr: 0.000010
179
+ 2023-10-23 18:43:45,427 DEV : loss 0.20938090980052948 - f1-score (micro avg) 0.8452
180
+ 2023-10-23 18:43:45,434 saving best model
181
+ 2023-10-23 18:43:46,030 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-23 18:43:47,632 epoch 8 - iter 30/304 - loss 0.03183422 - time (sec): 1.60 - samples/sec: 1932.26 - lr: 0.000010 - momentum: 0.000000
183
+ 2023-10-23 18:43:49,244 epoch 8 - iter 60/304 - loss 0.01926877 - time (sec): 3.21 - samples/sec: 1929.60 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-23 18:43:50,853 epoch 8 - iter 90/304 - loss 0.01690674 - time (sec): 4.82 - samples/sec: 1878.48 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-23 18:43:52,474 epoch 8 - iter 120/304 - loss 0.01440643 - time (sec): 6.44 - samples/sec: 1894.60 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-23 18:43:54,084 epoch 8 - iter 150/304 - loss 0.01298928 - time (sec): 8.05 - samples/sec: 1886.85 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-23 18:43:55,707 epoch 8 - iter 180/304 - loss 0.01657404 - time (sec): 9.67 - samples/sec: 1909.40 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-23 18:43:57,324 epoch 8 - iter 210/304 - loss 0.01802301 - time (sec): 11.29 - samples/sec: 1911.99 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-23 18:43:58,931 epoch 8 - iter 240/304 - loss 0.01886392 - time (sec): 12.90 - samples/sec: 1900.67 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-23 18:44:00,549 epoch 8 - iter 270/304 - loss 0.01870973 - time (sec): 14.52 - samples/sec: 1906.77 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-23 18:44:02,173 epoch 8 - iter 300/304 - loss 0.01803136 - time (sec): 16.14 - samples/sec: 1899.42 - lr: 0.000007 - momentum: 0.000000
192
+ 2023-10-23 18:44:02,386 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-23 18:44:02,386 EPOCH 8 done: loss 0.0178 - lr: 0.000007
194
+ 2023-10-23 18:44:03,237 DEV : loss 0.1909065842628479 - f1-score (micro avg) 0.8507
195
+ 2023-10-23 18:44:03,244 saving best model
196
+ 2023-10-23 18:44:03,837 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-23 18:44:05,449 epoch 9 - iter 30/304 - loss 0.01349758 - time (sec): 1.61 - samples/sec: 1896.16 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-23 18:44:07,058 epoch 9 - iter 60/304 - loss 0.00860278 - time (sec): 3.22 - samples/sec: 1901.81 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-23 18:44:08,675 epoch 9 - iter 90/304 - loss 0.01102899 - time (sec): 4.84 - samples/sec: 1899.79 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-23 18:44:10,283 epoch 9 - iter 120/304 - loss 0.01139409 - time (sec): 6.44 - samples/sec: 1853.44 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-23 18:44:11,909 epoch 9 - iter 150/304 - loss 0.00988333 - time (sec): 8.07 - samples/sec: 1884.99 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-23 18:44:13,520 epoch 9 - iter 180/304 - loss 0.00940289 - time (sec): 9.68 - samples/sec: 1882.25 - lr: 0.000005 - momentum: 0.000000
203
+ 2023-10-23 18:44:15,131 epoch 9 - iter 210/304 - loss 0.00908137 - time (sec): 11.29 - samples/sec: 1902.28 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-23 18:44:16,743 epoch 9 - iter 240/304 - loss 0.00915917 - time (sec): 12.90 - samples/sec: 1905.28 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-23 18:44:18,359 epoch 9 - iter 270/304 - loss 0.00879020 - time (sec): 14.52 - samples/sec: 1915.81 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-23 18:44:19,973 epoch 9 - iter 300/304 - loss 0.00952046 - time (sec): 16.13 - samples/sec: 1903.34 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-23 18:44:20,182 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-23 18:44:20,182 EPOCH 9 done: loss 0.0111 - lr: 0.000003
209
+ 2023-10-23 18:44:21,061 DEV : loss 0.20735178887844086 - f1-score (micro avg) 0.8585
210
+ 2023-10-23 18:44:21,068 saving best model
211
+ 2023-10-23 18:44:21,674 ----------------------------------------------------------------------------------------------------
212
+ 2023-10-23 18:44:23,277 epoch 10 - iter 30/304 - loss 0.01463854 - time (sec): 1.60 - samples/sec: 1941.31 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-23 18:44:24,898 epoch 10 - iter 60/304 - loss 0.01215426 - time (sec): 3.22 - samples/sec: 1990.23 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-23 18:44:26,503 epoch 10 - iter 90/304 - loss 0.01217807 - time (sec): 4.83 - samples/sec: 1945.29 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-23 18:44:28,113 epoch 10 - iter 120/304 - loss 0.00968072 - time (sec): 6.44 - samples/sec: 1919.25 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-23 18:44:29,718 epoch 10 - iter 150/304 - loss 0.00809136 - time (sec): 8.04 - samples/sec: 1894.51 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-23 18:44:31,336 epoch 10 - iter 180/304 - loss 0.00930065 - time (sec): 9.66 - samples/sec: 1883.87 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 18:44:32,949 epoch 10 - iter 210/304 - loss 0.01166669 - time (sec): 11.27 - samples/sec: 1886.95 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 18:44:34,563 epoch 10 - iter 240/304 - loss 0.01041781 - time (sec): 12.89 - samples/sec: 1874.19 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-23 18:44:36,192 epoch 10 - iter 270/304 - loss 0.00977246 - time (sec): 14.52 - samples/sec: 1888.06 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-23 18:44:37,814 epoch 10 - iter 300/304 - loss 0.01050597 - time (sec): 16.14 - samples/sec: 1901.21 - lr: 0.000000 - momentum: 0.000000
222
+ 2023-10-23 18:44:38,025 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-23 18:44:38,026 EPOCH 10 done: loss 0.0104 - lr: 0.000000
224
+ 2023-10-23 18:44:39,272 DEV : loss 0.2081773281097412 - f1-score (micro avg) 0.8622
225
+ 2023-10-23 18:44:39,281 saving best model
226
+ 2023-10-23 18:44:40,548 ----------------------------------------------------------------------------------------------------
227
+ 2023-10-23 18:44:40,550 Loading model from best epoch ...
228
+ 2023-10-23 18:44:42,797 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-date, B-date, E-date, I-date, S-object, B-object, E-object, I-object
229
+ 2023-10-23 18:44:43,555
230
+ Results:
231
+ - F-score (micro) 0.8148
232
+ - F-score (macro) 0.6971
233
+ - Accuracy 0.6939
234
+
235
+ By class:
236
+ precision recall f1-score support
237
+
238
+ scope 0.7439 0.8079 0.7746 151
239
+ pers 0.8411 0.9375 0.8867 96
240
+ work 0.7885 0.8632 0.8241 95
241
+ loc 1.0000 1.0000 1.0000 3
242
+ date 0.0000 0.0000 0.0000 3
243
+
244
+ micro avg 0.7795 0.8534 0.8148 348
245
+ macro avg 0.6747 0.7217 0.6971 348
246
+ weighted avg 0.7787 0.8534 0.8143 348
247
+
248
+ 2023-10-23 18:44:43,555 ----------------------------------------------------------------------------------------------------