Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs4-wsFalse-e10-lr5e-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
718e591
•
1 Parent(s): d2afe7c

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +246 -0
training.log ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 15:13:39,404 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 15:13:39,405 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 15:13:39,405 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 15:13:39,405 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 15:13:39,405 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 15:13:39,405 Train: 1100 sentences
55
+ 2023-10-23 15:13:39,405 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 15:13:39,405 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 15:13:39,405 Training Params:
58
+ 2023-10-23 15:13:39,405 - learning_rate: "5e-05"
59
+ 2023-10-23 15:13:39,405 - mini_batch_size: "4"
60
+ 2023-10-23 15:13:39,405 - max_epochs: "10"
61
+ 2023-10-23 15:13:39,405 - shuffle: "True"
62
+ 2023-10-23 15:13:39,405 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 15:13:39,406 Plugins:
64
+ 2023-10-23 15:13:39,406 - TensorboardLogger
65
+ 2023-10-23 15:13:39,406 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 15:13:39,406 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 15:13:39,406 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 15:13:39,406 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 15:13:39,406 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 15:13:39,406 Computation:
71
+ 2023-10-23 15:13:39,406 - compute on device: cuda:0
72
+ 2023-10-23 15:13:39,406 - embedding storage: none
73
+ 2023-10-23 15:13:39,406 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 15:13:39,406 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
75
+ 2023-10-23 15:13:39,406 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 15:13:39,406 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 15:13:39,406 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 15:13:40,797 epoch 1 - iter 27/275 - loss 2.85099834 - time (sec): 1.39 - samples/sec: 1490.02 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-23 15:13:42,204 epoch 1 - iter 54/275 - loss 1.98989650 - time (sec): 2.80 - samples/sec: 1502.60 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-23 15:13:43,597 epoch 1 - iter 81/275 - loss 1.57639023 - time (sec): 4.19 - samples/sec: 1515.41 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-23 15:13:44,980 epoch 1 - iter 108/275 - loss 1.31045055 - time (sec): 5.57 - samples/sec: 1535.50 - lr: 0.000019 - momentum: 0.000000
82
+ 2023-10-23 15:13:46,368 epoch 1 - iter 135/275 - loss 1.11796556 - time (sec): 6.96 - samples/sec: 1579.21 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-23 15:13:47,752 epoch 1 - iter 162/275 - loss 0.98984678 - time (sec): 8.34 - samples/sec: 1582.40 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-23 15:13:49,154 epoch 1 - iter 189/275 - loss 0.88452568 - time (sec): 9.75 - samples/sec: 1602.85 - lr: 0.000034 - momentum: 0.000000
85
+ 2023-10-23 15:13:50,552 epoch 1 - iter 216/275 - loss 0.79851785 - time (sec): 11.14 - samples/sec: 1604.43 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-23 15:13:51,944 epoch 1 - iter 243/275 - loss 0.73667649 - time (sec): 12.54 - samples/sec: 1603.61 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-23 15:13:53,340 epoch 1 - iter 270/275 - loss 0.68382485 - time (sec): 13.93 - samples/sec: 1605.84 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-23 15:13:53,601 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 15:13:53,601 EPOCH 1 done: loss 0.6743 - lr: 0.000049
90
+ 2023-10-23 15:13:54,024 DEV : loss 0.16227713227272034 - f1-score (micro avg) 0.7883
91
+ 2023-10-23 15:13:54,030 saving best model
92
+ 2023-10-23 15:13:54,442 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 15:13:55,813 epoch 2 - iter 27/275 - loss 0.20233743 - time (sec): 1.37 - samples/sec: 1494.47 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-23 15:13:57,204 epoch 2 - iter 54/275 - loss 0.19503699 - time (sec): 2.76 - samples/sec: 1515.14 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-23 15:13:58,606 epoch 2 - iter 81/275 - loss 0.16867119 - time (sec): 4.16 - samples/sec: 1498.94 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-23 15:13:59,994 epoch 2 - iter 108/275 - loss 0.15825984 - time (sec): 5.55 - samples/sec: 1589.39 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-23 15:14:01,547 epoch 2 - iter 135/275 - loss 0.16482149 - time (sec): 7.10 - samples/sec: 1554.01 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-23 15:14:02,941 epoch 2 - iter 162/275 - loss 0.16345789 - time (sec): 8.50 - samples/sec: 1572.62 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-23 15:14:04,336 epoch 2 - iter 189/275 - loss 0.15612920 - time (sec): 9.89 - samples/sec: 1594.30 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-23 15:14:05,727 epoch 2 - iter 216/275 - loss 0.15525773 - time (sec): 11.28 - samples/sec: 1588.42 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-23 15:14:07,122 epoch 2 - iter 243/275 - loss 0.15469491 - time (sec): 12.68 - samples/sec: 1582.10 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-23 15:14:08,516 epoch 2 - iter 270/275 - loss 0.15330438 - time (sec): 14.07 - samples/sec: 1592.61 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-23 15:14:08,776 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 15:14:08,776 EPOCH 2 done: loss 0.1517 - lr: 0.000045
105
+ 2023-10-23 15:14:09,320 DEV : loss 0.1382952332496643 - f1-score (micro avg) 0.85
106
+ 2023-10-23 15:14:09,326 saving best model
107
+ 2023-10-23 15:14:09,858 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 15:14:11,261 epoch 3 - iter 27/275 - loss 0.07398573 - time (sec): 1.40 - samples/sec: 1582.45 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-23 15:14:12,640 epoch 3 - iter 54/275 - loss 0.07255848 - time (sec): 2.78 - samples/sec: 1635.07 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-23 15:14:14,019 epoch 3 - iter 81/275 - loss 0.09260881 - time (sec): 4.16 - samples/sec: 1636.11 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-23 15:14:15,432 epoch 3 - iter 108/275 - loss 0.10038786 - time (sec): 5.57 - samples/sec: 1683.28 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-23 15:14:16,828 epoch 3 - iter 135/275 - loss 0.11158213 - time (sec): 6.97 - samples/sec: 1634.97 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-23 15:14:18,217 epoch 3 - iter 162/275 - loss 0.10488053 - time (sec): 8.36 - samples/sec: 1645.75 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-23 15:14:19,591 epoch 3 - iter 189/275 - loss 0.10338026 - time (sec): 9.73 - samples/sec: 1629.10 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-23 15:14:20,967 epoch 3 - iter 216/275 - loss 0.09795357 - time (sec): 11.11 - samples/sec: 1633.41 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-23 15:14:22,359 epoch 3 - iter 243/275 - loss 0.09516637 - time (sec): 12.50 - samples/sec: 1621.44 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-23 15:14:23,741 epoch 3 - iter 270/275 - loss 0.09534248 - time (sec): 13.88 - samples/sec: 1606.25 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-23 15:14:23,992 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 15:14:23,992 EPOCH 3 done: loss 0.0958 - lr: 0.000039
120
+ 2023-10-23 15:14:24,535 DEV : loss 0.14920854568481445 - f1-score (micro avg) 0.8585
121
+ 2023-10-23 15:14:24,541 saving best model
122
+ 2023-10-23 15:14:25,071 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 15:14:26,463 epoch 4 - iter 27/275 - loss 0.07018825 - time (sec): 1.39 - samples/sec: 1406.62 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-23 15:14:27,845 epoch 4 - iter 54/275 - loss 0.06226657 - time (sec): 2.77 - samples/sec: 1467.36 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-23 15:14:29,239 epoch 4 - iter 81/275 - loss 0.06582253 - time (sec): 4.16 - samples/sec: 1478.90 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-23 15:14:30,622 epoch 4 - iter 108/275 - loss 0.06988629 - time (sec): 5.55 - samples/sec: 1503.23 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-23 15:14:32,012 epoch 4 - iter 135/275 - loss 0.07096498 - time (sec): 6.94 - samples/sec: 1555.50 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-23 15:14:33,383 epoch 4 - iter 162/275 - loss 0.07062111 - time (sec): 8.31 - samples/sec: 1570.54 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-23 15:14:34,767 epoch 4 - iter 189/275 - loss 0.07193160 - time (sec): 9.69 - samples/sec: 1575.30 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-23 15:14:36,144 epoch 4 - iter 216/275 - loss 0.06931385 - time (sec): 11.07 - samples/sec: 1567.56 - lr: 0.000035 - momentum: 0.000000
131
+ 2023-10-23 15:14:37,539 epoch 4 - iter 243/275 - loss 0.07498190 - time (sec): 12.46 - samples/sec: 1603.76 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-23 15:14:38,929 epoch 4 - iter 270/275 - loss 0.07480236 - time (sec): 13.85 - samples/sec: 1610.05 - lr: 0.000034 - momentum: 0.000000
133
+ 2023-10-23 15:14:39,184 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 15:14:39,184 EPOCH 4 done: loss 0.0745 - lr: 0.000034
135
+ 2023-10-23 15:14:39,715 DEV : loss 0.13010956346988678 - f1-score (micro avg) 0.89
136
+ 2023-10-23 15:14:39,721 saving best model
137
+ 2023-10-23 15:14:40,258 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-23 15:14:41,583 epoch 5 - iter 27/275 - loss 0.02728475 - time (sec): 1.32 - samples/sec: 1564.46 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-23 15:14:42,969 epoch 5 - iter 54/275 - loss 0.04115997 - time (sec): 2.71 - samples/sec: 1638.98 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-23 15:14:44,351 epoch 5 - iter 81/275 - loss 0.03672202 - time (sec): 4.09 - samples/sec: 1651.11 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-23 15:14:45,736 epoch 5 - iter 108/275 - loss 0.04656876 - time (sec): 5.47 - samples/sec: 1641.82 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-23 15:14:47,113 epoch 5 - iter 135/275 - loss 0.04880371 - time (sec): 6.85 - samples/sec: 1638.52 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-23 15:14:48,495 epoch 5 - iter 162/275 - loss 0.04745679 - time (sec): 8.23 - samples/sec: 1628.96 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-23 15:14:49,876 epoch 5 - iter 189/275 - loss 0.04420481 - time (sec): 9.61 - samples/sec: 1619.83 - lr: 0.000030 - momentum: 0.000000
145
+ 2023-10-23 15:14:51,251 epoch 5 - iter 216/275 - loss 0.05291350 - time (sec): 10.99 - samples/sec: 1619.27 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-23 15:14:52,632 epoch 5 - iter 243/275 - loss 0.05506509 - time (sec): 12.37 - samples/sec: 1607.86 - lr: 0.000029 - momentum: 0.000000
147
+ 2023-10-23 15:14:54,011 epoch 5 - iter 270/275 - loss 0.05098026 - time (sec): 13.75 - samples/sec: 1616.76 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-23 15:14:54,271 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-23 15:14:54,271 EPOCH 5 done: loss 0.0498 - lr: 0.000028
150
+ 2023-10-23 15:14:54,814 DEV : loss 0.15523016452789307 - f1-score (micro avg) 0.8808
151
+ 2023-10-23 15:14:54,820 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-23 15:14:56,209 epoch 6 - iter 27/275 - loss 0.03346794 - time (sec): 1.39 - samples/sec: 1506.99 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-23 15:14:57,587 epoch 6 - iter 54/275 - loss 0.02766177 - time (sec): 2.77 - samples/sec: 1555.59 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-23 15:14:58,965 epoch 6 - iter 81/275 - loss 0.03507040 - time (sec): 4.14 - samples/sec: 1569.64 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-23 15:15:00,347 epoch 6 - iter 108/275 - loss 0.04627198 - time (sec): 5.53 - samples/sec: 1617.08 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-23 15:15:01,742 epoch 6 - iter 135/275 - loss 0.04081860 - time (sec): 6.92 - samples/sec: 1642.71 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-23 15:15:03,133 epoch 6 - iter 162/275 - loss 0.03948313 - time (sec): 8.31 - samples/sec: 1648.43 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-23 15:15:04,519 epoch 6 - iter 189/275 - loss 0.03974615 - time (sec): 9.70 - samples/sec: 1625.19 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-23 15:15:05,899 epoch 6 - iter 216/275 - loss 0.03703249 - time (sec): 11.08 - samples/sec: 1631.94 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-23 15:15:07,283 epoch 6 - iter 243/275 - loss 0.03628317 - time (sec): 12.46 - samples/sec: 1637.85 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-23 15:15:08,667 epoch 6 - iter 270/275 - loss 0.03321791 - time (sec): 13.85 - samples/sec: 1610.64 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-23 15:15:08,923 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-23 15:15:08,924 EPOCH 6 done: loss 0.0338 - lr: 0.000022
164
+ 2023-10-23 15:15:09,469 DEV : loss 0.16956964135169983 - f1-score (micro avg) 0.8878
165
+ 2023-10-23 15:15:09,475 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-23 15:15:10,860 epoch 7 - iter 27/275 - loss 0.01659930 - time (sec): 1.38 - samples/sec: 1808.86 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-23 15:15:12,243 epoch 7 - iter 54/275 - loss 0.02442399 - time (sec): 2.77 - samples/sec: 1658.83 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-23 15:15:13,624 epoch 7 - iter 81/275 - loss 0.02758310 - time (sec): 4.15 - samples/sec: 1566.42 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-23 15:15:15,025 epoch 7 - iter 108/275 - loss 0.03395004 - time (sec): 5.55 - samples/sec: 1604.11 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-23 15:15:16,405 epoch 7 - iter 135/275 - loss 0.03222094 - time (sec): 6.93 - samples/sec: 1586.04 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-23 15:15:17,674 epoch 7 - iter 162/275 - loss 0.02996231 - time (sec): 8.20 - samples/sec: 1633.21 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-23 15:15:18,924 epoch 7 - iter 189/275 - loss 0.02575164 - time (sec): 9.45 - samples/sec: 1656.59 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-23 15:15:20,180 epoch 7 - iter 216/275 - loss 0.02705132 - time (sec): 10.70 - samples/sec: 1661.96 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-23 15:15:21,430 epoch 7 - iter 243/275 - loss 0.02524744 - time (sec): 11.95 - samples/sec: 1669.03 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-23 15:15:22,701 epoch 7 - iter 270/275 - loss 0.02345507 - time (sec): 13.23 - samples/sec: 1694.86 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-23 15:15:22,930 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-23 15:15:22,930 EPOCH 7 done: loss 0.0232 - lr: 0.000017
178
+ 2023-10-23 15:15:23,473 DEV : loss 0.17189306020736694 - f1-score (micro avg) 0.8846
179
+ 2023-10-23 15:15:23,479 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-23 15:15:24,783 epoch 8 - iter 27/275 - loss 0.02467631 - time (sec): 1.30 - samples/sec: 1552.65 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-23 15:15:26,110 epoch 8 - iter 54/275 - loss 0.01460542 - time (sec): 2.63 - samples/sec: 1604.67 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-23 15:15:27,415 epoch 8 - iter 81/275 - loss 0.01439412 - time (sec): 3.93 - samples/sec: 1671.43 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-23 15:15:28,668 epoch 8 - iter 108/275 - loss 0.01281004 - time (sec): 5.19 - samples/sec: 1639.19 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-23 15:15:29,919 epoch 8 - iter 135/275 - loss 0.01418760 - time (sec): 6.44 - samples/sec: 1691.37 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-23 15:15:31,170 epoch 8 - iter 162/275 - loss 0.01694494 - time (sec): 7.69 - samples/sec: 1704.91 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-23 15:15:32,415 epoch 8 - iter 189/275 - loss 0.01803220 - time (sec): 8.94 - samples/sec: 1696.09 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-23 15:15:33,667 epoch 8 - iter 216/275 - loss 0.01988452 - time (sec): 10.19 - samples/sec: 1732.94 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-23 15:15:34,928 epoch 8 - iter 243/275 - loss 0.01921107 - time (sec): 11.45 - samples/sec: 1758.27 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-23 15:15:36,171 epoch 8 - iter 270/275 - loss 0.01986813 - time (sec): 12.69 - samples/sec: 1757.50 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-23 15:15:36,405 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-23 15:15:36,405 EPOCH 8 done: loss 0.0195 - lr: 0.000011
192
+ 2023-10-23 15:15:36,947 DEV : loss 0.17288783192634583 - f1-score (micro avg) 0.8975
193
+ 2023-10-23 15:15:36,953 saving best model
194
+ 2023-10-23 15:15:37,480 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-23 15:15:38,876 epoch 9 - iter 27/275 - loss 0.01201343 - time (sec): 1.39 - samples/sec: 1526.37 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-23 15:15:40,270 epoch 9 - iter 54/275 - loss 0.02331793 - time (sec): 2.79 - samples/sec: 1641.42 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-23 15:15:41,660 epoch 9 - iter 81/275 - loss 0.01787529 - time (sec): 4.18 - samples/sec: 1658.99 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-23 15:15:43,039 epoch 9 - iter 108/275 - loss 0.01485053 - time (sec): 5.56 - samples/sec: 1646.12 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-23 15:15:44,434 epoch 9 - iter 135/275 - loss 0.01434536 - time (sec): 6.95 - samples/sec: 1632.76 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-23 15:15:45,827 epoch 9 - iter 162/275 - loss 0.01222986 - time (sec): 8.34 - samples/sec: 1617.76 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-23 15:15:47,184 epoch 9 - iter 189/275 - loss 0.01344065 - time (sec): 9.70 - samples/sec: 1605.55 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-23 15:15:48,564 epoch 9 - iter 216/275 - loss 0.01339077 - time (sec): 11.08 - samples/sec: 1610.15 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-23 15:15:49,954 epoch 9 - iter 243/275 - loss 0.01313977 - time (sec): 12.47 - samples/sec: 1612.49 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-23 15:15:51,352 epoch 9 - iter 270/275 - loss 0.01372486 - time (sec): 13.87 - samples/sec: 1618.66 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-23 15:15:51,611 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-23 15:15:51,611 EPOCH 9 done: loss 0.0135 - lr: 0.000006
207
+ 2023-10-23 15:15:52,154 DEV : loss 0.17795315384864807 - f1-score (micro avg) 0.899
208
+ 2023-10-23 15:15:52,160 saving best model
209
+ 2023-10-23 15:15:52,692 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-23 15:15:54,104 epoch 10 - iter 27/275 - loss 0.00192733 - time (sec): 1.41 - samples/sec: 1610.07 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-23 15:15:55,503 epoch 10 - iter 54/275 - loss 0.00262015 - time (sec): 2.81 - samples/sec: 1560.71 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-23 15:15:56,917 epoch 10 - iter 81/275 - loss 0.00265573 - time (sec): 4.22 - samples/sec: 1539.55 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-23 15:15:58,325 epoch 10 - iter 108/275 - loss 0.00243482 - time (sec): 5.63 - samples/sec: 1524.48 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-23 15:15:59,730 epoch 10 - iter 135/275 - loss 0.00410184 - time (sec): 7.04 - samples/sec: 1519.93 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-23 15:16:01,149 epoch 10 - iter 162/275 - loss 0.00385736 - time (sec): 8.46 - samples/sec: 1521.09 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-23 15:16:02,547 epoch 10 - iter 189/275 - loss 0.00369809 - time (sec): 9.85 - samples/sec: 1552.52 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-23 15:16:03,940 epoch 10 - iter 216/275 - loss 0.00349045 - time (sec): 11.25 - samples/sec: 1557.52 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 15:16:05,320 epoch 10 - iter 243/275 - loss 0.00544919 - time (sec): 12.63 - samples/sec: 1563.92 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 15:16:06,720 epoch 10 - iter 270/275 - loss 0.00907705 - time (sec): 14.03 - samples/sec: 1590.33 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-23 15:16:06,982 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-23 15:16:06,982 EPOCH 10 done: loss 0.0089 - lr: 0.000000
222
+ 2023-10-23 15:16:07,541 DEV : loss 0.17612943053245544 - f1-score (micro avg) 0.9012
223
+ 2023-10-23 15:16:07,547 saving best model
224
+ 2023-10-23 15:16:08,503 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-23 15:16:08,504 Loading model from best epoch ...
226
+ 2023-10-23 15:16:10,288 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
227
+ 2023-10-23 15:16:10,966
228
+ Results:
229
+ - F-score (micro) 0.9263
230
+ - F-score (macro) 0.6568
231
+ - Accuracy 0.867
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ scope 0.9195 0.9091 0.9143 176
237
+ pers 0.9841 0.9688 0.9764 128
238
+ work 0.8816 0.9054 0.8933 74
239
+ object 0.5000 0.5000 0.5000 2
240
+ loc 0.0000 0.0000 0.0000 2
241
+
242
+ micro avg 0.9312 0.9215 0.9263 382
243
+ macro avg 0.6570 0.6566 0.6568 382
244
+ weighted avg 0.9268 0.9215 0.9241 382
245
+
246
+ 2023-10-23 15:16:10,966 ----------------------------------------------------------------------------------------------------