Hugging Face's logo

stefan-it
/
hmbench-newseye-fi-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
Finnish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
b03033f
•
1 Parent(s): 6960875

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +243 -0
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 20:59:54,156 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 20:59:54,157 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-25 20:59:54,157 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 20:59:54,157 MultiCorpus: 1166 train + 165 dev + 415 test sentences
52
+ - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
53
+ 2023-10-25 20:59:54,157 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 20:59:54,157 Train: 1166 sentences
55
+ 2023-10-25 20:59:54,157 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 20:59:54,157 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 20:59:54,157 Training Params:
58
+ 2023-10-25 20:59:54,157 - learning_rate: "3e-05"
59
+ 2023-10-25 20:59:54,157 - mini_batch_size: "4"
60
+ 2023-10-25 20:59:54,157 - max_epochs: "10"
61
+ 2023-10-25 20:59:54,157 - shuffle: "True"
62
+ 2023-10-25 20:59:54,158 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 20:59:54,158 Plugins:
64
+ 2023-10-25 20:59:54,158 - TensorboardLogger
65
+ 2023-10-25 20:59:54,158 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 20:59:54,158 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 20:59:54,158 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 20:59:54,158 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 20:59:54,158 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 20:59:54,158 Computation:
71
+ 2023-10-25 20:59:54,158 - compute on device: cuda:0
72
+ 2023-10-25 20:59:54,158 - embedding storage: none
73
+ 2023-10-25 20:59:54,158 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 20:59:54,158 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-25 20:59:54,158 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 20:59:54,158 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 20:59:54,158 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 20:59:55,465 epoch 1 - iter 29/292 - loss 2.86541598 - time (sec): 1.31 - samples/sec: 2860.19 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 20:59:56,853 epoch 1 - iter 58/292 - loss 2.05975293 - time (sec): 2.69 - samples/sec: 3359.48 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 20:59:58,259 epoch 1 - iter 87/292 - loss 1.51451020 - time (sec): 4.10 - samples/sec: 3531.96 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-25 20:59:59,549 epoch 1 - iter 116/292 - loss 1.27384924 - time (sec): 5.39 - samples/sec: 3495.41 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-25 21:00:00,811 epoch 1 - iter 145/292 - loss 1.11376262 - time (sec): 6.65 - samples/sec: 3466.71 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-25 21:00:02,161 epoch 1 - iter 174/292 - loss 0.97422500 - time (sec): 8.00 - samples/sec: 3503.92 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-25 21:00:03,427 epoch 1 - iter 203/292 - loss 0.89929848 - time (sec): 9.27 - samples/sec: 3393.73 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-25 21:00:04,663 epoch 1 - iter 232/292 - loss 0.82959634 - time (sec): 10.50 - samples/sec: 3372.16 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-25 21:00:05,904 epoch 1 - iter 261/292 - loss 0.78238070 - time (sec): 11.74 - samples/sec: 3319.59 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-25 21:00:07,217 epoch 1 - iter 290/292 - loss 0.72116046 - time (sec): 13.06 - samples/sec: 3383.27 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-25 21:00:07,293 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:00:07,293 EPOCH 1 done: loss 0.7173 - lr: 0.000030
90
+ 2023-10-25 21:00:07,947 DEV : loss 0.15696528553962708 - f1-score (micro avg) 0.5511
91
+ 2023-10-25 21:00:07,951 saving best model
92
+ 2023-10-25 21:00:08,347 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:00:09,548 epoch 2 - iter 29/292 - loss 0.17890778 - time (sec): 1.20 - samples/sec: 3436.36 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 21:00:10,790 epoch 2 - iter 58/292 - loss 0.19515003 - time (sec): 2.44 - samples/sec: 3323.93 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 21:00:12,088 epoch 2 - iter 87/292 - loss 0.17002125 - time (sec): 3.74 - samples/sec: 3331.71 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 21:00:13,413 epoch 2 - iter 116/292 - loss 0.16239763 - time (sec): 5.06 - samples/sec: 3330.73 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 21:00:14,715 epoch 2 - iter 145/292 - loss 0.15872220 - time (sec): 6.37 - samples/sec: 3353.82 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 21:00:16,024 epoch 2 - iter 174/292 - loss 0.17064690 - time (sec): 7.68 - samples/sec: 3268.81 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 21:00:17,377 epoch 2 - iter 203/292 - loss 0.17532894 - time (sec): 9.03 - samples/sec: 3244.48 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 21:00:18,717 epoch 2 - iter 232/292 - loss 0.17700183 - time (sec): 10.37 - samples/sec: 3216.85 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 21:00:20,133 epoch 2 - iter 261/292 - loss 0.16918114 - time (sec): 11.78 - samples/sec: 3325.36 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 21:00:21,438 epoch 2 - iter 290/292 - loss 0.15999812 - time (sec): 13.09 - samples/sec: 3384.76 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 21:00:21,523 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:00:21,523 EPOCH 2 done: loss 0.1600 - lr: 0.000027
105
+ 2023-10-25 21:00:22,424 DEV : loss 0.13564454019069672 - f1-score (micro avg) 0.7072
106
+ 2023-10-25 21:00:22,428 saving best model
107
+ 2023-10-25 21:00:22,981 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:00:24,323 epoch 3 - iter 29/292 - loss 0.14544586 - time (sec): 1.34 - samples/sec: 3595.36 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 21:00:25,651 epoch 3 - iter 58/292 - loss 0.10941303 - time (sec): 2.67 - samples/sec: 3579.86 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 21:00:26,955 epoch 3 - iter 87/292 - loss 0.09430565 - time (sec): 3.97 - samples/sec: 3464.62 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 21:00:28,224 epoch 3 - iter 116/292 - loss 0.09566966 - time (sec): 5.24 - samples/sec: 3428.46 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 21:00:29,476 epoch 3 - iter 145/292 - loss 0.09347375 - time (sec): 6.49 - samples/sec: 3358.49 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 21:00:30,736 epoch 3 - iter 174/292 - loss 0.09163215 - time (sec): 7.75 - samples/sec: 3302.95 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 21:00:32,016 epoch 3 - iter 203/292 - loss 0.08722664 - time (sec): 9.03 - samples/sec: 3361.36 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 21:00:33,295 epoch 3 - iter 232/292 - loss 0.08761881 - time (sec): 10.31 - samples/sec: 3382.93 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 21:00:34,563 epoch 3 - iter 261/292 - loss 0.08941822 - time (sec): 11.58 - samples/sec: 3385.11 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 21:00:35,926 epoch 3 - iter 290/292 - loss 0.08796314 - time (sec): 12.94 - samples/sec: 3404.11 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-25 21:00:36,011 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:00:36,011 EPOCH 3 done: loss 0.0893 - lr: 0.000023
120
+ 2023-10-25 21:00:36,917 DEV : loss 0.13917604088783264 - f1-score (micro avg) 0.7064
121
+ 2023-10-25 21:00:36,922 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-25 21:00:38,201 epoch 4 - iter 29/292 - loss 0.06653490 - time (sec): 1.28 - samples/sec: 3265.55 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-25 21:00:39,479 epoch 4 - iter 58/292 - loss 0.05686471 - time (sec): 2.56 - samples/sec: 3556.95 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 21:00:40,763 epoch 4 - iter 87/292 - loss 0.05278725 - time (sec): 3.84 - samples/sec: 3383.00 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-25 21:00:42,031 epoch 4 - iter 116/292 - loss 0.05170961 - time (sec): 5.11 - samples/sec: 3384.12 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 21:00:43,330 epoch 4 - iter 145/292 - loss 0.05608612 - time (sec): 6.41 - samples/sec: 3383.63 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 21:00:44,645 epoch 4 - iter 174/292 - loss 0.05282409 - time (sec): 7.72 - samples/sec: 3404.02 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-25 21:00:45,906 epoch 4 - iter 203/292 - loss 0.05927506 - time (sec): 8.98 - samples/sec: 3389.18 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 21:00:47,284 epoch 4 - iter 232/292 - loss 0.05914609 - time (sec): 10.36 - samples/sec: 3417.43 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 21:00:48,539 epoch 4 - iter 261/292 - loss 0.05675851 - time (sec): 11.62 - samples/sec: 3436.37 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-25 21:00:49,827 epoch 4 - iter 290/292 - loss 0.05609862 - time (sec): 12.90 - samples/sec: 3427.20 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-25 21:00:49,908 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-25 21:00:49,908 EPOCH 4 done: loss 0.0559 - lr: 0.000020
134
+ 2023-10-25 21:00:50,821 DEV : loss 0.13928386569023132 - f1-score (micro avg) 0.7093
135
+ 2023-10-25 21:00:50,825 saving best model
136
+ 2023-10-25 21:00:51,682 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-25 21:00:52,908 epoch 5 - iter 29/292 - loss 0.02277200 - time (sec): 1.22 - samples/sec: 3015.46 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-25 21:00:54,240 epoch 5 - iter 58/292 - loss 0.03421365 - time (sec): 2.56 - samples/sec: 3261.14 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-25 21:00:55,565 epoch 5 - iter 87/292 - loss 0.03319117 - time (sec): 3.88 - samples/sec: 3447.28 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 21:00:56,821 epoch 5 - iter 116/292 - loss 0.03424275 - time (sec): 5.14 - samples/sec: 3422.46 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 21:00:58,079 epoch 5 - iter 145/292 - loss 0.03661161 - time (sec): 6.39 - samples/sec: 3365.61 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-25 21:00:59,374 epoch 5 - iter 174/292 - loss 0.03815798 - time (sec): 7.69 - samples/sec: 3355.52 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 21:01:00,716 epoch 5 - iter 203/292 - loss 0.04010743 - time (sec): 9.03 - samples/sec: 3417.96 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 21:01:02,019 epoch 5 - iter 232/292 - loss 0.03710160 - time (sec): 10.33 - samples/sec: 3430.04 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-25 21:01:03,316 epoch 5 - iter 261/292 - loss 0.03759294 - time (sec): 11.63 - samples/sec: 3417.16 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-25 21:01:04,653 epoch 5 - iter 290/292 - loss 0.03667198 - time (sec): 12.97 - samples/sec: 3414.67 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 21:01:04,732 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-25 21:01:04,733 EPOCH 5 done: loss 0.0367 - lr: 0.000017
149
+ 2023-10-25 21:01:05,633 DEV : loss 0.14212724566459656 - f1-score (micro avg) 0.714
150
+ 2023-10-25 21:01:05,637 saving best model
151
+ 2023-10-25 21:01:06,315 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-25 21:01:07,672 epoch 6 - iter 29/292 - loss 0.02796383 - time (sec): 1.35 - samples/sec: 3938.43 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-25 21:01:08,973 epoch 6 - iter 58/292 - loss 0.02811284 - time (sec): 2.66 - samples/sec: 3543.28 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 21:01:10,276 epoch 6 - iter 87/292 - loss 0.03036771 - time (sec): 3.96 - samples/sec: 3475.85 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-25 21:01:11,696 epoch 6 - iter 116/292 - loss 0.02940868 - time (sec): 5.38 - samples/sec: 3517.10 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-25 21:01:13,051 epoch 6 - iter 145/292 - loss 0.02904224 - time (sec): 6.73 - samples/sec: 3393.12 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 21:01:14,484 epoch 6 - iter 174/292 - loss 0.02614340 - time (sec): 8.17 - samples/sec: 3365.99 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-25 21:01:15,834 epoch 6 - iter 203/292 - loss 0.02631470 - time (sec): 9.52 - samples/sec: 3344.04 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-25 21:01:17,211 epoch 6 - iter 232/292 - loss 0.02881547 - time (sec): 10.89 - samples/sec: 3326.96 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 21:01:18,573 epoch 6 - iter 261/292 - loss 0.02920586 - time (sec): 12.25 - samples/sec: 3328.26 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-25 21:01:19,809 epoch 6 - iter 290/292 - loss 0.02831814 - time (sec): 13.49 - samples/sec: 3271.32 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-25 21:01:19,899 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 21:01:19,900 EPOCH 6 done: loss 0.0283 - lr: 0.000013
164
+ 2023-10-25 21:01:20,807 DEV : loss 0.1747400164604187 - f1-score (micro avg) 0.7122
165
+ 2023-10-25 21:01:20,811 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-25 21:01:22,111 epoch 7 - iter 29/292 - loss 0.04120099 - time (sec): 1.30 - samples/sec: 3294.77 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-25 21:01:23,385 epoch 7 - iter 58/292 - loss 0.02762419 - time (sec): 2.57 - samples/sec: 3376.34 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-25 21:01:24,813 epoch 7 - iter 87/292 - loss 0.02358102 - time (sec): 4.00 - samples/sec: 3458.12 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-25 21:01:26,154 epoch 7 - iter 116/292 - loss 0.02313168 - time (sec): 5.34 - samples/sec: 3412.19 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-25 21:01:27,465 epoch 7 - iter 145/292 - loss 0.02003259 - time (sec): 6.65 - samples/sec: 3395.06 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-25 21:01:28,781 epoch 7 - iter 174/292 - loss 0.01901409 - time (sec): 7.97 - samples/sec: 3406.98 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-25 21:01:30,060 epoch 7 - iter 203/292 - loss 0.01913836 - time (sec): 9.25 - samples/sec: 3379.93 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-25 21:01:31,363 epoch 7 - iter 232/292 - loss 0.02025448 - time (sec): 10.55 - samples/sec: 3344.38 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-25 21:01:32,656 epoch 7 - iter 261/292 - loss 0.02111959 - time (sec): 11.84 - samples/sec: 3351.11 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-25 21:01:33,948 epoch 7 - iter 290/292 - loss 0.02062935 - time (sec): 13.14 - samples/sec: 3356.78 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-25 21:01:34,042 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-25 21:01:34,042 EPOCH 7 done: loss 0.0205 - lr: 0.000010
178
+ 2023-10-25 21:01:34,950 DEV : loss 0.17978323996067047 - f1-score (micro avg) 0.7419
179
+ 2023-10-25 21:01:34,954 saving best model
180
+ 2023-10-25 21:01:35,635 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-25 21:01:36,928 epoch 8 - iter 29/292 - loss 0.01127436 - time (sec): 1.29 - samples/sec: 3561.67 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-25 21:01:38,170 epoch 8 - iter 58/292 - loss 0.01585167 - time (sec): 2.53 - samples/sec: 3458.37 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-25 21:01:39,442 epoch 8 - iter 87/292 - loss 0.01729172 - time (sec): 3.80 - samples/sec: 3291.43 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-25 21:01:40,697 epoch 8 - iter 116/292 - loss 0.01428530 - time (sec): 5.06 - samples/sec: 3342.05 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-25 21:01:41,956 epoch 8 - iter 145/292 - loss 0.01396528 - time (sec): 6.32 - samples/sec: 3384.13 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-25 21:01:43,276 epoch 8 - iter 174/292 - loss 0.01386840 - time (sec): 7.64 - samples/sec: 3420.43 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-25 21:01:44,553 epoch 8 - iter 203/292 - loss 0.01341978 - time (sec): 8.91 - samples/sec: 3435.77 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-25 21:01:45,972 epoch 8 - iter 232/292 - loss 0.01198981 - time (sec): 10.33 - samples/sec: 3441.57 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-25 21:01:47,238 epoch 8 - iter 261/292 - loss 0.01283600 - time (sec): 11.60 - samples/sec: 3447.91 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-25 21:01:48,534 epoch 8 - iter 290/292 - loss 0.01389923 - time (sec): 12.90 - samples/sec: 3440.30 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-25 21:01:48,615 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-25 21:01:48,615 EPOCH 8 done: loss 0.0139 - lr: 0.000007
193
+ 2023-10-25 21:01:49,531 DEV : loss 0.1903691589832306 - f1-score (micro avg) 0.7183
194
+ 2023-10-25 21:01:49,536 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-25 21:01:50,791 epoch 9 - iter 29/292 - loss 0.00703447 - time (sec): 1.25 - samples/sec: 3230.77 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-25 21:01:52,270 epoch 9 - iter 58/292 - loss 0.01503000 - time (sec): 2.73 - samples/sec: 3130.91 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-25 21:01:53,536 epoch 9 - iter 87/292 - loss 0.01311829 - time (sec): 4.00 - samples/sec: 3223.13 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-25 21:01:54,838 epoch 9 - iter 116/292 - loss 0.01085621 - time (sec): 5.30 - samples/sec: 3138.99 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-25 21:01:56,138 epoch 9 - iter 145/292 - loss 0.00936798 - time (sec): 6.60 - samples/sec: 3217.65 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-25 21:01:57,488 epoch 9 - iter 174/292 - loss 0.00878729 - time (sec): 7.95 - samples/sec: 3312.64 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-25 21:01:58,753 epoch 9 - iter 203/292 - loss 0.00963486 - time (sec): 9.22 - samples/sec: 3320.35 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-25 21:02:00,043 epoch 9 - iter 232/292 - loss 0.01175699 - time (sec): 10.51 - samples/sec: 3347.16 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-25 21:02:01,331 epoch 9 - iter 261/292 - loss 0.01082544 - time (sec): 11.79 - samples/sec: 3336.12 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-25 21:02:02,644 epoch 9 - iter 290/292 - loss 0.01194434 - time (sec): 13.11 - samples/sec: 3364.77 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-25 21:02:02,725 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-25 21:02:02,726 EPOCH 9 done: loss 0.0121 - lr: 0.000003
207
+ 2023-10-25 21:02:03,635 DEV : loss 0.20435144007205963 - f1-score (micro avg) 0.7343
208
+ 2023-10-25 21:02:03,639 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-25 21:02:04,904 epoch 10 - iter 29/292 - loss 0.00257441 - time (sec): 1.26 - samples/sec: 3070.38 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-25 21:02:06,161 epoch 10 - iter 58/292 - loss 0.00640555 - time (sec): 2.52 - samples/sec: 3097.68 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-25 21:02:07,517 epoch 10 - iter 87/292 - loss 0.00952813 - time (sec): 3.88 - samples/sec: 3268.70 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-25 21:02:08,853 epoch 10 - iter 116/292 - loss 0.00793282 - time (sec): 5.21 - samples/sec: 3338.84 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-25 21:02:10,204 epoch 10 - iter 145/292 - loss 0.00718311 - time (sec): 6.56 - samples/sec: 3416.28 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 21:02:11,520 epoch 10 - iter 174/292 - loss 0.00721069 - time (sec): 7.88 - samples/sec: 3472.31 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-25 21:02:12,820 epoch 10 - iter 203/292 - loss 0.00752348 - time (sec): 9.18 - samples/sec: 3499.53 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-25 21:02:14,047 epoch 10 - iter 232/292 - loss 0.00774661 - time (sec): 10.41 - samples/sec: 3454.80 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 21:02:15,293 epoch 10 - iter 261/292 - loss 0.00819500 - time (sec): 11.65 - samples/sec: 3424.87 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-25 21:02:16,548 epoch 10 - iter 290/292 - loss 0.00778659 - time (sec): 12.91 - samples/sec: 3421.32 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-25 21:02:16,633 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-25 21:02:16,634 EPOCH 10 done: loss 0.0079 - lr: 0.000000
221
+ 2023-10-25 21:02:17,546 DEV : loss 0.2082153558731079 - f1-score (micro avg) 0.7284
222
+ 2023-10-25 21:02:18,071 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-25 21:02:18,073 Loading model from best epoch ...
224
+ 2023-10-25 21:02:19,750 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
225
+ 2023-10-25 21:02:21,279
226
+ Results:
227
+ - F-score (micro) 0.7611
228
+ - F-score (macro) 0.6901
229
+ - Accuracy 0.6413
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ PER 0.7962 0.8534 0.8239 348
235
+ LOC 0.6646 0.8352 0.7402 261
236
+ ORG 0.4528 0.4615 0.4571 52
237
+ HumanProd 0.7083 0.7727 0.7391 22
238
+
239
+ micro avg 0.7147 0.8141 0.7611 683
240
+ macro avg 0.6555 0.7307 0.6901 683
241
+ weighted avg 0.7170 0.8141 0.7613 683
242
+
243
+ 2023-10-25 21:02:21,279 ----------------------------------------------------------------------------------------------------