Hugging Face's logo

stefan-it
/
hmbench-newseye-fi-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
Finnish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
4bbb6d6
•
1 Parent(s): 8405eee

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +242 -0
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 21:22:49,010 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:22:49,011 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 21:22:49,011 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:22:49,012 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 21:22:49,012 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:22:49,012 Train: 1166 sentences
55
+ 2023-10-25 21:22:49,012 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:22:49,012 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:22:49,012 Training Params:
58
+ 2023-10-25 21:22:49,012 - learning_rate: "5e-05"
59
+ 2023-10-25 21:22:49,012 - mini_batch_size: "4"
60
+ 2023-10-25 21:22:49,012 - max_epochs: "10"
61
+ 2023-10-25 21:22:49,012 - shuffle: "True"
62
+ 2023-10-25 21:22:49,012 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:22:49,012 Plugins:
64
+ 2023-10-25 21:22:49,012 - TensorboardLogger
65
+ 2023-10-25 21:22:49,012 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:22:49,012 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:22:49,012 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:22:49,012 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:22:49,012 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:22:49,012 Computation:
71
+ 2023-10-25 21:22:49,012 - compute on device: cuda:0
72
+ 2023-10-25 21:22:49,012 - embedding storage: none
73
+ 2023-10-25 21:22:49,012 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:22:49,012 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-25 21:22:49,012 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:22:49,012 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:22:49,012 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:22:50,365 epoch 1 - iter 29/292 - loss 3.04468690 - time (sec): 1.35 - samples/sec: 3544.24 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-25 21:22:51,616 epoch 1 - iter 58/292 - loss 2.08228056 - time (sec): 2.60 - samples/sec: 3418.55 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-25 21:22:52,870 epoch 1 - iter 87/292 - loss 1.67391242 - time (sec): 3.86 - samples/sec: 3380.18 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-25 21:22:54,119 epoch 1 - iter 116/292 - loss 1.39271840 - time (sec): 5.11 - samples/sec: 3361.81 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-25 21:22:55,408 epoch 1 - iter 145/292 - loss 1.19734159 - time (sec): 6.39 - samples/sec: 3286.22 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-25 21:22:56,810 epoch 1 - iter 174/292 - loss 1.01730119 - time (sec): 7.80 - samples/sec: 3367.82 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-25 21:22:58,079 epoch 1 - iter 203/292 - loss 0.91202992 - time (sec): 9.07 - samples/sec: 3355.88 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-25 21:22:59,525 epoch 1 - iter 232/292 - loss 0.82288451 - time (sec): 10.51 - samples/sec: 3320.22 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-25 21:23:00,832 epoch 1 - iter 261/292 - loss 0.74308263 - time (sec): 11.82 - samples/sec: 3348.87 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-25 21:23:02,179 epoch 1 - iter 290/292 - loss 0.68034745 - time (sec): 13.17 - samples/sec: 3354.10 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-25 21:23:02,263 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:23:02,263 EPOCH 1 done: loss 0.6780 - lr: 0.000049
90
+ 2023-10-25 21:23:02,769 DEV : loss 0.15992717444896698 - f1-score (micro avg) 0.5378
91
+ 2023-10-25 21:23:02,773 saving best model
92
+ 2023-10-25 21:23:03,304 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:23:04,601 epoch 2 - iter 29/292 - loss 0.21214502 - time (sec): 1.30 - samples/sec: 3350.43 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-25 21:23:05,969 epoch 2 - iter 58/292 - loss 0.16803234 - time (sec): 2.66 - samples/sec: 3478.53 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 21:23:07,229 epoch 2 - iter 87/292 - loss 0.16062619 - time (sec): 3.92 - samples/sec: 3417.74 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 21:23:08,555 epoch 2 - iter 116/292 - loss 0.17011069 - time (sec): 5.25 - samples/sec: 3419.64 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 21:23:09,852 epoch 2 - iter 145/292 - loss 0.16743668 - time (sec): 6.55 - samples/sec: 3382.00 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 21:23:11,093 epoch 2 - iter 174/292 - loss 0.16331818 - time (sec): 7.79 - samples/sec: 3318.18 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 21:23:12,390 epoch 2 - iter 203/292 - loss 0.16521386 - time (sec): 9.08 - samples/sec: 3293.04 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 21:23:13,727 epoch 2 - iter 232/292 - loss 0.16386177 - time (sec): 10.42 - samples/sec: 3308.08 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 21:23:15,077 epoch 2 - iter 261/292 - loss 0.15723361 - time (sec): 11.77 - samples/sec: 3350.27 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 21:23:16,379 epoch 2 - iter 290/292 - loss 0.15379255 - time (sec): 13.07 - samples/sec: 3390.10 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-25 21:23:16,458 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:23:16,458 EPOCH 2 done: loss 0.1536 - lr: 0.000045
105
+ 2023-10-25 21:23:17,366 DEV : loss 0.12357047200202942 - f1-score (micro avg) 0.7236
106
+ 2023-10-25 21:23:17,370 saving best model
107
+ 2023-10-25 21:23:17,907 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:23:19,208 epoch 3 - iter 29/292 - loss 0.08209900 - time (sec): 1.30 - samples/sec: 3698.78 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-25 21:23:20,480 epoch 3 - iter 58/292 - loss 0.08954013 - time (sec): 2.57 - samples/sec: 3585.69 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 21:23:21,942 epoch 3 - iter 87/292 - loss 0.09024601 - time (sec): 4.03 - samples/sec: 3363.73 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-25 21:23:23,235 epoch 3 - iter 116/292 - loss 0.09815526 - time (sec): 5.32 - samples/sec: 3316.48 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 21:23:24,526 epoch 3 - iter 145/292 - loss 0.10736630 - time (sec): 6.61 - samples/sec: 3329.89 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-25 21:23:25,765 epoch 3 - iter 174/292 - loss 0.10295479 - time (sec): 7.85 - samples/sec: 3267.84 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 21:23:27,043 epoch 3 - iter 203/292 - loss 0.09578494 - time (sec): 9.13 - samples/sec: 3300.02 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-25 21:23:28,435 epoch 3 - iter 232/292 - loss 0.09515875 - time (sec): 10.52 - samples/sec: 3296.33 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-25 21:23:29,808 epoch 3 - iter 261/292 - loss 0.09502063 - time (sec): 11.90 - samples/sec: 3318.84 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-25 21:23:31,136 epoch 3 - iter 290/292 - loss 0.09090155 - time (sec): 13.22 - samples/sec: 3350.86 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-25 21:23:31,223 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:23:31,223 EPOCH 3 done: loss 0.0908 - lr: 0.000039
120
+ 2023-10-25 21:23:32,135 DEV : loss 0.11771436035633087 - f1-score (micro avg) 0.7456
121
+ 2023-10-25 21:23:32,140 saving best model
122
+ 2023-10-25 21:23:32,814 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:23:34,120 epoch 4 - iter 29/292 - loss 0.04447974 - time (sec): 1.30 - samples/sec: 3415.97 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-25 21:23:35,447 epoch 4 - iter 58/292 - loss 0.05748043 - time (sec): 2.63 - samples/sec: 3591.72 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-25 21:23:36,803 epoch 4 - iter 87/292 - loss 0.05839321 - time (sec): 3.99 - samples/sec: 3601.72 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-25 21:23:38,071 epoch 4 - iter 116/292 - loss 0.05373818 - time (sec): 5.25 - samples/sec: 3569.23 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-25 21:23:39,367 epoch 4 - iter 145/292 - loss 0.06079832 - time (sec): 6.55 - samples/sec: 3529.73 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-25 21:23:40,548 epoch 4 - iter 174/292 - loss 0.05840615 - time (sec): 7.73 - samples/sec: 3460.91 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-25 21:23:41,735 epoch 4 - iter 203/292 - loss 0.05922118 - time (sec): 8.92 - samples/sec: 3457.73 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-25 21:23:43,026 epoch 4 - iter 232/292 - loss 0.05817814 - time (sec): 10.21 - samples/sec: 3490.62 - lr: 0.000035 - momentum: 0.000000
131
+ 2023-10-25 21:23:44,270 epoch 4 - iter 261/292 - loss 0.05811754 - time (sec): 11.45 - samples/sec: 3463.49 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-25 21:23:45,618 epoch 4 - iter 290/292 - loss 0.05637850 - time (sec): 12.80 - samples/sec: 3456.42 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-25 21:23:45,698 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:23:45,698 EPOCH 4 done: loss 0.0563 - lr: 0.000033
135
+ 2023-10-25 21:23:46,613 DEV : loss 0.16891229152679443 - f1-score (micro avg) 0.7172
136
+ 2023-10-25 21:23:46,618 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-25 21:23:48,047 epoch 5 - iter 29/292 - loss 0.01793138 - time (sec): 1.43 - samples/sec: 3282.09 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-25 21:23:49,387 epoch 5 - iter 58/292 - loss 0.03776489 - time (sec): 2.77 - samples/sec: 3374.60 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-25 21:23:50,675 epoch 5 - iter 87/292 - loss 0.03871292 - time (sec): 4.06 - samples/sec: 3416.95 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-25 21:23:51,995 epoch 5 - iter 116/292 - loss 0.03671836 - time (sec): 5.38 - samples/sec: 3461.52 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-25 21:23:53,267 epoch 5 - iter 145/292 - loss 0.03345817 - time (sec): 6.65 - samples/sec: 3532.80 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-25 21:23:54,488 epoch 5 - iter 174/292 - loss 0.03604099 - time (sec): 7.87 - samples/sec: 3450.29 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-25 21:23:55,717 epoch 5 - iter 203/292 - loss 0.03563773 - time (sec): 9.10 - samples/sec: 3475.36 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-25 21:23:56,883 epoch 5 - iter 232/292 - loss 0.03978405 - time (sec): 10.26 - samples/sec: 3450.93 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-25 21:23:58,127 epoch 5 - iter 261/292 - loss 0.03922902 - time (sec): 11.51 - samples/sec: 3449.17 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-25 21:23:59,426 epoch 5 - iter 290/292 - loss 0.04000375 - time (sec): 12.81 - samples/sec: 3454.07 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-25 21:23:59,515 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-25 21:23:59,515 EPOCH 5 done: loss 0.0398 - lr: 0.000028
149
+ 2023-10-25 21:24:00,428 DEV : loss 0.12579147517681122 - f1-score (micro avg) 0.7352
150
+ 2023-10-25 21:24:00,433 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-25 21:24:01,711 epoch 6 - iter 29/292 - loss 0.02611874 - time (sec): 1.28 - samples/sec: 3400.46 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-25 21:24:02,992 epoch 6 - iter 58/292 - loss 0.03086291 - time (sec): 2.56 - samples/sec: 3281.23 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-25 21:24:04,290 epoch 6 - iter 87/292 - loss 0.02541001 - time (sec): 3.86 - samples/sec: 3282.22 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-25 21:24:05,568 epoch 6 - iter 116/292 - loss 0.02774603 - time (sec): 5.13 - samples/sec: 3237.20 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-25 21:24:06,856 epoch 6 - iter 145/292 - loss 0.02771761 - time (sec): 6.42 - samples/sec: 3299.67 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-25 21:24:08,149 epoch 6 - iter 174/292 - loss 0.02765889 - time (sec): 7.71 - samples/sec: 3353.44 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-25 21:24:09,408 epoch 6 - iter 203/292 - loss 0.02925281 - time (sec): 8.97 - samples/sec: 3370.19 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-25 21:24:10,826 epoch 6 - iter 232/292 - loss 0.02864905 - time (sec): 10.39 - samples/sec: 3431.12 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-25 21:24:12,058 epoch 6 - iter 261/292 - loss 0.02763788 - time (sec): 11.62 - samples/sec: 3413.92 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-25 21:24:13,367 epoch 6 - iter 290/292 - loss 0.02581966 - time (sec): 12.93 - samples/sec: 3424.87 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-25 21:24:13,446 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-25 21:24:13,446 EPOCH 6 done: loss 0.0257 - lr: 0.000022
163
+ 2023-10-25 21:24:14,365 DEV : loss 0.1791224181652069 - f1-score (micro avg) 0.7289
164
+ 2023-10-25 21:24:14,370 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-25 21:24:15,661 epoch 7 - iter 29/292 - loss 0.01525348 - time (sec): 1.29 - samples/sec: 2948.18 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-25 21:24:16,980 epoch 7 - iter 58/292 - loss 0.02610841 - time (sec): 2.61 - samples/sec: 3107.31 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-25 21:24:18,373 epoch 7 - iter 87/292 - loss 0.02233332 - time (sec): 4.00 - samples/sec: 3326.21 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-25 21:24:19,793 epoch 7 - iter 116/292 - loss 0.01975879 - time (sec): 5.42 - samples/sec: 3136.62 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-25 21:24:21,105 epoch 7 - iter 145/292 - loss 0.02079285 - time (sec): 6.73 - samples/sec: 3140.38 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-25 21:24:22,435 epoch 7 - iter 174/292 - loss 0.01893185 - time (sec): 8.06 - samples/sec: 3231.57 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-25 21:24:23,760 epoch 7 - iter 203/292 - loss 0.01874262 - time (sec): 9.39 - samples/sec: 3280.58 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-25 21:24:25,035 epoch 7 - iter 232/292 - loss 0.01913688 - time (sec): 10.66 - samples/sec: 3308.42 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-25 21:24:26,341 epoch 7 - iter 261/292 - loss 0.01811495 - time (sec): 11.97 - samples/sec: 3278.83 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-25 21:24:27,679 epoch 7 - iter 290/292 - loss 0.01871243 - time (sec): 13.31 - samples/sec: 3314.90 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-25 21:24:27,767 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-25 21:24:27,768 EPOCH 7 done: loss 0.0196 - lr: 0.000017
177
+ 2023-10-25 21:24:28,684 DEV : loss 0.18422643840312958 - f1-score (micro avg) 0.6875
178
+ 2023-10-25 21:24:28,688 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-25 21:24:29,929 epoch 8 - iter 29/292 - loss 0.00351023 - time (sec): 1.24 - samples/sec: 3412.68 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-25 21:24:31,209 epoch 8 - iter 58/292 - loss 0.00912950 - time (sec): 2.52 - samples/sec: 3786.95 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-25 21:24:32,409 epoch 8 - iter 87/292 - loss 0.00811109 - time (sec): 3.72 - samples/sec: 3672.28 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-25 21:24:33,594 epoch 8 - iter 116/292 - loss 0.00685205 - time (sec): 4.90 - samples/sec: 3593.20 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-25 21:24:34,855 epoch 8 - iter 145/292 - loss 0.00786036 - time (sec): 6.17 - samples/sec: 3596.15 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-25 21:24:36,191 epoch 8 - iter 174/292 - loss 0.01019612 - time (sec): 7.50 - samples/sec: 3593.87 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-25 21:24:37,508 epoch 8 - iter 203/292 - loss 0.00968103 - time (sec): 8.82 - samples/sec: 3519.18 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-25 21:24:38,796 epoch 8 - iter 232/292 - loss 0.00998358 - time (sec): 10.11 - samples/sec: 3443.22 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-25 21:24:40,122 epoch 8 - iter 261/292 - loss 0.00986264 - time (sec): 11.43 - samples/sec: 3449.32 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-25 21:24:41,512 epoch 8 - iter 290/292 - loss 0.01018475 - time (sec): 12.82 - samples/sec: 3452.18 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-25 21:24:41,591 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-25 21:24:41,591 EPOCH 8 done: loss 0.0104 - lr: 0.000011
191
+ 2023-10-25 21:24:42,498 DEV : loss 0.19869066774845123 - f1-score (micro avg) 0.7532
192
+ 2023-10-25 21:24:42,503 saving best model
193
+ 2023-10-25 21:24:43,185 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-25 21:24:44,510 epoch 9 - iter 29/292 - loss 0.00300745 - time (sec): 1.32 - samples/sec: 3463.47 - lr: 0.000011 - momentum: 0.000000
195
+ 2023-10-25 21:24:45,815 epoch 9 - iter 58/292 - loss 0.00560549 - time (sec): 2.63 - samples/sec: 3327.56 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-25 21:24:47,124 epoch 9 - iter 87/292 - loss 0.00597532 - time (sec): 3.94 - samples/sec: 3373.84 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-25 21:24:48,472 epoch 9 - iter 116/292 - loss 0.00660099 - time (sec): 5.28 - samples/sec: 3450.68 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-25 21:24:49,731 epoch 9 - iter 145/292 - loss 0.00583953 - time (sec): 6.54 - samples/sec: 3382.80 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-25 21:24:51,039 epoch 9 - iter 174/292 - loss 0.00673963 - time (sec): 7.85 - samples/sec: 3371.39 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-25 21:24:52,313 epoch 9 - iter 203/292 - loss 0.00632106 - time (sec): 9.13 - samples/sec: 3357.34 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-25 21:24:53,579 epoch 9 - iter 232/292 - loss 0.00585454 - time (sec): 10.39 - samples/sec: 3307.81 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-25 21:24:54,953 epoch 9 - iter 261/292 - loss 0.00520285 - time (sec): 11.77 - samples/sec: 3336.98 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-25 21:24:56,314 epoch 9 - iter 290/292 - loss 0.00729847 - time (sec): 13.13 - samples/sec: 3355.06 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-25 21:24:56,404 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-25 21:24:56,404 EPOCH 9 done: loss 0.0072 - lr: 0.000006
206
+ 2023-10-25 21:24:57,331 DEV : loss 0.207131028175354 - f1-score (micro avg) 0.7122
207
+ 2023-10-25 21:24:57,336 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-25 21:24:58,656 epoch 10 - iter 29/292 - loss 0.00724381 - time (sec): 1.32 - samples/sec: 3476.36 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-25 21:24:59,897 epoch 10 - iter 58/292 - loss 0.00640674 - time (sec): 2.56 - samples/sec: 3323.92 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-25 21:25:01,158 epoch 10 - iter 87/292 - loss 0.00503092 - time (sec): 3.82 - samples/sec: 3221.06 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-25 21:25:02,538 epoch 10 - iter 116/292 - loss 0.00775827 - time (sec): 5.20 - samples/sec: 3346.98 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-25 21:25:03,822 epoch 10 - iter 145/292 - loss 0.00633399 - time (sec): 6.48 - samples/sec: 3367.76 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-25 21:25:05,151 epoch 10 - iter 174/292 - loss 0.00539255 - time (sec): 7.81 - samples/sec: 3425.52 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 21:25:06,458 epoch 10 - iter 203/292 - loss 0.00516222 - time (sec): 9.12 - samples/sec: 3487.33 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-25 21:25:07,712 epoch 10 - iter 232/292 - loss 0.00511528 - time (sec): 10.38 - samples/sec: 3432.05 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-25 21:25:09,027 epoch 10 - iter 261/292 - loss 0.00467370 - time (sec): 11.69 - samples/sec: 3408.74 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 21:25:10,287 epoch 10 - iter 290/292 - loss 0.00471642 - time (sec): 12.95 - samples/sec: 3410.43 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-25 21:25:10,370 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-25 21:25:10,370 EPOCH 10 done: loss 0.0047 - lr: 0.000000
220
+ 2023-10-25 21:25:11,373 DEV : loss 0.20934493839740753 - f1-score (micro avg) 0.7235
221
+ 2023-10-25 21:25:11,898 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-25 21:25:11,899 Loading model from best epoch ...
223
+ 2023-10-25 21:25:13,646 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
224
+ 2023-10-25 21:25:15,364
225
+ Results:
226
+ - F-score (micro) 0.7502
227
+ - F-score (macro) 0.6687
228
+ - Accuracy 0.6236
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ PER 0.7936 0.8506 0.8211 348
234
+ LOC 0.6594 0.8084 0.7263 261
235
+ ORG 0.4038 0.4038 0.4038 52
236
+ HumanProd 0.6800 0.7727 0.7234 22
237
+
238
+ micro avg 0.7078 0.7980 0.7502 683
239
+ macro avg 0.6342 0.7089 0.6687 683
240
+ weighted avg 0.7090 0.7980 0.7500 683
241
+
242
+ 2023-10-25 21:25:15,364 ----------------------------------------------------------------------------------------------------