Hugging Face's logo

stefan-it
/
hmbench-newseye-sv-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
Swedish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
f84ec95
•
1 Parent(s): 693c77b

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 21:05:32,624 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:05:32,625 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 21:05:32,625 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:05:32,625 MultiCorpus: 1085 train + 148 dev + 364 test sentences
52
+ - NER_HIPE_2022 Corpus: 1085 train + 148 dev + 364 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/sv/with_doc_seperator
53
+ 2023-10-25 21:05:32,625 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:05:32,625 Train: 1085 sentences
55
+ 2023-10-25 21:05:32,625 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:05:32,625 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:05:32,625 Training Params:
58
+ 2023-10-25 21:05:32,625 - learning_rate: "5e-05"
59
+ 2023-10-25 21:05:32,625 - mini_batch_size: "4"
60
+ 2023-10-25 21:05:32,625 - max_epochs: "10"
61
+ 2023-10-25 21:05:32,625 - shuffle: "True"
62
+ 2023-10-25 21:05:32,625 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:05:32,625 Plugins:
64
+ 2023-10-25 21:05:32,625 - TensorboardLogger
65
+ 2023-10-25 21:05:32,625 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:05:32,625 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:05:32,625 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:05:32,625 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:05:32,625 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:05:32,625 Computation:
71
+ 2023-10-25 21:05:32,625 - compute on device: cuda:0
72
+ 2023-10-25 21:05:32,625 - embedding storage: none
73
+ 2023-10-25 21:05:32,626 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:05:32,626 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-25 21:05:32,626 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:05:32,626 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:05:32,626 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:05:34,162 epoch 1 - iter 27/272 - loss 2.73607380 - time (sec): 1.54 - samples/sec: 3350.45 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-25 21:05:35,786 epoch 1 - iter 54/272 - loss 1.84896315 - time (sec): 3.16 - samples/sec: 3383.35 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-25 21:05:37,361 epoch 1 - iter 81/272 - loss 1.37269521 - time (sec): 4.73 - samples/sec: 3351.43 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-25 21:05:38,976 epoch 1 - iter 108/272 - loss 1.10859483 - time (sec): 6.35 - samples/sec: 3413.69 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-25 21:05:40,561 epoch 1 - iter 135/272 - loss 0.95656040 - time (sec): 7.93 - samples/sec: 3364.00 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-25 21:05:42,187 epoch 1 - iter 162/272 - loss 0.83486853 - time (sec): 9.56 - samples/sec: 3338.14 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-25 21:05:43,828 epoch 1 - iter 189/272 - loss 0.73760380 - time (sec): 11.20 - samples/sec: 3341.22 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-25 21:05:45,392 epoch 1 - iter 216/272 - loss 0.67349066 - time (sec): 12.77 - samples/sec: 3329.37 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-25 21:05:46,811 epoch 1 - iter 243/272 - loss 0.63006514 - time (sec): 14.18 - samples/sec: 3314.75 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-25 21:05:48,248 epoch 1 - iter 270/272 - loss 0.58984536 - time (sec): 15.62 - samples/sec: 3318.65 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-25 21:05:48,340 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:05:48,340 EPOCH 1 done: loss 0.5882 - lr: 0.000049
90
+ 2023-10-25 21:05:49,100 DEV : loss 0.13279995322227478 - f1-score (micro avg) 0.6869
91
+ 2023-10-25 21:05:49,109 saving best model
92
+ 2023-10-25 21:05:49,629 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:05:50,990 epoch 2 - iter 27/272 - loss 0.16014777 - time (sec): 1.36 - samples/sec: 3565.41 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-25 21:05:52,395 epoch 2 - iter 54/272 - loss 0.14356362 - time (sec): 2.76 - samples/sec: 3582.12 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 21:05:53,853 epoch 2 - iter 81/272 - loss 0.14683167 - time (sec): 4.22 - samples/sec: 3572.70 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 21:05:55,348 epoch 2 - iter 108/272 - loss 0.14493448 - time (sec): 5.72 - samples/sec: 3574.26 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 21:05:56,817 epoch 2 - iter 135/272 - loss 0.14341750 - time (sec): 7.19 - samples/sec: 3607.07 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 21:05:58,276 epoch 2 - iter 162/272 - loss 0.13309816 - time (sec): 8.65 - samples/sec: 3590.36 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 21:05:59,691 epoch 2 - iter 189/272 - loss 0.13345670 - time (sec): 10.06 - samples/sec: 3575.57 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 21:06:01,102 epoch 2 - iter 216/272 - loss 0.12800000 - time (sec): 11.47 - samples/sec: 3563.37 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 21:06:02,569 epoch 2 - iter 243/272 - loss 0.12507971 - time (sec): 12.94 - samples/sec: 3603.58 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 21:06:03,956 epoch 2 - iter 270/272 - loss 0.12227685 - time (sec): 14.33 - samples/sec: 3615.14 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-25 21:06:04,048 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:06:04,049 EPOCH 2 done: loss 0.1240 - lr: 0.000045
105
+ 2023-10-25 21:06:05,740 DEV : loss 0.11688721925020218 - f1-score (micro avg) 0.7738
106
+ 2023-10-25 21:06:05,750 saving best model
107
+ 2023-10-25 21:06:06,490 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:06:07,926 epoch 3 - iter 27/272 - loss 0.05272744 - time (sec): 1.43 - samples/sec: 3684.31 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-25 21:06:09,417 epoch 3 - iter 54/272 - loss 0.06315361 - time (sec): 2.92 - samples/sec: 3609.68 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 21:06:10,876 epoch 3 - iter 81/272 - loss 0.06829449 - time (sec): 4.38 - samples/sec: 3616.16 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-25 21:06:12,390 epoch 3 - iter 108/272 - loss 0.07194428 - time (sec): 5.90 - samples/sec: 3559.81 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 21:06:13,842 epoch 3 - iter 135/272 - loss 0.07458317 - time (sec): 7.35 - samples/sec: 3480.29 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-25 21:06:15,350 epoch 3 - iter 162/272 - loss 0.07504227 - time (sec): 8.86 - samples/sec: 3434.72 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 21:06:16,845 epoch 3 - iter 189/272 - loss 0.07582093 - time (sec): 10.35 - samples/sec: 3415.59 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-25 21:06:18,396 epoch 3 - iter 216/272 - loss 0.07747465 - time (sec): 11.90 - samples/sec: 3445.16 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-25 21:06:19,917 epoch 3 - iter 243/272 - loss 0.07480487 - time (sec): 13.42 - samples/sec: 3420.94 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-25 21:06:21,418 epoch 3 - iter 270/272 - loss 0.07056925 - time (sec): 14.93 - samples/sec: 3458.13 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-25 21:06:21,550 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:06:21,550 EPOCH 3 done: loss 0.0709 - lr: 0.000039
120
+ 2023-10-25 21:06:22,770 DEV : loss 0.11765002459287643 - f1-score (micro avg) 0.7812
121
+ 2023-10-25 21:06:22,777 saving best model
122
+ 2023-10-25 21:06:23,502 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:06:25,013 epoch 4 - iter 27/272 - loss 0.06309874 - time (sec): 1.51 - samples/sec: 3903.99 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-25 21:06:26,492 epoch 4 - iter 54/272 - loss 0.05289798 - time (sec): 2.99 - samples/sec: 3515.76 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-25 21:06:28,004 epoch 4 - iter 81/272 - loss 0.04365696 - time (sec): 4.50 - samples/sec: 3405.93 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-25 21:06:29,539 epoch 4 - iter 108/272 - loss 0.03848979 - time (sec): 6.04 - samples/sec: 3480.18 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-25 21:06:31,122 epoch 4 - iter 135/272 - loss 0.04217353 - time (sec): 7.62 - samples/sec: 3449.76 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-25 21:06:32,608 epoch 4 - iter 162/272 - loss 0.04215972 - time (sec): 9.10 - samples/sec: 3391.67 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-25 21:06:34,094 epoch 4 - iter 189/272 - loss 0.04333349 - time (sec): 10.59 - samples/sec: 3427.56 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-25 21:06:35,607 epoch 4 - iter 216/272 - loss 0.04312284 - time (sec): 12.10 - samples/sec: 3392.55 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-25 21:06:37,160 epoch 4 - iter 243/272 - loss 0.04177106 - time (sec): 13.66 - samples/sec: 3420.69 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-25 21:06:38,661 epoch 4 - iter 270/272 - loss 0.04273552 - time (sec): 15.16 - samples/sec: 3398.72 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-25 21:06:38,769 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:06:38,769 EPOCH 4 done: loss 0.0429 - lr: 0.000033
135
+ 2023-10-25 21:06:39,974 DEV : loss 0.14461365342140198 - f1-score (micro avg) 0.7817
136
+ 2023-10-25 21:06:39,982 saving best model
137
+ 2023-10-25 21:06:40,659 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:06:42,161 epoch 5 - iter 27/272 - loss 0.03578132 - time (sec): 1.50 - samples/sec: 2946.96 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-25 21:06:43,729 epoch 5 - iter 54/272 - loss 0.03982125 - time (sec): 3.07 - samples/sec: 3388.05 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-25 21:06:45,201 epoch 5 - iter 81/272 - loss 0.04578774 - time (sec): 4.54 - samples/sec: 3182.37 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-25 21:06:46,722 epoch 5 - iter 108/272 - loss 0.03957806 - time (sec): 6.06 - samples/sec: 3235.40 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-25 21:06:48,179 epoch 5 - iter 135/272 - loss 0.03548740 - time (sec): 7.52 - samples/sec: 3194.94 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-25 21:06:49,746 epoch 5 - iter 162/272 - loss 0.03664451 - time (sec): 9.08 - samples/sec: 3246.35 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-25 21:06:51,313 epoch 5 - iter 189/272 - loss 0.03629779 - time (sec): 10.65 - samples/sec: 3276.18 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-25 21:06:52,866 epoch 5 - iter 216/272 - loss 0.03416917 - time (sec): 12.20 - samples/sec: 3298.02 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-25 21:06:54,354 epoch 5 - iter 243/272 - loss 0.03457437 - time (sec): 13.69 - samples/sec: 3311.03 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-25 21:06:55,840 epoch 5 - iter 270/272 - loss 0.03329317 - time (sec): 15.18 - samples/sec: 3405.57 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-25 21:06:55,935 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:06:55,935 EPOCH 5 done: loss 0.0332 - lr: 0.000028
150
+ 2023-10-25 21:06:57,114 DEV : loss 0.15152905881404877 - f1-score (micro avg) 0.7956
151
+ 2023-10-25 21:06:57,121 saving best model
152
+ 2023-10-25 21:06:57,844 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-25 21:06:59,315 epoch 6 - iter 27/272 - loss 0.02662659 - time (sec): 1.47 - samples/sec: 3739.49 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-25 21:07:01,237 epoch 6 - iter 54/272 - loss 0.02520854 - time (sec): 3.39 - samples/sec: 3147.08 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-25 21:07:02,760 epoch 6 - iter 81/272 - loss 0.02763396 - time (sec): 4.91 - samples/sec: 3276.21 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-25 21:07:04,284 epoch 6 - iter 108/272 - loss 0.02306852 - time (sec): 6.44 - samples/sec: 3290.51 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-25 21:07:05,826 epoch 6 - iter 135/272 - loss 0.02493619 - time (sec): 7.98 - samples/sec: 3360.42 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-25 21:07:07,346 epoch 6 - iter 162/272 - loss 0.02506762 - time (sec): 9.50 - samples/sec: 3355.79 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-25 21:07:08,822 epoch 6 - iter 189/272 - loss 0.02389920 - time (sec): 10.97 - samples/sec: 3399.74 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-25 21:07:10,291 epoch 6 - iter 216/272 - loss 0.02348636 - time (sec): 12.44 - samples/sec: 3400.09 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-25 21:07:11,766 epoch 6 - iter 243/272 - loss 0.02385580 - time (sec): 13.92 - samples/sec: 3412.25 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-25 21:07:13,222 epoch 6 - iter 270/272 - loss 0.02429412 - time (sec): 15.37 - samples/sec: 3368.14 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-25 21:07:13,322 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-25 21:07:13,323 EPOCH 6 done: loss 0.0244 - lr: 0.000022
165
+ 2023-10-25 21:07:14,531 DEV : loss 0.18444250524044037 - f1-score (micro avg) 0.7963
166
+ 2023-10-25 21:07:14,540 saving best model
167
+ 2023-10-25 21:07:15,252 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-25 21:07:16,718 epoch 7 - iter 27/272 - loss 0.01815834 - time (sec): 1.46 - samples/sec: 3493.39 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-25 21:07:18,161 epoch 7 - iter 54/272 - loss 0.01737148 - time (sec): 2.91 - samples/sec: 3410.74 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-25 21:07:19,666 epoch 7 - iter 81/272 - loss 0.01790111 - time (sec): 4.41 - samples/sec: 3587.60 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-25 21:07:21,195 epoch 7 - iter 108/272 - loss 0.01703003 - time (sec): 5.94 - samples/sec: 3629.33 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-25 21:07:22,744 epoch 7 - iter 135/272 - loss 0.01648317 - time (sec): 7.49 - samples/sec: 3656.34 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-25 21:07:24,329 epoch 7 - iter 162/272 - loss 0.01658498 - time (sec): 9.08 - samples/sec: 3607.73 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-25 21:07:25,916 epoch 7 - iter 189/272 - loss 0.01502441 - time (sec): 10.66 - samples/sec: 3532.25 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-25 21:07:27,504 epoch 7 - iter 216/272 - loss 0.01519647 - time (sec): 12.25 - samples/sec: 3545.79 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-25 21:07:28,965 epoch 7 - iter 243/272 - loss 0.01481267 - time (sec): 13.71 - samples/sec: 3443.69 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-25 21:07:30,440 epoch 7 - iter 270/272 - loss 0.01479507 - time (sec): 15.19 - samples/sec: 3401.04 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-25 21:07:30,542 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-25 21:07:30,542 EPOCH 7 done: loss 0.0151 - lr: 0.000017
180
+ 2023-10-25 21:07:31,893 DEV : loss 0.18188118934631348 - f1-score (micro avg) 0.7927
181
+ 2023-10-25 21:07:31,901 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-25 21:07:33,374 epoch 8 - iter 27/272 - loss 0.01173756 - time (sec): 1.47 - samples/sec: 4062.71 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-25 21:07:34,856 epoch 8 - iter 54/272 - loss 0.01144365 - time (sec): 2.95 - samples/sec: 3968.39 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-25 21:07:36,354 epoch 8 - iter 81/272 - loss 0.01050122 - time (sec): 4.45 - samples/sec: 3641.66 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-25 21:07:37,856 epoch 8 - iter 108/272 - loss 0.00954095 - time (sec): 5.95 - samples/sec: 3611.45 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-25 21:07:39,419 epoch 8 - iter 135/272 - loss 0.00867344 - time (sec): 7.52 - samples/sec: 3549.08 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-25 21:07:40,932 epoch 8 - iter 162/272 - loss 0.00912422 - time (sec): 9.03 - samples/sec: 3482.29 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-25 21:07:42,439 epoch 8 - iter 189/272 - loss 0.00858298 - time (sec): 10.54 - samples/sec: 3441.14 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-25 21:07:43,956 epoch 8 - iter 216/272 - loss 0.00857042 - time (sec): 12.05 - samples/sec: 3459.67 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-25 21:07:45,546 epoch 8 - iter 243/272 - loss 0.00832379 - time (sec): 13.64 - samples/sec: 3461.18 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-25 21:07:47,010 epoch 8 - iter 270/272 - loss 0.00849181 - time (sec): 15.11 - samples/sec: 3423.99 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-25 21:07:47,113 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-25 21:07:47,114 EPOCH 8 done: loss 0.0085 - lr: 0.000011
194
+ 2023-10-25 21:07:48,321 DEV : loss 0.17987406253814697 - f1-score (micro avg) 0.8066
195
+ 2023-10-25 21:07:48,328 saving best model
196
+ 2023-10-25 21:07:49,042 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-25 21:07:50,558 epoch 9 - iter 27/272 - loss 0.00059481 - time (sec): 1.51 - samples/sec: 3896.57 - lr: 0.000011 - momentum: 0.000000
198
+ 2023-10-25 21:07:52,032 epoch 9 - iter 54/272 - loss 0.00437637 - time (sec): 2.99 - samples/sec: 3442.08 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-25 21:07:53,621 epoch 9 - iter 81/272 - loss 0.00449556 - time (sec): 4.58 - samples/sec: 3517.08 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-25 21:07:55,148 epoch 9 - iter 108/272 - loss 0.00672091 - time (sec): 6.10 - samples/sec: 3507.96 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-25 21:07:56,692 epoch 9 - iter 135/272 - loss 0.00680104 - time (sec): 7.65 - samples/sec: 3455.22 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-25 21:07:58,219 epoch 9 - iter 162/272 - loss 0.00656457 - time (sec): 9.17 - samples/sec: 3439.60 - lr: 0.000008 - momentum: 0.000000
203
+ 2023-10-25 21:07:59,678 epoch 9 - iter 189/272 - loss 0.00653987 - time (sec): 10.63 - samples/sec: 3390.09 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-25 21:08:01,096 epoch 9 - iter 216/272 - loss 0.00686872 - time (sec): 12.05 - samples/sec: 3379.14 - lr: 0.000007 - momentum: 0.000000
205
+ 2023-10-25 21:08:02,916 epoch 9 - iter 243/272 - loss 0.00643747 - time (sec): 13.87 - samples/sec: 3356.97 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-25 21:08:04,356 epoch 9 - iter 270/272 - loss 0.00654410 - time (sec): 15.31 - samples/sec: 3368.70 - lr: 0.000006 - momentum: 0.000000
207
+ 2023-10-25 21:08:04,457 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-25 21:08:04,458 EPOCH 9 done: loss 0.0065 - lr: 0.000006
209
+ 2023-10-25 21:08:05,753 DEV : loss 0.19414767622947693 - f1-score (micro avg) 0.7883
210
+ 2023-10-25 21:08:05,762 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-25 21:08:07,206 epoch 10 - iter 27/272 - loss 0.00949480 - time (sec): 1.44 - samples/sec: 3040.73 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-25 21:08:08,729 epoch 10 - iter 54/272 - loss 0.00586201 - time (sec): 2.97 - samples/sec: 3077.41 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-25 21:08:10,230 epoch 10 - iter 81/272 - loss 0.00514860 - time (sec): 4.47 - samples/sec: 3137.90 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-25 21:08:11,771 epoch 10 - iter 108/272 - loss 0.00510123 - time (sec): 6.01 - samples/sec: 3259.80 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-25 21:08:13,329 epoch 10 - iter 135/272 - loss 0.00443539 - time (sec): 7.57 - samples/sec: 3352.04 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-25 21:08:14,883 epoch 10 - iter 162/272 - loss 0.00394396 - time (sec): 9.12 - samples/sec: 3329.12 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-25 21:08:16,414 epoch 10 - iter 189/272 - loss 0.00341668 - time (sec): 10.65 - samples/sec: 3309.64 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-25 21:08:17,913 epoch 10 - iter 216/272 - loss 0.00373493 - time (sec): 12.15 - samples/sec: 3380.68 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-25 21:08:19,424 epoch 10 - iter 243/272 - loss 0.00455730 - time (sec): 13.66 - samples/sec: 3379.38 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-25 21:08:20,883 epoch 10 - iter 270/272 - loss 0.00439589 - time (sec): 15.12 - samples/sec: 3427.85 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-25 21:08:20,975 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-25 21:08:20,976 EPOCH 10 done: loss 0.0044 - lr: 0.000000
223
+ 2023-10-25 21:08:22,205 DEV : loss 0.19060413539409637 - f1-score (micro avg) 0.7905
224
+ 2023-10-25 21:08:22,747 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-25 21:08:22,749 Loading model from best epoch ...
226
+ 2023-10-25 21:08:24,708 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd, S-ORG, B-ORG, E-ORG, I-ORG
227
+ 2023-10-25 21:08:26,730
228
+ Results:
229
+ - F-score (micro) 0.7882
230
+ - F-score (macro) 0.7203
231
+ - Accuracy 0.6653
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.8411 0.8654 0.8531 312
237
+ PER 0.7206 0.8558 0.7824 208
238
+ ORG 0.4355 0.4909 0.4615 55
239
+ HumanProd 0.6897 0.9091 0.7843 22
240
+
241
+ micro avg 0.7511 0.8291 0.7882 597
242
+ macro avg 0.6717 0.7803 0.7203 597
243
+ weighted avg 0.7562 0.8291 0.7899 597
244
+
245
+ 2023-10-25 21:08:26,730 ----------------------------------------------------------------------------------------------------