Hugging Face's logo

stefan-it
/
hmbench-newseye-sv-hmbert_64k-bs4-wsFalse-e10-lr3e-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
df77d27
•
1 Parent(s): e16a1fc

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 21:02:12,929 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:02:12,930 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 21:02:12,930 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:02:12,930 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 21:02:12,930 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:02:12,930 Train: 1085 sentences
55
+ 2023-10-25 21:02:12,930 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:02:12,930 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:02:12,931 Training Params:
58
+ 2023-10-25 21:02:12,931 - learning_rate: "3e-05"
59
+ 2023-10-25 21:02:12,931 - mini_batch_size: "4"
60
+ 2023-10-25 21:02:12,931 - max_epochs: "10"
61
+ 2023-10-25 21:02:12,931 - shuffle: "True"
62
+ 2023-10-25 21:02:12,931 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:02:12,931 Plugins:
64
+ 2023-10-25 21:02:12,931 - TensorboardLogger
65
+ 2023-10-25 21:02:12,931 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:02:12,931 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:02:12,931 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:02:12,931 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:02:12,931 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:02:12,931 Computation:
71
+ 2023-10-25 21:02:12,931 - compute on device: cuda:0
72
+ 2023-10-25 21:02:12,931 - embedding storage: none
73
+ 2023-10-25 21:02:12,931 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:02:12,931 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-25 21:02:12,931 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:02:12,931 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:02:12,931 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:02:14,503 epoch 1 - iter 27/272 - loss 2.87919023 - time (sec): 1.57 - samples/sec: 3275.13 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 21:02:16,095 epoch 1 - iter 54/272 - loss 2.21963696 - time (sec): 3.16 - samples/sec: 3380.08 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 21:02:17,664 epoch 1 - iter 81/272 - loss 1.64921279 - time (sec): 4.73 - samples/sec: 3353.42 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-25 21:02:19,260 epoch 1 - iter 108/272 - loss 1.33307817 - time (sec): 6.33 - samples/sec: 3425.48 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-25 21:02:20,809 epoch 1 - iter 135/272 - loss 1.15572546 - time (sec): 7.88 - samples/sec: 3388.58 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-25 21:02:22,406 epoch 1 - iter 162/272 - loss 1.01002583 - time (sec): 9.47 - samples/sec: 3368.78 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-25 21:02:23,977 epoch 1 - iter 189/272 - loss 0.89259816 - time (sec): 11.04 - samples/sec: 3388.81 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-25 21:02:25,526 epoch 1 - iter 216/272 - loss 0.81375199 - time (sec): 12.59 - samples/sec: 3374.87 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-25 21:02:26,975 epoch 1 - iter 243/272 - loss 0.75888383 - time (sec): 14.04 - samples/sec: 3348.25 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-25 21:02:28,446 epoch 1 - iter 270/272 - loss 0.70942154 - time (sec): 15.51 - samples/sec: 3341.63 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-25 21:02:28,540 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:02:28,541 EPOCH 1 done: loss 0.7075 - lr: 0.000030
90
+ 2023-10-25 21:02:29,692 DEV : loss 0.15761442482471466 - f1-score (micro avg) 0.6439
91
+ 2023-10-25 21:02:29,702 saving best model
92
+ 2023-10-25 21:02:30,216 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:02:31,704 epoch 2 - iter 27/272 - loss 0.17595089 - time (sec): 1.49 - samples/sec: 3259.34 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 21:02:33,206 epoch 2 - iter 54/272 - loss 0.15919573 - time (sec): 2.99 - samples/sec: 3312.90 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 21:02:34,643 epoch 2 - iter 81/272 - loss 0.15943867 - time (sec): 4.42 - samples/sec: 3408.85 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 21:02:36,202 epoch 2 - iter 108/272 - loss 0.15319579 - time (sec): 5.98 - samples/sec: 3414.65 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 21:02:37,804 epoch 2 - iter 135/272 - loss 0.15029334 - time (sec): 7.59 - samples/sec: 3416.82 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 21:02:39,423 epoch 2 - iter 162/272 - loss 0.14192725 - time (sec): 9.20 - samples/sec: 3372.06 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 21:02:40,981 epoch 2 - iter 189/272 - loss 0.14097129 - time (sec): 10.76 - samples/sec: 3341.97 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 21:02:42,573 epoch 2 - iter 216/272 - loss 0.13630344 - time (sec): 12.36 - samples/sec: 3308.21 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 21:02:44,189 epoch 2 - iter 243/272 - loss 0.13343320 - time (sec): 13.97 - samples/sec: 3337.05 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 21:02:45,741 epoch 2 - iter 270/272 - loss 0.12992319 - time (sec): 15.52 - samples/sec: 3336.25 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 21:02:45,845 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:02:45,845 EPOCH 2 done: loss 0.1314 - lr: 0.000027
105
+ 2023-10-25 21:02:46,993 DEV : loss 0.10909783095121384 - f1-score (micro avg) 0.7844
106
+ 2023-10-25 21:02:46,999 saving best model
107
+ 2023-10-25 21:02:47,820 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:02:49,170 epoch 3 - iter 27/272 - loss 0.06595269 - time (sec): 1.35 - samples/sec: 3922.55 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 21:02:50,566 epoch 3 - iter 54/272 - loss 0.06250690 - time (sec): 2.74 - samples/sec: 3850.02 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 21:02:51,996 epoch 3 - iter 81/272 - loss 0.06055673 - time (sec): 4.17 - samples/sec: 3799.59 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 21:02:53,490 epoch 3 - iter 108/272 - loss 0.06786572 - time (sec): 5.67 - samples/sec: 3705.33 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 21:02:54,961 epoch 3 - iter 135/272 - loss 0.06991093 - time (sec): 7.14 - samples/sec: 3583.88 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 21:02:56,499 epoch 3 - iter 162/272 - loss 0.07228279 - time (sec): 8.67 - samples/sec: 3506.91 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 21:02:58,031 epoch 3 - iter 189/272 - loss 0.08048214 - time (sec): 10.21 - samples/sec: 3464.11 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 21:02:59,619 epoch 3 - iter 216/272 - loss 0.08966991 - time (sec): 11.79 - samples/sec: 3476.65 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 21:03:01,102 epoch 3 - iter 243/272 - loss 0.08674602 - time (sec): 13.28 - samples/sec: 3458.55 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 21:03:02,581 epoch 3 - iter 270/272 - loss 0.08151681 - time (sec): 14.76 - samples/sec: 3497.60 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-25 21:03:02,705 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:03:02,705 EPOCH 3 done: loss 0.0820 - lr: 0.000023
120
+ 2023-10-25 21:03:03,886 DEV : loss 0.11511397361755371 - f1-score (micro avg) 0.7905
121
+ 2023-10-25 21:03:03,892 saving best model
122
+ 2023-10-25 21:03:04,419 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:03:05,861 epoch 4 - iter 27/272 - loss 0.05514955 - time (sec): 1.44 - samples/sec: 4091.83 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 21:03:07,255 epoch 4 - iter 54/272 - loss 0.05253139 - time (sec): 2.83 - samples/sec: 3707.24 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-25 21:03:08,687 epoch 4 - iter 81/272 - loss 0.04688129 - time (sec): 4.27 - samples/sec: 3592.67 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 21:03:10,211 epoch 4 - iter 108/272 - loss 0.04168124 - time (sec): 5.79 - samples/sec: 3627.43 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 21:03:11,807 epoch 4 - iter 135/272 - loss 0.05340026 - time (sec): 7.39 - samples/sec: 3558.06 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-25 21:03:13,348 epoch 4 - iter 162/272 - loss 0.05297633 - time (sec): 8.93 - samples/sec: 3458.96 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 21:03:14,952 epoch 4 - iter 189/272 - loss 0.05246380 - time (sec): 10.53 - samples/sec: 3446.82 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 21:03:16,486 epoch 4 - iter 216/272 - loss 0.05066621 - time (sec): 12.06 - samples/sec: 3403.09 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-25 21:03:18,557 epoch 4 - iter 243/272 - loss 0.05014524 - time (sec): 14.14 - samples/sec: 3304.57 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-25 21:03:20,120 epoch 4 - iter 270/272 - loss 0.04972528 - time (sec): 15.70 - samples/sec: 3281.53 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-25 21:03:20,234 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:03:20,235 EPOCH 4 done: loss 0.0499 - lr: 0.000020
135
+ 2023-10-25 21:03:21,366 DEV : loss 0.11980650573968887 - f1-score (micro avg) 0.8296
136
+ 2023-10-25 21:03:21,372 saving best model
137
+ 2023-10-25 21:03:22,161 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:03:23,687 epoch 5 - iter 27/272 - loss 0.03676313 - time (sec): 1.52 - samples/sec: 2900.24 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-25 21:03:25,283 epoch 5 - iter 54/272 - loss 0.03268754 - time (sec): 3.12 - samples/sec: 3331.32 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 21:03:26,777 epoch 5 - iter 81/272 - loss 0.04226472 - time (sec): 4.61 - samples/sec: 3131.07 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 21:03:28,306 epoch 5 - iter 108/272 - loss 0.03782648 - time (sec): 6.14 - samples/sec: 3192.44 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-25 21:03:29,883 epoch 5 - iter 135/272 - loss 0.03598627 - time (sec): 7.72 - samples/sec: 3111.21 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 21:03:31,497 epoch 5 - iter 162/272 - loss 0.03756257 - time (sec): 9.33 - samples/sec: 3159.82 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 21:03:33,034 epoch 5 - iter 189/272 - loss 0.03380943 - time (sec): 10.87 - samples/sec: 3210.33 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-25 21:03:34,673 epoch 5 - iter 216/272 - loss 0.03483693 - time (sec): 12.51 - samples/sec: 3217.67 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-25 21:03:36,212 epoch 5 - iter 243/272 - loss 0.03499034 - time (sec): 14.05 - samples/sec: 3227.06 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 21:03:37,816 epoch 5 - iter 270/272 - loss 0.03406093 - time (sec): 15.65 - samples/sec: 3302.50 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-25 21:03:37,918 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:03:37,918 EPOCH 5 done: loss 0.0339 - lr: 0.000017
150
+ 2023-10-25 21:03:39,053 DEV : loss 0.14052635431289673 - f1-score (micro avg) 0.7978
151
+ 2023-10-25 21:03:39,061 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-25 21:03:40,614 epoch 6 - iter 27/272 - loss 0.02057250 - time (sec): 1.55 - samples/sec: 3540.09 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-25 21:03:42,091 epoch 6 - iter 54/272 - loss 0.02284458 - time (sec): 3.03 - samples/sec: 3522.62 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 21:03:43,623 epoch 6 - iter 81/272 - loss 0.02523857 - time (sec): 4.56 - samples/sec: 3529.28 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-25 21:03:45,164 epoch 6 - iter 108/272 - loss 0.02438575 - time (sec): 6.10 - samples/sec: 3472.15 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-25 21:03:46,765 epoch 6 - iter 135/272 - loss 0.02417577 - time (sec): 7.70 - samples/sec: 3480.96 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 21:03:48,374 epoch 6 - iter 162/272 - loss 0.02230052 - time (sec): 9.31 - samples/sec: 3423.41 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-25 21:03:49,941 epoch 6 - iter 189/272 - loss 0.02171114 - time (sec): 10.88 - samples/sec: 3429.88 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-25 21:03:51,501 epoch 6 - iter 216/272 - loss 0.02180756 - time (sec): 12.44 - samples/sec: 3401.89 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 21:03:53,056 epoch 6 - iter 243/272 - loss 0.02467375 - time (sec): 13.99 - samples/sec: 3394.02 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-25 21:03:54,577 epoch 6 - iter 270/272 - loss 0.02404132 - time (sec): 15.51 - samples/sec: 3337.83 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-25 21:03:54,683 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 21:03:54,683 EPOCH 6 done: loss 0.0241 - lr: 0.000013
164
+ 2023-10-25 21:03:55,907 DEV : loss 0.18079355359077454 - f1-score (micro avg) 0.7837
165
+ 2023-10-25 21:03:55,916 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-25 21:03:57,423 epoch 7 - iter 27/272 - loss 0.02323336 - time (sec): 1.51 - samples/sec: 3398.22 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-25 21:03:58,985 epoch 7 - iter 54/272 - loss 0.02182723 - time (sec): 3.07 - samples/sec: 3232.35 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-25 21:04:00,477 epoch 7 - iter 81/272 - loss 0.01847419 - time (sec): 4.56 - samples/sec: 3471.43 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-25 21:04:02,065 epoch 7 - iter 108/272 - loss 0.01720781 - time (sec): 6.15 - samples/sec: 3507.88 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-25 21:04:03,678 epoch 7 - iter 135/272 - loss 0.01776059 - time (sec): 7.76 - samples/sec: 3528.75 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-25 21:04:05,202 epoch 7 - iter 162/272 - loss 0.02107932 - time (sec): 9.28 - samples/sec: 3526.34 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-25 21:04:06,709 epoch 7 - iter 189/272 - loss 0.01920136 - time (sec): 10.79 - samples/sec: 3489.78 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-25 21:04:08,341 epoch 7 - iter 216/272 - loss 0.01899765 - time (sec): 12.42 - samples/sec: 3496.34 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-25 21:04:09,831 epoch 7 - iter 243/272 - loss 0.01879286 - time (sec): 13.91 - samples/sec: 3393.48 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-25 21:04:11,305 epoch 7 - iter 270/272 - loss 0.01843357 - time (sec): 15.39 - samples/sec: 3356.66 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-25 21:04:11,415 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-25 21:04:11,416 EPOCH 7 done: loss 0.0188 - lr: 0.000010
178
+ 2023-10-25 21:04:12,682 DEV : loss 0.15969781577587128 - f1-score (micro avg) 0.8305
179
+ 2023-10-25 21:04:12,689 saving best model
180
+ 2023-10-25 21:04:13,973 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-25 21:04:15,512 epoch 8 - iter 27/272 - loss 0.01464099 - time (sec): 1.54 - samples/sec: 3892.95 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-25 21:04:17,057 epoch 8 - iter 54/272 - loss 0.01115447 - time (sec): 3.08 - samples/sec: 3804.70 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-25 21:04:18,556 epoch 8 - iter 81/272 - loss 0.01060002 - time (sec): 4.58 - samples/sec: 3539.69 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-25 21:04:20,061 epoch 8 - iter 108/272 - loss 0.01043073 - time (sec): 6.09 - samples/sec: 3533.46 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-25 21:04:21,636 epoch 8 - iter 135/272 - loss 0.01027025 - time (sec): 7.66 - samples/sec: 3482.52 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-25 21:04:23,132 epoch 8 - iter 162/272 - loss 0.01146835 - time (sec): 9.16 - samples/sec: 3434.44 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-25 21:04:24,628 epoch 8 - iter 189/272 - loss 0.01133446 - time (sec): 10.65 - samples/sec: 3404.02 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-25 21:04:26,193 epoch 8 - iter 216/272 - loss 0.01203709 - time (sec): 12.22 - samples/sec: 3413.26 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-25 21:04:27,820 epoch 8 - iter 243/272 - loss 0.01153724 - time (sec): 13.84 - samples/sec: 3410.96 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-25 21:04:29,331 epoch 8 - iter 270/272 - loss 0.01213084 - time (sec): 15.35 - samples/sec: 3368.92 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-25 21:04:29,438 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-25 21:04:29,439 EPOCH 8 done: loss 0.0121 - lr: 0.000007
193
+ 2023-10-25 21:04:30,581 DEV : loss 0.1854364275932312 - f1-score (micro avg) 0.8066
194
+ 2023-10-25 21:04:30,588 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-25 21:04:32,228 epoch 9 - iter 27/272 - loss 0.00265158 - time (sec): 1.64 - samples/sec: 3595.47 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-25 21:04:33,785 epoch 9 - iter 54/272 - loss 0.00311819 - time (sec): 3.20 - samples/sec: 3216.61 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-25 21:04:35,405 epoch 9 - iter 81/272 - loss 0.00570425 - time (sec): 4.82 - samples/sec: 3341.78 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-25 21:04:37,015 epoch 9 - iter 108/272 - loss 0.00786022 - time (sec): 6.43 - samples/sec: 3331.93 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-25 21:04:38,648 epoch 9 - iter 135/272 - loss 0.00774158 - time (sec): 8.06 - samples/sec: 3278.98 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-25 21:04:40,250 epoch 9 - iter 162/272 - loss 0.00653485 - time (sec): 9.66 - samples/sec: 3266.43 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-25 21:04:41,736 epoch 9 - iter 189/272 - loss 0.00646242 - time (sec): 11.15 - samples/sec: 3233.93 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-25 21:04:43,262 epoch 9 - iter 216/272 - loss 0.00777496 - time (sec): 12.67 - samples/sec: 3213.16 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-25 21:04:44,834 epoch 9 - iter 243/272 - loss 0.00741950 - time (sec): 14.25 - samples/sec: 3268.88 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-25 21:04:46,387 epoch 9 - iter 270/272 - loss 0.00739841 - time (sec): 15.80 - samples/sec: 3264.98 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-25 21:04:46,502 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-25 21:04:46,502 EPOCH 9 done: loss 0.0073 - lr: 0.000003
207
+ 2023-10-25 21:04:47,711 DEV : loss 0.1734946370124817 - f1-score (micro avg) 0.8287
208
+ 2023-10-25 21:04:47,718 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-25 21:04:49,223 epoch 10 - iter 27/272 - loss 0.01618621 - time (sec): 1.50 - samples/sec: 2918.63 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-25 21:04:50,710 epoch 10 - iter 54/272 - loss 0.00960812 - time (sec): 2.99 - samples/sec: 3052.34 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-25 21:04:52,202 epoch 10 - iter 81/272 - loss 0.00757130 - time (sec): 4.48 - samples/sec: 3127.09 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-25 21:04:53,765 epoch 10 - iter 108/272 - loss 0.00746314 - time (sec): 6.04 - samples/sec: 3239.68 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-25 21:04:55,313 epoch 10 - iter 135/272 - loss 0.00634969 - time (sec): 7.59 - samples/sec: 3340.14 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 21:04:56,852 epoch 10 - iter 162/272 - loss 0.00612372 - time (sec): 9.13 - samples/sec: 3324.67 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-25 21:04:58,389 epoch 10 - iter 189/272 - loss 0.00539305 - time (sec): 10.67 - samples/sec: 3303.91 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-25 21:04:59,958 epoch 10 - iter 216/272 - loss 0.00535593 - time (sec): 12.24 - samples/sec: 3355.96 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 21:05:01,476 epoch 10 - iter 243/272 - loss 0.00627154 - time (sec): 13.76 - samples/sec: 3355.88 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-25 21:05:03,068 epoch 10 - iter 270/272 - loss 0.00597542 - time (sec): 15.35 - samples/sec: 3376.78 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-25 21:05:03,174 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-25 21:05:03,175 EPOCH 10 done: loss 0.0062 - lr: 0.000000
221
+ 2023-10-25 21:05:04,336 DEV : loss 0.17761798202991486 - f1-score (micro avg) 0.8287
222
+ 2023-10-25 21:05:04,881 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-25 21:05:04,882 Loading model from best epoch ...
224
+ 2023-10-25 21:05:06,915 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
225
+ 2023-10-25 21:05:09,305
226
+ Results:
227
+ - F-score (micro) 0.7896
228
+ - F-score (macro) 0.7538
229
+ - Accuracy 0.6658
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ LOC 0.8435 0.8462 0.8448 312
235
+ PER 0.7102 0.8365 0.7682 208
236
+ ORG 0.5273 0.5273 0.5273 55
237
+ HumanProd 0.8077 0.9545 0.8750 22
238
+
239
+ micro avg 0.7637 0.8174 0.7896 597
240
+ macro avg 0.7222 0.7911 0.7538 597
241
+ weighted avg 0.7666 0.8174 0.7900 597
242
+
243
+ 2023-10-25 21:05:09,305 ----------------------------------------------------------------------------------------------------