Hugging Face's logo

stefan-it
/
hmbench-newseye-sv-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
Swedish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
dbbe809
·
1 Parent(s): 26ae301

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 21:33:51,878 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:33:51,879 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 21:33:51,879 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:33:51,880 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 21:33:51,880 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:33:51,880 Train: 1085 sentences
55
+ 2023-10-25 21:33:51,880 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:33:51,880 Training Params:
58
+ 2023-10-25 21:33:51,880 - learning_rate: "5e-05"
59
+ 2023-10-25 21:33:51,880 - mini_batch_size: "8"
60
+ 2023-10-25 21:33:51,880 - max_epochs: "10"
61
+ 2023-10-25 21:33:51,880 - shuffle: "True"
62
+ 2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:33:51,880 Plugins:
64
+ 2023-10-25 21:33:51,880 - TensorboardLogger
65
+ 2023-10-25 21:33:51,880 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:33:51,880 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:33:51,880 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:33:51,880 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:33:51,880 Computation:
71
+ 2023-10-25 21:33:51,880 - compute on device: cuda:0
72
+ 2023-10-25 21:33:51,880 - embedding storage: none
73
+ 2023-10-25 21:33:51,881 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:33:51,881 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-25 21:33:51,881 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:33:51,881 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:33:51,881 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:33:52,790 epoch 1 - iter 13/136 - loss 2.59051122 - time (sec): 0.91 - samples/sec: 5504.78 - lr: 0.000004 - momentum: 0.000000
79
+ 2023-10-25 21:33:53,806 epoch 1 - iter 26/136 - loss 2.00418505 - time (sec): 1.92 - samples/sec: 5261.02 - lr: 0.000009 - momentum: 0.000000
80
+ 2023-10-25 21:33:54,806 epoch 1 - iter 39/136 - loss 1.53400120 - time (sec): 2.92 - samples/sec: 5235.21 - lr: 0.000014 - momentum: 0.000000
81
+ 2023-10-25 21:33:55,907 epoch 1 - iter 52/136 - loss 1.25236188 - time (sec): 4.03 - samples/sec: 5213.17 - lr: 0.000019 - momentum: 0.000000
82
+ 2023-10-25 21:33:56,961 epoch 1 - iter 65/136 - loss 1.09370900 - time (sec): 5.08 - samples/sec: 5086.47 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-25 21:33:58,003 epoch 1 - iter 78/136 - loss 0.96770702 - time (sec): 6.12 - samples/sec: 5037.96 - lr: 0.000028 - momentum: 0.000000
84
+ 2023-10-25 21:33:59,051 epoch 1 - iter 91/136 - loss 0.86306761 - time (sec): 7.17 - samples/sec: 5068.05 - lr: 0.000033 - momentum: 0.000000
85
+ 2023-10-25 21:34:00,036 epoch 1 - iter 104/136 - loss 0.78919472 - time (sec): 8.15 - samples/sec: 5034.91 - lr: 0.000038 - momentum: 0.000000
86
+ 2023-10-25 21:34:01,075 epoch 1 - iter 117/136 - loss 0.72503737 - time (sec): 9.19 - samples/sec: 5003.90 - lr: 0.000043 - momentum: 0.000000
87
+ 2023-10-25 21:34:01,983 epoch 1 - iter 130/136 - loss 0.68591323 - time (sec): 10.10 - samples/sec: 4944.79 - lr: 0.000047 - momentum: 0.000000
88
+ 2023-10-25 21:34:02,385 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:34:02,385 EPOCH 1 done: loss 0.6651 - lr: 0.000047
90
+ 2023-10-25 21:34:03,425 DEV : loss 0.12261621654033661 - f1-score (micro avg) 0.7132
91
+ 2023-10-25 21:34:03,431 saving best model
92
+ 2023-10-25 21:34:03,923 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:34:04,893 epoch 2 - iter 13/136 - loss 0.12096013 - time (sec): 0.97 - samples/sec: 5279.05 - lr: 0.000050 - momentum: 0.000000
94
+ 2023-10-25 21:34:05,859 epoch 2 - iter 26/136 - loss 0.13795080 - time (sec): 1.93 - samples/sec: 5464.64 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 21:34:06,909 epoch 2 - iter 39/136 - loss 0.13603380 - time (sec): 2.98 - samples/sec: 4998.10 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 21:34:07,877 epoch 2 - iter 52/136 - loss 0.13411210 - time (sec): 3.95 - samples/sec: 4984.89 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 21:34:08,809 epoch 2 - iter 65/136 - loss 0.12883628 - time (sec): 4.88 - samples/sec: 5023.44 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 21:34:09,762 epoch 2 - iter 78/136 - loss 0.13332562 - time (sec): 5.84 - samples/sec: 5105.30 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 21:34:10,762 epoch 2 - iter 91/136 - loss 0.13183996 - time (sec): 6.84 - samples/sec: 5115.96 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 21:34:11,773 epoch 2 - iter 104/136 - loss 0.13051739 - time (sec): 7.85 - samples/sec: 5030.07 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 21:34:12,740 epoch 2 - iter 117/136 - loss 0.12896418 - time (sec): 8.82 - samples/sec: 5111.03 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 21:34:13,702 epoch 2 - iter 130/136 - loss 0.12638642 - time (sec): 9.78 - samples/sec: 5071.78 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-25 21:34:14,159 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:34:14,159 EPOCH 2 done: loss 0.1251 - lr: 0.000045
105
+ 2023-10-25 21:34:15,382 DEV : loss 0.10230904072523117 - f1-score (micro avg) 0.769
106
+ 2023-10-25 21:34:15,388 saving best model
107
+ 2023-10-25 21:34:16,085 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:34:17,037 epoch 3 - iter 13/136 - loss 0.06535754 - time (sec): 0.95 - samples/sec: 4487.39 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-25 21:34:17,959 epoch 3 - iter 26/136 - loss 0.07728296 - time (sec): 1.87 - samples/sec: 4793.63 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 21:34:19,031 epoch 3 - iter 39/136 - loss 0.06353931 - time (sec): 2.94 - samples/sec: 4846.67 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-25 21:34:19,925 epoch 3 - iter 52/136 - loss 0.06837432 - time (sec): 3.84 - samples/sec: 4968.20 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 21:34:20,989 epoch 3 - iter 65/136 - loss 0.06431996 - time (sec): 4.90 - samples/sec: 4916.87 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-25 21:34:22,022 epoch 3 - iter 78/136 - loss 0.06167304 - time (sec): 5.93 - samples/sec: 5110.38 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 21:34:23,093 epoch 3 - iter 91/136 - loss 0.06277312 - time (sec): 7.01 - samples/sec: 5092.42 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-25 21:34:23,978 epoch 3 - iter 104/136 - loss 0.06304171 - time (sec): 7.89 - samples/sec: 5074.43 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-25 21:34:24,902 epoch 3 - iter 117/136 - loss 0.06234476 - time (sec): 8.81 - samples/sec: 5029.02 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-25 21:34:25,862 epoch 3 - iter 130/136 - loss 0.06152829 - time (sec): 9.77 - samples/sec: 5041.98 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-25 21:34:26,356 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:34:26,357 EPOCH 3 done: loss 0.0619 - lr: 0.000039
120
+ 2023-10-25 21:34:27,513 DEV : loss 0.11677566170692444 - f1-score (micro avg) 0.7711
121
+ 2023-10-25 21:34:27,519 saving best model
122
+ 2023-10-25 21:34:28,211 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:34:29,551 epoch 4 - iter 13/136 - loss 0.03055324 - time (sec): 1.34 - samples/sec: 4020.86 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-25 21:34:30,638 epoch 4 - iter 26/136 - loss 0.03116300 - time (sec): 2.42 - samples/sec: 4639.52 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-25 21:34:31,721 epoch 4 - iter 39/136 - loss 0.03021750 - time (sec): 3.51 - samples/sec: 4715.23 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-25 21:34:32,625 epoch 4 - iter 52/136 - loss 0.02989708 - time (sec): 4.41 - samples/sec: 4771.58 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-25 21:34:33,518 epoch 4 - iter 65/136 - loss 0.03206761 - time (sec): 5.30 - samples/sec: 4780.00 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-25 21:34:34,528 epoch 4 - iter 78/136 - loss 0.03406822 - time (sec): 6.31 - samples/sec: 4756.18 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-25 21:34:35,598 epoch 4 - iter 91/136 - loss 0.03482818 - time (sec): 7.38 - samples/sec: 4768.44 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-25 21:34:36,625 epoch 4 - iter 104/136 - loss 0.03447137 - time (sec): 8.41 - samples/sec: 4839.62 - lr: 0.000035 - momentum: 0.000000
131
+ 2023-10-25 21:34:37,523 epoch 4 - iter 117/136 - loss 0.03504448 - time (sec): 9.31 - samples/sec: 4838.91 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-25 21:34:38,577 epoch 4 - iter 130/136 - loss 0.03602045 - time (sec): 10.36 - samples/sec: 4814.68 - lr: 0.000034 - momentum: 0.000000
133
+ 2023-10-25 21:34:38,986 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:34:38,987 EPOCH 4 done: loss 0.0358 - lr: 0.000034
135
+ 2023-10-25 21:34:40,156 DEV : loss 0.11416536569595337 - f1-score (micro avg) 0.8133
136
+ 2023-10-25 21:34:40,164 saving best model
137
+ 2023-10-25 21:34:40,872 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:34:41,893 epoch 5 - iter 13/136 - loss 0.01946253 - time (sec): 1.02 - samples/sec: 4960.50 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-25 21:34:42,855 epoch 5 - iter 26/136 - loss 0.01547288 - time (sec): 1.98 - samples/sec: 4757.71 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-25 21:34:43,781 epoch 5 - iter 39/136 - loss 0.01856037 - time (sec): 2.91 - samples/sec: 4834.98 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-25 21:34:44,751 epoch 5 - iter 52/136 - loss 0.02123076 - time (sec): 3.88 - samples/sec: 4870.86 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-25 21:34:45,642 epoch 5 - iter 65/136 - loss 0.02421228 - time (sec): 4.77 - samples/sec: 4872.99 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-25 21:34:46,757 epoch 5 - iter 78/136 - loss 0.02165472 - time (sec): 5.88 - samples/sec: 4950.75 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-25 21:34:47,991 epoch 5 - iter 91/136 - loss 0.02043650 - time (sec): 7.12 - samples/sec: 4934.45 - lr: 0.000030 - momentum: 0.000000
145
+ 2023-10-25 21:34:48,983 epoch 5 - iter 104/136 - loss 0.02120918 - time (sec): 8.11 - samples/sec: 4956.52 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-25 21:34:49,861 epoch 5 - iter 117/136 - loss 0.02482853 - time (sec): 8.99 - samples/sec: 4962.83 - lr: 0.000029 - momentum: 0.000000
147
+ 2023-10-25 21:34:50,832 epoch 5 - iter 130/136 - loss 0.02472568 - time (sec): 9.96 - samples/sec: 4991.68 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-25 21:34:51,249 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:34:51,249 EPOCH 5 done: loss 0.0240 - lr: 0.000028
150
+ 2023-10-25 21:34:52,460 DEV : loss 0.12781116366386414 - f1-score (micro avg) 0.8117
151
+ 2023-10-25 21:34:52,467 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-25 21:34:53,956 epoch 6 - iter 13/136 - loss 0.00771416 - time (sec): 1.49 - samples/sec: 3794.62 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-25 21:34:55,019 epoch 6 - iter 26/136 - loss 0.01804796 - time (sec): 2.55 - samples/sec: 4164.42 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-25 21:34:55,948 epoch 6 - iter 39/136 - loss 0.01483424 - time (sec): 3.48 - samples/sec: 4473.84 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-25 21:34:56,965 epoch 6 - iter 52/136 - loss 0.01612002 - time (sec): 4.50 - samples/sec: 4502.50 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-25 21:34:57,931 epoch 6 - iter 65/136 - loss 0.01886579 - time (sec): 5.46 - samples/sec: 4495.53 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-25 21:34:58,949 epoch 6 - iter 78/136 - loss 0.01674238 - time (sec): 6.48 - samples/sec: 4628.11 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-25 21:34:59,937 epoch 6 - iter 91/136 - loss 0.01760742 - time (sec): 7.47 - samples/sec: 4692.38 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-25 21:35:00,995 epoch 6 - iter 104/136 - loss 0.01821699 - time (sec): 8.53 - samples/sec: 4795.24 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-25 21:35:02,018 epoch 6 - iter 117/136 - loss 0.02000563 - time (sec): 9.55 - samples/sec: 4754.41 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-25 21:35:02,921 epoch 6 - iter 130/136 - loss 0.01883848 - time (sec): 10.45 - samples/sec: 4821.33 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-25 21:35:03,286 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 21:35:03,286 EPOCH 6 done: loss 0.0184 - lr: 0.000023
164
+ 2023-10-25 21:35:04,573 DEV : loss 0.14983585476875305 - f1-score (micro avg) 0.8152
165
+ 2023-10-25 21:35:04,580 saving best model
166
+ 2023-10-25 21:35:05,282 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-25 21:35:06,301 epoch 7 - iter 13/136 - loss 0.01240694 - time (sec): 1.02 - samples/sec: 4330.78 - lr: 0.000022 - momentum: 0.000000
168
+ 2023-10-25 21:35:07,183 epoch 7 - iter 26/136 - loss 0.01223001 - time (sec): 1.90 - samples/sec: 4670.10 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-25 21:35:08,168 epoch 7 - iter 39/136 - loss 0.01307552 - time (sec): 2.88 - samples/sec: 4570.45 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-25 21:35:09,250 epoch 7 - iter 52/136 - loss 0.01143417 - time (sec): 3.97 - samples/sec: 4751.28 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-25 21:35:10,157 epoch 7 - iter 65/136 - loss 0.01047760 - time (sec): 4.87 - samples/sec: 4788.91 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-25 21:35:11,094 epoch 7 - iter 78/136 - loss 0.01355259 - time (sec): 5.81 - samples/sec: 4932.77 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-25 21:35:12,100 epoch 7 - iter 91/136 - loss 0.01486358 - time (sec): 6.82 - samples/sec: 4996.59 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-25 21:35:13,026 epoch 7 - iter 104/136 - loss 0.01535576 - time (sec): 7.74 - samples/sec: 5024.62 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-25 21:35:14,023 epoch 7 - iter 117/136 - loss 0.01407148 - time (sec): 8.74 - samples/sec: 5059.63 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-25 21:35:14,953 epoch 7 - iter 130/136 - loss 0.01377123 - time (sec): 9.67 - samples/sec: 5086.11 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-25 21:35:15,457 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-25 21:35:15,457 EPOCH 7 done: loss 0.0141 - lr: 0.000017
179
+ 2023-10-25 21:35:16,727 DEV : loss 0.1700810343027115 - f1-score (micro avg) 0.8125
180
+ 2023-10-25 21:35:16,733 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-25 21:35:17,638 epoch 8 - iter 13/136 - loss 0.00268544 - time (sec): 0.90 - samples/sec: 4952.01 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-25 21:35:19,021 epoch 8 - iter 26/136 - loss 0.00772798 - time (sec): 2.29 - samples/sec: 4415.85 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-25 21:35:20,065 epoch 8 - iter 39/136 - loss 0.00859103 - time (sec): 3.33 - samples/sec: 4731.91 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-25 21:35:21,066 epoch 8 - iter 52/136 - loss 0.01223108 - time (sec): 4.33 - samples/sec: 4749.17 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-25 21:35:22,005 epoch 8 - iter 65/136 - loss 0.01102516 - time (sec): 5.27 - samples/sec: 4730.92 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-25 21:35:22,995 epoch 8 - iter 78/136 - loss 0.01255129 - time (sec): 6.26 - samples/sec: 4887.61 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-25 21:35:23,945 epoch 8 - iter 91/136 - loss 0.01134563 - time (sec): 7.21 - samples/sec: 4920.30 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-25 21:35:24,996 epoch 8 - iter 104/136 - loss 0.01063784 - time (sec): 8.26 - samples/sec: 4886.69 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-25 21:35:25,876 epoch 8 - iter 117/136 - loss 0.01079658 - time (sec): 9.14 - samples/sec: 4920.33 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-25 21:35:26,908 epoch 8 - iter 130/136 - loss 0.00982405 - time (sec): 10.17 - samples/sec: 4907.66 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-25 21:35:27,362 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-25 21:35:27,362 EPOCH 8 done: loss 0.0104 - lr: 0.000012
193
+ 2023-10-25 21:35:28,655 DEV : loss 0.17804576456546783 - f1-score (micro avg) 0.8116
194
+ 2023-10-25 21:35:28,661 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-25 21:35:29,627 epoch 9 - iter 13/136 - loss 0.00055046 - time (sec): 0.96 - samples/sec: 4989.89 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-25 21:35:30,468 epoch 9 - iter 26/136 - loss 0.00298412 - time (sec): 1.81 - samples/sec: 4763.26 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-25 21:35:31,439 epoch 9 - iter 39/136 - loss 0.00647008 - time (sec): 2.78 - samples/sec: 4928.77 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-25 21:35:32,428 epoch 9 - iter 52/136 - loss 0.00565494 - time (sec): 3.77 - samples/sec: 4839.08 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-25 21:35:33,500 epoch 9 - iter 65/136 - loss 0.00505945 - time (sec): 4.84 - samples/sec: 4901.28 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-25 21:35:34,602 epoch 9 - iter 78/136 - loss 0.00449225 - time (sec): 5.94 - samples/sec: 4962.79 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-25 21:35:35,623 epoch 9 - iter 91/136 - loss 0.00512371 - time (sec): 6.96 - samples/sec: 5020.44 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-25 21:35:36,716 epoch 9 - iter 104/136 - loss 0.00515854 - time (sec): 8.05 - samples/sec: 5076.11 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-25 21:35:37,644 epoch 9 - iter 117/136 - loss 0.00609712 - time (sec): 8.98 - samples/sec: 5112.01 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-25 21:35:38,560 epoch 9 - iter 130/136 - loss 0.00628290 - time (sec): 9.90 - samples/sec: 5080.59 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-25 21:35:38,954 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-25 21:35:38,954 EPOCH 9 done: loss 0.0064 - lr: 0.000006
207
+ 2023-10-25 21:35:40,225 DEV : loss 0.18354582786560059 - f1-score (micro avg) 0.8175
208
+ 2023-10-25 21:35:40,231 saving best model
209
+ 2023-10-25 21:35:40,903 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-25 21:35:41,884 epoch 10 - iter 13/136 - loss 0.00268180 - time (sec): 0.98 - samples/sec: 4610.51 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-25 21:35:43,155 epoch 10 - iter 26/136 - loss 0.00574221 - time (sec): 2.25 - samples/sec: 4107.44 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-25 21:35:44,144 epoch 10 - iter 39/136 - loss 0.00437948 - time (sec): 3.24 - samples/sec: 4659.58 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-25 21:35:45,004 epoch 10 - iter 52/136 - loss 0.00591017 - time (sec): 4.10 - samples/sec: 4701.14 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-25 21:35:45,924 epoch 10 - iter 65/136 - loss 0.00477376 - time (sec): 5.02 - samples/sec: 4776.88 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-25 21:35:47,009 epoch 10 - iter 78/136 - loss 0.00422044 - time (sec): 6.10 - samples/sec: 4768.42 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-25 21:35:48,051 epoch 10 - iter 91/136 - loss 0.00414085 - time (sec): 7.15 - samples/sec: 4778.06 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-25 21:35:48,971 epoch 10 - iter 104/136 - loss 0.00387906 - time (sec): 8.07 - samples/sec: 4878.30 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-25 21:35:49,893 epoch 10 - iter 117/136 - loss 0.00431272 - time (sec): 8.99 - samples/sec: 4954.92 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-25 21:35:50,958 epoch 10 - iter 130/136 - loss 0.00472815 - time (sec): 10.05 - samples/sec: 4952.02 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-25 21:35:51,450 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-25 21:35:51,451 EPOCH 10 done: loss 0.0052 - lr: 0.000000
222
+ 2023-10-25 21:35:52,725 DEV : loss 0.18221181631088257 - f1-score (micro avg) 0.825
223
+ 2023-10-25 21:35:52,731 saving best model
224
+ 2023-10-25 21:35:53,934 ----------------------------------------------------------------------------------------------------
225
+ 2023-10-25 21:35:53,935 Loading model from best epoch ...
226
+ 2023-10-25 21:35:55,878 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 21:35:57,804
228
+ Results:
229
+ - F-score (micro) 0.7849
230
+ - F-score (macro) 0.7239
231
+ - Accuracy 0.6605
232
+
233
+ By class:
234
+ precision recall f1-score support
235
+
236
+ LOC 0.8349 0.8750 0.8545 312
237
+ PER 0.6842 0.8750 0.7679 208
238
+ ORG 0.4259 0.4182 0.4220 55
239
+ HumanProd 0.8000 0.9091 0.8511 22
240
+
241
+ micro avg 0.7411 0.8342 0.7849 597
242
+ macro avg 0.6862 0.7693 0.7239 597
243
+ weighted avg 0.7434 0.8342 0.7843 597
244
+
245
+ 2023-10-25 21:35:57,804 ----------------------------------------------------------------------------------------------------