Hugging Face's logo

stefan-it
/
hmbench-newseye-sv-hmbert_64k-bs4-wsFalse-e10-lr3e-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
e936bd7
·
1 Parent(s): 97e701b

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +244 -0
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 21:36:16,098 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:36:16,099 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 21:36:16,099 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:36:16,099 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 21:36:16,099 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:36:16,099 Train: 1085 sentences
55
+ 2023-10-25 21:36:16,099 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:36:16,100 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:36:16,100 Training Params:
58
+ 2023-10-25 21:36:16,100 - learning_rate: "3e-05"
59
+ 2023-10-25 21:36:16,100 - mini_batch_size: "4"
60
+ 2023-10-25 21:36:16,100 - max_epochs: "10"
61
+ 2023-10-25 21:36:16,100 - shuffle: "True"
62
+ 2023-10-25 21:36:16,100 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:36:16,100 Plugins:
64
+ 2023-10-25 21:36:16,100 - TensorboardLogger
65
+ 2023-10-25 21:36:16,100 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:36:16,100 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:36:16,100 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:36:16,100 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:36:16,100 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:36:16,100 Computation:
71
+ 2023-10-25 21:36:16,100 - compute on device: cuda:0
72
+ 2023-10-25 21:36:16,100 - embedding storage: none
73
+ 2023-10-25 21:36:16,100 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:36:16,100 Model training base path: "hmbench-newseye/sv-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-25 21:36:16,100 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:36:16,100 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:36:16,100 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:36:17,592 epoch 1 - iter 27/272 - loss 2.65474957 - time (sec): 1.49 - samples/sec: 3443.20 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 21:36:19,071 epoch 1 - iter 54/272 - loss 1.95673918 - time (sec): 2.97 - samples/sec: 3496.32 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 21:36:20,628 epoch 1 - iter 81/272 - loss 1.46307628 - time (sec): 4.53 - samples/sec: 3568.70 - lr: 0.000009 - momentum: 0.000000
81
+ 2023-10-25 21:36:22,257 epoch 1 - iter 108/272 - loss 1.21997753 - time (sec): 6.16 - samples/sec: 3569.29 - lr: 0.000012 - momentum: 0.000000
82
+ 2023-10-25 21:36:23,862 epoch 1 - iter 135/272 - loss 1.06410884 - time (sec): 7.76 - samples/sec: 3468.98 - lr: 0.000015 - momentum: 0.000000
83
+ 2023-10-25 21:36:25,355 epoch 1 - iter 162/272 - loss 0.94145184 - time (sec): 9.25 - samples/sec: 3461.97 - lr: 0.000018 - momentum: 0.000000
84
+ 2023-10-25 21:36:26,744 epoch 1 - iter 189/272 - loss 0.84157685 - time (sec): 10.64 - samples/sec: 3530.87 - lr: 0.000021 - momentum: 0.000000
85
+ 2023-10-25 21:36:28,108 epoch 1 - iter 216/272 - loss 0.77482516 - time (sec): 12.01 - samples/sec: 3510.36 - lr: 0.000024 - momentum: 0.000000
86
+ 2023-10-25 21:36:29,524 epoch 1 - iter 243/272 - loss 0.70539388 - time (sec): 13.42 - samples/sec: 3558.79 - lr: 0.000027 - momentum: 0.000000
87
+ 2023-10-25 21:36:30,876 epoch 1 - iter 270/272 - loss 0.66693078 - time (sec): 14.77 - samples/sec: 3501.73 - lr: 0.000030 - momentum: 0.000000
88
+ 2023-10-25 21:36:30,968 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:36:30,969 EPOCH 1 done: loss 0.6644 - lr: 0.000030
90
+ 2023-10-25 21:36:32,031 DEV : loss 0.13923215866088867 - f1-score (micro avg) 0.6887
91
+ 2023-10-25 21:36:32,037 saving best model
92
+ 2023-10-25 21:36:32,530 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:36:33,922 epoch 2 - iter 27/272 - loss 0.13712817 - time (sec): 1.39 - samples/sec: 3749.80 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 21:36:35,305 epoch 2 - iter 54/272 - loss 0.14265572 - time (sec): 2.77 - samples/sec: 3871.37 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 21:36:36,738 epoch 2 - iter 81/272 - loss 0.13770316 - time (sec): 4.21 - samples/sec: 3643.51 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 21:36:38,169 epoch 2 - iter 108/272 - loss 0.13487633 - time (sec): 5.64 - samples/sec: 3586.44 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 21:36:39,640 epoch 2 - iter 135/272 - loss 0.12662835 - time (sec): 7.11 - samples/sec: 3596.54 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 21:36:41,053 epoch 2 - iter 162/272 - loss 0.13170245 - time (sec): 8.52 - samples/sec: 3604.95 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 21:36:42,545 epoch 2 - iter 189/272 - loss 0.13769892 - time (sec): 10.01 - samples/sec: 3644.20 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 21:36:43,931 epoch 2 - iter 216/272 - loss 0.13518913 - time (sec): 11.40 - samples/sec: 3583.68 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 21:36:45,316 epoch 2 - iter 243/272 - loss 0.13506088 - time (sec): 12.78 - samples/sec: 3645.16 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 21:36:46,650 epoch 2 - iter 270/272 - loss 0.13127930 - time (sec): 14.12 - samples/sec: 3651.29 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 21:36:46,768 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:36:46,768 EPOCH 2 done: loss 0.1314 - lr: 0.000027
105
+ 2023-10-25 21:36:48,045 DEV : loss 0.10660745203495026 - f1-score (micro avg) 0.7532
106
+ 2023-10-25 21:36:48,051 saving best model
107
+ 2023-10-25 21:36:48,725 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:36:50,078 epoch 3 - iter 27/272 - loss 0.06727833 - time (sec): 1.35 - samples/sec: 3224.34 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 21:36:51,520 epoch 3 - iter 54/272 - loss 0.07452004 - time (sec): 2.79 - samples/sec: 3379.71 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 21:36:52,983 epoch 3 - iter 81/272 - loss 0.06497320 - time (sec): 4.26 - samples/sec: 3522.04 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 21:36:54,367 epoch 3 - iter 108/272 - loss 0.07157426 - time (sec): 5.64 - samples/sec: 3448.54 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 21:36:55,856 epoch 3 - iter 135/272 - loss 0.07014469 - time (sec): 7.13 - samples/sec: 3580.67 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 21:36:57,282 epoch 3 - iter 162/272 - loss 0.07193507 - time (sec): 8.56 - samples/sec: 3659.46 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 21:36:58,714 epoch 3 - iter 189/272 - loss 0.07142812 - time (sec): 9.99 - samples/sec: 3694.40 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 21:37:00,075 epoch 3 - iter 216/272 - loss 0.07085430 - time (sec): 11.35 - samples/sec: 3651.23 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 21:37:01,431 epoch 3 - iter 243/272 - loss 0.07029081 - time (sec): 12.70 - samples/sec: 3631.45 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 21:37:02,883 epoch 3 - iter 270/272 - loss 0.06959342 - time (sec): 14.16 - samples/sec: 3643.29 - lr: 0.000023 - momentum: 0.000000
118
+ 2023-10-25 21:37:02,985 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:37:02,986 EPOCH 3 done: loss 0.0701 - lr: 0.000023
120
+ 2023-10-25 21:37:04,144 DEV : loss 0.10616882890462875 - f1-score (micro avg) 0.7942
121
+ 2023-10-25 21:37:04,150 saving best model
122
+ 2023-10-25 21:37:04,868 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:37:06,327 epoch 4 - iter 27/272 - loss 0.02755718 - time (sec): 1.46 - samples/sec: 3921.24 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 21:37:07,756 epoch 4 - iter 54/272 - loss 0.03125274 - time (sec): 2.89 - samples/sec: 3970.57 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-25 21:37:09,238 epoch 4 - iter 81/272 - loss 0.03309291 - time (sec): 4.37 - samples/sec: 3920.29 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 21:37:10,671 epoch 4 - iter 108/272 - loss 0.03220408 - time (sec): 5.80 - samples/sec: 3760.69 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 21:37:12,054 epoch 4 - iter 135/272 - loss 0.03239834 - time (sec): 7.18 - samples/sec: 3602.46 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-25 21:37:13,609 epoch 4 - iter 162/272 - loss 0.03733691 - time (sec): 8.74 - samples/sec: 3535.60 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 21:37:15,194 epoch 4 - iter 189/272 - loss 0.03815361 - time (sec): 10.32 - samples/sec: 3611.73 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 21:37:16,627 epoch 4 - iter 216/272 - loss 0.03849085 - time (sec): 11.76 - samples/sec: 3579.76 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-25 21:37:18,099 epoch 4 - iter 243/272 - loss 0.03882976 - time (sec): 13.23 - samples/sec: 3521.96 - lr: 0.000020 - momentum: 0.000000
132
+ 2023-10-25 21:37:19,590 epoch 4 - iter 270/272 - loss 0.03977053 - time (sec): 14.72 - samples/sec: 3500.83 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-25 21:37:19,696 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:37:19,696 EPOCH 4 done: loss 0.0394 - lr: 0.000020
135
+ 2023-10-25 21:37:21,213 DEV : loss 0.13888561725616455 - f1-score (micro avg) 0.8022
136
+ 2023-10-25 21:37:21,219 saving best model
137
+ 2023-10-25 21:37:21,909 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:37:23,361 epoch 5 - iter 27/272 - loss 0.01745196 - time (sec): 1.45 - samples/sec: 3573.87 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-25 21:37:24,832 epoch 5 - iter 54/272 - loss 0.01893335 - time (sec): 2.92 - samples/sec: 3355.12 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 21:37:26,256 epoch 5 - iter 81/272 - loss 0.02213397 - time (sec): 4.34 - samples/sec: 3300.38 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 21:37:27,692 epoch 5 - iter 108/272 - loss 0.02108827 - time (sec): 5.78 - samples/sec: 3388.76 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-25 21:37:29,117 epoch 5 - iter 135/272 - loss 0.02358492 - time (sec): 7.21 - samples/sec: 3392.69 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 21:37:30,670 epoch 5 - iter 162/272 - loss 0.02172849 - time (sec): 8.76 - samples/sec: 3489.99 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 21:37:32,231 epoch 5 - iter 189/272 - loss 0.02333344 - time (sec): 10.32 - samples/sec: 3527.51 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-25 21:37:33,724 epoch 5 - iter 216/272 - loss 0.02626849 - time (sec): 11.81 - samples/sec: 3528.15 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-25 21:37:35,167 epoch 5 - iter 243/272 - loss 0.02839398 - time (sec): 13.26 - samples/sec: 3486.38 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 21:37:36,681 epoch 5 - iter 270/272 - loss 0.02784007 - time (sec): 14.77 - samples/sec: 3508.99 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-25 21:37:36,786 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:37:36,786 EPOCH 5 done: loss 0.0278 - lr: 0.000017
150
+ 2023-10-25 21:37:37,960 DEV : loss 0.15720747411251068 - f1-score (micro avg) 0.8303
151
+ 2023-10-25 21:37:37,967 saving best model
152
+ 2023-10-25 21:37:38,672 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-25 21:37:40,208 epoch 6 - iter 27/272 - loss 0.02100579 - time (sec): 1.53 - samples/sec: 3741.48 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 21:37:41,702 epoch 6 - iter 54/272 - loss 0.02444168 - time (sec): 3.03 - samples/sec: 3732.58 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-25 21:37:43,184 epoch 6 - iter 81/272 - loss 0.02024815 - time (sec): 4.51 - samples/sec: 3562.71 - lr: 0.000016 - momentum: 0.000000
156
+ 2023-10-25 21:37:44,712 epoch 6 - iter 108/272 - loss 0.02102848 - time (sec): 6.04 - samples/sec: 3469.50 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 21:37:46,104 epoch 6 - iter 135/272 - loss 0.02392105 - time (sec): 7.43 - samples/sec: 3437.82 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-25 21:37:47,572 epoch 6 - iter 162/272 - loss 0.02188491 - time (sec): 8.90 - samples/sec: 3479.00 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-25 21:37:49,043 epoch 6 - iter 189/272 - loss 0.02382525 - time (sec): 10.37 - samples/sec: 3558.80 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 21:37:50,545 epoch 6 - iter 216/272 - loss 0.02244042 - time (sec): 11.87 - samples/sec: 3553.28 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-25 21:37:52,020 epoch 6 - iter 243/272 - loss 0.02270981 - time (sec): 13.34 - samples/sec: 3529.79 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-25 21:37:53,451 epoch 6 - iter 270/272 - loss 0.02162726 - time (sec): 14.77 - samples/sec: 3500.62 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-25 21:37:53,556 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-25 21:37:53,556 EPOCH 6 done: loss 0.0215 - lr: 0.000013
165
+ 2023-10-25 21:37:54,933 DEV : loss 0.15974003076553345 - f1-score (micro avg) 0.8095
166
+ 2023-10-25 21:37:54,939 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-25 21:37:56,442 epoch 7 - iter 27/272 - loss 0.01980615 - time (sec): 1.50 - samples/sec: 2945.32 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-25 21:37:57,960 epoch 7 - iter 54/272 - loss 0.01724369 - time (sec): 3.02 - samples/sec: 3022.59 - lr: 0.000013 - momentum: 0.000000
169
+ 2023-10-25 21:37:59,454 epoch 7 - iter 81/272 - loss 0.01339852 - time (sec): 4.51 - samples/sec: 3129.68 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-25 21:38:01,009 epoch 7 - iter 108/272 - loss 0.01352837 - time (sec): 6.07 - samples/sec: 3240.56 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-25 21:38:02,460 epoch 7 - iter 135/272 - loss 0.01334570 - time (sec): 7.52 - samples/sec: 3253.53 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-25 21:38:03,936 epoch 7 - iter 162/272 - loss 0.01470991 - time (sec): 9.00 - samples/sec: 3320.79 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-25 21:38:05,467 epoch 7 - iter 189/272 - loss 0.01466955 - time (sec): 10.53 - samples/sec: 3377.68 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-25 21:38:06,964 epoch 7 - iter 216/272 - loss 0.01430832 - time (sec): 12.02 - samples/sec: 3355.20 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-25 21:38:08,466 epoch 7 - iter 243/272 - loss 0.01369448 - time (sec): 13.53 - samples/sec: 3400.77 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-25 21:38:09,982 epoch 7 - iter 270/272 - loss 0.01347495 - time (sec): 15.04 - samples/sec: 3427.29 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-25 21:38:10,095 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-25 21:38:10,096 EPOCH 7 done: loss 0.0134 - lr: 0.000010
179
+ 2023-10-25 21:38:11,350 DEV : loss 0.166848286986351 - f1-score (micro avg) 0.8259
180
+ 2023-10-25 21:38:11,356 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-25 21:38:12,831 epoch 8 - iter 27/272 - loss 0.00458623 - time (sec): 1.47 - samples/sec: 3264.34 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-25 21:38:14,339 epoch 8 - iter 54/272 - loss 0.00846915 - time (sec): 2.98 - samples/sec: 3473.62 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-25 21:38:15,847 epoch 8 - iter 81/272 - loss 0.01019042 - time (sec): 4.49 - samples/sec: 3586.96 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-25 21:38:17,381 epoch 8 - iter 108/272 - loss 0.01175752 - time (sec): 6.02 - samples/sec: 3538.21 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-25 21:38:18,883 epoch 8 - iter 135/272 - loss 0.01022689 - time (sec): 7.53 - samples/sec: 3419.07 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-25 21:38:20,751 epoch 8 - iter 162/272 - loss 0.01201647 - time (sec): 9.39 - samples/sec: 3359.94 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-25 21:38:22,326 epoch 8 - iter 189/272 - loss 0.01181327 - time (sec): 10.97 - samples/sec: 3333.47 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-25 21:38:23,890 epoch 8 - iter 216/272 - loss 0.01211581 - time (sec): 12.53 - samples/sec: 3352.87 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-25 21:38:25,605 epoch 8 - iter 243/272 - loss 0.01103217 - time (sec): 14.25 - samples/sec: 3271.14 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-25 21:38:27,138 epoch 8 - iter 270/272 - loss 0.01086758 - time (sec): 15.78 - samples/sec: 3282.26 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-25 21:38:27,242 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-25 21:38:27,242 EPOCH 8 done: loss 0.0108 - lr: 0.000007
193
+ 2023-10-25 21:38:28,449 DEV : loss 0.17616702616214752 - f1-score (micro avg) 0.8349
194
+ 2023-10-25 21:38:28,455 saving best model
195
+ 2023-10-25 21:38:29,166 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-25 21:38:30,600 epoch 9 - iter 27/272 - loss 0.00211304 - time (sec): 1.43 - samples/sec: 3416.58 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-25 21:38:32,009 epoch 9 - iter 54/272 - loss 0.00398583 - time (sec): 2.84 - samples/sec: 3137.80 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-25 21:38:33,429 epoch 9 - iter 81/272 - loss 0.00422015 - time (sec): 4.26 - samples/sec: 3363.98 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-25 21:38:34,839 epoch 9 - iter 108/272 - loss 0.00414286 - time (sec): 5.67 - samples/sec: 3383.74 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-25 21:38:36,374 epoch 9 - iter 135/272 - loss 0.00508803 - time (sec): 7.20 - samples/sec: 3433.77 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-25 21:38:37,878 epoch 9 - iter 162/272 - loss 0.00567152 - time (sec): 8.71 - samples/sec: 3573.28 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-25 21:38:39,332 epoch 9 - iter 189/272 - loss 0.00571780 - time (sec): 10.16 - samples/sec: 3614.06 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-25 21:38:40,804 epoch 9 - iter 216/272 - loss 0.00674595 - time (sec): 11.63 - samples/sec: 3651.36 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-25 21:38:42,221 epoch 9 - iter 243/272 - loss 0.00841894 - time (sec): 13.05 - samples/sec: 3679.51 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-25 21:38:43,518 epoch 9 - iter 270/272 - loss 0.00848400 - time (sec): 14.35 - samples/sec: 3599.69 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-25 21:38:43,617 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-25 21:38:43,617 EPOCH 9 done: loss 0.0084 - lr: 0.000003
208
+ 2023-10-25 21:38:44,853 DEV : loss 0.18914948403835297 - f1-score (micro avg) 0.8343
209
+ 2023-10-25 21:38:44,859 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-25 21:38:46,264 epoch 10 - iter 27/272 - loss 0.00970450 - time (sec): 1.40 - samples/sec: 3397.91 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-25 21:38:47,640 epoch 10 - iter 54/272 - loss 0.00836191 - time (sec): 2.78 - samples/sec: 3602.53 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-25 21:38:49,022 epoch 10 - iter 81/272 - loss 0.00803990 - time (sec): 4.16 - samples/sec: 3771.60 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-25 21:38:50,383 epoch 10 - iter 108/272 - loss 0.00794155 - time (sec): 5.52 - samples/sec: 3606.04 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 21:38:51,751 epoch 10 - iter 135/272 - loss 0.00705511 - time (sec): 6.89 - samples/sec: 3645.93 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-25 21:38:53,162 epoch 10 - iter 162/272 - loss 0.00622416 - time (sec): 8.30 - samples/sec: 3632.63 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-25 21:38:54,557 epoch 10 - iter 189/272 - loss 0.00552767 - time (sec): 9.70 - samples/sec: 3660.02 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 21:38:56,071 epoch 10 - iter 216/272 - loss 0.00549638 - time (sec): 11.21 - samples/sec: 3661.33 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-25 21:38:57,521 epoch 10 - iter 243/272 - loss 0.00587848 - time (sec): 12.66 - samples/sec: 3653.32 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-25 21:38:58,984 epoch 10 - iter 270/272 - loss 0.00686666 - time (sec): 14.12 - samples/sec: 3675.73 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-25 21:38:59,080 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-25 21:38:59,080 EPOCH 10 done: loss 0.0069 - lr: 0.000000
222
+ 2023-10-25 21:39:00,327 DEV : loss 0.1866416335105896 - f1-score (micro avg) 0.8296
223
+ 2023-10-25 21:39:00,870 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-25 21:39:00,871 Loading model from best epoch ...
225
+ 2023-10-25 21:39:02,819 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
226
+ 2023-10-25 21:39:05,281
227
+ Results:
228
+ - F-score (micro) 0.7832
229
+ - F-score (macro) 0.7318
230
+ - Accuracy 0.66
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ LOC 0.8277 0.8622 0.8446 312
236
+ PER 0.6654 0.8702 0.7542 208
237
+ ORG 0.5778 0.4727 0.5200 55
238
+ HumanProd 0.7600 0.8636 0.8085 22
239
+
240
+ micro avg 0.7421 0.8291 0.7832 597
241
+ macro avg 0.7077 0.7672 0.7318 597
242
+ weighted avg 0.7456 0.8291 0.7818 597
243
+
244
+ 2023-10-25 21:39:05,281 ----------------------------------------------------------------------------------------------------