Hugging Face's logo

stefan-it
/
hmbench-newseye-fi-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
Finnish
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
71ebc80
•
1 Parent(s): d5560cf

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +242 -0
training.log ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 21:25:37,600 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:25:37,601 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 21:25:37,601 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:25:37,601 MultiCorpus: 1166 train + 165 dev + 415 test sentences
52
+ - NER_HIPE_2022 Corpus: 1166 train + 165 dev + 415 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fi/with_doc_seperator
53
+ 2023-10-25 21:25:37,601 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:25:37,601 Train: 1166 sentences
55
+ 2023-10-25 21:25:37,601 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:25:37,601 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:25:37,601 Training Params:
58
+ 2023-10-25 21:25:37,601 - learning_rate: "3e-05"
59
+ 2023-10-25 21:25:37,601 - mini_batch_size: "8"
60
+ 2023-10-25 21:25:37,601 - max_epochs: "10"
61
+ 2023-10-25 21:25:37,601 - shuffle: "True"
62
+ 2023-10-25 21:25:37,601 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:25:37,601 Plugins:
64
+ 2023-10-25 21:25:37,601 - TensorboardLogger
65
+ 2023-10-25 21:25:37,601 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:25:37,601 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:25:37,602 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:25:37,602 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:25:37,602 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:25:37,602 Computation:
71
+ 2023-10-25 21:25:37,602 - compute on device: cuda:0
72
+ 2023-10-25 21:25:37,602 - embedding storage: none
73
+ 2023-10-25 21:25:37,602 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:25:37,602 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-25 21:25:37,602 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:25:37,602 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:25:37,602 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:25:38,456 epoch 1 - iter 14/146 - loss 2.60294278 - time (sec): 0.85 - samples/sec: 4554.56 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-25 21:25:39,251 epoch 1 - iter 28/146 - loss 2.23371535 - time (sec): 1.65 - samples/sec: 4624.06 - lr: 0.000006 - momentum: 0.000000
80
+ 2023-10-25 21:25:40,234 epoch 1 - iter 42/146 - loss 1.80138209 - time (sec): 2.63 - samples/sec: 4632.61 - lr: 0.000008 - momentum: 0.000000
81
+ 2023-10-25 21:25:41,163 epoch 1 - iter 56/146 - loss 1.53922194 - time (sec): 3.56 - samples/sec: 4611.81 - lr: 0.000011 - momentum: 0.000000
82
+ 2023-10-25 21:25:42,048 epoch 1 - iter 70/146 - loss 1.31289657 - time (sec): 4.44 - samples/sec: 4710.80 - lr: 0.000014 - momentum: 0.000000
83
+ 2023-10-25 21:25:42,819 epoch 1 - iter 84/146 - loss 1.19311406 - time (sec): 5.22 - samples/sec: 4682.69 - lr: 0.000017 - momentum: 0.000000
84
+ 2023-10-25 21:25:43,898 epoch 1 - iter 98/146 - loss 1.06894666 - time (sec): 6.30 - samples/sec: 4636.30 - lr: 0.000020 - momentum: 0.000000
85
+ 2023-10-25 21:25:44,851 epoch 1 - iter 112/146 - loss 0.96000516 - time (sec): 7.25 - samples/sec: 4688.87 - lr: 0.000023 - momentum: 0.000000
86
+ 2023-10-25 21:25:45,925 epoch 1 - iter 126/146 - loss 0.87262223 - time (sec): 8.32 - samples/sec: 4714.46 - lr: 0.000026 - momentum: 0.000000
87
+ 2023-10-25 21:25:46,732 epoch 1 - iter 140/146 - loss 0.82531461 - time (sec): 9.13 - samples/sec: 4677.43 - lr: 0.000029 - momentum: 0.000000
88
+ 2023-10-25 21:25:47,124 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:25:47,125 EPOCH 1 done: loss 0.8031 - lr: 0.000029
90
+ 2023-10-25 21:25:47,636 DEV : loss 0.17106929421424866 - f1-score (micro avg) 0.5556
91
+ 2023-10-25 21:25:47,641 saving best model
92
+ 2023-10-25 21:25:48,125 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:25:49,058 epoch 2 - iter 14/146 - loss 0.21725174 - time (sec): 0.93 - samples/sec: 4670.16 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-25 21:25:49,982 epoch 2 - iter 28/146 - loss 0.26028088 - time (sec): 1.86 - samples/sec: 4639.64 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-25 21:25:50,829 epoch 2 - iter 42/146 - loss 0.23972876 - time (sec): 2.70 - samples/sec: 4534.87 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-25 21:25:51,852 epoch 2 - iter 56/146 - loss 0.21456830 - time (sec): 3.73 - samples/sec: 4529.17 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-25 21:25:52,760 epoch 2 - iter 70/146 - loss 0.20980275 - time (sec): 4.63 - samples/sec: 4586.61 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-25 21:25:53,548 epoch 2 - iter 84/146 - loss 0.20500047 - time (sec): 5.42 - samples/sec: 4663.26 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-25 21:25:54,385 epoch 2 - iter 98/146 - loss 0.20211037 - time (sec): 6.26 - samples/sec: 4703.40 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-25 21:25:55,213 epoch 2 - iter 112/146 - loss 0.19844997 - time (sec): 7.09 - samples/sec: 4734.97 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-25 21:25:56,153 epoch 2 - iter 126/146 - loss 0.19974107 - time (sec): 8.03 - samples/sec: 4721.44 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-25 21:25:57,151 epoch 2 - iter 140/146 - loss 0.19108156 - time (sec): 9.03 - samples/sec: 4716.34 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-25 21:25:57,479 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:25:57,479 EPOCH 2 done: loss 0.1879 - lr: 0.000027
105
+ 2023-10-25 21:25:58,559 DEV : loss 0.11886167526245117 - f1-score (micro avg) 0.628
106
+ 2023-10-25 21:25:58,564 saving best model
107
+ 2023-10-25 21:25:59,181 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:26:00,384 epoch 3 - iter 14/146 - loss 0.09759941 - time (sec): 1.20 - samples/sec: 4773.89 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-25 21:26:01,355 epoch 3 - iter 28/146 - loss 0.10716313 - time (sec): 2.17 - samples/sec: 4677.63 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-25 21:26:02,184 epoch 3 - iter 42/146 - loss 0.10722639 - time (sec): 3.00 - samples/sec: 4725.88 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-25 21:26:03,077 epoch 3 - iter 56/146 - loss 0.10523426 - time (sec): 3.89 - samples/sec: 4598.51 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-25 21:26:04,013 epoch 3 - iter 70/146 - loss 0.10392697 - time (sec): 4.83 - samples/sec: 4631.03 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-25 21:26:04,838 epoch 3 - iter 84/146 - loss 0.10454309 - time (sec): 5.65 - samples/sec: 4614.89 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-25 21:26:05,722 epoch 3 - iter 98/146 - loss 0.09893681 - time (sec): 6.54 - samples/sec: 4658.43 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-25 21:26:06,558 epoch 3 - iter 112/146 - loss 0.09875386 - time (sec): 7.38 - samples/sec: 4621.33 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-25 21:26:07,479 epoch 3 - iter 126/146 - loss 0.09913673 - time (sec): 8.30 - samples/sec: 4648.08 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-25 21:26:08,263 epoch 3 - iter 140/146 - loss 0.09719812 - time (sec): 9.08 - samples/sec: 4722.37 - lr: 0.000024 - momentum: 0.000000
118
+ 2023-10-25 21:26:08,631 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:26:08,631 EPOCH 3 done: loss 0.0987 - lr: 0.000024
120
+ 2023-10-25 21:26:09,551 DEV : loss 0.10990928113460541 - f1-score (micro avg) 0.7281
121
+ 2023-10-25 21:26:09,556 saving best model
122
+ 2023-10-25 21:26:10,167 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:26:10,976 epoch 4 - iter 14/146 - loss 0.08318771 - time (sec): 0.81 - samples/sec: 4774.15 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-25 21:26:11,965 epoch 4 - iter 28/146 - loss 0.06355907 - time (sec): 1.80 - samples/sec: 4570.83 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-25 21:26:12,846 epoch 4 - iter 42/146 - loss 0.05940453 - time (sec): 2.68 - samples/sec: 4712.30 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-25 21:26:13,683 epoch 4 - iter 56/146 - loss 0.05624618 - time (sec): 3.51 - samples/sec: 4578.48 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-25 21:26:14,614 epoch 4 - iter 70/146 - loss 0.05687332 - time (sec): 4.44 - samples/sec: 4793.07 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-25 21:26:15,618 epoch 4 - iter 84/146 - loss 0.05866038 - time (sec): 5.45 - samples/sec: 4832.66 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-25 21:26:16,470 epoch 4 - iter 98/146 - loss 0.05691631 - time (sec): 6.30 - samples/sec: 4897.68 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-25 21:26:17,311 epoch 4 - iter 112/146 - loss 0.06125083 - time (sec): 7.14 - samples/sec: 4852.90 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-25 21:26:18,415 epoch 4 - iter 126/146 - loss 0.06362815 - time (sec): 8.25 - samples/sec: 4759.95 - lr: 0.000021 - momentum: 0.000000
132
+ 2023-10-25 21:26:19,217 epoch 4 - iter 140/146 - loss 0.06182318 - time (sec): 9.05 - samples/sec: 4740.79 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-25 21:26:19,541 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:26:19,541 EPOCH 4 done: loss 0.0618 - lr: 0.000020
135
+ 2023-10-25 21:26:20,462 DEV : loss 0.0920729711651802 - f1-score (micro avg) 0.7702
136
+ 2023-10-25 21:26:20,467 saving best model
137
+ 2023-10-25 21:26:20,948 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:26:21,871 epoch 5 - iter 14/146 - loss 0.03669754 - time (sec): 0.92 - samples/sec: 4823.31 - lr: 0.000020 - momentum: 0.000000
139
+ 2023-10-25 21:26:22,778 epoch 5 - iter 28/146 - loss 0.03920318 - time (sec): 1.83 - samples/sec: 4663.07 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-25 21:26:23,664 epoch 5 - iter 42/146 - loss 0.03549894 - time (sec): 2.71 - samples/sec: 4675.88 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-25 21:26:24,500 epoch 5 - iter 56/146 - loss 0.03524770 - time (sec): 3.55 - samples/sec: 4765.02 - lr: 0.000019 - momentum: 0.000000
142
+ 2023-10-25 21:26:25,348 epoch 5 - iter 70/146 - loss 0.03474532 - time (sec): 4.40 - samples/sec: 4816.39 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-25 21:26:26,121 epoch 5 - iter 84/146 - loss 0.03887679 - time (sec): 5.17 - samples/sec: 4820.26 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-25 21:26:27,253 epoch 5 - iter 98/146 - loss 0.04147485 - time (sec): 6.30 - samples/sec: 4715.08 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-25 21:26:28,113 epoch 5 - iter 112/146 - loss 0.04145546 - time (sec): 7.16 - samples/sec: 4758.84 - lr: 0.000018 - momentum: 0.000000
146
+ 2023-10-25 21:26:29,050 epoch 5 - iter 126/146 - loss 0.04076736 - time (sec): 8.10 - samples/sec: 4785.00 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-25 21:26:29,887 epoch 5 - iter 140/146 - loss 0.03908635 - time (sec): 8.94 - samples/sec: 4809.16 - lr: 0.000017 - momentum: 0.000000
148
+ 2023-10-25 21:26:30,239 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:26:30,239 EPOCH 5 done: loss 0.0394 - lr: 0.000017
150
+ 2023-10-25 21:26:31,319 DEV : loss 0.11569201946258545 - f1-score (micro avg) 0.7261
151
+ 2023-10-25 21:26:31,324 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-25 21:26:32,244 epoch 6 - iter 14/146 - loss 0.03038153 - time (sec): 0.92 - samples/sec: 5188.57 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-25 21:26:33,136 epoch 6 - iter 28/146 - loss 0.03130799 - time (sec): 1.81 - samples/sec: 4906.54 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-25 21:26:33,995 epoch 6 - iter 42/146 - loss 0.02641538 - time (sec): 2.67 - samples/sec: 4942.07 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-25 21:26:34,916 epoch 6 - iter 56/146 - loss 0.03146130 - time (sec): 3.59 - samples/sec: 4891.39 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-25 21:26:35,779 epoch 6 - iter 70/146 - loss 0.03030920 - time (sec): 4.45 - samples/sec: 4938.51 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-25 21:26:36,627 epoch 6 - iter 84/146 - loss 0.02957139 - time (sec): 5.30 - samples/sec: 4865.32 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-25 21:26:37,593 epoch 6 - iter 98/146 - loss 0.02770553 - time (sec): 6.27 - samples/sec: 4793.74 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-25 21:26:38,516 epoch 6 - iter 112/146 - loss 0.02699072 - time (sec): 7.19 - samples/sec: 4747.91 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-25 21:26:39,578 epoch 6 - iter 126/146 - loss 0.02595757 - time (sec): 8.25 - samples/sec: 4701.74 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-25 21:26:40,381 epoch 6 - iter 140/146 - loss 0.02607979 - time (sec): 9.06 - samples/sec: 4699.00 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-25 21:26:40,763 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 21:26:40,764 EPOCH 6 done: loss 0.0259 - lr: 0.000014
164
+ 2023-10-25 21:26:41,690 DEV : loss 0.12295451760292053 - f1-score (micro avg) 0.7401
165
+ 2023-10-25 21:26:41,696 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-25 21:26:42,577 epoch 7 - iter 14/146 - loss 0.02415144 - time (sec): 0.88 - samples/sec: 5234.42 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-25 21:26:43,586 epoch 7 - iter 28/146 - loss 0.03236498 - time (sec): 1.89 - samples/sec: 4997.27 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-25 21:26:44,412 epoch 7 - iter 42/146 - loss 0.03067054 - time (sec): 2.71 - samples/sec: 4934.20 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-25 21:26:45,263 epoch 7 - iter 56/146 - loss 0.02611424 - time (sec): 3.57 - samples/sec: 4843.92 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-25 21:26:46,053 epoch 7 - iter 70/146 - loss 0.02398715 - time (sec): 4.36 - samples/sec: 4818.12 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-25 21:26:47,091 epoch 7 - iter 84/146 - loss 0.02253424 - time (sec): 5.39 - samples/sec: 4774.42 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-25 21:26:47,983 epoch 7 - iter 98/146 - loss 0.02258653 - time (sec): 6.29 - samples/sec: 4831.43 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-25 21:26:48,818 epoch 7 - iter 112/146 - loss 0.02125092 - time (sec): 7.12 - samples/sec: 4805.93 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-25 21:26:49,735 epoch 7 - iter 126/146 - loss 0.02038749 - time (sec): 8.04 - samples/sec: 4787.52 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-25 21:26:50,593 epoch 7 - iter 140/146 - loss 0.02016293 - time (sec): 8.90 - samples/sec: 4762.46 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-25 21:26:51,047 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-25 21:26:51,048 EPOCH 7 done: loss 0.0195 - lr: 0.000010
178
+ 2023-10-25 21:26:51,973 DEV : loss 0.1449124813079834 - f1-score (micro avg) 0.7158
179
+ 2023-10-25 21:26:51,978 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-25 21:26:52,924 epoch 8 - iter 14/146 - loss 0.01568499 - time (sec): 0.95 - samples/sec: 4492.68 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-25 21:26:53,864 epoch 8 - iter 28/146 - loss 0.01851063 - time (sec): 1.88 - samples/sec: 4485.90 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-25 21:26:54,698 epoch 8 - iter 42/146 - loss 0.01478075 - time (sec): 2.72 - samples/sec: 4596.52 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-25 21:26:55,645 epoch 8 - iter 56/146 - loss 0.01476943 - time (sec): 3.67 - samples/sec: 4680.34 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-25 21:26:56,459 epoch 8 - iter 70/146 - loss 0.01459552 - time (sec): 4.48 - samples/sec: 4686.56 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-25 21:26:57,274 epoch 8 - iter 84/146 - loss 0.01588161 - time (sec): 5.30 - samples/sec: 4758.94 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-25 21:26:58,098 epoch 8 - iter 98/146 - loss 0.01515460 - time (sec): 6.12 - samples/sec: 4735.78 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-25 21:26:59,012 epoch 8 - iter 112/146 - loss 0.01564759 - time (sec): 7.03 - samples/sec: 4711.07 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-25 21:26:59,942 epoch 8 - iter 126/146 - loss 0.01592133 - time (sec): 7.96 - samples/sec: 4714.23 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-25 21:27:00,945 epoch 8 - iter 140/146 - loss 0.01519304 - time (sec): 8.97 - samples/sec: 4745.85 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-25 21:27:01,340 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-25 21:27:01,340 EPOCH 8 done: loss 0.0159 - lr: 0.000007
192
+ 2023-10-25 21:27:02,424 DEV : loss 0.14217789471149445 - f1-score (micro avg) 0.755
193
+ 2023-10-25 21:27:02,430 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-25 21:27:03,382 epoch 9 - iter 14/146 - loss 0.00940644 - time (sec): 0.95 - samples/sec: 5197.42 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-25 21:27:04,214 epoch 9 - iter 28/146 - loss 0.01224290 - time (sec): 1.78 - samples/sec: 5124.09 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-25 21:27:05,021 epoch 9 - iter 42/146 - loss 0.01134241 - time (sec): 2.59 - samples/sec: 5030.86 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-25 21:27:05,958 epoch 9 - iter 56/146 - loss 0.01127674 - time (sec): 3.53 - samples/sec: 5002.42 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-25 21:27:06,926 epoch 9 - iter 70/146 - loss 0.01508017 - time (sec): 4.50 - samples/sec: 4872.49 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-25 21:27:07,920 epoch 9 - iter 84/146 - loss 0.01540634 - time (sec): 5.49 - samples/sec: 4773.73 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-25 21:27:08,821 epoch 9 - iter 98/146 - loss 0.01387577 - time (sec): 6.39 - samples/sec: 4775.83 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-25 21:27:09,723 epoch 9 - iter 112/146 - loss 0.01346312 - time (sec): 7.29 - samples/sec: 4762.16 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-25 21:27:10,619 epoch 9 - iter 126/146 - loss 0.01415713 - time (sec): 8.19 - samples/sec: 4712.60 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-25 21:27:11,529 epoch 9 - iter 140/146 - loss 0.01466539 - time (sec): 9.10 - samples/sec: 4690.74 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-25 21:27:11,876 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-25 21:27:11,877 EPOCH 9 done: loss 0.0142 - lr: 0.000004
206
+ 2023-10-25 21:27:12,796 DEV : loss 0.14243099093437195 - f1-score (micro avg) 0.7387
207
+ 2023-10-25 21:27:12,801 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-25 21:27:13,674 epoch 10 - iter 14/146 - loss 0.00899830 - time (sec): 0.87 - samples/sec: 4927.08 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-25 21:27:14,530 epoch 10 - iter 28/146 - loss 0.00557953 - time (sec): 1.73 - samples/sec: 4608.78 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-25 21:27:15,417 epoch 10 - iter 42/146 - loss 0.01050729 - time (sec): 2.61 - samples/sec: 4620.84 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-25 21:27:16,202 epoch 10 - iter 56/146 - loss 0.01109768 - time (sec): 3.40 - samples/sec: 4647.40 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-25 21:27:17,172 epoch 10 - iter 70/146 - loss 0.01198941 - time (sec): 4.37 - samples/sec: 4708.51 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-25 21:27:18,082 epoch 10 - iter 84/146 - loss 0.01146295 - time (sec): 5.28 - samples/sec: 4686.69 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-25 21:27:18,904 epoch 10 - iter 98/146 - loss 0.01083949 - time (sec): 6.10 - samples/sec: 4773.97 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-25 21:27:19,896 epoch 10 - iter 112/146 - loss 0.01100900 - time (sec): 7.09 - samples/sec: 4798.30 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-25 21:27:20,832 epoch 10 - iter 126/146 - loss 0.01016506 - time (sec): 8.03 - samples/sec: 4761.08 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 21:27:21,781 epoch 10 - iter 140/146 - loss 0.01013197 - time (sec): 8.98 - samples/sec: 4791.19 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-25 21:27:22,091 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-25 21:27:22,091 EPOCH 10 done: loss 0.0099 - lr: 0.000000
220
+ 2023-10-25 21:27:23,012 DEV : loss 0.14977367222309113 - f1-score (micro avg) 0.7419
221
+ 2023-10-25 21:27:23,485 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-25 21:27:23,486 Loading model from best epoch ...
223
+ 2023-10-25 21:27:25,065 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
224
+ 2023-10-25 21:27:26,606
225
+ Results:
226
+ - F-score (micro) 0.7631
227
+ - F-score (macro) 0.6653
228
+ - Accuracy 0.6408
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ PER 0.7919 0.8420 0.8162 348
234
+ LOC 0.7026 0.8238 0.7584 261
235
+ ORG 0.5111 0.4423 0.4742 52
236
+ HumanProd 0.5556 0.6818 0.6122 22
237
+
238
+ micro avg 0.7299 0.7994 0.7631 683
239
+ macro avg 0.6403 0.6975 0.6653 683
240
+ weighted avg 0.7288 0.7994 0.7615 683
241
+
242
+ 2023-10-25 21:27:26,606 ----------------------------------------------------------------------------------------------------