Hugging Face's logo

stefan-it
/
hmbench-newseye-fi-hmbert_64k-bs8-wsFalse-e10-lr5e-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
73730f6
•
1 Parent(s): 965e7a6

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 21:27:49,476 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 21:27:49,477 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 21:27:49,477 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 21:27:49,477 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 21:27:49,477 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 21:27:49,477 Train: 1166 sentences
55
+ 2023-10-25 21:27:49,477 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 21:27:49,477 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 21:27:49,477 Training Params:
58
+ 2023-10-25 21:27:49,477 - learning_rate: "5e-05"
59
+ 2023-10-25 21:27:49,477 - mini_batch_size: "8"
60
+ 2023-10-25 21:27:49,477 - max_epochs: "10"
61
+ 2023-10-25 21:27:49,477 - shuffle: "True"
62
+ 2023-10-25 21:27:49,477 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 21:27:49,477 Plugins:
64
+ 2023-10-25 21:27:49,477 - TensorboardLogger
65
+ 2023-10-25 21:27:49,477 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 21:27:49,477 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 21:27:49,477 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 21:27:49,477 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 21:27:49,477 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 21:27:49,477 Computation:
71
+ 2023-10-25 21:27:49,477 - compute on device: cuda:0
72
+ 2023-10-25 21:27:49,477 - embedding storage: none
73
+ 2023-10-25 21:27:49,477 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 21:27:49,477 Model training base path: "hmbench-newseye/fi-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-25 21:27:49,477 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 21:27:49,477 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 21:27:49,478 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 21:27:50,374 epoch 1 - iter 14/146 - loss 2.52526717 - time (sec): 0.90 - samples/sec: 4334.26 - lr: 0.000004 - momentum: 0.000000
79
+ 2023-10-25 21:27:51,165 epoch 1 - iter 28/146 - loss 1.96710579 - time (sec): 1.69 - samples/sec: 4519.61 - lr: 0.000009 - momentum: 0.000000
80
+ 2023-10-25 21:27:52,148 epoch 1 - iter 42/146 - loss 1.59185410 - time (sec): 2.67 - samples/sec: 4566.94 - lr: 0.000014 - momentum: 0.000000
81
+ 2023-10-25 21:27:53,087 epoch 1 - iter 56/146 - loss 1.35500246 - time (sec): 3.61 - samples/sec: 4550.27 - lr: 0.000019 - momentum: 0.000000
82
+ 2023-10-25 21:27:53,966 epoch 1 - iter 70/146 - loss 1.14468229 - time (sec): 4.49 - samples/sec: 4665.80 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-25 21:27:54,730 epoch 1 - iter 84/146 - loss 1.03230977 - time (sec): 5.25 - samples/sec: 4651.66 - lr: 0.000028 - momentum: 0.000000
84
+ 2023-10-25 21:27:55,831 epoch 1 - iter 98/146 - loss 0.91852887 - time (sec): 6.35 - samples/sec: 4594.65 - lr: 0.000033 - momentum: 0.000000
85
+ 2023-10-25 21:27:56,790 epoch 1 - iter 112/146 - loss 0.82179505 - time (sec): 7.31 - samples/sec: 4648.55 - lr: 0.000038 - momentum: 0.000000
86
+ 2023-10-25 21:27:57,868 epoch 1 - iter 126/146 - loss 0.74630898 - time (sec): 8.39 - samples/sec: 4676.66 - lr: 0.000043 - momentum: 0.000000
87
+ 2023-10-25 21:27:58,648 epoch 1 - iter 140/146 - loss 0.70541709 - time (sec): 9.17 - samples/sec: 4657.20 - lr: 0.000048 - momentum: 0.000000
88
+ 2023-10-25 21:27:59,025 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 21:27:59,025 EPOCH 1 done: loss 0.6862 - lr: 0.000048
90
+ 2023-10-25 21:27:59,692 DEV : loss 0.1474415361881256 - f1-score (micro avg) 0.5733
91
+ 2023-10-25 21:27:59,697 saving best model
92
+ 2023-10-25 21:28:00,164 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 21:28:01,070 epoch 2 - iter 14/146 - loss 0.17089233 - time (sec): 0.90 - samples/sec: 4814.35 - lr: 0.000050 - momentum: 0.000000
94
+ 2023-10-25 21:28:02,016 epoch 2 - iter 28/146 - loss 0.21428820 - time (sec): 1.85 - samples/sec: 4654.61 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 21:28:02,882 epoch 2 - iter 42/146 - loss 0.20237772 - time (sec): 2.72 - samples/sec: 4512.63 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 21:28:03,920 epoch 2 - iter 56/146 - loss 0.18853700 - time (sec): 3.75 - samples/sec: 4493.86 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 21:28:04,814 epoch 2 - iter 70/146 - loss 0.18382748 - time (sec): 4.65 - samples/sec: 4572.10 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 21:28:05,612 epoch 2 - iter 84/146 - loss 0.18071178 - time (sec): 5.45 - samples/sec: 4642.87 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 21:28:06,448 epoch 2 - iter 98/146 - loss 0.17992603 - time (sec): 6.28 - samples/sec: 4685.36 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 21:28:07,296 epoch 2 - iter 112/146 - loss 0.17844954 - time (sec): 7.13 - samples/sec: 4705.85 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 21:28:08,253 epoch 2 - iter 126/146 - loss 0.17872038 - time (sec): 8.09 - samples/sec: 4685.94 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 21:28:09,246 epoch 2 - iter 140/146 - loss 0.17249572 - time (sec): 9.08 - samples/sec: 4687.55 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-25 21:28:09,584 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 21:28:09,584 EPOCH 2 done: loss 0.1707 - lr: 0.000045
105
+ 2023-10-25 21:28:10,498 DEV : loss 0.1254296749830246 - f1-score (micro avg) 0.6564
106
+ 2023-10-25 21:28:10,503 saving best model
107
+ 2023-10-25 21:28:11,122 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-25 21:28:12,433 epoch 3 - iter 14/146 - loss 0.08260202 - time (sec): 1.31 - samples/sec: 4377.23 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-25 21:28:13,378 epoch 3 - iter 28/146 - loss 0.09990362 - time (sec): 2.25 - samples/sec: 4505.97 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 21:28:14,194 epoch 3 - iter 42/146 - loss 0.10051524 - time (sec): 3.07 - samples/sec: 4619.88 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-25 21:28:15,072 epoch 3 - iter 56/146 - loss 0.09789885 - time (sec): 3.95 - samples/sec: 4535.60 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 21:28:15,991 epoch 3 - iter 70/146 - loss 0.09781657 - time (sec): 4.87 - samples/sec: 4595.00 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-25 21:28:16,812 epoch 3 - iter 84/146 - loss 0.09773301 - time (sec): 5.69 - samples/sec: 4587.72 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 21:28:17,705 epoch 3 - iter 98/146 - loss 0.09125920 - time (sec): 6.58 - samples/sec: 4628.73 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-25 21:28:18,551 epoch 3 - iter 112/146 - loss 0.09081431 - time (sec): 7.43 - samples/sec: 4588.91 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-25 21:28:19,452 epoch 3 - iter 126/146 - loss 0.09242276 - time (sec): 8.33 - samples/sec: 4629.85 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-25 21:28:20,231 epoch 3 - iter 140/146 - loss 0.08938489 - time (sec): 9.11 - samples/sec: 4708.37 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-25 21:28:20,593 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-25 21:28:20,593 EPOCH 3 done: loss 0.0898 - lr: 0.000039
120
+ 2023-10-25 21:28:21,508 DEV : loss 0.11051346361637115 - f1-score (micro avg) 0.7417
121
+ 2023-10-25 21:28:21,513 saving best model
122
+ 2023-10-25 21:28:21,994 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-25 21:28:22,771 epoch 4 - iter 14/146 - loss 0.06118331 - time (sec): 0.78 - samples/sec: 4971.16 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-25 21:28:23,745 epoch 4 - iter 28/146 - loss 0.04975956 - time (sec): 1.75 - samples/sec: 4691.92 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-25 21:28:24,628 epoch 4 - iter 42/146 - loss 0.04676491 - time (sec): 2.63 - samples/sec: 4792.58 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-25 21:28:25,468 epoch 4 - iter 56/146 - loss 0.04813187 - time (sec): 3.47 - samples/sec: 4634.02 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-25 21:28:26,397 epoch 4 - iter 70/146 - loss 0.04806710 - time (sec): 4.40 - samples/sec: 4840.63 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-25 21:28:27,403 epoch 4 - iter 84/146 - loss 0.05168396 - time (sec): 5.41 - samples/sec: 4870.21 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-25 21:28:28,249 epoch 4 - iter 98/146 - loss 0.05023341 - time (sec): 6.25 - samples/sec: 4935.40 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-25 21:28:29,084 epoch 4 - iter 112/146 - loss 0.05330836 - time (sec): 7.09 - samples/sec: 4889.49 - lr: 0.000035 - momentum: 0.000000
131
+ 2023-10-25 21:28:30,183 epoch 4 - iter 126/146 - loss 0.05565502 - time (sec): 8.19 - samples/sec: 4793.60 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-25 21:28:30,966 epoch 4 - iter 140/146 - loss 0.05422907 - time (sec): 8.97 - samples/sec: 4782.18 - lr: 0.000034 - momentum: 0.000000
133
+ 2023-10-25 21:28:31,283 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-25 21:28:31,283 EPOCH 4 done: loss 0.0546 - lr: 0.000034
135
+ 2023-10-25 21:28:32,200 DEV : loss 0.09850870817899704 - f1-score (micro avg) 0.7521
136
+ 2023-10-25 21:28:32,205 saving best model
137
+ 2023-10-25 21:28:32,815 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-25 21:28:33,722 epoch 5 - iter 14/146 - loss 0.02659804 - time (sec): 0.91 - samples/sec: 4906.64 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-25 21:28:34,641 epoch 5 - iter 28/146 - loss 0.03160875 - time (sec): 1.82 - samples/sec: 4673.76 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-25 21:28:35,524 epoch 5 - iter 42/146 - loss 0.02704574 - time (sec): 2.71 - samples/sec: 4687.55 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-25 21:28:36,385 epoch 5 - iter 56/146 - loss 0.02872717 - time (sec): 3.57 - samples/sec: 4740.65 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-25 21:28:37,247 epoch 5 - iter 70/146 - loss 0.02814581 - time (sec): 4.43 - samples/sec: 4780.67 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-25 21:28:38,017 epoch 5 - iter 84/146 - loss 0.02973212 - time (sec): 5.20 - samples/sec: 4792.43 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-25 21:28:39,141 epoch 5 - iter 98/146 - loss 0.03124285 - time (sec): 6.32 - samples/sec: 4699.64 - lr: 0.000030 - momentum: 0.000000
145
+ 2023-10-25 21:28:39,990 epoch 5 - iter 112/146 - loss 0.03154566 - time (sec): 7.17 - samples/sec: 4751.94 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-25 21:28:40,965 epoch 5 - iter 126/146 - loss 0.03179183 - time (sec): 8.15 - samples/sec: 4757.02 - lr: 0.000029 - momentum: 0.000000
147
+ 2023-10-25 21:28:41,808 epoch 5 - iter 140/146 - loss 0.03049933 - time (sec): 8.99 - samples/sec: 4780.25 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-25 21:28:42,164 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 21:28:42,165 EPOCH 5 done: loss 0.0306 - lr: 0.000028
150
+ 2023-10-25 21:28:43,083 DEV : loss 0.11159916967153549 - f1-score (micro avg) 0.7301
151
+ 2023-10-25 21:28:43,088 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-25 21:28:44,021 epoch 6 - iter 14/146 - loss 0.02453557 - time (sec): 0.93 - samples/sec: 5113.56 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-25 21:28:44,918 epoch 6 - iter 28/146 - loss 0.02735209 - time (sec): 1.83 - samples/sec: 4855.99 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-25 21:28:45,785 epoch 6 - iter 42/146 - loss 0.02225382 - time (sec): 2.70 - samples/sec: 4893.55 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-25 21:28:46,824 epoch 6 - iter 56/146 - loss 0.03298141 - time (sec): 3.73 - samples/sec: 4702.92 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-25 21:28:47,652 epoch 6 - iter 70/146 - loss 0.03018167 - time (sec): 4.56 - samples/sec: 4819.79 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-25 21:28:48,464 epoch 6 - iter 84/146 - loss 0.02855897 - time (sec): 5.38 - samples/sec: 4798.07 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-25 21:28:49,401 epoch 6 - iter 98/146 - loss 0.02624982 - time (sec): 6.31 - samples/sec: 4759.70 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-25 21:28:50,309 epoch 6 - iter 112/146 - loss 0.02634661 - time (sec): 7.22 - samples/sec: 4728.86 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-25 21:28:51,351 epoch 6 - iter 126/146 - loss 0.02455669 - time (sec): 8.26 - samples/sec: 4696.35 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-25 21:28:52,156 epoch 6 - iter 140/146 - loss 0.02413772 - time (sec): 9.07 - samples/sec: 4692.77 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-25 21:28:52,526 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 21:28:52,526 EPOCH 6 done: loss 0.0243 - lr: 0.000023
164
+ 2023-10-25 21:28:53,437 DEV : loss 0.12900103628635406 - f1-score (micro avg) 0.7484
165
+ 2023-10-25 21:28:53,442 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-25 21:28:54,337 epoch 7 - iter 14/146 - loss 0.01901767 - time (sec): 0.89 - samples/sec: 5157.57 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-25 21:28:55,345 epoch 7 - iter 28/146 - loss 0.02538527 - time (sec): 1.90 - samples/sec: 4964.20 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-25 21:28:56,194 epoch 7 - iter 42/146 - loss 0.02265917 - time (sec): 2.75 - samples/sec: 4868.84 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-25 21:28:57,056 epoch 7 - iter 56/146 - loss 0.01889249 - time (sec): 3.61 - samples/sec: 4781.15 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-25 21:28:57,849 epoch 7 - iter 70/146 - loss 0.01700472 - time (sec): 4.41 - samples/sec: 4763.45 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-25 21:28:58,890 epoch 7 - iter 84/146 - loss 0.01723572 - time (sec): 5.45 - samples/sec: 4727.82 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-25 21:28:59,804 epoch 7 - iter 98/146 - loss 0.01698293 - time (sec): 6.36 - samples/sec: 4774.84 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-25 21:29:00,640 epoch 7 - iter 112/146 - loss 0.01540217 - time (sec): 7.20 - samples/sec: 4755.44 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-25 21:29:01,566 epoch 7 - iter 126/146 - loss 0.01515024 - time (sec): 8.12 - samples/sec: 4737.44 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-25 21:29:02,435 epoch 7 - iter 140/146 - loss 0.01548718 - time (sec): 8.99 - samples/sec: 4711.76 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-25 21:29:02,899 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-25 21:29:02,899 EPOCH 7 done: loss 0.0149 - lr: 0.000017
178
+ 2023-10-25 21:29:03,821 DEV : loss 0.16139209270477295 - f1-score (micro avg) 0.719
179
+ 2023-10-25 21:29:03,825 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-25 21:29:04,777 epoch 8 - iter 14/146 - loss 0.01190115 - time (sec): 0.95 - samples/sec: 4467.82 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-25 21:29:05,705 epoch 8 - iter 28/146 - loss 0.01702526 - time (sec): 1.88 - samples/sec: 4501.00 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-25 21:29:06,547 epoch 8 - iter 42/146 - loss 0.01300344 - time (sec): 2.72 - samples/sec: 4594.14 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-25 21:29:07,500 epoch 8 - iter 56/146 - loss 0.01363888 - time (sec): 3.67 - samples/sec: 4669.93 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-25 21:29:08,334 epoch 8 - iter 70/146 - loss 0.01399870 - time (sec): 4.51 - samples/sec: 4657.71 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-25 21:29:09,169 epoch 8 - iter 84/146 - loss 0.01463633 - time (sec): 5.34 - samples/sec: 4716.96 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-25 21:29:10,006 epoch 8 - iter 98/146 - loss 0.01386733 - time (sec): 6.18 - samples/sec: 4689.65 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-25 21:29:10,942 epoch 8 - iter 112/146 - loss 0.01351418 - time (sec): 7.12 - samples/sec: 4656.21 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-25 21:29:11,872 epoch 8 - iter 126/146 - loss 0.01318788 - time (sec): 8.05 - samples/sec: 4666.02 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-25 21:29:12,874 epoch 8 - iter 140/146 - loss 0.01256842 - time (sec): 9.05 - samples/sec: 4703.36 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-25 21:29:13,263 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-25 21:29:13,264 EPOCH 8 done: loss 0.0127 - lr: 0.000012
192
+ 2023-10-25 21:29:14,203 DEV : loss 0.16343142092227936 - f1-score (micro avg) 0.7269
193
+ 2023-10-25 21:29:14,208 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-25 21:29:15,182 epoch 9 - iter 14/146 - loss 0.00051275 - time (sec): 0.97 - samples/sec: 5085.26 - lr: 0.000011 - momentum: 0.000000
195
+ 2023-10-25 21:29:16,024 epoch 9 - iter 28/146 - loss 0.00491903 - time (sec): 1.82 - samples/sec: 5033.56 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-25 21:29:16,859 epoch 9 - iter 42/146 - loss 0.00934029 - time (sec): 2.65 - samples/sec: 4919.50 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-25 21:29:17,799 epoch 9 - iter 56/146 - loss 0.00934967 - time (sec): 3.59 - samples/sec: 4914.97 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-25 21:29:18,748 epoch 9 - iter 70/146 - loss 0.01185195 - time (sec): 4.54 - samples/sec: 4825.98 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-25 21:29:19,899 epoch 9 - iter 84/146 - loss 0.01258572 - time (sec): 5.69 - samples/sec: 4605.52 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-25 21:29:20,792 epoch 9 - iter 98/146 - loss 0.01171045 - time (sec): 6.58 - samples/sec: 4635.70 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-25 21:29:21,692 epoch 9 - iter 112/146 - loss 0.01098300 - time (sec): 7.48 - samples/sec: 4640.80 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-25 21:29:22,569 epoch 9 - iter 126/146 - loss 0.01080796 - time (sec): 8.36 - samples/sec: 4615.82 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-25 21:29:23,467 epoch 9 - iter 140/146 - loss 0.01040519 - time (sec): 9.26 - samples/sec: 4609.56 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-25 21:29:23,818 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-25 21:29:23,818 EPOCH 9 done: loss 0.0101 - lr: 0.000006
206
+ 2023-10-25 21:29:24,734 DEV : loss 0.16184502840042114 - f1-score (micro avg) 0.7387
207
+ 2023-10-25 21:29:24,738 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-25 21:29:25,626 epoch 10 - iter 14/146 - loss 0.00435948 - time (sec): 0.89 - samples/sec: 4844.74 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-25 21:29:26,494 epoch 10 - iter 28/146 - loss 0.00294552 - time (sec): 1.75 - samples/sec: 4538.68 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-25 21:29:27,388 epoch 10 - iter 42/146 - loss 0.00866389 - time (sec): 2.65 - samples/sec: 4561.33 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-25 21:29:28,184 epoch 10 - iter 56/146 - loss 0.00811777 - time (sec): 3.44 - samples/sec: 4587.61 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-25 21:29:29,168 epoch 10 - iter 70/146 - loss 0.00765822 - time (sec): 4.43 - samples/sec: 4645.83 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-25 21:29:30,062 epoch 10 - iter 84/146 - loss 0.00758295 - time (sec): 5.32 - samples/sec: 4648.84 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-25 21:29:30,892 epoch 10 - iter 98/146 - loss 0.00682628 - time (sec): 6.15 - samples/sec: 4734.92 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-25 21:29:31,880 epoch 10 - iter 112/146 - loss 0.00744500 - time (sec): 7.14 - samples/sec: 4766.54 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-25 21:29:32,788 epoch 10 - iter 126/146 - loss 0.00674236 - time (sec): 8.05 - samples/sec: 4750.00 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-25 21:29:33,723 epoch 10 - iter 140/146 - loss 0.00623926 - time (sec): 8.98 - samples/sec: 4789.04 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-25 21:29:34,035 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-25 21:29:34,035 EPOCH 10 done: loss 0.0060 - lr: 0.000000
220
+ 2023-10-25 21:29:34,945 DEV : loss 0.164560928940773 - f1-score (micro avg) 0.7473
221
+ 2023-10-25 21:29:35,418 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-25 21:29:35,419 Loading model from best epoch ...
223
+ 2023-10-25 21:29:37,026 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 21:29:38,560
225
+ Results:
226
+ - F-score (micro) 0.7441
227
+ - F-score (macro) 0.6586
228
+ - Accuracy 0.6156
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ PER 0.7978 0.8506 0.8234 348
234
+ LOC 0.6375 0.7816 0.7022 261
235
+ ORG 0.4884 0.4038 0.4421 52
236
+ HumanProd 0.5862 0.7727 0.6667 22
237
+
238
+ micro avg 0.7051 0.7877 0.7441 683
239
+ macro avg 0.6275 0.7022 0.6586 683
240
+ weighted avg 0.7062 0.7877 0.7430 683
241
+
242
+ 2023-10-25 21:29:38,560 ----------------------------------------------------------------------------------------------------