Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
f104962
•
1 Parent(s): 1c2332f

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a7f85a6da5c41a7d519689d2a6c509f88794856b200b96b882a8de9460629b
3
+ size 443335879
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 13:13:53 0.0000 0.7518 0.1836 0.6857 0.6020 0.6411 0.4840
3
+ 2 13:14:31 0.0000 0.1618 0.1280 0.6460 0.7162 0.6793 0.5357
4
+ 3 13:15:09 0.0000 0.0882 0.1201 0.7469 0.7498 0.7483 0.6124
5
+ 4 13:15:47 0.0000 0.0506 0.1425 0.7239 0.7709 0.7467 0.6113
6
+ 5 13:16:24 0.0000 0.0352 0.1665 0.7272 0.7733 0.7495 0.6162
7
+ 6 13:17:02 0.0000 0.0212 0.1730 0.7548 0.7944 0.7741 0.6480
8
+ 7 13:17:39 0.0000 0.0155 0.1986 0.7874 0.7787 0.7830 0.6587
9
+ 8 13:18:17 0.0000 0.0108 0.2085 0.7622 0.7920 0.7768 0.6506
10
+ 9 13:18:55 0.0000 0.0070 0.2127 0.7544 0.8022 0.7776 0.6527
11
+ 10 13:19:33 0.0000 0.0051 0.2154 0.7484 0.8045 0.7754 0.6500
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 13:13:20,057 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 13:13:20,058 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 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=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 13:13:20,058 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
52
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
53
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 13:13:20,058 Train: 3575 sentences
55
+ 2023-10-13 13:13:20,058 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 13:13:20,058 Training Params:
58
+ 2023-10-13 13:13:20,058 - learning_rate: "3e-05"
59
+ 2023-10-13 13:13:20,058 - mini_batch_size: "8"
60
+ 2023-10-13 13:13:20,058 - max_epochs: "10"
61
+ 2023-10-13 13:13:20,058 - shuffle: "True"
62
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 13:13:20,058 Plugins:
64
+ 2023-10-13 13:13:20,058 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 13:13:20,058 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 13:13:20,058 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 13:13:20,058 Computation:
70
+ 2023-10-13 13:13:20,058 - compute on device: cuda:0
71
+ 2023-10-13 13:13:20,058 - embedding storage: none
72
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 13:13:20,058 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4"
74
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 13:13:20,058 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 13:13:22,914 epoch 1 - iter 44/447 - loss 3.11777082 - time (sec): 2.85 - samples/sec: 3068.12 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 13:13:25,858 epoch 1 - iter 88/447 - loss 2.36193790 - time (sec): 5.80 - samples/sec: 3064.20 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 13:13:28,576 epoch 1 - iter 132/447 - loss 1.79092667 - time (sec): 8.52 - samples/sec: 3020.50 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 13:13:31,655 epoch 1 - iter 176/447 - loss 1.44848537 - time (sec): 11.60 - samples/sec: 2976.51 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 13:13:34,436 epoch 1 - iter 220/447 - loss 1.23228332 - time (sec): 14.38 - samples/sec: 2970.99 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 13:13:37,240 epoch 1 - iter 264/447 - loss 1.08886007 - time (sec): 17.18 - samples/sec: 2964.39 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 13:13:39,997 epoch 1 - iter 308/447 - loss 0.98213248 - time (sec): 19.94 - samples/sec: 2970.69 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 13:13:42,747 epoch 1 - iter 352/447 - loss 0.89561881 - time (sec): 22.69 - samples/sec: 2980.97 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 13:13:45,432 epoch 1 - iter 396/447 - loss 0.82242688 - time (sec): 25.37 - samples/sec: 2981.41 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 13:13:48,627 epoch 1 - iter 440/447 - loss 0.75951686 - time (sec): 28.57 - samples/sec: 2983.72 - lr: 0.000029 - momentum: 0.000000
86
+ 2023-10-13 13:13:49,039 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 13:13:49,040 EPOCH 1 done: loss 0.7518 - lr: 0.000029
88
+ 2023-10-13 13:13:53,953 DEV : loss 0.18360073864459991 - f1-score (micro avg) 0.6411
89
+ 2023-10-13 13:13:53,978 saving best model
90
+ 2023-10-13 13:13:54,320 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 13:13:57,283 epoch 2 - iter 44/447 - loss 0.21325634 - time (sec): 2.96 - samples/sec: 3023.79 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 13:14:00,394 epoch 2 - iter 88/447 - loss 0.19763757 - time (sec): 6.07 - samples/sec: 3047.06 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 13:14:02,962 epoch 2 - iter 132/447 - loss 0.18755004 - time (sec): 8.64 - samples/sec: 3031.14 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 13:14:05,602 epoch 2 - iter 176/447 - loss 0.19041313 - time (sec): 11.28 - samples/sec: 3055.96 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 13:14:08,514 epoch 2 - iter 220/447 - loss 0.18445879 - time (sec): 14.19 - samples/sec: 3035.46 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 13:14:11,208 epoch 2 - iter 264/447 - loss 0.17645831 - time (sec): 16.89 - samples/sec: 3063.78 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 13:14:13,825 epoch 2 - iter 308/447 - loss 0.17200425 - time (sec): 19.50 - samples/sec: 3061.76 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 13:14:16,387 epoch 2 - iter 352/447 - loss 0.16971408 - time (sec): 22.07 - samples/sec: 3070.68 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 13:14:19,560 epoch 2 - iter 396/447 - loss 0.16473002 - time (sec): 25.24 - samples/sec: 3044.12 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 13:14:22,291 epoch 2 - iter 440/447 - loss 0.16259189 - time (sec): 27.97 - samples/sec: 3047.79 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 13:14:22,795 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 13:14:22,796 EPOCH 2 done: loss 0.1618 - lr: 0.000027
103
+ 2023-10-13 13:14:31,384 DEV : loss 0.1280011683702469 - f1-score (micro avg) 0.6793
104
+ 2023-10-13 13:14:31,411 saving best model
105
+ 2023-10-13 13:14:31,868 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 13:14:34,764 epoch 3 - iter 44/447 - loss 0.10970391 - time (sec): 2.89 - samples/sec: 2957.74 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 13:14:38,002 epoch 3 - iter 88/447 - loss 0.10095129 - time (sec): 6.13 - samples/sec: 2911.29 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 13:14:40,901 epoch 3 - iter 132/447 - loss 0.09159053 - time (sec): 9.03 - samples/sec: 2902.88 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 13:14:43,698 epoch 3 - iter 176/447 - loss 0.09005402 - time (sec): 11.83 - samples/sec: 2913.87 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 13:14:46,381 epoch 3 - iter 220/447 - loss 0.08834012 - time (sec): 14.51 - samples/sec: 2898.73 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 13:14:49,199 epoch 3 - iter 264/447 - loss 0.08867495 - time (sec): 17.33 - samples/sec: 2917.60 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 13:14:51,891 epoch 3 - iter 308/447 - loss 0.08828525 - time (sec): 20.02 - samples/sec: 2931.90 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 13:14:54,732 epoch 3 - iter 352/447 - loss 0.08402043 - time (sec): 22.86 - samples/sec: 2953.93 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 13:14:57,347 epoch 3 - iter 396/447 - loss 0.08793302 - time (sec): 25.48 - samples/sec: 2976.67 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 13:15:00,431 epoch 3 - iter 440/447 - loss 0.08822390 - time (sec): 28.56 - samples/sec: 2987.02 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 13:15:00,838 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 13:15:00,839 EPOCH 3 done: loss 0.0882 - lr: 0.000023
118
+ 2023-10-13 13:15:09,537 DEV : loss 0.1200539767742157 - f1-score (micro avg) 0.7483
119
+ 2023-10-13 13:15:09,567 saving best model
120
+ 2023-10-13 13:15:09,992 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 13:15:12,750 epoch 4 - iter 44/447 - loss 0.04601992 - time (sec): 2.76 - samples/sec: 3061.98 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 13:15:15,345 epoch 4 - iter 88/447 - loss 0.05132868 - time (sec): 5.35 - samples/sec: 3066.86 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 13:15:18,079 epoch 4 - iter 132/447 - loss 0.04850121 - time (sec): 8.09 - samples/sec: 3088.42 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 13:15:20,701 epoch 4 - iter 176/447 - loss 0.04502986 - time (sec): 10.71 - samples/sec: 3112.42 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 13:15:24,117 epoch 4 - iter 220/447 - loss 0.04746775 - time (sec): 14.12 - samples/sec: 3070.89 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 13:15:26,903 epoch 4 - iter 264/447 - loss 0.04791562 - time (sec): 16.91 - samples/sec: 3071.67 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 13:15:29,531 epoch 4 - iter 308/447 - loss 0.04886274 - time (sec): 19.54 - samples/sec: 3060.31 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 13:15:32,213 epoch 4 - iter 352/447 - loss 0.04909487 - time (sec): 22.22 - samples/sec: 3052.34 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 13:15:35,496 epoch 4 - iter 396/447 - loss 0.04995671 - time (sec): 25.50 - samples/sec: 3031.17 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 13:15:38,187 epoch 4 - iter 440/447 - loss 0.05051059 - time (sec): 28.19 - samples/sec: 3023.06 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 13:15:38,616 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 13:15:38,617 EPOCH 4 done: loss 0.0506 - lr: 0.000020
133
+ 2023-10-13 13:15:47,029 DEV : loss 0.14254607260227203 - f1-score (micro avg) 0.7467
134
+ 2023-10-13 13:15:47,056 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-13 13:15:49,999 epoch 5 - iter 44/447 - loss 0.03966301 - time (sec): 2.94 - samples/sec: 3049.04 - lr: 0.000020 - momentum: 0.000000
136
+ 2023-10-13 13:15:52,832 epoch 5 - iter 88/447 - loss 0.03669848 - time (sec): 5.78 - samples/sec: 2990.27 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-13 13:15:55,761 epoch 5 - iter 132/447 - loss 0.03533218 - time (sec): 8.70 - samples/sec: 3000.27 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 13:15:58,591 epoch 5 - iter 176/447 - loss 0.03429375 - time (sec): 11.53 - samples/sec: 3006.74 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 13:16:01,229 epoch 5 - iter 220/447 - loss 0.03499214 - time (sec): 14.17 - samples/sec: 3009.08 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-13 13:16:04,099 epoch 5 - iter 264/447 - loss 0.03588282 - time (sec): 17.04 - samples/sec: 3007.92 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 13:16:07,274 epoch 5 - iter 308/447 - loss 0.03556606 - time (sec): 20.22 - samples/sec: 2996.33 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 13:16:09,873 epoch 5 - iter 352/447 - loss 0.03896903 - time (sec): 22.82 - samples/sec: 3006.18 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-13 13:16:12,685 epoch 5 - iter 396/447 - loss 0.03718731 - time (sec): 25.63 - samples/sec: 2995.43 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 13:16:15,538 epoch 5 - iter 440/447 - loss 0.03556750 - time (sec): 28.48 - samples/sec: 2997.63 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 13:16:15,921 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-13 13:16:15,922 EPOCH 5 done: loss 0.0352 - lr: 0.000017
147
+ 2023-10-13 13:16:24,461 DEV : loss 0.16648352146148682 - f1-score (micro avg) 0.7495
148
+ 2023-10-13 13:16:24,487 saving best model
149
+ 2023-10-13 13:16:24,910 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 13:16:27,776 epoch 6 - iter 44/447 - loss 0.01297918 - time (sec): 2.86 - samples/sec: 3007.92 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-13 13:16:30,760 epoch 6 - iter 88/447 - loss 0.01521816 - time (sec): 5.85 - samples/sec: 3013.80 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 13:16:33,450 epoch 6 - iter 132/447 - loss 0.01783763 - time (sec): 8.53 - samples/sec: 3042.85 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 13:16:36,642 epoch 6 - iter 176/447 - loss 0.01724718 - time (sec): 11.73 - samples/sec: 3055.21 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-13 13:16:39,440 epoch 6 - iter 220/447 - loss 0.01881627 - time (sec): 14.53 - samples/sec: 2985.20 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 13:16:42,158 epoch 6 - iter 264/447 - loss 0.01817880 - time (sec): 17.24 - samples/sec: 2985.53 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 13:16:45,022 epoch 6 - iter 308/447 - loss 0.01947892 - time (sec): 20.11 - samples/sec: 2982.50 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-13 13:16:47,824 epoch 6 - iter 352/447 - loss 0.02012745 - time (sec): 22.91 - samples/sec: 2969.62 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 13:16:50,622 epoch 6 - iter 396/447 - loss 0.02016141 - time (sec): 25.71 - samples/sec: 2992.05 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 13:16:53,327 epoch 6 - iter 440/447 - loss 0.02126196 - time (sec): 28.41 - samples/sec: 3002.50 - lr: 0.000013 - momentum: 0.000000
160
+ 2023-10-13 13:16:53,729 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 13:16:53,730 EPOCH 6 done: loss 0.0212 - lr: 0.000013
162
+ 2023-10-13 13:17:02,414 DEV : loss 0.173013374209404 - f1-score (micro avg) 0.7741
163
+ 2023-10-13 13:17:02,440 saving best model
164
+ 2023-10-13 13:17:02,868 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 13:17:06,304 epoch 7 - iter 44/447 - loss 0.02481076 - time (sec): 3.43 - samples/sec: 2891.86 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 13:17:09,074 epoch 7 - iter 88/447 - loss 0.01608324 - time (sec): 6.20 - samples/sec: 2875.39 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 13:17:12,040 epoch 7 - iter 132/447 - loss 0.01410154 - time (sec): 9.17 - samples/sec: 2899.58 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 13:17:14,929 epoch 7 - iter 176/447 - loss 0.01489213 - time (sec): 12.06 - samples/sec: 2938.16 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 13:17:17,754 epoch 7 - iter 220/447 - loss 0.01604270 - time (sec): 14.88 - samples/sec: 2952.10 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 13:17:20,446 epoch 7 - iter 264/447 - loss 0.01618986 - time (sec): 17.58 - samples/sec: 2938.06 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 13:17:23,179 epoch 7 - iter 308/447 - loss 0.01644546 - time (sec): 20.31 - samples/sec: 2961.42 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 13:17:25,924 epoch 7 - iter 352/447 - loss 0.01537412 - time (sec): 23.05 - samples/sec: 2965.75 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 13:17:28,546 epoch 7 - iter 396/447 - loss 0.01579262 - time (sec): 25.68 - samples/sec: 2974.59 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 13:17:31,395 epoch 7 - iter 440/447 - loss 0.01544474 - time (sec): 28.53 - samples/sec: 2995.90 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 13:17:31,781 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 13:17:31,782 EPOCH 7 done: loss 0.0155 - lr: 0.000010
177
+ 2023-10-13 13:17:39,921 DEV : loss 0.1985795646905899 - f1-score (micro avg) 0.783
178
+ 2023-10-13 13:17:39,950 saving best model
179
+ 2023-10-13 13:17:40,398 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 13:17:43,232 epoch 8 - iter 44/447 - loss 0.00957408 - time (sec): 2.83 - samples/sec: 3033.73 - lr: 0.000010 - momentum: 0.000000
181
+ 2023-10-13 13:17:46,091 epoch 8 - iter 88/447 - loss 0.00922003 - time (sec): 5.69 - samples/sec: 3010.78 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 13:17:48,808 epoch 8 - iter 132/447 - loss 0.01038901 - time (sec): 8.41 - samples/sec: 3015.07 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 13:17:51,553 epoch 8 - iter 176/447 - loss 0.01041656 - time (sec): 11.15 - samples/sec: 3004.15 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-13 13:17:54,368 epoch 8 - iter 220/447 - loss 0.00978835 - time (sec): 13.97 - samples/sec: 2991.67 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 13:17:57,374 epoch 8 - iter 264/447 - loss 0.00983571 - time (sec): 16.97 - samples/sec: 2957.65 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 13:18:00,184 epoch 8 - iter 308/447 - loss 0.00935734 - time (sec): 19.78 - samples/sec: 2954.35 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-13 13:18:03,374 epoch 8 - iter 352/447 - loss 0.01020653 - time (sec): 22.97 - samples/sec: 2943.90 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 13:18:06,439 epoch 8 - iter 396/447 - loss 0.01083975 - time (sec): 26.04 - samples/sec: 2945.85 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 13:18:09,151 epoch 8 - iter 440/447 - loss 0.01083258 - time (sec): 28.75 - samples/sec: 2958.89 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-13 13:18:09,642 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 13:18:09,643 EPOCH 8 done: loss 0.0108 - lr: 0.000007
192
+ 2023-10-13 13:18:17,739 DEV : loss 0.2084827721118927 - f1-score (micro avg) 0.7768
193
+ 2023-10-13 13:18:17,767 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-13 13:18:20,478 epoch 9 - iter 44/447 - loss 0.00612637 - time (sec): 2.71 - samples/sec: 3061.27 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 13:18:23,449 epoch 9 - iter 88/447 - loss 0.00545493 - time (sec): 5.68 - samples/sec: 2988.83 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 13:18:26,013 epoch 9 - iter 132/447 - loss 0.00810978 - time (sec): 8.24 - samples/sec: 3022.80 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 13:18:28,792 epoch 9 - iter 176/447 - loss 0.00943692 - time (sec): 11.02 - samples/sec: 3017.39 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 13:18:31,737 epoch 9 - iter 220/447 - loss 0.00827507 - time (sec): 13.97 - samples/sec: 3011.35 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 13:18:34,594 epoch 9 - iter 264/447 - loss 0.00745688 - time (sec): 16.83 - samples/sec: 2998.27 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 13:18:37,258 epoch 9 - iter 308/447 - loss 0.00768552 - time (sec): 19.49 - samples/sec: 3026.07 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 13:18:41,084 epoch 9 - iter 352/447 - loss 0.00760993 - time (sec): 23.32 - samples/sec: 2963.42 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 13:18:43,947 epoch 9 - iter 396/447 - loss 0.00728736 - time (sec): 26.18 - samples/sec: 2954.39 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 13:18:46,795 epoch 9 - iter 440/447 - loss 0.00694997 - time (sec): 29.03 - samples/sec: 2944.30 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-13 13:18:47,199 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-13 13:18:47,199 EPOCH 9 done: loss 0.0070 - lr: 0.000003
206
+ 2023-10-13 13:18:55,583 DEV : loss 0.2126864343881607 - f1-score (micro avg) 0.7776
207
+ 2023-10-13 13:18:55,611 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-13 13:18:58,894 epoch 10 - iter 44/447 - loss 0.00635944 - time (sec): 3.28 - samples/sec: 3012.37 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-13 13:19:02,008 epoch 10 - iter 88/447 - loss 0.00527678 - time (sec): 6.40 - samples/sec: 2899.98 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 13:19:04,861 epoch 10 - iter 132/447 - loss 0.00649806 - time (sec): 9.25 - samples/sec: 2899.02 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-13 13:19:07,541 epoch 10 - iter 176/447 - loss 0.00621582 - time (sec): 11.93 - samples/sec: 2918.26 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 13:19:10,370 epoch 10 - iter 220/447 - loss 0.00571437 - time (sec): 14.76 - samples/sec: 2934.41 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 13:19:13,065 epoch 10 - iter 264/447 - loss 0.00591055 - time (sec): 17.45 - samples/sec: 2939.79 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-13 13:19:15,840 epoch 10 - iter 308/447 - loss 0.00566945 - time (sec): 20.23 - samples/sec: 2941.50 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 13:19:18,771 epoch 10 - iter 352/447 - loss 0.00536572 - time (sec): 23.16 - samples/sec: 2940.96 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 13:19:21,445 epoch 10 - iter 396/447 - loss 0.00529827 - time (sec): 25.83 - samples/sec: 2959.09 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-13 13:19:24,347 epoch 10 - iter 440/447 - loss 0.00512907 - time (sec): 28.73 - samples/sec: 2976.79 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 13:19:24,753 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-13 13:19:24,753 EPOCH 10 done: loss 0.0051 - lr: 0.000000
220
+ 2023-10-13 13:19:33,426 DEV : loss 0.2154415100812912 - f1-score (micro avg) 0.7754
221
+ 2023-10-13 13:19:33,796 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-13 13:19:33,798 Loading model from best epoch ...
223
+ 2023-10-13 13:19:35,452 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
224
+ 2023-10-13 13:19:40,515
225
+ Results:
226
+ - F-score (micro) 0.7437
227
+ - F-score (macro) 0.6536
228
+ - Accuracy 0.6094
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ loc 0.8596 0.8322 0.8457 596
234
+ pers 0.6605 0.7538 0.7041 333
235
+ org 0.5310 0.4545 0.4898 132
236
+ prod 0.5957 0.4242 0.4956 66
237
+ time 0.7115 0.7551 0.7327 49
238
+
239
+ micro avg 0.7459 0.7415 0.7437 1176
240
+ macro avg 0.6717 0.6440 0.6536 1176
241
+ weighted avg 0.7454 0.7415 0.7413 1176
242
+
243
+ 2023-10-13 13:19:40,515 ----------------------------------------------------------------------------------------------------