Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
e20ca7d
•
1 Parent(s): 4715869

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 +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5eec8fb3f58cfde3282caa7cffd4d91f878b83fd31fdb795bd770dadeaf0904
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 12:42:05 0.0000 0.6927 0.1951 0.6649 0.5927 0.6267 0.4691
3
+ 2 12:42:43 0.0000 0.1650 0.1415 0.6406 0.6927 0.6657 0.5139
4
+ 3 12:43:22 0.0000 0.0897 0.1257 0.7442 0.7326 0.7384 0.6057
5
+ 4 12:44:00 0.0000 0.0535 0.1439 0.7615 0.7740 0.7677 0.6429
6
+ 5 12:44:38 0.0000 0.0340 0.1617 0.7771 0.7795 0.7783 0.6525
7
+ 6 12:45:16 0.0000 0.0244 0.1754 0.7720 0.7811 0.7765 0.6495
8
+ 7 12:45:53 0.0000 0.0152 0.1842 0.7752 0.7764 0.7758 0.6516
9
+ 8 12:46:31 0.0000 0.0093 0.2056 0.7804 0.7889 0.7846 0.6629
10
+ 9 12:47:09 0.0000 0.0071 0.2144 0.7879 0.7873 0.7876 0.6660
11
+ 10 12:47:47 0.0000 0.0052 0.2112 0.7728 0.7952 0.7838 0.6621
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 12:41:31,655 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 12:41:31,656 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 12:41:31,656 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 12:41:31,656 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 12:41:31,656 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 12:41:31,656 Train: 3575 sentences
55
+ 2023-10-13 12:41:31,656 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 12:41:31,656 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 12:41:31,656 Training Params:
58
+ 2023-10-13 12:41:31,656 - learning_rate: "3e-05"
59
+ 2023-10-13 12:41:31,656 - mini_batch_size: "8"
60
+ 2023-10-13 12:41:31,656 - max_epochs: "10"
61
+ 2023-10-13 12:41:31,656 - shuffle: "True"
62
+ 2023-10-13 12:41:31,656 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 12:41:31,656 Plugins:
64
+ 2023-10-13 12:41:31,656 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 12:41:31,656 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 12:41:31,656 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 12:41:31,657 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 12:41:31,657 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 12:41:31,657 Computation:
70
+ 2023-10-13 12:41:31,657 - compute on device: cuda:0
71
+ 2023-10-13 12:41:31,657 - embedding storage: none
72
+ 2023-10-13 12:41:31,657 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 12:41:31,657 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
74
+ 2023-10-13 12:41:31,657 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 12:41:31,657 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 12:41:34,383 epoch 1 - iter 44/447 - loss 2.86252177 - time (sec): 2.73 - samples/sec: 3026.88 - lr: 0.000003 - momentum: 0.000000
77
+ 2023-10-13 12:41:37,304 epoch 1 - iter 88/447 - loss 2.08375789 - time (sec): 5.65 - samples/sec: 3029.24 - lr: 0.000006 - momentum: 0.000000
78
+ 2023-10-13 12:41:39,959 epoch 1 - iter 132/447 - loss 1.59708301 - time (sec): 8.30 - samples/sec: 3013.37 - lr: 0.000009 - momentum: 0.000000
79
+ 2023-10-13 12:41:42,919 epoch 1 - iter 176/447 - loss 1.27742097 - time (sec): 11.26 - samples/sec: 3070.12 - lr: 0.000012 - momentum: 0.000000
80
+ 2023-10-13 12:41:45,863 epoch 1 - iter 220/447 - loss 1.09002352 - time (sec): 14.21 - samples/sec: 3048.86 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-13 12:41:48,731 epoch 1 - iter 264/447 - loss 0.96186677 - time (sec): 17.07 - samples/sec: 3044.44 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-13 12:41:51,437 epoch 1 - iter 308/447 - loss 0.87551581 - time (sec): 19.78 - samples/sec: 3033.31 - lr: 0.000021 - momentum: 0.000000
83
+ 2023-10-13 12:41:54,379 epoch 1 - iter 352/447 - loss 0.81029456 - time (sec): 22.72 - samples/sec: 2996.66 - lr: 0.000024 - momentum: 0.000000
84
+ 2023-10-13 12:41:57,492 epoch 1 - iter 396/447 - loss 0.74501254 - time (sec): 25.83 - samples/sec: 2986.20 - lr: 0.000027 - momentum: 0.000000
85
+ 2023-10-13 12:42:00,160 epoch 1 - iter 440/447 - loss 0.69746191 - time (sec): 28.50 - samples/sec: 2996.51 - lr: 0.000029 - momentum: 0.000000
86
+ 2023-10-13 12:42:00,562 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 12:42:00,563 EPOCH 1 done: loss 0.6927 - lr: 0.000029
88
+ 2023-10-13 12:42:05,856 DEV : loss 0.19505180418491364 - f1-score (micro avg) 0.6267
89
+ 2023-10-13 12:42:05,882 saving best model
90
+ 2023-10-13 12:42:06,236 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 12:42:09,017 epoch 2 - iter 44/447 - loss 0.21696724 - time (sec): 2.78 - samples/sec: 2924.66 - lr: 0.000030 - momentum: 0.000000
92
+ 2023-10-13 12:42:11,819 epoch 2 - iter 88/447 - loss 0.20487957 - time (sec): 5.58 - samples/sec: 2946.26 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-13 12:42:14,636 epoch 2 - iter 132/447 - loss 0.19251978 - time (sec): 8.40 - samples/sec: 2958.63 - lr: 0.000029 - momentum: 0.000000
94
+ 2023-10-13 12:42:17,702 epoch 2 - iter 176/447 - loss 0.17906352 - time (sec): 11.46 - samples/sec: 2901.31 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-13 12:42:20,409 epoch 2 - iter 220/447 - loss 0.17778899 - time (sec): 14.17 - samples/sec: 2925.37 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-13 12:42:23,246 epoch 2 - iter 264/447 - loss 0.17239185 - time (sec): 17.01 - samples/sec: 2930.20 - lr: 0.000028 - momentum: 0.000000
97
+ 2023-10-13 12:42:25,994 epoch 2 - iter 308/447 - loss 0.17298603 - time (sec): 19.76 - samples/sec: 2936.17 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-13 12:42:29,071 epoch 2 - iter 352/447 - loss 0.16720639 - time (sec): 22.83 - samples/sec: 2937.10 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-13 12:42:31,912 epoch 2 - iter 396/447 - loss 0.16724068 - time (sec): 25.67 - samples/sec: 2988.06 - lr: 0.000027 - momentum: 0.000000
100
+ 2023-10-13 12:42:34,661 epoch 2 - iter 440/447 - loss 0.16528204 - time (sec): 28.42 - samples/sec: 3000.44 - lr: 0.000027 - momentum: 0.000000
101
+ 2023-10-13 12:42:35,128 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 12:42:35,128 EPOCH 2 done: loss 0.1650 - lr: 0.000027
103
+ 2023-10-13 12:42:43,746 DEV : loss 0.14146439731121063 - f1-score (micro avg) 0.6657
104
+ 2023-10-13 12:42:43,775 saving best model
105
+ 2023-10-13 12:42:44,193 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 12:42:46,901 epoch 3 - iter 44/447 - loss 0.10202154 - time (sec): 2.71 - samples/sec: 3013.94 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-13 12:42:49,545 epoch 3 - iter 88/447 - loss 0.09540967 - time (sec): 5.35 - samples/sec: 2993.34 - lr: 0.000026 - momentum: 0.000000
108
+ 2023-10-13 12:42:52,480 epoch 3 - iter 132/447 - loss 0.09869171 - time (sec): 8.28 - samples/sec: 2988.36 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-13 12:42:55,163 epoch 3 - iter 176/447 - loss 0.10009313 - time (sec): 10.97 - samples/sec: 3015.11 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-13 12:42:57,900 epoch 3 - iter 220/447 - loss 0.10031670 - time (sec): 13.70 - samples/sec: 2996.70 - lr: 0.000025 - momentum: 0.000000
111
+ 2023-10-13 12:43:00,688 epoch 3 - iter 264/447 - loss 0.09570394 - time (sec): 16.49 - samples/sec: 3021.04 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-13 12:43:03,521 epoch 3 - iter 308/447 - loss 0.09263551 - time (sec): 19.32 - samples/sec: 3015.52 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-13 12:43:06,404 epoch 3 - iter 352/447 - loss 0.09283022 - time (sec): 22.21 - samples/sec: 3003.11 - lr: 0.000024 - momentum: 0.000000
114
+ 2023-10-13 12:43:09,295 epoch 3 - iter 396/447 - loss 0.08983680 - time (sec): 25.10 - samples/sec: 3009.43 - lr: 0.000024 - momentum: 0.000000
115
+ 2023-10-13 12:43:12,073 epoch 3 - iter 440/447 - loss 0.09082591 - time (sec): 27.88 - samples/sec: 3018.36 - lr: 0.000023 - momentum: 0.000000
116
+ 2023-10-13 12:43:12,851 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 12:43:12,851 EPOCH 3 done: loss 0.0897 - lr: 0.000023
118
+ 2023-10-13 12:43:22,018 DEV : loss 0.1257464587688446 - f1-score (micro avg) 0.7384
119
+ 2023-10-13 12:43:22,051 saving best model
120
+ 2023-10-13 12:43:22,459 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 12:43:25,496 epoch 4 - iter 44/447 - loss 0.06020034 - time (sec): 3.04 - samples/sec: 2684.53 - lr: 0.000023 - momentum: 0.000000
122
+ 2023-10-13 12:43:28,410 epoch 4 - iter 88/447 - loss 0.06022402 - time (sec): 5.95 - samples/sec: 2785.84 - lr: 0.000023 - momentum: 0.000000
123
+ 2023-10-13 12:43:31,098 epoch 4 - iter 132/447 - loss 0.05742048 - time (sec): 8.64 - samples/sec: 2869.36 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-13 12:43:34,344 epoch 4 - iter 176/447 - loss 0.05712786 - time (sec): 11.88 - samples/sec: 2929.12 - lr: 0.000022 - momentum: 0.000000
125
+ 2023-10-13 12:43:37,147 epoch 4 - iter 220/447 - loss 0.05283087 - time (sec): 14.69 - samples/sec: 2943.10 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-13 12:43:40,002 epoch 4 - iter 264/447 - loss 0.05318470 - time (sec): 17.54 - samples/sec: 2944.15 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-13 12:43:42,801 epoch 4 - iter 308/447 - loss 0.05227936 - time (sec): 20.34 - samples/sec: 2954.65 - lr: 0.000021 - momentum: 0.000000
128
+ 2023-10-13 12:43:45,653 epoch 4 - iter 352/447 - loss 0.05160845 - time (sec): 23.19 - samples/sec: 2949.49 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-13 12:43:48,609 epoch 4 - iter 396/447 - loss 0.05224703 - time (sec): 26.15 - samples/sec: 2957.04 - lr: 0.000020 - momentum: 0.000000
130
+ 2023-10-13 12:43:51,250 epoch 4 - iter 440/447 - loss 0.05330500 - time (sec): 28.79 - samples/sec: 2965.16 - lr: 0.000020 - momentum: 0.000000
131
+ 2023-10-13 12:43:51,663 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 12:43:51,663 EPOCH 4 done: loss 0.0535 - lr: 0.000020
133
+ 2023-10-13 12:44:00,532 DEV : loss 0.14387159049510956 - f1-score (micro avg) 0.7677
134
+ 2023-10-13 12:44:00,559 saving best model
135
+ 2023-10-13 12:44:00,978 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 12:44:03,885 epoch 5 - iter 44/447 - loss 0.04206078 - time (sec): 2.91 - samples/sec: 2913.13 - lr: 0.000020 - momentum: 0.000000
137
+ 2023-10-13 12:44:06,598 epoch 5 - iter 88/447 - loss 0.03343777 - time (sec): 5.62 - samples/sec: 2946.94 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-13 12:44:09,347 epoch 5 - iter 132/447 - loss 0.03138511 - time (sec): 8.37 - samples/sec: 2986.43 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-13 12:44:12,075 epoch 5 - iter 176/447 - loss 0.03300357 - time (sec): 11.10 - samples/sec: 2967.47 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-13 12:44:15,150 epoch 5 - iter 220/447 - loss 0.03298000 - time (sec): 14.17 - samples/sec: 2974.89 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-13 12:44:17,806 epoch 5 - iter 264/447 - loss 0.03394846 - time (sec): 16.83 - samples/sec: 2980.12 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-13 12:44:20,488 epoch 5 - iter 308/447 - loss 0.03350148 - time (sec): 19.51 - samples/sec: 2994.44 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-13 12:44:23,656 epoch 5 - iter 352/447 - loss 0.03406508 - time (sec): 22.68 - samples/sec: 3003.88 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-13 12:44:26,614 epoch 5 - iter 396/447 - loss 0.03446389 - time (sec): 25.63 - samples/sec: 3012.96 - lr: 0.000017 - momentum: 0.000000
145
+ 2023-10-13 12:44:29,587 epoch 5 - iter 440/447 - loss 0.03444354 - time (sec): 28.61 - samples/sec: 2983.31 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-13 12:44:29,981 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 12:44:29,981 EPOCH 5 done: loss 0.0340 - lr: 0.000017
148
+ 2023-10-13 12:44:38,623 DEV : loss 0.16171278059482574 - f1-score (micro avg) 0.7783
149
+ 2023-10-13 12:44:38,651 saving best model
150
+ 2023-10-13 12:44:39,090 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 12:44:42,275 epoch 6 - iter 44/447 - loss 0.02199878 - time (sec): 3.18 - samples/sec: 3022.58 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-13 12:44:45,000 epoch 6 - iter 88/447 - loss 0.01791271 - time (sec): 5.91 - samples/sec: 3016.28 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-13 12:44:47,967 epoch 6 - iter 132/447 - loss 0.01908459 - time (sec): 8.88 - samples/sec: 3001.10 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-13 12:44:50,765 epoch 6 - iter 176/447 - loss 0.02371749 - time (sec): 11.67 - samples/sec: 3033.68 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-13 12:44:53,605 epoch 6 - iter 220/447 - loss 0.02416858 - time (sec): 14.51 - samples/sec: 3058.44 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-13 12:44:56,283 epoch 6 - iter 264/447 - loss 0.02335894 - time (sec): 17.19 - samples/sec: 3043.29 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-13 12:44:59,072 epoch 6 - iter 308/447 - loss 0.02268652 - time (sec): 19.98 - samples/sec: 3016.88 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-13 12:45:01,767 epoch 6 - iter 352/447 - loss 0.02424439 - time (sec): 22.68 - samples/sec: 3009.53 - lr: 0.000014 - momentum: 0.000000
159
+ 2023-10-13 12:45:04,569 epoch 6 - iter 396/447 - loss 0.02494761 - time (sec): 25.48 - samples/sec: 3020.77 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-13 12:45:07,181 epoch 6 - iter 440/447 - loss 0.02450484 - time (sec): 28.09 - samples/sec: 3020.74 - lr: 0.000013 - momentum: 0.000000
161
+ 2023-10-13 12:45:07,807 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 12:45:07,807 EPOCH 6 done: loss 0.0244 - lr: 0.000013
163
+ 2023-10-13 12:45:16,042 DEV : loss 0.17539535462856293 - f1-score (micro avg) 0.7765
164
+ 2023-10-13 12:45:16,072 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 12:45:19,440 epoch 7 - iter 44/447 - loss 0.01357369 - time (sec): 3.37 - samples/sec: 2730.95 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-13 12:45:22,746 epoch 7 - iter 88/447 - loss 0.01403634 - time (sec): 6.67 - samples/sec: 2843.58 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-13 12:45:25,595 epoch 7 - iter 132/447 - loss 0.01539611 - time (sec): 9.52 - samples/sec: 2903.29 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-13 12:45:28,448 epoch 7 - iter 176/447 - loss 0.01710186 - time (sec): 12.38 - samples/sec: 2971.82 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-13 12:45:31,550 epoch 7 - iter 220/447 - loss 0.01634294 - time (sec): 15.48 - samples/sec: 2950.74 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-13 12:45:34,209 epoch 7 - iter 264/447 - loss 0.01602423 - time (sec): 18.14 - samples/sec: 2939.09 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-13 12:45:36,766 epoch 7 - iter 308/447 - loss 0.01550904 - time (sec): 20.69 - samples/sec: 2950.56 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-13 12:45:39,529 epoch 7 - iter 352/447 - loss 0.01612650 - time (sec): 23.46 - samples/sec: 2954.33 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-13 12:45:42,057 epoch 7 - iter 396/447 - loss 0.01558782 - time (sec): 25.98 - samples/sec: 2967.20 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-13 12:45:44,752 epoch 7 - iter 440/447 - loss 0.01530422 - time (sec): 28.68 - samples/sec: 2965.04 - lr: 0.000010 - momentum: 0.000000
175
+ 2023-10-13 12:45:45,265 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 12:45:45,265 EPOCH 7 done: loss 0.0152 - lr: 0.000010
177
+ 2023-10-13 12:45:53,827 DEV : loss 0.18422970175743103 - f1-score (micro avg) 0.7758
178
+ 2023-10-13 12:45:53,857 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-13 12:45:56,629 epoch 8 - iter 44/447 - loss 0.00798763 - time (sec): 2.77 - samples/sec: 3120.73 - lr: 0.000010 - momentum: 0.000000
180
+ 2023-10-13 12:45:59,360 epoch 8 - iter 88/447 - loss 0.00777261 - time (sec): 5.50 - samples/sec: 3050.62 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-13 12:46:03,058 epoch 8 - iter 132/447 - loss 0.00764591 - time (sec): 9.20 - samples/sec: 2909.35 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-13 12:46:06,043 epoch 8 - iter 176/447 - loss 0.00851798 - time (sec): 12.18 - samples/sec: 2888.94 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-13 12:46:08,754 epoch 8 - iter 220/447 - loss 0.00875116 - time (sec): 14.90 - samples/sec: 2926.03 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-13 12:46:11,769 epoch 8 - iter 264/447 - loss 0.00970690 - time (sec): 17.91 - samples/sec: 2922.91 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-13 12:46:14,532 epoch 8 - iter 308/447 - loss 0.00932691 - time (sec): 20.67 - samples/sec: 2946.73 - lr: 0.000008 - momentum: 0.000000
186
+ 2023-10-13 12:46:17,149 epoch 8 - iter 352/447 - loss 0.00886594 - time (sec): 23.29 - samples/sec: 2958.75 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-13 12:46:19,955 epoch 8 - iter 396/447 - loss 0.00894768 - time (sec): 26.10 - samples/sec: 2967.27 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-13 12:46:22,571 epoch 8 - iter 440/447 - loss 0.00921656 - time (sec): 28.71 - samples/sec: 2972.85 - lr: 0.000007 - momentum: 0.000000
189
+ 2023-10-13 12:46:22,952 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-13 12:46:22,952 EPOCH 8 done: loss 0.0093 - lr: 0.000007
191
+ 2023-10-13 12:46:31,318 DEV : loss 0.2055710256099701 - f1-score (micro avg) 0.7846
192
+ 2023-10-13 12:46:31,349 saving best model
193
+ 2023-10-13 12:46:31,806 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-13 12:46:34,789 epoch 9 - iter 44/447 - loss 0.00632862 - time (sec): 2.98 - samples/sec: 2741.13 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-13 12:46:38,014 epoch 9 - iter 88/447 - loss 0.00391427 - time (sec): 6.21 - samples/sec: 2820.55 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-13 12:46:40,912 epoch 9 - iter 132/447 - loss 0.00600799 - time (sec): 9.10 - samples/sec: 2861.99 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-13 12:46:43,703 epoch 9 - iter 176/447 - loss 0.00647352 - time (sec): 11.90 - samples/sec: 2895.16 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-13 12:46:46,314 epoch 9 - iter 220/447 - loss 0.00669799 - time (sec): 14.51 - samples/sec: 2947.90 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-13 12:46:48,942 epoch 9 - iter 264/447 - loss 0.00717437 - time (sec): 17.13 - samples/sec: 2969.34 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-13 12:46:51,618 epoch 9 - iter 308/447 - loss 0.00633304 - time (sec): 19.81 - samples/sec: 2976.81 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-13 12:46:54,292 epoch 9 - iter 352/447 - loss 0.00630348 - time (sec): 22.48 - samples/sec: 2987.23 - lr: 0.000004 - momentum: 0.000000
202
+ 2023-10-13 12:46:57,800 epoch 9 - iter 396/447 - loss 0.00673031 - time (sec): 25.99 - samples/sec: 2963.79 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-13 12:47:00,643 epoch 9 - iter 440/447 - loss 0.00677427 - time (sec): 28.84 - samples/sec: 2958.97 - lr: 0.000003 - momentum: 0.000000
204
+ 2023-10-13 12:47:01,044 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-13 12:47:01,044 EPOCH 9 done: loss 0.0071 - lr: 0.000003
206
+ 2023-10-13 12:47:09,395 DEV : loss 0.21442939341068268 - f1-score (micro avg) 0.7876
207
+ 2023-10-13 12:47:09,425 saving best model
208
+ 2023-10-13 12:47:09,938 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 12:47:12,923 epoch 10 - iter 44/447 - loss 0.00347708 - time (sec): 2.98 - samples/sec: 3022.65 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-13 12:47:15,674 epoch 10 - iter 88/447 - loss 0.00567608 - time (sec): 5.73 - samples/sec: 3017.03 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-13 12:47:18,567 epoch 10 - iter 132/447 - loss 0.00482620 - time (sec): 8.63 - samples/sec: 2983.60 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-13 12:47:21,552 epoch 10 - iter 176/447 - loss 0.00604485 - time (sec): 11.61 - samples/sec: 2982.37 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-13 12:47:24,150 epoch 10 - iter 220/447 - loss 0.00591778 - time (sec): 14.21 - samples/sec: 3001.57 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 12:47:26,840 epoch 10 - iter 264/447 - loss 0.00602543 - time (sec): 16.90 - samples/sec: 3005.87 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-13 12:47:29,663 epoch 10 - iter 308/447 - loss 0.00564455 - time (sec): 19.72 - samples/sec: 3012.65 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 12:47:33,086 epoch 10 - iter 352/447 - loss 0.00531102 - time (sec): 23.15 - samples/sec: 3009.37 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 12:47:35,778 epoch 10 - iter 396/447 - loss 0.00565506 - time (sec): 25.84 - samples/sec: 2999.81 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 12:47:38,391 epoch 10 - iter 440/447 - loss 0.00523144 - time (sec): 28.45 - samples/sec: 2997.36 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 12:47:38,804 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 12:47:38,804 EPOCH 10 done: loss 0.0052 - lr: 0.000000
221
+ 2023-10-13 12:47:47,440 DEV : loss 0.21124331653118134 - f1-score (micro avg) 0.7838
222
+ 2023-10-13 12:47:47,791 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 12:47:47,792 Loading model from best epoch ...
224
+ 2023-10-13 12:47:49,218 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
225
+ 2023-10-13 12:47:54,501
226
+ Results:
227
+ - F-score (micro) 0.7514
228
+ - F-score (macro) 0.6796
229
+ - Accuracy 0.6216
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8401 0.8289 0.8345 596
235
+ pers 0.6885 0.7568 0.7210 333
236
+ org 0.5455 0.5455 0.5455 132
237
+ prod 0.7021 0.5000 0.5841 66
238
+ time 0.6923 0.7347 0.7129 49
239
+
240
+ micro avg 0.7485 0.7543 0.7514 1176
241
+ macro avg 0.6937 0.6732 0.6796 1176
242
+ weighted avg 0.7502 0.7543 0.7508 1176
243
+
244
+ 2023-10-13 12:47:54,502 ----------------------------------------------------------------------------------------------------