Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
a8dea24
·
1 Parent(s): f95680a

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 +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e60380e835d29d99f1666da4bb289449a659999d03b102a8e334d98460f48b6
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 12:01:14 0.0000 0.5761 0.1917 0.4860 0.6396 0.5523 0.3957
3
+ 2 12:02:09 0.0000 0.1637 0.1673 0.6669 0.6794 0.6731 0.5387
4
+ 3 12:03:01 0.0000 0.0964 0.1544 0.7362 0.7115 0.7237 0.5841
5
+ 4 12:03:51 0.0000 0.0628 0.1983 0.7696 0.7522 0.7608 0.6367
6
+ 5 12:04:45 0.0000 0.0453 0.2249 0.7718 0.7404 0.7558 0.6238
7
+ 6 12:05:36 0.0000 0.0267 0.2265 0.7448 0.7780 0.7610 0.6350
8
+ 7 12:06:27 0.0000 0.0188 0.2377 0.7846 0.7576 0.7709 0.6477
9
+ 8 12:07:19 0.0000 0.0110 0.2359 0.8032 0.7756 0.7892 0.6685
10
+ 9 12:08:11 0.0000 0.0073 0.2453 0.7797 0.7858 0.7827 0.6607
11
+ 10 12:09:02 0.0000 0.0045 0.2510 0.8055 0.7834 0.7943 0.6747
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 12:00:27,065 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 12:00:27,066 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 12:00:27,066 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 12:00:27,066 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 12:00:27,066 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 12:00:27,066 Train: 3575 sentences
55
+ 2023-10-13 12:00:27,066 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 12:00:27,066 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 12:00:27,066 Training Params:
58
+ 2023-10-13 12:00:27,066 - learning_rate: "5e-05"
59
+ 2023-10-13 12:00:27,066 - mini_batch_size: "4"
60
+ 2023-10-13 12:00:27,066 - max_epochs: "10"
61
+ 2023-10-13 12:00:27,066 - shuffle: "True"
62
+ 2023-10-13 12:00:27,066 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 12:00:27,066 Plugins:
64
+ 2023-10-13 12:00:27,066 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 12:00:27,066 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 12:00:27,066 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 12:00:27,066 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 12:00:27,066 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 12:00:27,066 Computation:
70
+ 2023-10-13 12:00:27,067 - compute on device: cuda:0
71
+ 2023-10-13 12:00:27,067 - embedding storage: none
72
+ 2023-10-13 12:00:27,067 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 12:00:27,067 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 12:00:27,067 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 12:00:27,067 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 12:00:31,356 epoch 1 - iter 89/894 - loss 2.65202089 - time (sec): 4.29 - samples/sec: 2230.44 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 12:00:35,325 epoch 1 - iter 178/894 - loss 1.69966045 - time (sec): 8.26 - samples/sec: 2125.46 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 12:00:39,217 epoch 1 - iter 267/894 - loss 1.30319450 - time (sec): 12.15 - samples/sec: 2082.04 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 12:00:43,289 epoch 1 - iter 356/894 - loss 1.06401462 - time (sec): 16.22 - samples/sec: 2087.13 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 12:00:47,424 epoch 1 - iter 445/894 - loss 0.91793285 - time (sec): 20.36 - samples/sec: 2064.05 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-13 12:00:51,643 epoch 1 - iter 534/894 - loss 0.80690184 - time (sec): 24.58 - samples/sec: 2073.01 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-13 12:00:55,771 epoch 1 - iter 623/894 - loss 0.72960178 - time (sec): 28.70 - samples/sec: 2074.20 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-13 12:01:00,063 epoch 1 - iter 712/894 - loss 0.66121317 - time (sec): 33.00 - samples/sec: 2095.23 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-13 12:01:04,132 epoch 1 - iter 801/894 - loss 0.61592548 - time (sec): 37.06 - samples/sec: 2080.65 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-13 12:01:08,647 epoch 1 - iter 890/894 - loss 0.57823314 - time (sec): 41.58 - samples/sec: 2070.70 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-13 12:01:08,863 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 12:01:08,863 EPOCH 1 done: loss 0.5761 - lr: 0.000050
88
+ 2023-10-13 12:01:14,125 DEV : loss 0.19171087443828583 - f1-score (micro avg) 0.5523
89
+ 2023-10-13 12:01:14,162 saving best model
90
+ 2023-10-13 12:01:14,561 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 12:01:19,169 epoch 2 - iter 89/894 - loss 0.16742899 - time (sec): 4.61 - samples/sec: 1876.18 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 12:01:24,154 epoch 2 - iter 178/894 - loss 0.18661985 - time (sec): 9.59 - samples/sec: 1799.79 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 12:01:28,900 epoch 2 - iter 267/894 - loss 0.18491634 - time (sec): 14.34 - samples/sec: 1810.30 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 12:01:33,617 epoch 2 - iter 356/894 - loss 0.17699142 - time (sec): 19.05 - samples/sec: 1803.39 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 12:01:38,281 epoch 2 - iter 445/894 - loss 0.17304819 - time (sec): 23.72 - samples/sec: 1787.25 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 12:01:43,059 epoch 2 - iter 534/894 - loss 0.16781167 - time (sec): 28.50 - samples/sec: 1795.31 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 12:01:47,846 epoch 2 - iter 623/894 - loss 0.16699818 - time (sec): 33.28 - samples/sec: 1814.02 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 12:01:51,935 epoch 2 - iter 712/894 - loss 0.16546982 - time (sec): 37.37 - samples/sec: 1837.50 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 12:01:56,087 epoch 2 - iter 801/894 - loss 0.16583765 - time (sec): 41.52 - samples/sec: 1849.52 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 12:02:00,492 epoch 2 - iter 890/894 - loss 0.16396919 - time (sec): 45.93 - samples/sec: 1877.86 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-13 12:02:00,666 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 12:02:00,666 EPOCH 2 done: loss 0.1637 - lr: 0.000044
103
+ 2023-10-13 12:02:09,259 DEV : loss 0.1673235297203064 - f1-score (micro avg) 0.6731
104
+ 2023-10-13 12:02:09,287 saving best model
105
+ 2023-10-13 12:02:09,740 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 12:02:14,071 epoch 3 - iter 89/894 - loss 0.11293528 - time (sec): 4.32 - samples/sec: 1806.55 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 12:02:18,083 epoch 3 - iter 178/894 - loss 0.09808312 - time (sec): 8.34 - samples/sec: 1941.24 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 12:02:22,186 epoch 3 - iter 267/894 - loss 0.10487395 - time (sec): 12.44 - samples/sec: 1958.54 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 12:02:26,519 epoch 3 - iter 356/894 - loss 0.09664391 - time (sec): 16.77 - samples/sec: 1981.81 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 12:02:31,084 epoch 3 - iter 445/894 - loss 0.09801920 - time (sec): 21.34 - samples/sec: 1989.82 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 12:02:35,161 epoch 3 - iter 534/894 - loss 0.09498912 - time (sec): 25.41 - samples/sec: 2021.14 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 12:02:39,416 epoch 3 - iter 623/894 - loss 0.09310128 - time (sec): 29.67 - samples/sec: 2021.67 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 12:02:43,736 epoch 3 - iter 712/894 - loss 0.09653710 - time (sec): 33.99 - samples/sec: 2015.81 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 12:02:47,930 epoch 3 - iter 801/894 - loss 0.09612514 - time (sec): 38.18 - samples/sec: 2015.52 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-13 12:02:52,340 epoch 3 - iter 890/894 - loss 0.09660086 - time (sec): 42.59 - samples/sec: 2024.95 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 12:02:52,514 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 12:02:52,514 EPOCH 3 done: loss 0.0964 - lr: 0.000039
118
+ 2023-10-13 12:03:01,037 DEV : loss 0.1543554961681366 - f1-score (micro avg) 0.7237
119
+ 2023-10-13 12:03:01,064 saving best model
120
+ 2023-10-13 12:03:01,494 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 12:03:05,695 epoch 4 - iter 89/894 - loss 0.06872160 - time (sec): 4.20 - samples/sec: 2147.40 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 12:03:09,945 epoch 4 - iter 178/894 - loss 0.06523083 - time (sec): 8.45 - samples/sec: 2031.05 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 12:03:14,291 epoch 4 - iter 267/894 - loss 0.06233008 - time (sec): 12.80 - samples/sec: 2053.49 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 12:03:18,654 epoch 4 - iter 356/894 - loss 0.06329979 - time (sec): 17.16 - samples/sec: 2106.44 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 12:03:22,852 epoch 4 - iter 445/894 - loss 0.06037310 - time (sec): 21.36 - samples/sec: 2099.06 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 12:03:26,947 epoch 4 - iter 534/894 - loss 0.06290240 - time (sec): 25.45 - samples/sec: 2104.17 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 12:03:30,914 epoch 4 - iter 623/894 - loss 0.06194766 - time (sec): 29.42 - samples/sec: 2101.71 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 12:03:35,018 epoch 4 - iter 712/894 - loss 0.06159615 - time (sec): 33.52 - samples/sec: 2095.48 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-13 12:03:39,166 epoch 4 - iter 801/894 - loss 0.06291890 - time (sec): 37.67 - samples/sec: 2060.79 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 12:03:43,303 epoch 4 - iter 890/894 - loss 0.06248239 - time (sec): 41.81 - samples/sec: 2062.20 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 12:03:43,493 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 12:03:43,493 EPOCH 4 done: loss 0.0628 - lr: 0.000033
133
+ 2023-10-13 12:03:51,962 DEV : loss 0.19826681911945343 - f1-score (micro avg) 0.7608
134
+ 2023-10-13 12:03:51,990 saving best model
135
+ 2023-10-13 12:03:52,464 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 12:03:57,042 epoch 5 - iter 89/894 - loss 0.05415502 - time (sec): 4.57 - samples/sec: 2124.39 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 12:04:01,786 epoch 5 - iter 178/894 - loss 0.05000802 - time (sec): 9.32 - samples/sec: 1905.31 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 12:04:06,621 epoch 5 - iter 267/894 - loss 0.05083210 - time (sec): 14.15 - samples/sec: 1878.52 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 12:04:11,213 epoch 5 - iter 356/894 - loss 0.04975196 - time (sec): 18.75 - samples/sec: 1850.66 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 12:04:15,475 epoch 5 - iter 445/894 - loss 0.04576638 - time (sec): 23.01 - samples/sec: 1900.36 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 12:04:19,525 epoch 5 - iter 534/894 - loss 0.04845092 - time (sec): 27.06 - samples/sec: 1939.73 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 12:04:23,737 epoch 5 - iter 623/894 - loss 0.04814231 - time (sec): 31.27 - samples/sec: 1941.02 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-13 12:04:28,002 epoch 5 - iter 712/894 - loss 0.04696082 - time (sec): 35.53 - samples/sec: 1955.02 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 12:04:32,196 epoch 5 - iter 801/894 - loss 0.04514786 - time (sec): 39.73 - samples/sec: 1956.95 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 12:04:36,300 epoch 5 - iter 890/894 - loss 0.04547050 - time (sec): 43.83 - samples/sec: 1966.57 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 12:04:36,493 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 12:04:36,493 EPOCH 5 done: loss 0.0453 - lr: 0.000028
148
+ 2023-10-13 12:04:44,989 DEV : loss 0.2249317169189453 - f1-score (micro avg) 0.7558
149
+ 2023-10-13 12:04:45,019 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 12:04:49,517 epoch 6 - iter 89/894 - loss 0.02250297 - time (sec): 4.50 - samples/sec: 1927.38 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-13 12:04:53,620 epoch 6 - iter 178/894 - loss 0.02755065 - time (sec): 8.60 - samples/sec: 1904.80 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 12:04:57,991 epoch 6 - iter 267/894 - loss 0.02537520 - time (sec): 12.97 - samples/sec: 1969.77 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-13 12:05:02,077 epoch 6 - iter 356/894 - loss 0.02778131 - time (sec): 17.06 - samples/sec: 2019.16 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 12:05:06,083 epoch 6 - iter 445/894 - loss 0.02565103 - time (sec): 21.06 - samples/sec: 1994.56 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-13 12:05:10,138 epoch 6 - iter 534/894 - loss 0.02415612 - time (sec): 25.12 - samples/sec: 2001.89 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-13 12:05:14,184 epoch 6 - iter 623/894 - loss 0.02615286 - time (sec): 29.16 - samples/sec: 1993.85 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-13 12:05:18,598 epoch 6 - iter 712/894 - loss 0.02606805 - time (sec): 33.58 - samples/sec: 2035.76 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-13 12:05:22,821 epoch 6 - iter 801/894 - loss 0.02757777 - time (sec): 37.80 - samples/sec: 2034.05 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 12:05:27,484 epoch 6 - iter 890/894 - loss 0.02680885 - time (sec): 42.46 - samples/sec: 2027.87 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-13 12:05:27,693 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 12:05:27,693 EPOCH 6 done: loss 0.0267 - lr: 0.000022
162
+ 2023-10-13 12:05:36,241 DEV : loss 0.2265176773071289 - f1-score (micro avg) 0.761
163
+ 2023-10-13 12:05:36,268 saving best model
164
+ 2023-10-13 12:05:36,722 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 12:05:41,169 epoch 7 - iter 89/894 - loss 0.01241443 - time (sec): 4.45 - samples/sec: 1976.84 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-13 12:05:45,326 epoch 7 - iter 178/894 - loss 0.01280006 - time (sec): 8.60 - samples/sec: 1988.62 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 12:05:50,011 epoch 7 - iter 267/894 - loss 0.01410320 - time (sec): 13.29 - samples/sec: 2051.18 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-13 12:05:54,218 epoch 7 - iter 356/894 - loss 0.01506068 - time (sec): 17.50 - samples/sec: 2036.46 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-13 12:05:58,380 epoch 7 - iter 445/894 - loss 0.01802183 - time (sec): 21.66 - samples/sec: 2050.15 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-13 12:06:02,559 epoch 7 - iter 534/894 - loss 0.01957567 - time (sec): 25.84 - samples/sec: 2036.06 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-13 12:06:06,819 epoch 7 - iter 623/894 - loss 0.01864068 - time (sec): 30.10 - samples/sec: 2025.40 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 12:06:10,824 epoch 7 - iter 712/894 - loss 0.01838519 - time (sec): 34.10 - samples/sec: 2028.91 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-13 12:06:14,873 epoch 7 - iter 801/894 - loss 0.01897641 - time (sec): 38.15 - samples/sec: 2020.45 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 12:06:19,125 epoch 7 - iter 890/894 - loss 0.01885509 - time (sec): 42.40 - samples/sec: 2034.65 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-13 12:06:19,303 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 12:06:19,304 EPOCH 7 done: loss 0.0188 - lr: 0.000017
177
+ 2023-10-13 12:06:27,833 DEV : loss 0.23773737251758575 - f1-score (micro avg) 0.7709
178
+ 2023-10-13 12:06:27,862 saving best model
179
+ 2023-10-13 12:06:28,338 ----------------------------------------------------------------------------------------------------
180
+ 2023-10-13 12:06:32,884 epoch 8 - iter 89/894 - loss 0.01758360 - time (sec): 4.54 - samples/sec: 1907.50 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-13 12:06:37,227 epoch 8 - iter 178/894 - loss 0.01300323 - time (sec): 8.89 - samples/sec: 2000.63 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-13 12:06:41,456 epoch 8 - iter 267/894 - loss 0.01026527 - time (sec): 13.12 - samples/sec: 2049.43 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-13 12:06:45,592 epoch 8 - iter 356/894 - loss 0.00865146 - time (sec): 17.25 - samples/sec: 2112.95 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-13 12:06:49,491 epoch 8 - iter 445/894 - loss 0.01113562 - time (sec): 21.15 - samples/sec: 2087.22 - lr: 0.000014 - momentum: 0.000000
185
+ 2023-10-13 12:06:53,684 epoch 8 - iter 534/894 - loss 0.01103381 - time (sec): 25.34 - samples/sec: 2076.68 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-13 12:06:58,224 epoch 8 - iter 623/894 - loss 0.01078598 - time (sec): 29.88 - samples/sec: 2063.56 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-13 12:07:02,633 epoch 8 - iter 712/894 - loss 0.01053832 - time (sec): 34.29 - samples/sec: 2039.31 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-13 12:07:06,832 epoch 8 - iter 801/894 - loss 0.01089148 - time (sec): 38.49 - samples/sec: 2028.88 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-13 12:07:10,958 epoch 8 - iter 890/894 - loss 0.01109678 - time (sec): 42.62 - samples/sec: 2022.12 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-13 12:07:11,139 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-13 12:07:11,139 EPOCH 8 done: loss 0.0110 - lr: 0.000011
192
+ 2023-10-13 12:07:19,962 DEV : loss 0.23593451082706451 - f1-score (micro avg) 0.7892
193
+ 2023-10-13 12:07:19,992 saving best model
194
+ 2023-10-13 12:07:20,478 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-13 12:07:24,789 epoch 9 - iter 89/894 - loss 0.00628948 - time (sec): 4.30 - samples/sec: 1921.98 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-13 12:07:29,139 epoch 9 - iter 178/894 - loss 0.00390042 - time (sec): 8.65 - samples/sec: 2031.56 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-13 12:07:33,428 epoch 9 - iter 267/894 - loss 0.00644408 - time (sec): 12.94 - samples/sec: 2000.87 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-13 12:07:37,671 epoch 9 - iter 356/894 - loss 0.00542230 - time (sec): 17.18 - samples/sec: 2057.31 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-13 12:07:41,968 epoch 9 - iter 445/894 - loss 0.00725202 - time (sec): 21.48 - samples/sec: 2057.49 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-13 12:07:46,266 epoch 9 - iter 534/894 - loss 0.00698739 - time (sec): 25.78 - samples/sec: 2073.97 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-13 12:07:50,551 epoch 9 - iter 623/894 - loss 0.00633533 - time (sec): 30.06 - samples/sec: 2062.87 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-13 12:07:54,589 epoch 9 - iter 712/894 - loss 0.00588233 - time (sec): 34.10 - samples/sec: 2053.11 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-13 12:07:58,682 epoch 9 - iter 801/894 - loss 0.00614205 - time (sec): 38.19 - samples/sec: 2047.19 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-13 12:08:03,257 epoch 9 - iter 890/894 - loss 0.00729369 - time (sec): 42.77 - samples/sec: 2013.71 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-13 12:08:03,460 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-13 12:08:03,461 EPOCH 9 done: loss 0.0073 - lr: 0.000006
207
+ 2023-10-13 12:08:11,860 DEV : loss 0.24528658390045166 - f1-score (micro avg) 0.7827
208
+ 2023-10-13 12:08:11,887 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 12:08:15,936 epoch 10 - iter 89/894 - loss 0.00803708 - time (sec): 4.05 - samples/sec: 2170.54 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-13 12:08:20,177 epoch 10 - iter 178/894 - loss 0.00744826 - time (sec): 8.29 - samples/sec: 2017.30 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-13 12:08:24,447 epoch 10 - iter 267/894 - loss 0.00540126 - time (sec): 12.56 - samples/sec: 2013.04 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-13 12:08:28,584 epoch 10 - iter 356/894 - loss 0.00463210 - time (sec): 16.69 - samples/sec: 2041.58 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-13 12:08:32,819 epoch 10 - iter 445/894 - loss 0.00503189 - time (sec): 20.93 - samples/sec: 2066.56 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-13 12:08:37,002 epoch 10 - iter 534/894 - loss 0.00461758 - time (sec): 25.11 - samples/sec: 2079.27 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-13 12:08:41,295 epoch 10 - iter 623/894 - loss 0.00437106 - time (sec): 29.41 - samples/sec: 2072.49 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-13 12:08:45,312 epoch 10 - iter 712/894 - loss 0.00448286 - time (sec): 33.42 - samples/sec: 2070.88 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 12:08:49,472 epoch 10 - iter 801/894 - loss 0.00428854 - time (sec): 37.58 - samples/sec: 2051.98 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 12:08:53,712 epoch 10 - iter 890/894 - loss 0.00454052 - time (sec): 41.82 - samples/sec: 2060.73 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 12:08:53,895 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 12:08:53,895 EPOCH 10 done: loss 0.0045 - lr: 0.000000
221
+ 2023-10-13 12:09:02,408 DEV : loss 0.25100380182266235 - f1-score (micro avg) 0.7943
222
+ 2023-10-13 12:09:02,436 saving best model
223
+ 2023-10-13 12:09:03,246 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-13 12:09:03,247 Loading model from best epoch ...
225
+ 2023-10-13 12:09:04,728 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
226
+ 2023-10-13 12:09:09,207
227
+ Results:
228
+ - F-score (micro) 0.7421
229
+ - F-score (macro) 0.6478
230
+ - Accuracy 0.6085
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.8375 0.8473 0.8424 596
236
+ pers 0.6768 0.7357 0.7050 333
237
+ org 0.5392 0.4167 0.4701 132
238
+ prod 0.5490 0.4242 0.4786 66
239
+ time 0.6964 0.7959 0.7429 49
240
+
241
+ micro avg 0.7428 0.7415 0.7421 1176
242
+ macro avg 0.6598 0.6440 0.6478 1176
243
+ weighted avg 0.7364 0.7415 0.7371 1176
244
+
245
+ 2023-10-13 12:09:09,207 ----------------------------------------------------------------------------------------------------