Hugging Face's logo

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

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
2c9721b
•
1 Parent(s): f89dac3

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697650786.46dc0c540dd0.2878.1 +3 -0
  5. test.tsv +0 -0
  6. training.log +248 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95393704e4129907cace09ff2c92118b511e16c0caddf89377314cb43d1904ce
3
+ size 19050210
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 17:40:02 0.0000 1.2874 0.4237 1.0000 0.0023 0.0047 0.0023
3
+ 2 17:40:21 0.0000 0.4465 0.3345 0.4009 0.2181 0.2825 0.1700
4
+ 3 17:40:40 0.0000 0.3646 0.3076 0.3980 0.2869 0.3335 0.2086
5
+ 4 17:41:00 0.0000 0.3266 0.3057 0.3585 0.3307 0.3440 0.2201
6
+ 5 17:41:19 0.0000 0.2971 0.3028 0.3923 0.3190 0.3519 0.2255
7
+ 6 17:41:38 0.0000 0.2773 0.3090 0.4223 0.3253 0.3675 0.2373
8
+ 7 17:41:57 0.0000 0.2598 0.3014 0.4075 0.3550 0.3794 0.2489
9
+ 8 17:42:16 0.0000 0.2483 0.2988 0.3974 0.3769 0.3868 0.2558
10
+ 9 17:42:35 0.0000 0.2399 0.3023 0.4154 0.3761 0.3947 0.2631
11
+ 10 17:42:55 0.0000 0.2359 0.3022 0.4174 0.3714 0.3930 0.2617
runs/events.out.tfevents.1697650786.46dc0c540dd0.2878.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adec8af799c1c3853976d3d84f817e2f9b022d0b81b00108ffdc79f75488b1ce
3
+ size 502124
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 17:39:46,413 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 17:39:46,413 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), 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=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-18 17:39:46,413 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 17:39:46,413 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
+ 2023-10-18 17:39:46,413 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 17:39:46,413 Train: 3575 sentences
55
+ 2023-10-18 17:39:46,413 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 17:39:46,413 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 17:39:46,413 Training Params:
58
+ 2023-10-18 17:39:46,414 - learning_rate: "5e-05"
59
+ 2023-10-18 17:39:46,414 - mini_batch_size: "4"
60
+ 2023-10-18 17:39:46,414 - max_epochs: "10"
61
+ 2023-10-18 17:39:46,414 - shuffle: "True"
62
+ 2023-10-18 17:39:46,414 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 17:39:46,414 Plugins:
64
+ 2023-10-18 17:39:46,414 - TensorboardLogger
65
+ 2023-10-18 17:39:46,414 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 17:39:46,414 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 17:39:46,414 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 17:39:46,414 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 17:39:46,414 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 17:39:46,414 Computation:
71
+ 2023-10-18 17:39:46,414 - compute on device: cuda:0
72
+ 2023-10-18 17:39:46,414 - embedding storage: none
73
+ 2023-10-18 17:39:46,414 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 17:39:46,414 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-18 17:39:46,414 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 17:39:46,414 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 17:39:46,414 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 17:39:47,622 epoch 1 - iter 89/894 - loss 3.56088883 - time (sec): 1.21 - samples/sec: 6861.97 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 17:39:48,995 epoch 1 - iter 178/894 - loss 3.27510972 - time (sec): 2.58 - samples/sec: 6479.87 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 17:39:50,373 epoch 1 - iter 267/894 - loss 2.81223450 - time (sec): 3.96 - samples/sec: 6392.20 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 17:39:51,750 epoch 1 - iter 356/894 - loss 2.34160427 - time (sec): 5.34 - samples/sec: 6341.25 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 17:39:53,122 epoch 1 - iter 445/894 - loss 1.99483895 - time (sec): 6.71 - samples/sec: 6435.14 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-18 17:39:54,518 epoch 1 - iter 534/894 - loss 1.76339110 - time (sec): 8.10 - samples/sec: 6399.97 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-18 17:39:55,900 epoch 1 - iter 623/894 - loss 1.60438052 - time (sec): 9.49 - samples/sec: 6363.56 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-18 17:39:57,316 epoch 1 - iter 712/894 - loss 1.46822053 - time (sec): 10.90 - samples/sec: 6361.48 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-18 17:39:58,713 epoch 1 - iter 801/894 - loss 1.37216087 - time (sec): 12.30 - samples/sec: 6342.23 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-18 17:40:00,082 epoch 1 - iter 890/894 - loss 1.29129924 - time (sec): 13.67 - samples/sec: 6295.80 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-18 17:40:00,144 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 17:40:00,144 EPOCH 1 done: loss 1.2874 - lr: 0.000050
90
+ 2023-10-18 17:40:02,389 DEV : loss 0.42374274134635925 - f1-score (micro avg) 0.0047
91
+ 2023-10-18 17:40:02,417 saving best model
92
+ 2023-10-18 17:40:02,449 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-18 17:40:03,852 epoch 2 - iter 89/894 - loss 0.53456617 - time (sec): 1.40 - samples/sec: 6761.96 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 17:40:05,224 epoch 2 - iter 178/894 - loss 0.48876177 - time (sec): 2.77 - samples/sec: 6667.46 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-18 17:40:06,685 epoch 2 - iter 267/894 - loss 0.48305597 - time (sec): 4.24 - samples/sec: 6520.37 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 17:40:08,045 epoch 2 - iter 356/894 - loss 0.47711486 - time (sec): 5.60 - samples/sec: 6263.90 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-18 17:40:09,415 epoch 2 - iter 445/894 - loss 0.46925640 - time (sec): 6.97 - samples/sec: 6328.63 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 17:40:10,812 epoch 2 - iter 534/894 - loss 0.45601089 - time (sec): 8.36 - samples/sec: 6251.92 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-18 17:40:12,213 epoch 2 - iter 623/894 - loss 0.45694794 - time (sec): 9.76 - samples/sec: 6209.82 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 17:40:13,604 epoch 2 - iter 712/894 - loss 0.45374120 - time (sec): 11.15 - samples/sec: 6209.76 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-18 17:40:14,984 epoch 2 - iter 801/894 - loss 0.45183281 - time (sec): 12.53 - samples/sec: 6213.64 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 17:40:16,315 epoch 2 - iter 890/894 - loss 0.44611403 - time (sec): 13.87 - samples/sec: 6220.24 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-18 17:40:16,371 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-18 17:40:16,371 EPOCH 2 done: loss 0.4465 - lr: 0.000044
105
+ 2023-10-18 17:40:21,629 DEV : loss 0.33446836471557617 - f1-score (micro avg) 0.2825
106
+ 2023-10-18 17:40:21,655 saving best model
107
+ 2023-10-18 17:40:21,692 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-18 17:40:23,074 epoch 3 - iter 89/894 - loss 0.37382829 - time (sec): 1.38 - samples/sec: 5689.22 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-18 17:40:24,471 epoch 3 - iter 178/894 - loss 0.38391719 - time (sec): 2.78 - samples/sec: 6001.80 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 17:40:25,842 epoch 3 - iter 267/894 - loss 0.38351814 - time (sec): 4.15 - samples/sec: 5934.83 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-18 17:40:27,227 epoch 3 - iter 356/894 - loss 0.37200370 - time (sec): 5.53 - samples/sec: 6050.91 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 17:40:28,617 epoch 3 - iter 445/894 - loss 0.36806798 - time (sec): 6.92 - samples/sec: 6106.77 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-18 17:40:30,026 epoch 3 - iter 534/894 - loss 0.36726729 - time (sec): 8.33 - samples/sec: 6160.71 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 17:40:31,399 epoch 3 - iter 623/894 - loss 0.36063396 - time (sec): 9.71 - samples/sec: 6126.60 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-18 17:40:32,762 epoch 3 - iter 712/894 - loss 0.36575094 - time (sec): 11.07 - samples/sec: 6135.09 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 17:40:34,215 epoch 3 - iter 801/894 - loss 0.36442893 - time (sec): 12.52 - samples/sec: 6201.81 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 17:40:35,641 epoch 3 - iter 890/894 - loss 0.36483048 - time (sec): 13.95 - samples/sec: 6178.05 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-18 17:40:35,698 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-18 17:40:35,698 EPOCH 3 done: loss 0.3646 - lr: 0.000039
120
+ 2023-10-18 17:40:40,927 DEV : loss 0.3075636327266693 - f1-score (micro avg) 0.3335
121
+ 2023-10-18 17:40:40,953 saving best model
122
+ 2023-10-18 17:40:40,988 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-18 17:40:42,396 epoch 4 - iter 89/894 - loss 0.33269146 - time (sec): 1.41 - samples/sec: 6501.63 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 17:40:43,794 epoch 4 - iter 178/894 - loss 0.34094448 - time (sec): 2.81 - samples/sec: 6329.83 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-18 17:40:45,184 epoch 4 - iter 267/894 - loss 0.34400084 - time (sec): 4.20 - samples/sec: 6379.06 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 17:40:46,582 epoch 4 - iter 356/894 - loss 0.33882719 - time (sec): 5.59 - samples/sec: 6391.37 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-18 17:40:47,931 epoch 4 - iter 445/894 - loss 0.33813656 - time (sec): 6.94 - samples/sec: 6345.08 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 17:40:49,322 epoch 4 - iter 534/894 - loss 0.33235534 - time (sec): 8.33 - samples/sec: 6301.14 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-18 17:40:50,663 epoch 4 - iter 623/894 - loss 0.32836804 - time (sec): 9.67 - samples/sec: 6326.35 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 17:40:51,909 epoch 4 - iter 712/894 - loss 0.32290979 - time (sec): 10.92 - samples/sec: 6372.20 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 17:40:53,313 epoch 4 - iter 801/894 - loss 0.32823727 - time (sec): 12.32 - samples/sec: 6320.06 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-18 17:40:54,663 epoch 4 - iter 890/894 - loss 0.32666126 - time (sec): 13.67 - samples/sec: 6305.84 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-18 17:40:54,722 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-18 17:40:54,722 EPOCH 4 done: loss 0.3266 - lr: 0.000033
135
+ 2023-10-18 17:41:00,006 DEV : loss 0.3056620657444 - f1-score (micro avg) 0.344
136
+ 2023-10-18 17:41:00,032 saving best model
137
+ 2023-10-18 17:41:00,066 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-18 17:41:01,447 epoch 5 - iter 89/894 - loss 0.28380145 - time (sec): 1.38 - samples/sec: 5916.31 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-18 17:41:02,817 epoch 5 - iter 178/894 - loss 0.30119921 - time (sec): 2.75 - samples/sec: 5831.65 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 17:41:04,183 epoch 5 - iter 267/894 - loss 0.28339258 - time (sec): 4.12 - samples/sec: 5840.96 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-18 17:41:05,570 epoch 5 - iter 356/894 - loss 0.28951457 - time (sec): 5.50 - samples/sec: 6113.84 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 17:41:06,973 epoch 5 - iter 445/894 - loss 0.28772870 - time (sec): 6.91 - samples/sec: 6168.89 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-18 17:41:08,411 epoch 5 - iter 534/894 - loss 0.28686799 - time (sec): 8.34 - samples/sec: 6214.59 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 17:41:09,777 epoch 5 - iter 623/894 - loss 0.28834965 - time (sec): 9.71 - samples/sec: 6237.61 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 17:41:11,142 epoch 5 - iter 712/894 - loss 0.29652767 - time (sec): 11.08 - samples/sec: 6243.32 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-18 17:41:12,534 epoch 5 - iter 801/894 - loss 0.29303123 - time (sec): 12.47 - samples/sec: 6200.43 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 17:41:13,939 epoch 5 - iter 890/894 - loss 0.29497246 - time (sec): 13.87 - samples/sec: 6214.23 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-18 17:41:13,998 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-18 17:41:13,998 EPOCH 5 done: loss 0.2971 - lr: 0.000028
150
+ 2023-10-18 17:41:18,978 DEV : loss 0.3028002083301544 - f1-score (micro avg) 0.3519
151
+ 2023-10-18 17:41:19,003 saving best model
152
+ 2023-10-18 17:41:19,038 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-18 17:41:20,430 epoch 6 - iter 89/894 - loss 0.30126272 - time (sec): 1.39 - samples/sec: 6024.34 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 17:41:21,869 epoch 6 - iter 178/894 - loss 0.27254140 - time (sec): 2.83 - samples/sec: 6564.55 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-18 17:41:23,268 epoch 6 - iter 267/894 - loss 0.25649955 - time (sec): 4.23 - samples/sec: 6363.86 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 17:41:24,660 epoch 6 - iter 356/894 - loss 0.26560972 - time (sec): 5.62 - samples/sec: 6220.58 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-18 17:41:26,014 epoch 6 - iter 445/894 - loss 0.27644281 - time (sec): 6.98 - samples/sec: 6234.12 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 17:41:27,384 epoch 6 - iter 534/894 - loss 0.27683306 - time (sec): 8.35 - samples/sec: 6205.24 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-18 17:41:28,745 epoch 6 - iter 623/894 - loss 0.27738781 - time (sec): 9.71 - samples/sec: 6201.08 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-18 17:41:30,134 epoch 6 - iter 712/894 - loss 0.27549257 - time (sec): 11.10 - samples/sec: 6217.29 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 17:41:31,587 epoch 6 - iter 801/894 - loss 0.27684533 - time (sec): 12.55 - samples/sec: 6196.98 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-18 17:41:32,991 epoch 6 - iter 890/894 - loss 0.27758019 - time (sec): 13.95 - samples/sec: 6178.48 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-18 17:41:33,050 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-18 17:41:33,050 EPOCH 6 done: loss 0.2773 - lr: 0.000022
165
+ 2023-10-18 17:41:38,288 DEV : loss 0.30895572900772095 - f1-score (micro avg) 0.3675
166
+ 2023-10-18 17:41:38,314 saving best model
167
+ 2023-10-18 17:41:38,348 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-18 17:41:39,740 epoch 7 - iter 89/894 - loss 0.23945029 - time (sec): 1.39 - samples/sec: 6134.96 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-18 17:41:41,103 epoch 7 - iter 178/894 - loss 0.24472136 - time (sec): 2.75 - samples/sec: 6145.87 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-18 17:41:42,459 epoch 7 - iter 267/894 - loss 0.24899507 - time (sec): 4.11 - samples/sec: 6014.48 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-18 17:41:43,845 epoch 7 - iter 356/894 - loss 0.26290285 - time (sec): 5.50 - samples/sec: 6101.12 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-18 17:41:45,225 epoch 7 - iter 445/894 - loss 0.25558011 - time (sec): 6.88 - samples/sec: 6150.11 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-18 17:41:46,604 epoch 7 - iter 534/894 - loss 0.25236895 - time (sec): 8.26 - samples/sec: 6113.46 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-18 17:41:47,974 epoch 7 - iter 623/894 - loss 0.25861698 - time (sec): 9.63 - samples/sec: 6128.98 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-18 17:41:49,409 epoch 7 - iter 712/894 - loss 0.25853236 - time (sec): 11.06 - samples/sec: 6213.92 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-18 17:41:50,809 epoch 7 - iter 801/894 - loss 0.25843522 - time (sec): 12.46 - samples/sec: 6173.81 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-18 17:41:52,190 epoch 7 - iter 890/894 - loss 0.26022956 - time (sec): 13.84 - samples/sec: 6227.19 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-18 17:41:52,253 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-18 17:41:52,254 EPOCH 7 done: loss 0.2598 - lr: 0.000017
180
+ 2023-10-18 17:41:57,547 DEV : loss 0.30144089460372925 - f1-score (micro avg) 0.3794
181
+ 2023-10-18 17:41:57,573 saving best model
182
+ 2023-10-18 17:41:57,606 ----------------------------------------------------------------------------------------------------
183
+ 2023-10-18 17:41:58,998 epoch 8 - iter 89/894 - loss 0.25238249 - time (sec): 1.39 - samples/sec: 5901.66 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-18 17:42:00,380 epoch 8 - iter 178/894 - loss 0.24111625 - time (sec): 2.77 - samples/sec: 6095.35 - lr: 0.000016 - momentum: 0.000000
185
+ 2023-10-18 17:42:01,751 epoch 8 - iter 267/894 - loss 0.24040542 - time (sec): 4.14 - samples/sec: 5994.20 - lr: 0.000015 - momentum: 0.000000
186
+ 2023-10-18 17:42:03,200 epoch 8 - iter 356/894 - loss 0.24702978 - time (sec): 5.59 - samples/sec: 5934.25 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-18 17:42:04,569 epoch 8 - iter 445/894 - loss 0.24595873 - time (sec): 6.96 - samples/sec: 6008.26 - lr: 0.000014 - momentum: 0.000000
188
+ 2023-10-18 17:42:05,978 epoch 8 - iter 534/894 - loss 0.25606875 - time (sec): 8.37 - samples/sec: 6045.47 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-18 17:42:07,402 epoch 8 - iter 623/894 - loss 0.24760570 - time (sec): 9.79 - samples/sec: 6192.33 - lr: 0.000013 - momentum: 0.000000
190
+ 2023-10-18 17:42:08,807 epoch 8 - iter 712/894 - loss 0.25033713 - time (sec): 11.20 - samples/sec: 6203.69 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-18 17:42:10,172 epoch 8 - iter 801/894 - loss 0.25087722 - time (sec): 12.57 - samples/sec: 6206.95 - lr: 0.000012 - momentum: 0.000000
192
+ 2023-10-18 17:42:11,599 epoch 8 - iter 890/894 - loss 0.24848771 - time (sec): 13.99 - samples/sec: 6164.42 - lr: 0.000011 - momentum: 0.000000
193
+ 2023-10-18 17:42:11,676 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-18 17:42:11,676 EPOCH 8 done: loss 0.2483 - lr: 0.000011
195
+ 2023-10-18 17:42:16,927 DEV : loss 0.29879170656204224 - f1-score (micro avg) 0.3868
196
+ 2023-10-18 17:42:16,953 saving best model
197
+ 2023-10-18 17:42:16,987 ----------------------------------------------------------------------------------------------------
198
+ 2023-10-18 17:42:18,387 epoch 9 - iter 89/894 - loss 0.23595464 - time (sec): 1.40 - samples/sec: 5922.44 - lr: 0.000011 - momentum: 0.000000
199
+ 2023-10-18 17:42:19,796 epoch 9 - iter 178/894 - loss 0.23156957 - time (sec): 2.81 - samples/sec: 6073.83 - lr: 0.000010 - momentum: 0.000000
200
+ 2023-10-18 17:42:21,181 epoch 9 - iter 267/894 - loss 0.24432659 - time (sec): 4.19 - samples/sec: 6056.05 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-18 17:42:22,530 epoch 9 - iter 356/894 - loss 0.23683646 - time (sec): 5.54 - samples/sec: 6078.25 - lr: 0.000009 - momentum: 0.000000
202
+ 2023-10-18 17:42:23,903 epoch 9 - iter 445/894 - loss 0.23601101 - time (sec): 6.91 - samples/sec: 6083.59 - lr: 0.000008 - momentum: 0.000000
203
+ 2023-10-18 17:42:25,297 epoch 9 - iter 534/894 - loss 0.23146609 - time (sec): 8.31 - samples/sec: 6160.96 - lr: 0.000008 - momentum: 0.000000
204
+ 2023-10-18 17:42:26,717 epoch 9 - iter 623/894 - loss 0.23681248 - time (sec): 9.73 - samples/sec: 6207.57 - lr: 0.000007 - momentum: 0.000000
205
+ 2023-10-18 17:42:28,054 epoch 9 - iter 712/894 - loss 0.23875417 - time (sec): 11.07 - samples/sec: 6173.32 - lr: 0.000007 - momentum: 0.000000
206
+ 2023-10-18 17:42:29,433 epoch 9 - iter 801/894 - loss 0.23968107 - time (sec): 12.45 - samples/sec: 6178.51 - lr: 0.000006 - momentum: 0.000000
207
+ 2023-10-18 17:42:30,871 epoch 9 - iter 890/894 - loss 0.24025730 - time (sec): 13.88 - samples/sec: 6210.19 - lr: 0.000006 - momentum: 0.000000
208
+ 2023-10-18 17:42:30,929 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-18 17:42:30,930 EPOCH 9 done: loss 0.2399 - lr: 0.000006
210
+ 2023-10-18 17:42:35,884 DEV : loss 0.30229300260543823 - f1-score (micro avg) 0.3947
211
+ 2023-10-18 17:42:35,911 saving best model
212
+ 2023-10-18 17:42:35,946 ----------------------------------------------------------------------------------------------------
213
+ 2023-10-18 17:42:37,286 epoch 10 - iter 89/894 - loss 0.23297878 - time (sec): 1.34 - samples/sec: 5957.31 - lr: 0.000005 - momentum: 0.000000
214
+ 2023-10-18 17:42:38,671 epoch 10 - iter 178/894 - loss 0.21576070 - time (sec): 2.72 - samples/sec: 6349.89 - lr: 0.000004 - momentum: 0.000000
215
+ 2023-10-18 17:42:40,035 epoch 10 - iter 267/894 - loss 0.22503277 - time (sec): 4.09 - samples/sec: 6305.28 - lr: 0.000004 - momentum: 0.000000
216
+ 2023-10-18 17:42:41,408 epoch 10 - iter 356/894 - loss 0.23222666 - time (sec): 5.46 - samples/sec: 6276.33 - lr: 0.000003 - momentum: 0.000000
217
+ 2023-10-18 17:42:42,826 epoch 10 - iter 445/894 - loss 0.23341935 - time (sec): 6.88 - samples/sec: 6380.28 - lr: 0.000003 - momentum: 0.000000
218
+ 2023-10-18 17:42:44,561 epoch 10 - iter 534/894 - loss 0.23166851 - time (sec): 8.61 - samples/sec: 6073.29 - lr: 0.000002 - momentum: 0.000000
219
+ 2023-10-18 17:42:45,993 epoch 10 - iter 623/894 - loss 0.23662064 - time (sec): 10.05 - samples/sec: 6036.84 - lr: 0.000002 - momentum: 0.000000
220
+ 2023-10-18 17:42:47,357 epoch 10 - iter 712/894 - loss 0.23735465 - time (sec): 11.41 - samples/sec: 6051.71 - lr: 0.000001 - momentum: 0.000000
221
+ 2023-10-18 17:42:48,742 epoch 10 - iter 801/894 - loss 0.23696194 - time (sec): 12.80 - samples/sec: 6066.99 - lr: 0.000001 - momentum: 0.000000
222
+ 2023-10-18 17:42:50,194 epoch 10 - iter 890/894 - loss 0.23560390 - time (sec): 14.25 - samples/sec: 6056.66 - lr: 0.000000 - momentum: 0.000000
223
+ 2023-10-18 17:42:50,255 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 17:42:50,255 EPOCH 10 done: loss 0.2359 - lr: 0.000000
225
+ 2023-10-18 17:42:55,223 DEV : loss 0.3022255003452301 - f1-score (micro avg) 0.393
226
+ 2023-10-18 17:42:55,281 ----------------------------------------------------------------------------------------------------
227
+ 2023-10-18 17:42:55,281 Loading model from best epoch ...
228
+ 2023-10-18 17:42:55,359 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
229
+ 2023-10-18 17:42:57,662
230
+ Results:
231
+ - F-score (micro) 0.3817
232
+ - F-score (macro) 0.188
233
+ - Accuracy 0.2493
234
+
235
+ By class:
236
+ precision recall f1-score support
237
+
238
+ loc 0.5260 0.5772 0.5504 596
239
+ pers 0.2013 0.2793 0.2340 333
240
+ org 0.0000 0.0000 0.0000 132
241
+ time 0.2143 0.1224 0.1558 49
242
+ prod 0.0000 0.0000 0.0000 66
243
+
244
+ micro avg 0.3869 0.3767 0.3817 1176
245
+ macro avg 0.1883 0.1958 0.1880 1176
246
+ weighted avg 0.3325 0.3767 0.3517 1176
247
+
248
+ 2023-10-18 17:42:57,662 ----------------------------------------------------------------------------------------------------