Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert_tiny-bs8-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
324275e
•
1 Parent(s): e1f99cf

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.1697651145.46dc0c540dd0.2878.3 +3 -0
  5. test.tsv +0 -0
  6. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12ec3f9975857f29ae2a0aec6395ef99087542748187d8c2a325ef7d8b84bb2
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 17:45:57 0.0000 1.5041 0.4547 0.0000 0.0000 0.0000 0.0000
3
+ 2 17:46:12 0.0000 0.4822 0.3523 0.3977 0.1079 0.1697 0.0945
4
+ 3 17:46:28 0.0000 0.3906 0.3125 0.4370 0.2361 0.3066 0.1871
5
+ 4 17:46:44 0.0000 0.3532 0.3131 0.4223 0.2869 0.3417 0.2146
6
+ 5 17:46:59 0.0000 0.3284 0.2935 0.3893 0.3135 0.3473 0.2213
7
+ 6 17:47:15 0.0000 0.3064 0.2914 0.4147 0.3307 0.3680 0.2378
8
+ 7 17:47:30 0.0000 0.2911 0.2890 0.3967 0.3346 0.3630 0.2346
9
+ 8 17:47:45 0.0000 0.2825 0.2879 0.4002 0.3401 0.3677 0.2389
10
+ 9 17:48:01 0.0000 0.2702 0.2887 0.4128 0.3425 0.3744 0.2443
11
+ 10 17:48:17 0.0000 0.2675 0.2890 0.4100 0.3401 0.3718 0.2426
runs/events.out.tfevents.1697651145.46dc0c540dd0.2878.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47a27998580272c14ac70cf7337f11b19ad31ff0dfc76b301e5b1f9024a0940e
3
+ size 253592
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 17:45:45,111 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 17:45:45,111 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 17:45:45,111 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 17:45:45,111 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 17:45:45,111 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 17:45:45,111 Train: 3575 sentences
55
+ 2023-10-18 17:45:45,111 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 17:45:45,111 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 17:45:45,111 Training Params:
58
+ 2023-10-18 17:45:45,111 - learning_rate: "5e-05"
59
+ 2023-10-18 17:45:45,111 - mini_batch_size: "8"
60
+ 2023-10-18 17:45:45,111 - max_epochs: "10"
61
+ 2023-10-18 17:45:45,111 - shuffle: "True"
62
+ 2023-10-18 17:45:45,111 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 17:45:45,111 Plugins:
64
+ 2023-10-18 17:45:45,111 - TensorboardLogger
65
+ 2023-10-18 17:45:45,111 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 17:45:45,111 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 17:45:45,112 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 17:45:45,112 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 17:45:45,112 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 17:45:45,112 Computation:
71
+ 2023-10-18 17:45:45,112 - compute on device: cuda:0
72
+ 2023-10-18 17:45:45,112 - embedding storage: none
73
+ 2023-10-18 17:45:45,112 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 17:45:45,112 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-18 17:45:45,112 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 17:45:45,112 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 17:45:45,112 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 17:45:46,424 epoch 1 - iter 44/447 - loss 3.63023183 - time (sec): 1.31 - samples/sec: 6249.34 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 17:45:47,340 epoch 1 - iter 88/447 - loss 3.47670301 - time (sec): 2.23 - samples/sec: 7442.66 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 17:45:48,324 epoch 1 - iter 132/447 - loss 3.17492072 - time (sec): 3.21 - samples/sec: 7810.71 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 17:45:49,295 epoch 1 - iter 176/447 - loss 2.82555737 - time (sec): 4.18 - samples/sec: 7998.44 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 17:45:50,276 epoch 1 - iter 220/447 - loss 2.42797386 - time (sec): 5.16 - samples/sec: 8200.94 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-18 17:45:51,302 epoch 1 - iter 264/447 - loss 2.13076998 - time (sec): 6.19 - samples/sec: 8265.38 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-18 17:45:52,327 epoch 1 - iter 308/447 - loss 1.91676111 - time (sec): 7.21 - samples/sec: 8275.15 - lr: 0.000034 - momentum: 0.000000
85
+ 2023-10-18 17:45:53,332 epoch 1 - iter 352/447 - loss 1.74561988 - time (sec): 8.22 - samples/sec: 8341.64 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-18 17:45:54,330 epoch 1 - iter 396/447 - loss 1.61932497 - time (sec): 9.22 - samples/sec: 8373.39 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-18 17:45:55,313 epoch 1 - iter 440/447 - loss 1.51895144 - time (sec): 10.20 - samples/sec: 8350.97 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-18 17:45:55,465 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 17:45:55,465 EPOCH 1 done: loss 1.5041 - lr: 0.000049
90
+ 2023-10-18 17:45:57,366 DEV : loss 0.45467135310173035 - f1-score (micro avg) 0.0
91
+ 2023-10-18 17:45:57,391 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 17:45:58,406 epoch 2 - iter 44/447 - loss 0.55495071 - time (sec): 1.02 - samples/sec: 9278.81 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-18 17:45:59,729 epoch 2 - iter 88/447 - loss 0.52145669 - time (sec): 2.34 - samples/sec: 7818.26 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 17:46:00,751 epoch 2 - iter 132/447 - loss 0.51503667 - time (sec): 3.36 - samples/sec: 8091.33 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-18 17:46:01,718 epoch 2 - iter 176/447 - loss 0.51312139 - time (sec): 4.33 - samples/sec: 8020.83 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 17:46:02,719 epoch 2 - iter 220/447 - loss 0.50166932 - time (sec): 5.33 - samples/sec: 8204.80 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-18 17:46:03,686 epoch 2 - iter 264/447 - loss 0.49283811 - time (sec): 6.29 - samples/sec: 8225.13 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 17:46:04,685 epoch 2 - iter 308/447 - loss 0.49657977 - time (sec): 7.29 - samples/sec: 8237.58 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-18 17:46:05,718 epoch 2 - iter 352/447 - loss 0.49009269 - time (sec): 8.33 - samples/sec: 8241.12 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 17:46:06,718 epoch 2 - iter 396/447 - loss 0.48910603 - time (sec): 9.33 - samples/sec: 8256.38 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-18 17:46:07,702 epoch 2 - iter 440/447 - loss 0.48266159 - time (sec): 10.31 - samples/sec: 8252.91 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 17:46:07,863 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 17:46:07,863 EPOCH 2 done: loss 0.4822 - lr: 0.000045
104
+ 2023-10-18 17:46:12,738 DEV : loss 0.35227200388908386 - f1-score (micro avg) 0.1697
105
+ 2023-10-18 17:46:12,763 saving best model
106
+ 2023-10-18 17:46:12,800 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 17:46:13,765 epoch 3 - iter 44/447 - loss 0.39653677 - time (sec): 0.96 - samples/sec: 8094.88 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-18 17:46:14,775 epoch 3 - iter 88/447 - loss 0.41886899 - time (sec): 1.98 - samples/sec: 8353.85 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-18 17:46:15,797 epoch 3 - iter 132/447 - loss 0.41806988 - time (sec): 3.00 - samples/sec: 8102.47 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 17:46:16,827 epoch 3 - iter 176/447 - loss 0.40474759 - time (sec): 4.03 - samples/sec: 8248.55 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-18 17:46:17,812 epoch 3 - iter 220/447 - loss 0.40178671 - time (sec): 5.01 - samples/sec: 8364.46 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 17:46:18,811 epoch 3 - iter 264/447 - loss 0.39833510 - time (sec): 6.01 - samples/sec: 8467.03 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-18 17:46:19,813 epoch 3 - iter 308/447 - loss 0.39305489 - time (sec): 7.01 - samples/sec: 8379.61 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 17:46:20,864 epoch 3 - iter 352/447 - loss 0.39147747 - time (sec): 8.06 - samples/sec: 8325.86 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-18 17:46:21,931 epoch 3 - iter 396/447 - loss 0.39451842 - time (sec): 9.13 - samples/sec: 8281.18 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 17:46:23,003 epoch 3 - iter 440/447 - loss 0.39174653 - time (sec): 10.20 - samples/sec: 8357.16 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 17:46:23,147 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 17:46:23,147 EPOCH 3 done: loss 0.3906 - lr: 0.000039
119
+ 2023-10-18 17:46:28,370 DEV : loss 0.3125365972518921 - f1-score (micro avg) 0.3066
120
+ 2023-10-18 17:46:28,397 saving best model
121
+ 2023-10-18 17:46:28,440 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 17:46:29,500 epoch 4 - iter 44/447 - loss 0.34658596 - time (sec): 1.06 - samples/sec: 8576.54 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-18 17:46:30,503 epoch 4 - iter 88/447 - loss 0.36650845 - time (sec): 2.06 - samples/sec: 8538.19 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 17:46:31,510 epoch 4 - iter 132/447 - loss 0.37690399 - time (sec): 3.07 - samples/sec: 8586.97 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-18 17:46:32,518 epoch 4 - iter 176/447 - loss 0.37315065 - time (sec): 4.08 - samples/sec: 8680.94 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 17:46:33,480 epoch 4 - iter 220/447 - loss 0.36813917 - time (sec): 5.04 - samples/sec: 8629.02 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-18 17:46:34,474 epoch 4 - iter 264/447 - loss 0.36318897 - time (sec): 6.03 - samples/sec: 8586.76 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 17:46:35,519 epoch 4 - iter 308/447 - loss 0.35678724 - time (sec): 7.08 - samples/sec: 8529.43 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-18 17:46:36,574 epoch 4 - iter 352/447 - loss 0.35194138 - time (sec): 8.13 - samples/sec: 8459.85 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 17:46:37,585 epoch 4 - iter 396/447 - loss 0.35494397 - time (sec): 9.14 - samples/sec: 8446.83 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 17:46:38,593 epoch 4 - iter 440/447 - loss 0.35274777 - time (sec): 10.15 - samples/sec: 8401.55 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-18 17:46:38,757 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 17:46:38,757 EPOCH 4 done: loss 0.3532 - lr: 0.000033
134
+ 2023-10-18 17:46:44,063 DEV : loss 0.3131018579006195 - f1-score (micro avg) 0.3417
135
+ 2023-10-18 17:46:44,088 saving best model
136
+ 2023-10-18 17:46:44,121 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 17:46:45,122 epoch 5 - iter 44/447 - loss 0.30571568 - time (sec): 1.00 - samples/sec: 8142.12 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-18 17:46:46,142 epoch 5 - iter 88/447 - loss 0.33894497 - time (sec): 2.02 - samples/sec: 7815.16 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-18 17:46:47,211 epoch 5 - iter 132/447 - loss 0.31782972 - time (sec): 3.09 - samples/sec: 7706.70 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 17:46:48,269 epoch 5 - iter 176/447 - loss 0.31678493 - time (sec): 4.15 - samples/sec: 8031.04 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-18 17:46:49,274 epoch 5 - iter 220/447 - loss 0.31827885 - time (sec): 5.15 - samples/sec: 8157.81 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 17:46:50,285 epoch 5 - iter 264/447 - loss 0.31772496 - time (sec): 6.16 - samples/sec: 8270.72 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-18 17:46:51,298 epoch 5 - iter 308/447 - loss 0.31931617 - time (sec): 7.18 - samples/sec: 8288.28 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 17:46:52,318 epoch 5 - iter 352/447 - loss 0.32349790 - time (sec): 8.20 - samples/sec: 8320.37 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 17:46:53,315 epoch 5 - iter 396/447 - loss 0.32487172 - time (sec): 9.19 - samples/sec: 8325.07 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-18 17:46:54,306 epoch 5 - iter 440/447 - loss 0.32512626 - time (sec): 10.18 - samples/sec: 8372.89 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 17:46:54,471 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 17:46:54,471 EPOCH 5 done: loss 0.3284 - lr: 0.000028
149
+ 2023-10-18 17:46:59,699 DEV : loss 0.2934885025024414 - f1-score (micro avg) 0.3473
150
+ 2023-10-18 17:46:59,723 saving best model
151
+ 2023-10-18 17:46:59,757 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 17:47:00,810 epoch 6 - iter 44/447 - loss 0.33102953 - time (sec): 1.05 - samples/sec: 7910.31 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-18 17:47:01,850 epoch 6 - iter 88/447 - loss 0.29089739 - time (sec): 2.09 - samples/sec: 8271.88 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 17:47:02,897 epoch 6 - iter 132/447 - loss 0.27937740 - time (sec): 3.14 - samples/sec: 8474.85 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-18 17:47:03,884 epoch 6 - iter 176/447 - loss 0.29312207 - time (sec): 4.13 - samples/sec: 8382.12 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 17:47:04,878 epoch 6 - iter 220/447 - loss 0.30141709 - time (sec): 5.12 - samples/sec: 8404.35 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-18 17:47:05,903 epoch 6 - iter 264/447 - loss 0.30127538 - time (sec): 6.15 - samples/sec: 8330.13 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 17:47:06,882 epoch 6 - iter 308/447 - loss 0.30249673 - time (sec): 7.12 - samples/sec: 8356.36 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-18 17:47:07,871 epoch 6 - iter 352/447 - loss 0.30097020 - time (sec): 8.11 - samples/sec: 8424.06 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-18 17:47:08,915 epoch 6 - iter 396/447 - loss 0.30519595 - time (sec): 9.16 - samples/sec: 8402.09 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 17:47:09,894 epoch 6 - iter 440/447 - loss 0.30649731 - time (sec): 10.14 - samples/sec: 8393.94 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-18 17:47:10,051 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 17:47:10,051 EPOCH 6 done: loss 0.3064 - lr: 0.000022
164
+ 2023-10-18 17:47:15,383 DEV : loss 0.29135483503341675 - f1-score (micro avg) 0.368
165
+ 2023-10-18 17:47:15,409 saving best model
166
+ 2023-10-18 17:47:15,440 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 17:47:16,409 epoch 7 - iter 44/447 - loss 0.27124394 - time (sec): 0.97 - samples/sec: 8470.90 - lr: 0.000022 - momentum: 0.000000
168
+ 2023-10-18 17:47:17,393 epoch 7 - iter 88/447 - loss 0.27751488 - time (sec): 1.95 - samples/sec: 8585.24 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-18 17:47:18,413 epoch 7 - iter 132/447 - loss 0.28270565 - time (sec): 2.97 - samples/sec: 8218.31 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-18 17:47:19,446 epoch 7 - iter 176/447 - loss 0.28697327 - time (sec): 4.01 - samples/sec: 8291.23 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-18 17:47:20,471 epoch 7 - iter 220/447 - loss 0.28533917 - time (sec): 5.03 - samples/sec: 8295.46 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-18 17:47:21,440 epoch 7 - iter 264/447 - loss 0.28421280 - time (sec): 6.00 - samples/sec: 8287.42 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-18 17:47:22,449 epoch 7 - iter 308/447 - loss 0.28908989 - time (sec): 7.01 - samples/sec: 8330.52 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-18 17:47:23,525 epoch 7 - iter 352/447 - loss 0.28831722 - time (sec): 8.08 - samples/sec: 8425.48 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-18 17:47:24,553 epoch 7 - iter 396/447 - loss 0.28733893 - time (sec): 9.11 - samples/sec: 8348.03 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-18 17:47:25,615 epoch 7 - iter 440/447 - loss 0.29081983 - time (sec): 10.17 - samples/sec: 8398.03 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-18 17:47:25,778 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 17:47:25,778 EPOCH 7 done: loss 0.2911 - lr: 0.000017
179
+ 2023-10-18 17:47:30,756 DEV : loss 0.2889775335788727 - f1-score (micro avg) 0.363
180
+ 2023-10-18 17:47:30,782 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-18 17:47:31,817 epoch 8 - iter 44/447 - loss 0.27122766 - time (sec): 1.03 - samples/sec: 7852.47 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-18 17:47:32,800 epoch 8 - iter 88/447 - loss 0.27239490 - time (sec): 2.02 - samples/sec: 8271.11 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-18 17:47:33,633 epoch 8 - iter 132/447 - loss 0.27395850 - time (sec): 2.85 - samples/sec: 8639.16 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-18 17:47:34,496 epoch 8 - iter 176/447 - loss 0.27805841 - time (sec): 3.71 - samples/sec: 8827.52 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-18 17:47:35,344 epoch 8 - iter 220/447 - loss 0.27997338 - time (sec): 4.56 - samples/sec: 9055.14 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-18 17:47:36,268 epoch 8 - iter 264/447 - loss 0.28648908 - time (sec): 5.49 - samples/sec: 9102.12 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-18 17:47:37,357 epoch 8 - iter 308/447 - loss 0.28405540 - time (sec): 6.57 - samples/sec: 9122.48 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-18 17:47:38,425 epoch 8 - iter 352/447 - loss 0.28687288 - time (sec): 7.64 - samples/sec: 9000.75 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-18 17:47:39,444 epoch 8 - iter 396/447 - loss 0.28653366 - time (sec): 8.66 - samples/sec: 8876.98 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-18 17:47:40,456 epoch 8 - iter 440/447 - loss 0.28373991 - time (sec): 9.67 - samples/sec: 8828.62 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-18 17:47:40,605 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-18 17:47:40,605 EPOCH 8 done: loss 0.2825 - lr: 0.000011
193
+ 2023-10-18 17:47:45,952 DEV : loss 0.2879358232021332 - f1-score (micro avg) 0.3677
194
+ 2023-10-18 17:47:45,979 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-18 17:47:47,006 epoch 9 - iter 44/447 - loss 0.27183602 - time (sec): 1.03 - samples/sec: 8000.53 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-18 17:47:48,025 epoch 9 - iter 88/447 - loss 0.26259942 - time (sec): 2.05 - samples/sec: 8257.05 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-18 17:47:49,009 epoch 9 - iter 132/447 - loss 0.26992750 - time (sec): 3.03 - samples/sec: 8293.21 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-18 17:47:49,989 epoch 9 - iter 176/447 - loss 0.26493230 - time (sec): 4.01 - samples/sec: 8324.07 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-18 17:47:50,977 epoch 9 - iter 220/447 - loss 0.26644403 - time (sec): 5.00 - samples/sec: 8318.87 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-18 17:47:51,984 epoch 9 - iter 264/447 - loss 0.26207838 - time (sec): 6.01 - samples/sec: 8424.72 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-18 17:47:53,030 epoch 9 - iter 308/447 - loss 0.26828243 - time (sec): 7.05 - samples/sec: 8473.53 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-18 17:47:53,988 epoch 9 - iter 352/447 - loss 0.26953453 - time (sec): 8.01 - samples/sec: 8451.29 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-18 17:47:54,994 epoch 9 - iter 396/447 - loss 0.27140936 - time (sec): 9.01 - samples/sec: 8428.25 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-18 17:47:56,012 epoch 9 - iter 440/447 - loss 0.26981883 - time (sec): 10.03 - samples/sec: 8518.48 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-18 17:47:56,171 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-18 17:47:56,171 EPOCH 9 done: loss 0.2702 - lr: 0.000006
207
+ 2023-10-18 17:48:01,497 DEV : loss 0.2887320816516876 - f1-score (micro avg) 0.3744
208
+ 2023-10-18 17:48:01,523 saving best model
209
+ 2023-10-18 17:48:01,562 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-18 17:48:02,553 epoch 10 - iter 44/447 - loss 0.25613707 - time (sec): 0.99 - samples/sec: 8003.44 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-18 17:48:03,577 epoch 10 - iter 88/447 - loss 0.24160136 - time (sec): 2.01 - samples/sec: 8521.32 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-18 17:48:04,552 epoch 10 - iter 132/447 - loss 0.25434692 - time (sec): 2.99 - samples/sec: 8567.48 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-18 17:48:05,521 epoch 10 - iter 176/447 - loss 0.26304286 - time (sec): 3.96 - samples/sec: 8549.81 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-18 17:48:06,578 epoch 10 - iter 220/447 - loss 0.26755417 - time (sec): 5.02 - samples/sec: 8613.78 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-18 17:48:07,539 epoch 10 - iter 264/447 - loss 0.26551062 - time (sec): 5.98 - samples/sec: 8631.16 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-18 17:48:08,548 epoch 10 - iter 308/447 - loss 0.27058725 - time (sec): 6.99 - samples/sec: 8586.48 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-18 17:48:09,548 epoch 10 - iter 352/447 - loss 0.27199708 - time (sec): 7.99 - samples/sec: 8560.23 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 17:48:10,564 epoch 10 - iter 396/447 - loss 0.27115365 - time (sec): 9.00 - samples/sec: 8546.42 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 17:48:11,555 epoch 10 - iter 440/447 - loss 0.26841919 - time (sec): 9.99 - samples/sec: 8532.39 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 17:48:11,713 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-18 17:48:11,713 EPOCH 10 done: loss 0.2675 - lr: 0.000000
222
+ 2023-10-18 17:48:17,028 DEV : loss 0.2889607846736908 - f1-score (micro avg) 0.3718
223
+ 2023-10-18 17:48:17,087 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 17:48:17,088 Loading model from best epoch ...
225
+ 2023-10-18 17:48:17,167 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
+ 2023-10-18 17:48:19,105
227
+ Results:
228
+ - F-score (micro) 0.3781
229
+ - F-score (macro) 0.1626
230
+ - Accuracy 0.2465
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.5388 0.5822 0.5597 596
236
+ pers 0.1865 0.2072 0.1963 333
237
+ org 0.0000 0.0000 0.0000 132
238
+ time 0.0952 0.0408 0.0571 49
239
+ prod 0.0000 0.0000 0.0000 66
240
+
241
+ micro avg 0.4039 0.3554 0.3781 1176
242
+ macro avg 0.1641 0.1660 0.1626 1176
243
+ weighted avg 0.3298 0.3554 0.3416 1176
244
+
245
+ 2023-10-18 17:48:19,105 ----------------------------------------------------------------------------------------------------