Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
ecd0178
•
1 Parent(s): 7de160a

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.1697654017.46dc0c540dd0.2878.19 +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:b1c36a5e46ef05a6ce5b8e094d3ed6bd63ed43052df30c4bedf569ef2707ba8f
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 18:33:50 0.0000 1.5345 0.4399 0.0000 0.0000 0.0000 0.0000
3
+ 2 18:34:05 0.0000 0.4744 0.3493 0.3423 0.0594 0.1013 0.0537
4
+ 3 18:34:21 0.0000 0.4005 0.3130 0.3904 0.2424 0.2991 0.1833
5
+ 4 18:34:37 0.0000 0.3624 0.3037 0.4194 0.2705 0.3289 0.2058
6
+ 5 18:34:53 0.0000 0.3282 0.3049 0.4105 0.3049 0.3499 0.2210
7
+ 6 18:35:08 0.0000 0.3141 0.3028 0.3970 0.3299 0.3604 0.2300
8
+ 7 18:35:24 0.0000 0.3002 0.2918 0.3971 0.3198 0.3543 0.2250
9
+ 8 18:35:40 0.0000 0.2907 0.2918 0.3926 0.3401 0.3645 0.2336
10
+ 9 18:35:55 0.0000 0.2808 0.2980 0.4047 0.3253 0.3606 0.2300
11
+ 10 18:36:11 0.0000 0.2758 0.2944 0.3950 0.3354 0.3628 0.2321
runs/events.out.tfevents.1697654017.46dc0c540dd0.2878.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4cbadb72899e07717eaeae18b85ae2e085ee79c07aa861960450c2fa28bd9a0
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 18:33:37,538 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 18:33:37,538 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 18:33:37,538 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 18:33:37,538 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 18:33:37,539 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 18:33:37,539 Train: 3575 sentences
55
+ 2023-10-18 18:33:37,539 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 18:33:37,539 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 18:33:37,539 Training Params:
58
+ 2023-10-18 18:33:37,539 - learning_rate: "5e-05"
59
+ 2023-10-18 18:33:37,539 - mini_batch_size: "8"
60
+ 2023-10-18 18:33:37,539 - max_epochs: "10"
61
+ 2023-10-18 18:33:37,539 - shuffle: "True"
62
+ 2023-10-18 18:33:37,539 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 18:33:37,539 Plugins:
64
+ 2023-10-18 18:33:37,539 - TensorboardLogger
65
+ 2023-10-18 18:33:37,539 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 18:33:37,539 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 18:33:37,539 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 18:33:37,539 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 18:33:37,539 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 18:33:37,539 Computation:
71
+ 2023-10-18 18:33:37,539 - compute on device: cuda:0
72
+ 2023-10-18 18:33:37,539 - embedding storage: none
73
+ 2023-10-18 18:33:37,539 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 18:33:37,539 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
75
+ 2023-10-18 18:33:37,539 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 18:33:37,539 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 18:33:37,539 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 18:33:38,584 epoch 1 - iter 44/447 - loss 3.33635249 - time (sec): 1.04 - samples/sec: 9031.98 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 18:33:39,596 epoch 1 - iter 88/447 - loss 3.23369667 - time (sec): 2.06 - samples/sec: 8843.47 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 18:33:40,624 epoch 1 - iter 132/447 - loss 3.00613659 - time (sec): 3.08 - samples/sec: 8783.54 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 18:33:41,663 epoch 1 - iter 176/447 - loss 2.71396245 - time (sec): 4.12 - samples/sec: 8518.45 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 18:33:42,733 epoch 1 - iter 220/447 - loss 2.38046964 - time (sec): 5.19 - samples/sec: 8459.77 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-18 18:33:43,772 epoch 1 - iter 264/447 - loss 2.12925483 - time (sec): 6.23 - samples/sec: 8330.58 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-18 18:33:44,841 epoch 1 - iter 308/447 - loss 1.91320497 - time (sec): 7.30 - samples/sec: 8317.29 - lr: 0.000034 - momentum: 0.000000
85
+ 2023-10-18 18:33:45,840 epoch 1 - iter 352/447 - loss 1.76692254 - time (sec): 8.30 - samples/sec: 8304.96 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-18 18:33:46,840 epoch 1 - iter 396/447 - loss 1.64812306 - time (sec): 9.30 - samples/sec: 8302.11 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-18 18:33:47,765 epoch 1 - iter 440/447 - loss 1.54768279 - time (sec): 10.23 - samples/sec: 8350.68 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-18 18:33:47,917 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 18:33:47,917 EPOCH 1 done: loss 1.5345 - lr: 0.000049
90
+ 2023-10-18 18:33:50,187 DEV : loss 0.43991518020629883 - f1-score (micro avg) 0.0
91
+ 2023-10-18 18:33:50,215 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 18:33:51,236 epoch 2 - iter 44/447 - loss 0.53951636 - time (sec): 1.02 - samples/sec: 9399.42 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-18 18:33:52,237 epoch 2 - iter 88/447 - loss 0.54048392 - time (sec): 2.02 - samples/sec: 9161.68 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 18:33:53,244 epoch 2 - iter 132/447 - loss 0.51411769 - time (sec): 3.03 - samples/sec: 8848.25 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-18 18:33:54,269 epoch 2 - iter 176/447 - loss 0.48625964 - time (sec): 4.05 - samples/sec: 8700.98 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 18:33:55,244 epoch 2 - iter 220/447 - loss 0.48222774 - time (sec): 5.03 - samples/sec: 8567.74 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-18 18:33:56,313 epoch 2 - iter 264/447 - loss 0.47749236 - time (sec): 6.10 - samples/sec: 8403.28 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 18:33:57,401 epoch 2 - iter 308/447 - loss 0.47712866 - time (sec): 7.19 - samples/sec: 8360.14 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-18 18:33:58,455 epoch 2 - iter 352/447 - loss 0.47982226 - time (sec): 8.24 - samples/sec: 8354.58 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 18:33:59,477 epoch 2 - iter 396/447 - loss 0.47767121 - time (sec): 9.26 - samples/sec: 8313.03 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-18 18:34:00,473 epoch 2 - iter 440/447 - loss 0.47472382 - time (sec): 10.26 - samples/sec: 8331.69 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 18:34:00,631 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 18:34:00,632 EPOCH 2 done: loss 0.4744 - lr: 0.000045
104
+ 2023-10-18 18:34:05,863 DEV : loss 0.34927892684936523 - f1-score (micro avg) 0.1013
105
+ 2023-10-18 18:34:05,892 saving best model
106
+ 2023-10-18 18:34:05,926 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 18:34:06,986 epoch 3 - iter 44/447 - loss 0.41430857 - time (sec): 1.06 - samples/sec: 8227.86 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-18 18:34:08,037 epoch 3 - iter 88/447 - loss 0.42596292 - time (sec): 2.11 - samples/sec: 8062.22 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-18 18:34:09,114 epoch 3 - iter 132/447 - loss 0.41735810 - time (sec): 3.19 - samples/sec: 8032.54 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 18:34:10,154 epoch 3 - iter 176/447 - loss 0.40121953 - time (sec): 4.23 - samples/sec: 7956.82 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-18 18:34:11,246 epoch 3 - iter 220/447 - loss 0.40989488 - time (sec): 5.32 - samples/sec: 7989.71 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 18:34:12,282 epoch 3 - iter 264/447 - loss 0.40691409 - time (sec): 6.36 - samples/sec: 7992.85 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-18 18:34:13,367 epoch 3 - iter 308/447 - loss 0.40246807 - time (sec): 7.44 - samples/sec: 8082.52 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 18:34:14,381 epoch 3 - iter 352/447 - loss 0.39964777 - time (sec): 8.45 - samples/sec: 8073.16 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-18 18:34:15,444 epoch 3 - iter 396/447 - loss 0.40686685 - time (sec): 9.52 - samples/sec: 8104.67 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 18:34:16,474 epoch 3 - iter 440/447 - loss 0.40199107 - time (sec): 10.55 - samples/sec: 8099.80 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 18:34:16,641 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 18:34:16,641 EPOCH 3 done: loss 0.4005 - lr: 0.000039
119
+ 2023-10-18 18:34:21,882 DEV : loss 0.3129710257053375 - f1-score (micro avg) 0.2991
120
+ 2023-10-18 18:34:21,910 saving best model
121
+ 2023-10-18 18:34:21,943 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 18:34:23,020 epoch 4 - iter 44/447 - loss 0.34905134 - time (sec): 1.08 - samples/sec: 8302.97 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-18 18:34:24,089 epoch 4 - iter 88/447 - loss 0.33784904 - time (sec): 2.15 - samples/sec: 8202.40 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 18:34:25,178 epoch 4 - iter 132/447 - loss 0.34129737 - time (sec): 3.23 - samples/sec: 8397.94 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-18 18:34:26,221 epoch 4 - iter 176/447 - loss 0.35267194 - time (sec): 4.28 - samples/sec: 8371.63 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 18:34:27,255 epoch 4 - iter 220/447 - loss 0.35297139 - time (sec): 5.31 - samples/sec: 8230.26 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-18 18:34:28,308 epoch 4 - iter 264/447 - loss 0.35619649 - time (sec): 6.36 - samples/sec: 8280.36 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 18:34:29,274 epoch 4 - iter 308/447 - loss 0.35922624 - time (sec): 7.33 - samples/sec: 8299.85 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-18 18:34:30,258 epoch 4 - iter 352/447 - loss 0.36302459 - time (sec): 8.31 - samples/sec: 8260.86 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 18:34:31,297 epoch 4 - iter 396/447 - loss 0.36296842 - time (sec): 9.35 - samples/sec: 8231.92 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 18:34:32,321 epoch 4 - iter 440/447 - loss 0.36140456 - time (sec): 10.38 - samples/sec: 8228.75 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-18 18:34:32,474 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 18:34:32,474 EPOCH 4 done: loss 0.3624 - lr: 0.000033
134
+ 2023-10-18 18:34:37,831 DEV : loss 0.3036978840827942 - f1-score (micro avg) 0.3289
135
+ 2023-10-18 18:34:37,862 saving best model
136
+ 2023-10-18 18:34:37,896 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 18:34:38,871 epoch 5 - iter 44/447 - loss 0.38380203 - time (sec): 0.97 - samples/sec: 7851.81 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-18 18:34:39,858 epoch 5 - iter 88/447 - loss 0.35069929 - time (sec): 1.96 - samples/sec: 8000.92 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-18 18:34:40,869 epoch 5 - iter 132/447 - loss 0.35025750 - time (sec): 2.97 - samples/sec: 7989.62 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 18:34:41,927 epoch 5 - iter 176/447 - loss 0.32746992 - time (sec): 4.03 - samples/sec: 8316.64 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-18 18:34:42,999 epoch 5 - iter 220/447 - loss 0.32093703 - time (sec): 5.10 - samples/sec: 8417.39 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 18:34:44,092 epoch 5 - iter 264/447 - loss 0.32327443 - time (sec): 6.20 - samples/sec: 8408.21 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-18 18:34:45,141 epoch 5 - iter 308/447 - loss 0.32315435 - time (sec): 7.24 - samples/sec: 8342.28 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 18:34:46,173 epoch 5 - iter 352/447 - loss 0.32526981 - time (sec): 8.28 - samples/sec: 8271.09 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 18:34:47,179 epoch 5 - iter 396/447 - loss 0.32725129 - time (sec): 9.28 - samples/sec: 8276.80 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-18 18:34:48,202 epoch 5 - iter 440/447 - loss 0.32840326 - time (sec): 10.31 - samples/sec: 8274.56 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 18:34:48,370 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 18:34:48,370 EPOCH 5 done: loss 0.3282 - lr: 0.000028
149
+ 2023-10-18 18:34:53,324 DEV : loss 0.30492323637008667 - f1-score (micro avg) 0.3499
150
+ 2023-10-18 18:34:53,354 saving best model
151
+ 2023-10-18 18:34:53,390 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 18:34:54,517 epoch 6 - iter 44/447 - loss 0.28364922 - time (sec): 1.13 - samples/sec: 7540.80 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-18 18:34:55,545 epoch 6 - iter 88/447 - loss 0.30524148 - time (sec): 2.15 - samples/sec: 7993.72 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 18:34:56,617 epoch 6 - iter 132/447 - loss 0.30377453 - time (sec): 3.23 - samples/sec: 8341.74 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-18 18:34:57,582 epoch 6 - iter 176/447 - loss 0.31103907 - time (sec): 4.19 - samples/sec: 8421.94 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 18:34:58,566 epoch 6 - iter 220/447 - loss 0.31842430 - time (sec): 5.17 - samples/sec: 8286.96 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-18 18:34:59,543 epoch 6 - iter 264/447 - loss 0.31506307 - time (sec): 6.15 - samples/sec: 8275.98 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 18:35:00,549 epoch 6 - iter 308/447 - loss 0.31532303 - time (sec): 7.16 - samples/sec: 8328.75 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-18 18:35:01,530 epoch 6 - iter 352/447 - loss 0.31862513 - time (sec): 8.14 - samples/sec: 8355.13 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-18 18:35:02,529 epoch 6 - iter 396/447 - loss 0.31647241 - time (sec): 9.14 - samples/sec: 8376.43 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 18:35:03,527 epoch 6 - iter 440/447 - loss 0.31494212 - time (sec): 10.14 - samples/sec: 8404.30 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-18 18:35:03,684 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 18:35:03,684 EPOCH 6 done: loss 0.3141 - lr: 0.000022
164
+ 2023-10-18 18:35:08,966 DEV : loss 0.3028465211391449 - f1-score (micro avg) 0.3604
165
+ 2023-10-18 18:35:08,994 saving best model
166
+ 2023-10-18 18:35:09,028 ----------------------------------------------------------------------------------------------------
167
+ 2023-10-18 18:35:10,060 epoch 7 - iter 44/447 - loss 0.32923135 - time (sec): 1.03 - samples/sec: 8106.31 - lr: 0.000022 - momentum: 0.000000
168
+ 2023-10-18 18:35:11,038 epoch 7 - iter 88/447 - loss 0.30360566 - time (sec): 2.01 - samples/sec: 8293.92 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-18 18:35:12,038 epoch 7 - iter 132/447 - loss 0.30120743 - time (sec): 3.01 - samples/sec: 8153.90 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-18 18:35:13,063 epoch 7 - iter 176/447 - loss 0.29389615 - time (sec): 4.03 - samples/sec: 8378.99 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-18 18:35:14,079 epoch 7 - iter 220/447 - loss 0.29926602 - time (sec): 5.05 - samples/sec: 8446.85 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-18 18:35:15,046 epoch 7 - iter 264/447 - loss 0.29100384 - time (sec): 6.02 - samples/sec: 8531.87 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-18 18:35:16,061 epoch 7 - iter 308/447 - loss 0.30005417 - time (sec): 7.03 - samples/sec: 8503.70 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-18 18:35:17,102 epoch 7 - iter 352/447 - loss 0.29977152 - time (sec): 8.07 - samples/sec: 8540.69 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-18 18:35:18,105 epoch 7 - iter 396/447 - loss 0.30209308 - time (sec): 9.08 - samples/sec: 8510.51 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-18 18:35:19,101 epoch 7 - iter 440/447 - loss 0.30016354 - time (sec): 10.07 - samples/sec: 8460.16 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-18 18:35:19,253 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-18 18:35:19,253 EPOCH 7 done: loss 0.3002 - lr: 0.000017
179
+ 2023-10-18 18:35:24,552 DEV : loss 0.2917996644973755 - f1-score (micro avg) 0.3543
180
+ 2023-10-18 18:35:24,583 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-18 18:35:25,619 epoch 8 - iter 44/447 - loss 0.30753885 - time (sec): 1.04 - samples/sec: 8181.07 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-18 18:35:26,616 epoch 8 - iter 88/447 - loss 0.29967643 - time (sec): 2.03 - samples/sec: 8244.97 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-18 18:35:27,649 epoch 8 - iter 132/447 - loss 0.29950276 - time (sec): 3.06 - samples/sec: 8325.53 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-18 18:35:28,633 epoch 8 - iter 176/447 - loss 0.29925959 - time (sec): 4.05 - samples/sec: 8497.58 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-18 18:35:29,642 epoch 8 - iter 220/447 - loss 0.29617713 - time (sec): 5.06 - samples/sec: 8453.57 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-18 18:35:30,733 epoch 8 - iter 264/447 - loss 0.29498884 - time (sec): 6.15 - samples/sec: 8516.03 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-18 18:35:31,700 epoch 8 - iter 308/447 - loss 0.29278015 - time (sec): 7.12 - samples/sec: 8480.48 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-18 18:35:32,710 epoch 8 - iter 352/447 - loss 0.29362748 - time (sec): 8.13 - samples/sec: 8493.47 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-18 18:35:33,733 epoch 8 - iter 396/447 - loss 0.28795118 - time (sec): 9.15 - samples/sec: 8504.46 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-18 18:35:34,698 epoch 8 - iter 440/447 - loss 0.29006311 - time (sec): 10.11 - samples/sec: 8454.88 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-18 18:35:34,845 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-18 18:35:34,845 EPOCH 8 done: loss 0.2907 - lr: 0.000011
193
+ 2023-10-18 18:35:40,117 DEV : loss 0.29176047444343567 - f1-score (micro avg) 0.3645
194
+ 2023-10-18 18:35:40,145 saving best model
195
+ 2023-10-18 18:35:40,180 ----------------------------------------------------------------------------------------------------
196
+ 2023-10-18 18:35:41,161 epoch 9 - iter 44/447 - loss 0.27815427 - time (sec): 0.98 - samples/sec: 8007.69 - lr: 0.000011 - momentum: 0.000000
197
+ 2023-10-18 18:35:42,203 epoch 9 - iter 88/447 - loss 0.29456349 - time (sec): 2.02 - samples/sec: 8744.68 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-18 18:35:43,193 epoch 9 - iter 132/447 - loss 0.30940547 - time (sec): 3.01 - samples/sec: 8679.69 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-18 18:35:44,197 epoch 9 - iter 176/447 - loss 0.29950930 - time (sec): 4.02 - samples/sec: 8612.02 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-18 18:35:45,156 epoch 9 - iter 220/447 - loss 0.29574842 - time (sec): 4.98 - samples/sec: 8552.28 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-18 18:35:46,233 epoch 9 - iter 264/447 - loss 0.29098159 - time (sec): 6.05 - samples/sec: 8608.97 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-18 18:35:47,237 epoch 9 - iter 308/447 - loss 0.28502560 - time (sec): 7.06 - samples/sec: 8656.29 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-18 18:35:48,230 epoch 9 - iter 352/447 - loss 0.28416310 - time (sec): 8.05 - samples/sec: 8593.79 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-18 18:35:49,241 epoch 9 - iter 396/447 - loss 0.28422952 - time (sec): 9.06 - samples/sec: 8574.72 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-18 18:35:50,207 epoch 9 - iter 440/447 - loss 0.28130013 - time (sec): 10.03 - samples/sec: 8520.33 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-18 18:35:50,362 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-18 18:35:50,362 EPOCH 9 done: loss 0.2808 - lr: 0.000006
208
+ 2023-10-18 18:35:55,812 DEV : loss 0.298006534576416 - f1-score (micro avg) 0.3606
209
+ 2023-10-18 18:35:55,841 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-18 18:35:56,799 epoch 10 - iter 44/447 - loss 0.23061533 - time (sec): 0.96 - samples/sec: 9276.23 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-18 18:35:57,825 epoch 10 - iter 88/447 - loss 0.24946824 - time (sec): 1.98 - samples/sec: 8725.00 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-18 18:35:58,817 epoch 10 - iter 132/447 - loss 0.24339995 - time (sec): 2.98 - samples/sec: 8314.11 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-18 18:35:59,824 epoch 10 - iter 176/447 - loss 0.25223271 - time (sec): 3.98 - samples/sec: 8273.66 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-18 18:36:00,855 epoch 10 - iter 220/447 - loss 0.25850329 - time (sec): 5.01 - samples/sec: 8212.99 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-18 18:36:01,880 epoch 10 - iter 264/447 - loss 0.26389720 - time (sec): 6.04 - samples/sec: 8151.84 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-18 18:36:02,949 epoch 10 - iter 308/447 - loss 0.26807520 - time (sec): 7.11 - samples/sec: 8067.37 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-18 18:36:04,057 epoch 10 - iter 352/447 - loss 0.27136731 - time (sec): 8.22 - samples/sec: 8137.26 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 18:36:05,175 epoch 10 - iter 396/447 - loss 0.26821511 - time (sec): 9.33 - samples/sec: 8233.20 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 18:36:06,174 epoch 10 - iter 440/447 - loss 0.27485413 - time (sec): 10.33 - samples/sec: 8242.45 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-18 18:36:06,341 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-18 18:36:06,341 EPOCH 10 done: loss 0.2758 - lr: 0.000000
222
+ 2023-10-18 18:36:11,515 DEV : loss 0.2943832576274872 - f1-score (micro avg) 0.3628
223
+ 2023-10-18 18:36:11,574 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 18:36:11,574 Loading model from best epoch ...
225
+ 2023-10-18 18:36:11,658 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 18:36:14,073
227
+ Results:
228
+ - F-score (micro) 0.3459
229
+ - F-score (macro) 0.1566
230
+ - Accuracy 0.2208
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.4685 0.5487 0.5054 596
236
+ pers 0.1655 0.2102 0.1852 333
237
+ org 0.0000 0.0000 0.0000 132
238
+ prod 0.0000 0.0000 0.0000 66
239
+ time 0.1875 0.0612 0.0923 49
240
+
241
+ micro avg 0.3518 0.3401 0.3459 1176
242
+ macro avg 0.1643 0.1640 0.1566 1176
243
+ weighted avg 0.2921 0.3401 0.3124 1176
244
+
245
+ 2023-10-18 18:36:14,073 ----------------------------------------------------------------------------------------------------