Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert-bs8-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
31275b4
•
1 Parent(s): 363b0d5

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8303328c15a3b32cab7018e0aef5c0163422580e4ddcec2c6fafb334416aaa56
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 11:44:49 0.0000 0.6828 0.1743 0.6610 0.6130 0.6361 0.4772
3
+ 2 11:45:27 0.0000 0.1500 0.1289 0.6799 0.7506 0.7135 0.5721
4
+ 3 11:46:05 0.0000 0.0817 0.1253 0.7079 0.7561 0.7312 0.5991
5
+ 4 11:46:43 0.0000 0.0506 0.1667 0.7527 0.7662 0.7594 0.6310
6
+ 5 11:47:21 0.0000 0.0361 0.1952 0.7633 0.7514 0.7573 0.6252
7
+ 6 11:47:59 0.0000 0.0233 0.2064 0.7207 0.7850 0.7515 0.6209
8
+ 7 11:48:37 0.0000 0.0149 0.1995 0.7581 0.8061 0.7814 0.6567
9
+ 8 11:49:14 0.0000 0.0098 0.2216 0.7758 0.7983 0.7869 0.6656
10
+ 9 11:49:52 0.0000 0.0058 0.2242 0.7881 0.7998 0.7939 0.6748
11
+ 10 11:50:30 0.0000 0.0040 0.2236 0.7840 0.8030 0.7934 0.6743
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 11:44:15,758 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 11:44:15,759 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 11:44:15,759 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 11:44:15,759 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 11:44:15,759 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 11:44:15,759 Train: 3575 sentences
55
+ 2023-10-13 11:44:15,759 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 11:44:15,759 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 11:44:15,759 Training Params:
58
+ 2023-10-13 11:44:15,760 - learning_rate: "5e-05"
59
+ 2023-10-13 11:44:15,760 - mini_batch_size: "8"
60
+ 2023-10-13 11:44:15,760 - max_epochs: "10"
61
+ 2023-10-13 11:44:15,760 - shuffle: "True"
62
+ 2023-10-13 11:44:15,760 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 11:44:15,760 Plugins:
64
+ 2023-10-13 11:44:15,760 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 11:44:15,760 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 11:44:15,760 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 11:44:15,760 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 11:44:15,760 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 11:44:15,760 Computation:
70
+ 2023-10-13 11:44:15,760 - compute on device: cuda:0
71
+ 2023-10-13 11:44:15,760 - embedding storage: none
72
+ 2023-10-13 11:44:15,760 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 11:44:15,760 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-13 11:44:15,760 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 11:44:15,760 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 11:44:18,820 epoch 1 - iter 44/447 - loss 3.00192754 - time (sec): 3.06 - samples/sec: 3107.41 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 11:44:21,453 epoch 1 - iter 88/447 - loss 2.12561225 - time (sec): 5.69 - samples/sec: 3053.75 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 11:44:24,069 epoch 1 - iter 132/447 - loss 1.62736701 - time (sec): 8.31 - samples/sec: 3012.86 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 11:44:26,817 epoch 1 - iter 176/447 - loss 1.31615057 - time (sec): 11.06 - samples/sec: 3025.58 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 11:44:29,573 epoch 1 - iter 220/447 - loss 1.13111058 - time (sec): 13.81 - samples/sec: 3009.28 - lr: 0.000024 - momentum: 0.000000
81
+ 2023-10-13 11:44:32,463 epoch 1 - iter 264/447 - loss 0.98651046 - time (sec): 16.70 - samples/sec: 3017.43 - lr: 0.000029 - momentum: 0.000000
82
+ 2023-10-13 11:44:35,214 epoch 1 - iter 308/447 - loss 0.88523112 - time (sec): 19.45 - samples/sec: 3032.23 - lr: 0.000034 - momentum: 0.000000
83
+ 2023-10-13 11:44:38,573 epoch 1 - iter 352/447 - loss 0.79933006 - time (sec): 22.81 - samples/sec: 2982.26 - lr: 0.000039 - momentum: 0.000000
84
+ 2023-10-13 11:44:41,327 epoch 1 - iter 396/447 - loss 0.73789913 - time (sec): 25.57 - samples/sec: 2984.81 - lr: 0.000044 - momentum: 0.000000
85
+ 2023-10-13 11:44:44,373 epoch 1 - iter 440/447 - loss 0.68906501 - time (sec): 28.61 - samples/sec: 2985.26 - lr: 0.000049 - momentum: 0.000000
86
+ 2023-10-13 11:44:44,800 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 11:44:44,800 EPOCH 1 done: loss 0.6828 - lr: 0.000049
88
+ 2023-10-13 11:44:49,329 DEV : loss 0.17432522773742676 - f1-score (micro avg) 0.6361
89
+ 2023-10-13 11:44:49,359 saving best model
90
+ 2023-10-13 11:44:49,798 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 11:44:52,910 epoch 2 - iter 44/447 - loss 0.16099947 - time (sec): 3.11 - samples/sec: 2748.55 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 11:44:55,787 epoch 2 - iter 88/447 - loss 0.18473236 - time (sec): 5.99 - samples/sec: 2846.17 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 11:44:58,532 epoch 2 - iter 132/447 - loss 0.17741855 - time (sec): 8.73 - samples/sec: 2942.70 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 11:45:01,432 epoch 2 - iter 176/447 - loss 0.17120620 - time (sec): 11.63 - samples/sec: 2930.41 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 11:45:04,076 epoch 2 - iter 220/447 - loss 0.16623014 - time (sec): 14.28 - samples/sec: 2939.48 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 11:45:07,067 epoch 2 - iter 264/447 - loss 0.15782578 - time (sec): 17.27 - samples/sec: 2928.18 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 11:45:10,075 epoch 2 - iter 308/447 - loss 0.15657926 - time (sec): 20.28 - samples/sec: 2950.92 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 11:45:12,864 epoch 2 - iter 352/447 - loss 0.15440721 - time (sec): 23.06 - samples/sec: 2941.58 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 11:45:15,607 epoch 2 - iter 396/447 - loss 0.15306937 - time (sec): 25.81 - samples/sec: 2941.23 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 11:45:18,675 epoch 2 - iter 440/447 - loss 0.15097223 - time (sec): 28.88 - samples/sec: 2955.45 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-13 11:45:19,094 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 11:45:19,094 EPOCH 2 done: loss 0.1500 - lr: 0.000045
103
+ 2023-10-13 11:45:27,170 DEV : loss 0.128895103931427 - f1-score (micro avg) 0.7135
104
+ 2023-10-13 11:45:27,197 saving best model
105
+ 2023-10-13 11:45:27,641 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 11:45:30,333 epoch 3 - iter 44/447 - loss 0.08954463 - time (sec): 2.69 - samples/sec: 2870.97 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 11:45:32,983 epoch 3 - iter 88/447 - loss 0.07907098 - time (sec): 5.34 - samples/sec: 2990.59 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 11:45:35,676 epoch 3 - iter 132/447 - loss 0.08762480 - time (sec): 8.03 - samples/sec: 2991.05 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 11:45:39,076 epoch 3 - iter 176/447 - loss 0.08018442 - time (sec): 11.43 - samples/sec: 2875.98 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 11:45:42,286 epoch 3 - iter 220/447 - loss 0.08160036 - time (sec): 14.64 - samples/sec: 2864.74 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 11:45:45,033 epoch 3 - iter 264/447 - loss 0.07929525 - time (sec): 17.39 - samples/sec: 2906.70 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 11:45:47,994 epoch 3 - iter 308/447 - loss 0.08305282 - time (sec): 20.35 - samples/sec: 2906.96 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 11:45:51,011 epoch 3 - iter 352/447 - loss 0.08280962 - time (sec): 23.36 - samples/sec: 2901.89 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 11:45:53,745 epoch 3 - iter 396/447 - loss 0.08300649 - time (sec): 26.10 - samples/sec: 2916.83 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-13 11:45:57,008 epoch 3 - iter 440/447 - loss 0.08157697 - time (sec): 29.36 - samples/sec: 2910.52 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 11:45:57,419 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 11:45:57,419 EPOCH 3 done: loss 0.0817 - lr: 0.000039
118
+ 2023-10-13 11:46:05,551 DEV : loss 0.12530890107154846 - f1-score (micro avg) 0.7312
119
+ 2023-10-13 11:46:05,579 saving best model
120
+ 2023-10-13 11:46:06,046 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 11:46:08,859 epoch 4 - iter 44/447 - loss 0.06395096 - time (sec): 2.81 - samples/sec: 3188.81 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 11:46:11,496 epoch 4 - iter 88/447 - loss 0.05609227 - time (sec): 5.45 - samples/sec: 3121.01 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 11:46:14,489 epoch 4 - iter 132/447 - loss 0.05254098 - time (sec): 8.44 - samples/sec: 3085.83 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 11:46:17,596 epoch 4 - iter 176/447 - loss 0.05434937 - time (sec): 11.55 - samples/sec: 3089.85 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 11:46:20,600 epoch 4 - iter 220/447 - loss 0.05216684 - time (sec): 14.55 - samples/sec: 3047.80 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 11:46:23,946 epoch 4 - iter 264/447 - loss 0.05292772 - time (sec): 17.90 - samples/sec: 2960.39 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 11:46:26,646 epoch 4 - iter 308/447 - loss 0.05273653 - time (sec): 20.60 - samples/sec: 2976.45 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 11:46:29,376 epoch 4 - iter 352/447 - loss 0.05196364 - time (sec): 23.33 - samples/sec: 2987.17 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-13 11:46:31,872 epoch 4 - iter 396/447 - loss 0.04948670 - time (sec): 25.82 - samples/sec: 2976.55 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 11:46:34,756 epoch 4 - iter 440/447 - loss 0.04973611 - time (sec): 28.71 - samples/sec: 2973.55 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 11:46:35,161 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 11:46:35,162 EPOCH 4 done: loss 0.0506 - lr: 0.000033
133
+ 2023-10-13 11:46:43,220 DEV : loss 0.16665692627429962 - f1-score (micro avg) 0.7594
134
+ 2023-10-13 11:46:43,248 saving best model
135
+ 2023-10-13 11:46:43,743 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 11:46:47,190 epoch 5 - iter 44/447 - loss 0.04162747 - time (sec): 3.44 - samples/sec: 2799.52 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 11:46:49,839 epoch 5 - iter 88/447 - loss 0.03504743 - time (sec): 6.09 - samples/sec: 2894.26 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 11:46:52,807 epoch 5 - iter 132/447 - loss 0.03495945 - time (sec): 9.06 - samples/sec: 2897.46 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 11:46:55,586 epoch 5 - iter 176/447 - loss 0.03617387 - time (sec): 11.84 - samples/sec: 2902.83 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 11:46:58,575 epoch 5 - iter 220/447 - loss 0.03429710 - time (sec): 14.83 - samples/sec: 2925.74 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 11:47:01,324 epoch 5 - iter 264/447 - loss 0.03544567 - time (sec): 17.58 - samples/sec: 2959.14 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 11:47:04,094 epoch 5 - iter 308/447 - loss 0.03369941 - time (sec): 20.35 - samples/sec: 2952.63 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-13 11:47:06,957 epoch 5 - iter 352/447 - loss 0.03451202 - time (sec): 23.21 - samples/sec: 2962.77 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 11:47:10,024 epoch 5 - iter 396/447 - loss 0.03499281 - time (sec): 26.28 - samples/sec: 2917.55 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 11:47:12,877 epoch 5 - iter 440/447 - loss 0.03611396 - time (sec): 29.13 - samples/sec: 2927.39 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 11:47:13,320 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 11:47:13,321 EPOCH 5 done: loss 0.0361 - lr: 0.000028
148
+ 2023-10-13 11:47:21,826 DEV : loss 0.19516603648662567 - f1-score (micro avg) 0.7573
149
+ 2023-10-13 11:47:21,857 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-13 11:47:24,788 epoch 6 - iter 44/447 - loss 0.02058854 - time (sec): 2.93 - samples/sec: 2932.43 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-13 11:47:27,413 epoch 6 - iter 88/447 - loss 0.02229072 - time (sec): 5.55 - samples/sec: 2914.52 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 11:47:30,610 epoch 6 - iter 132/447 - loss 0.01983331 - time (sec): 8.75 - samples/sec: 2861.48 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-13 11:47:33,740 epoch 6 - iter 176/447 - loss 0.02048267 - time (sec): 11.88 - samples/sec: 2858.33 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 11:47:36,507 epoch 6 - iter 220/447 - loss 0.01960330 - time (sec): 14.65 - samples/sec: 2836.30 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-13 11:47:39,303 epoch 6 - iter 264/447 - loss 0.01907838 - time (sec): 17.45 - samples/sec: 2843.15 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-13 11:47:41,984 epoch 6 - iter 308/447 - loss 0.02150005 - time (sec): 20.13 - samples/sec: 2851.58 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-13 11:47:44,621 epoch 6 - iter 352/447 - loss 0.02176467 - time (sec): 22.76 - samples/sec: 2898.74 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-13 11:47:47,920 epoch 6 - iter 396/447 - loss 0.02302182 - time (sec): 26.06 - samples/sec: 2922.86 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 11:47:50,941 epoch 6 - iter 440/447 - loss 0.02339372 - time (sec): 29.08 - samples/sec: 2930.41 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-13 11:47:51,371 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-13 11:47:51,372 EPOCH 6 done: loss 0.0233 - lr: 0.000022
162
+ 2023-10-13 11:47:59,864 DEV : loss 0.20644259452819824 - f1-score (micro avg) 0.7515
163
+ 2023-10-13 11:47:59,893 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-13 11:48:02,613 epoch 7 - iter 44/447 - loss 0.01706592 - time (sec): 2.72 - samples/sec: 3215.33 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-13 11:48:05,274 epoch 7 - iter 88/447 - loss 0.01709019 - time (sec): 5.38 - samples/sec: 3137.91 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-13 11:48:08,702 epoch 7 - iter 132/447 - loss 0.01581202 - time (sec): 8.81 - samples/sec: 3063.55 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 11:48:11,559 epoch 7 - iter 176/447 - loss 0.01433771 - time (sec): 11.66 - samples/sec: 3028.44 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-13 11:48:14,480 epoch 7 - iter 220/447 - loss 0.01468541 - time (sec): 14.59 - samples/sec: 3021.21 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-13 11:48:17,059 epoch 7 - iter 264/447 - loss 0.01493250 - time (sec): 17.16 - samples/sec: 3031.79 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-13 11:48:19,824 epoch 7 - iter 308/447 - loss 0.01340649 - time (sec): 19.93 - samples/sec: 3018.85 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-13 11:48:22,745 epoch 7 - iter 352/447 - loss 0.01446296 - time (sec): 22.85 - samples/sec: 2997.46 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 11:48:25,409 epoch 7 - iter 396/447 - loss 0.01498454 - time (sec): 25.51 - samples/sec: 2984.77 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-13 11:48:28,022 epoch 7 - iter 440/447 - loss 0.01502147 - time (sec): 28.13 - samples/sec: 2996.49 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 11:48:28,735 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-13 11:48:28,735 EPOCH 7 done: loss 0.0149 - lr: 0.000017
176
+ 2023-10-13 11:48:37,330 DEV : loss 0.19954054057598114 - f1-score (micro avg) 0.7814
177
+ 2023-10-13 11:48:37,360 saving best model
178
+ 2023-10-13 11:48:37,781 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-13 11:48:40,889 epoch 8 - iter 44/447 - loss 0.00534479 - time (sec): 3.11 - samples/sec: 2758.32 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-13 11:48:43,944 epoch 8 - iter 88/447 - loss 0.00779708 - time (sec): 6.16 - samples/sec: 2854.83 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-13 11:48:46,751 epoch 8 - iter 132/447 - loss 0.00659972 - time (sec): 8.97 - samples/sec: 2973.02 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-13 11:48:49,824 epoch 8 - iter 176/447 - loss 0.00669648 - time (sec): 12.04 - samples/sec: 2999.66 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-13 11:48:52,453 epoch 8 - iter 220/447 - loss 0.00843461 - time (sec): 14.67 - samples/sec: 2992.45 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-13 11:48:55,276 epoch 8 - iter 264/447 - loss 0.00900303 - time (sec): 17.49 - samples/sec: 2971.82 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-13 11:48:58,051 epoch 8 - iter 308/447 - loss 0.00962997 - time (sec): 20.27 - samples/sec: 3006.72 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-13 11:49:00,666 epoch 8 - iter 352/447 - loss 0.00959478 - time (sec): 22.88 - samples/sec: 3026.20 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-13 11:49:03,344 epoch 8 - iter 396/447 - loss 0.00940630 - time (sec): 25.56 - samples/sec: 3027.67 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-13 11:49:06,125 epoch 8 - iter 440/447 - loss 0.00959920 - time (sec): 28.34 - samples/sec: 3009.55 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-13 11:49:06,520 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-13 11:49:06,521 EPOCH 8 done: loss 0.0098 - lr: 0.000011
191
+ 2023-10-13 11:49:14,950 DEV : loss 0.22160013020038605 - f1-score (micro avg) 0.7869
192
+ 2023-10-13 11:49:14,980 saving best model
193
+ 2023-10-13 11:49:15,445 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-13 11:49:18,252 epoch 9 - iter 44/447 - loss 0.00961171 - time (sec): 2.80 - samples/sec: 2905.04 - lr: 0.000011 - momentum: 0.000000
195
+ 2023-10-13 11:49:21,188 epoch 9 - iter 88/447 - loss 0.00795760 - time (sec): 5.74 - samples/sec: 3027.22 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-13 11:49:24,129 epoch 9 - iter 132/447 - loss 0.00787975 - time (sec): 8.68 - samples/sec: 2963.45 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-13 11:49:27,046 epoch 9 - iter 176/447 - loss 0.00643769 - time (sec): 11.60 - samples/sec: 3004.95 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-13 11:49:30,207 epoch 9 - iter 220/447 - loss 0.00550591 - time (sec): 14.76 - samples/sec: 2958.57 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-13 11:49:32,877 epoch 9 - iter 264/447 - loss 0.00628025 - time (sec): 17.43 - samples/sec: 2976.74 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-13 11:49:35,917 epoch 9 - iter 308/447 - loss 0.00568075 - time (sec): 20.47 - samples/sec: 3002.41 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-13 11:49:38,518 epoch 9 - iter 352/447 - loss 0.00547781 - time (sec): 23.07 - samples/sec: 3011.57 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-13 11:49:41,118 epoch 9 - iter 396/447 - loss 0.00510707 - time (sec): 25.67 - samples/sec: 3015.03 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-13 11:49:43,957 epoch 9 - iter 440/447 - loss 0.00579440 - time (sec): 28.51 - samples/sec: 2993.00 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-13 11:49:44,368 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-13 11:49:44,369 EPOCH 9 done: loss 0.0058 - lr: 0.000006
206
+ 2023-10-13 11:49:52,737 DEV : loss 0.22420544922351837 - f1-score (micro avg) 0.7939
207
+ 2023-10-13 11:49:52,765 saving best model
208
+ 2023-10-13 11:49:53,207 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 11:49:56,079 epoch 10 - iter 44/447 - loss 0.00503684 - time (sec): 2.87 - samples/sec: 3031.57 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-13 11:49:58,702 epoch 10 - iter 88/447 - loss 0.00356275 - time (sec): 5.49 - samples/sec: 3012.23 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-13 11:50:01,395 epoch 10 - iter 132/447 - loss 0.00318696 - time (sec): 8.18 - samples/sec: 3059.58 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-13 11:50:04,264 epoch 10 - iter 176/447 - loss 0.00359811 - time (sec): 11.05 - samples/sec: 3046.15 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-13 11:50:07,363 epoch 10 - iter 220/447 - loss 0.00385787 - time (sec): 14.15 - samples/sec: 3025.06 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-13 11:50:10,306 epoch 10 - iter 264/447 - loss 0.00365876 - time (sec): 17.10 - samples/sec: 3014.61 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-13 11:50:13,281 epoch 10 - iter 308/447 - loss 0.00370964 - time (sec): 20.07 - samples/sec: 3007.91 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-13 11:50:15,872 epoch 10 - iter 352/447 - loss 0.00391637 - time (sec): 22.66 - samples/sec: 3016.13 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 11:50:18,576 epoch 10 - iter 396/447 - loss 0.00392657 - time (sec): 25.36 - samples/sec: 3013.15 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 11:50:21,544 epoch 10 - iter 440/447 - loss 0.00407881 - time (sec): 28.33 - samples/sec: 2997.94 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 11:50:22,045 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 11:50:22,045 EPOCH 10 done: loss 0.0040 - lr: 0.000000
221
+ 2023-10-13 11:50:30,395 DEV : loss 0.2235824018716812 - f1-score (micro avg) 0.7934
222
+ 2023-10-13 11:50:30,794 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 11:50:30,796 Loading model from best epoch ...
224
+ 2023-10-13 11:50:32,326 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
225
+ 2023-10-13 11:50:36,754
226
+ Results:
227
+ - F-score (micro) 0.7481
228
+ - F-score (macro) 0.6626
229
+ - Accuracy 0.6183
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8471 0.8456 0.8463 596
235
+ pers 0.6702 0.7568 0.7109 333
236
+ org 0.5227 0.5227 0.5227 132
237
+ prod 0.5714 0.4848 0.5246 66
238
+ time 0.7234 0.6939 0.7083 49
239
+
240
+ micro avg 0.7388 0.7577 0.7481 1176
241
+ macro avg 0.6670 0.6608 0.6626 1176
242
+ weighted avg 0.7400 0.7577 0.7478 1176
243
+
244
+ 2023-10-13 11:50:36,754 ----------------------------------------------------------------------------------------------------