Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
German
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
c7d85f3
·
1 Parent(s): 197776d

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 sha256:5b557f1404059c8d91bd7744d7af241c0f5cbe4c0b20970be8134802c9c982c9
3
+ size 443335879
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 12:48:56 0.0000 0.6027 0.1824 0.6510 0.5512 0.5970 0.4338
3
+ 2 12:49:35 0.0000 0.1560 0.1329 0.6710 0.7256 0.6972 0.5501
4
+ 3 12:50:13 0.0000 0.0821 0.1397 0.7522 0.7357 0.7439 0.6087
5
+ 4 12:50:51 0.0000 0.0507 0.1582 0.7724 0.7349 0.7532 0.6192
6
+ 5 12:51:30 0.0000 0.0355 0.1758 0.7581 0.7670 0.7625 0.6301
7
+ 6 12:52:08 0.0000 0.0222 0.2123 0.7725 0.7435 0.7578 0.6195
8
+ 7 12:52:46 0.0000 0.0132 0.2359 0.7409 0.7826 0.7612 0.6280
9
+ 8 12:53:24 0.0000 0.0095 0.2494 0.7969 0.7608 0.7784 0.6508
10
+ 9 12:54:02 0.0000 0.0073 0.2322 0.7762 0.7889 0.7825 0.6569
11
+ 10 12:54:40 0.0000 0.0047 0.2368 0.7789 0.7850 0.7819 0.6579
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 12:48:22,060 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 12:48:22,061 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 768)
7
+ (position_embeddings): Embedding(512, 768)
8
+ (token_type_embeddings): Embedding(2, 768)
9
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=768, out_features=768, bias=True)
18
+ (key): Linear(in_features=768, out_features=768, bias=True)
19
+ (value): Linear(in_features=768, out_features=768, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=768, out_features=768, bias=True)
24
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=3072, out_features=768, bias=True)
34
+ (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 12:48:22,061 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 12:48:22,062 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
52
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
53
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 12:48:22,062 Train: 3575 sentences
55
+ 2023-10-13 12:48:22,062 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 12:48:22,062 Training Params:
58
+ 2023-10-13 12:48:22,062 - learning_rate: "5e-05"
59
+ 2023-10-13 12:48:22,062 - mini_batch_size: "8"
60
+ 2023-10-13 12:48:22,062 - max_epochs: "10"
61
+ 2023-10-13 12:48:22,062 - shuffle: "True"
62
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 12:48:22,062 Plugins:
64
+ 2023-10-13 12:48:22,062 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 12:48:22,062 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 12:48:22,062 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 12:48:22,062 Computation:
70
+ 2023-10-13 12:48:22,062 - compute on device: cuda:0
71
+ 2023-10-13 12:48:22,062 - embedding storage: none
72
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 12:48:22,062 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
74
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 12:48:22,062 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 12:48:24,736 epoch 1 - iter 44/447 - loss 2.72113629 - time (sec): 2.67 - samples/sec: 3086.23 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 12:48:27,748 epoch 1 - iter 88/447 - loss 1.76254453 - time (sec): 5.69 - samples/sec: 3008.78 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 12:48:30,428 epoch 1 - iter 132/447 - loss 1.36926797 - time (sec): 8.36 - samples/sec: 2990.42 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 12:48:33,398 epoch 1 - iter 176/447 - loss 1.09736044 - time (sec): 11.33 - samples/sec: 3050.34 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 12:48:36,384 epoch 1 - iter 220/447 - loss 0.93710869 - time (sec): 14.32 - samples/sec: 3024.41 - lr: 0.000024 - momentum: 0.000000
81
+ 2023-10-13 12:48:39,333 epoch 1 - iter 264/447 - loss 0.82829129 - time (sec): 17.27 - samples/sec: 3009.72 - lr: 0.000029 - momentum: 0.000000
82
+ 2023-10-13 12:48:42,028 epoch 1 - iter 308/447 - loss 0.75538064 - time (sec): 19.96 - samples/sec: 3005.19 - lr: 0.000034 - momentum: 0.000000
83
+ 2023-10-13 12:48:44,956 epoch 1 - iter 352/447 - loss 0.70021192 - time (sec): 22.89 - samples/sec: 2974.25 - lr: 0.000039 - momentum: 0.000000
84
+ 2023-10-13 12:48:48,054 epoch 1 - iter 396/447 - loss 0.64625200 - time (sec): 25.99 - samples/sec: 2968.22 - lr: 0.000044 - momentum: 0.000000
85
+ 2023-10-13 12:48:50,791 epoch 1 - iter 440/447 - loss 0.60642690 - time (sec): 28.73 - samples/sec: 2972.97 - lr: 0.000049 - momentum: 0.000000
86
+ 2023-10-13 12:48:51,196 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 12:48:51,196 EPOCH 1 done: loss 0.6027 - lr: 0.000049
88
+ 2023-10-13 12:48:56,315 DEV : loss 0.18237876892089844 - f1-score (micro avg) 0.597
89
+ 2023-10-13 12:48:56,364 saving best model
90
+ 2023-10-13 12:48:56,829 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 12:48:59,725 epoch 2 - iter 44/447 - loss 0.19768284 - time (sec): 2.89 - samples/sec: 2808.02 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 12:49:02,590 epoch 2 - iter 88/447 - loss 0.18768155 - time (sec): 5.76 - samples/sec: 2855.46 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 12:49:05,392 epoch 2 - iter 132/447 - loss 0.17989274 - time (sec): 8.56 - samples/sec: 2902.30 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 12:49:08,357 epoch 2 - iter 176/447 - loss 0.16672786 - time (sec): 11.53 - samples/sec: 2885.66 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 12:49:11,204 epoch 2 - iter 220/447 - loss 0.16616890 - time (sec): 14.37 - samples/sec: 2884.18 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 12:49:14,037 epoch 2 - iter 264/447 - loss 0.16187003 - time (sec): 17.21 - samples/sec: 2896.45 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 12:49:16,772 epoch 2 - iter 308/447 - loss 0.16369277 - time (sec): 19.94 - samples/sec: 2908.91 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 12:49:19,882 epoch 2 - iter 352/447 - loss 0.15804249 - time (sec): 23.05 - samples/sec: 2909.39 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 12:49:22,765 epoch 2 - iter 396/447 - loss 0.15849072 - time (sec): 25.93 - samples/sec: 2958.06 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 12:49:25,599 epoch 2 - iter 440/447 - loss 0.15632034 - time (sec): 28.77 - samples/sec: 2964.47 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-13 12:49:26,075 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 12:49:26,075 EPOCH 2 done: loss 0.1560 - lr: 0.000045
103
+ 2023-10-13 12:49:34,983 DEV : loss 0.13287977874279022 - f1-score (micro avg) 0.6972
104
+ 2023-10-13 12:49:35,016 saving best model
105
+ 2023-10-13 12:49:35,506 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 12:49:38,199 epoch 3 - iter 44/447 - loss 0.08731570 - time (sec): 2.68 - samples/sec: 3037.64 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 12:49:40,892 epoch 3 - iter 88/447 - loss 0.08438381 - time (sec): 5.38 - samples/sec: 2977.90 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 12:49:43,924 epoch 3 - iter 132/447 - loss 0.08570094 - time (sec): 8.41 - samples/sec: 2944.04 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 12:49:46,612 epoch 3 - iter 176/447 - loss 0.08756481 - time (sec): 11.10 - samples/sec: 2979.75 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 12:49:49,330 epoch 3 - iter 220/447 - loss 0.09082623 - time (sec): 13.82 - samples/sec: 2972.54 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 12:49:52,197 epoch 3 - iter 264/447 - loss 0.08856938 - time (sec): 16.68 - samples/sec: 2986.60 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 12:49:55,140 epoch 3 - iter 308/447 - loss 0.08687729 - time (sec): 19.63 - samples/sec: 2969.21 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 12:49:58,082 epoch 3 - iter 352/447 - loss 0.08587287 - time (sec): 22.57 - samples/sec: 2955.23 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 12:50:00,987 epoch 3 - iter 396/447 - loss 0.08320635 - time (sec): 25.47 - samples/sec: 2965.27 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-13 12:50:03,734 epoch 3 - iter 440/447 - loss 0.08286656 - time (sec): 28.22 - samples/sec: 2981.68 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 12:50:04,509 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 12:50:04,510 EPOCH 3 done: loss 0.0821 - lr: 0.000039
118
+ 2023-10-13 12:50:13,364 DEV : loss 0.13965222239494324 - f1-score (micro avg) 0.7439
119
+ 2023-10-13 12:50:13,399 saving best model
120
+ 2023-10-13 12:50:13,905 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 12:50:16,806 epoch 4 - iter 44/447 - loss 0.06374565 - time (sec): 2.89 - samples/sec: 2818.47 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 12:50:19,552 epoch 4 - iter 88/447 - loss 0.06611011 - time (sec): 5.64 - samples/sec: 2940.44 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 12:50:22,225 epoch 4 - iter 132/447 - loss 0.05945489 - time (sec): 8.31 - samples/sec: 2982.35 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 12:50:25,405 epoch 4 - iter 176/447 - loss 0.05575885 - time (sec): 11.49 - samples/sec: 3029.54 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 12:50:28,204 epoch 4 - iter 220/447 - loss 0.05278981 - time (sec): 14.29 - samples/sec: 3024.95 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 12:50:31,045 epoch 4 - iter 264/447 - loss 0.05317609 - time (sec): 17.13 - samples/sec: 3014.77 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 12:50:33,781 epoch 4 - iter 308/447 - loss 0.05338658 - time (sec): 19.87 - samples/sec: 3025.23 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 12:50:36,538 epoch 4 - iter 352/447 - loss 0.05202556 - time (sec): 22.62 - samples/sec: 3023.70 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-13 12:50:39,597 epoch 4 - iter 396/447 - loss 0.05132416 - time (sec): 25.68 - samples/sec: 3010.67 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 12:50:42,247 epoch 4 - iter 440/447 - loss 0.05058772 - time (sec): 28.33 - samples/sec: 3013.07 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 12:50:42,652 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 12:50:42,653 EPOCH 4 done: loss 0.0507 - lr: 0.000033
133
+ 2023-10-13 12:50:51,797 DEV : loss 0.15824183821678162 - f1-score (micro avg) 0.7532
134
+ 2023-10-13 12:50:51,830 saving best model
135
+ 2023-10-13 12:50:52,335 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 12:50:55,282 epoch 5 - iter 44/447 - loss 0.02999823 - time (sec): 2.94 - samples/sec: 2875.83 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 12:50:58,080 epoch 5 - iter 88/447 - loss 0.03142316 - time (sec): 5.74 - samples/sec: 2884.02 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 12:51:00,834 epoch 5 - iter 132/447 - loss 0.03153706 - time (sec): 8.49 - samples/sec: 2941.59 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 12:51:03,670 epoch 5 - iter 176/447 - loss 0.03146456 - time (sec): 11.33 - samples/sec: 2905.90 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 12:51:06,980 epoch 5 - iter 220/447 - loss 0.03208178 - time (sec): 14.64 - samples/sec: 2879.23 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 12:51:09,695 epoch 5 - iter 264/447 - loss 0.03368068 - time (sec): 17.36 - samples/sec: 2889.22 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 12:51:12,451 epoch 5 - iter 308/447 - loss 0.03426693 - time (sec): 20.11 - samples/sec: 2904.70 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-13 12:51:15,623 epoch 5 - iter 352/447 - loss 0.03584978 - time (sec): 23.28 - samples/sec: 2925.57 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 12:51:18,634 epoch 5 - iter 396/447 - loss 0.03559068 - time (sec): 26.29 - samples/sec: 2937.26 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 12:51:21,576 epoch 5 - iter 440/447 - loss 0.03588276 - time (sec): 29.24 - samples/sec: 2919.05 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 12:51:21,988 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 12:51:21,989 EPOCH 5 done: loss 0.0355 - lr: 0.000028
148
+ 2023-10-13 12:51:30,616 DEV : loss 0.17583982646465302 - f1-score (micro avg) 0.7625
149
+ 2023-10-13 12:51:30,650 saving best model
150
+ 2023-10-13 12:51:31,135 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 12:51:34,394 epoch 6 - iter 44/447 - loss 0.01600788 - time (sec): 3.26 - samples/sec: 2954.25 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 12:51:37,101 epoch 6 - iter 88/447 - loss 0.01598411 - time (sec): 5.96 - samples/sec: 2988.06 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-13 12:51:40,033 epoch 6 - iter 132/447 - loss 0.01807915 - time (sec): 8.90 - samples/sec: 2994.03 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 12:51:42,899 epoch 6 - iter 176/447 - loss 0.01681758 - time (sec): 11.76 - samples/sec: 3010.57 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-13 12:51:45,738 epoch 6 - iter 220/447 - loss 0.01823050 - time (sec): 14.60 - samples/sec: 3040.07 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-13 12:51:48,430 epoch 6 - iter 264/447 - loss 0.02019697 - time (sec): 17.29 - samples/sec: 3025.48 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-13 12:51:51,200 epoch 6 - iter 308/447 - loss 0.01912780 - time (sec): 20.06 - samples/sec: 3004.35 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-13 12:51:53,876 epoch 6 - iter 352/447 - loss 0.02112949 - time (sec): 22.74 - samples/sec: 3001.14 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 12:51:56,698 epoch 6 - iter 396/447 - loss 0.02312469 - time (sec): 25.56 - samples/sec: 3010.87 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-13 12:51:59,256 epoch 6 - iter 440/447 - loss 0.02258683 - time (sec): 28.12 - samples/sec: 3017.49 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-13 12:51:59,876 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 12:51:59,877 EPOCH 6 done: loss 0.0222 - lr: 0.000022
163
+ 2023-10-13 12:52:08,836 DEV : loss 0.21230502426624298 - f1-score (micro avg) 0.7578
164
+ 2023-10-13 12:52:08,867 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 12:52:11,860 epoch 7 - iter 44/447 - loss 0.02437766 - time (sec): 2.99 - samples/sec: 3073.74 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-13 12:52:15,198 epoch 7 - iter 88/447 - loss 0.01924784 - time (sec): 6.33 - samples/sec: 2997.77 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 12:52:18,035 epoch 7 - iter 132/447 - loss 0.01736984 - time (sec): 9.17 - samples/sec: 3015.68 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-13 12:52:20,905 epoch 7 - iter 176/447 - loss 0.01662843 - time (sec): 12.04 - samples/sec: 3055.48 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-13 12:52:24,031 epoch 7 - iter 220/447 - loss 0.01461178 - time (sec): 15.16 - samples/sec: 3011.95 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-13 12:52:26,692 epoch 7 - iter 264/447 - loss 0.01314305 - time (sec): 17.82 - samples/sec: 2990.65 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-13 12:52:29,402 epoch 7 - iter 308/447 - loss 0.01265643 - time (sec): 20.53 - samples/sec: 2973.51 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 12:52:32,221 epoch 7 - iter 352/447 - loss 0.01273989 - time (sec): 23.35 - samples/sec: 2967.43 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-13 12:52:34,784 epoch 7 - iter 396/447 - loss 0.01331493 - time (sec): 25.92 - samples/sec: 2975.03 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 12:52:37,386 epoch 7 - iter 440/447 - loss 0.01337988 - time (sec): 28.52 - samples/sec: 2981.87 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-13 12:52:37,892 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 12:52:37,892 EPOCH 7 done: loss 0.0132 - lr: 0.000017
177
+ 2023-10-13 12:52:46,514 DEV : loss 0.23592258989810944 - f1-score (micro avg) 0.7612
178
+ 2023-10-13 12:52:46,545 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-13 12:52:49,368 epoch 8 - iter 44/447 - loss 0.01339854 - time (sec): 2.82 - samples/sec: 3064.25 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-13 12:52:52,244 epoch 8 - iter 88/447 - loss 0.01099649 - time (sec): 5.70 - samples/sec: 2945.77 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-13 12:52:55,576 epoch 8 - iter 132/447 - loss 0.00853314 - time (sec): 9.03 - samples/sec: 2964.34 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-13 12:52:58,656 epoch 8 - iter 176/447 - loss 0.00969601 - time (sec): 12.11 - samples/sec: 2906.80 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-13 12:53:01,479 epoch 8 - iter 220/447 - loss 0.01007474 - time (sec): 14.93 - samples/sec: 2918.87 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-13 12:53:04,582 epoch 8 - iter 264/447 - loss 0.01035185 - time (sec): 18.04 - samples/sec: 2902.77 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-13 12:53:07,412 epoch 8 - iter 308/447 - loss 0.01063796 - time (sec): 20.87 - samples/sec: 2919.76 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-13 12:53:10,111 epoch 8 - iter 352/447 - loss 0.00992196 - time (sec): 23.56 - samples/sec: 2924.33 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-13 12:53:12,894 epoch 8 - iter 396/447 - loss 0.00942271 - time (sec): 26.35 - samples/sec: 2938.99 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-13 12:53:15,454 epoch 8 - iter 440/447 - loss 0.00956868 - time (sec): 28.91 - samples/sec: 2952.81 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-13 12:53:15,838 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-13 12:53:15,838 EPOCH 8 done: loss 0.0095 - lr: 0.000011
191
+ 2023-10-13 12:53:24,513 DEV : loss 0.2494419664144516 - f1-score (micro avg) 0.7784
192
+ 2023-10-13 12:53:24,546 saving best model
193
+ 2023-10-13 12:53:25,426 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-13 12:53:28,519 epoch 9 - iter 44/447 - loss 0.00818351 - time (sec): 3.09 - samples/sec: 2643.65 - lr: 0.000011 - momentum: 0.000000
195
+ 2023-10-13 12:53:31,740 epoch 9 - iter 88/447 - loss 0.00467539 - time (sec): 6.31 - samples/sec: 2773.19 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-13 12:53:34,662 epoch 9 - iter 132/447 - loss 0.00483987 - time (sec): 9.23 - samples/sec: 2821.56 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-13 12:53:37,469 epoch 9 - iter 176/447 - loss 0.00526312 - time (sec): 12.04 - samples/sec: 2859.97 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-13 12:53:40,102 epoch 9 - iter 220/447 - loss 0.00658465 - time (sec): 14.67 - samples/sec: 2914.07 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-13 12:53:42,708 epoch 9 - iter 264/447 - loss 0.00837702 - time (sec): 17.28 - samples/sec: 2944.21 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-13 12:53:45,383 epoch 9 - iter 308/447 - loss 0.00730189 - time (sec): 19.96 - samples/sec: 2955.19 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-13 12:53:48,016 epoch 9 - iter 352/447 - loss 0.00753736 - time (sec): 22.59 - samples/sec: 2973.51 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-13 12:53:51,129 epoch 9 - iter 396/447 - loss 0.00741956 - time (sec): 25.70 - samples/sec: 2997.38 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-13 12:53:53,973 epoch 9 - iter 440/447 - loss 0.00707842 - time (sec): 28.55 - samples/sec: 2989.06 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-13 12:53:54,369 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-13 12:53:54,369 EPOCH 9 done: loss 0.0073 - lr: 0.000006
206
+ 2023-10-13 12:54:02,736 DEV : loss 0.2321784794330597 - f1-score (micro avg) 0.7825
207
+ 2023-10-13 12:54:02,767 saving best model
208
+ 2023-10-13 12:54:03,165 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-13 12:54:06,127 epoch 10 - iter 44/447 - loss 0.00185807 - time (sec): 2.96 - samples/sec: 3045.90 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-13 12:54:08,834 epoch 10 - iter 88/447 - loss 0.00465358 - time (sec): 5.67 - samples/sec: 3052.43 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-13 12:54:12,066 epoch 10 - iter 132/447 - loss 0.00358618 - time (sec): 8.90 - samples/sec: 2892.03 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-13 12:54:14,976 epoch 10 - iter 176/447 - loss 0.00391395 - time (sec): 11.81 - samples/sec: 2932.40 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-13 12:54:17,595 epoch 10 - iter 220/447 - loss 0.00416413 - time (sec): 14.43 - samples/sec: 2956.30 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-13 12:54:20,350 epoch 10 - iter 264/447 - loss 0.00456129 - time (sec): 17.18 - samples/sec: 2956.21 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-13 12:54:23,283 epoch 10 - iter 308/447 - loss 0.00441630 - time (sec): 20.12 - samples/sec: 2953.83 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-13 12:54:26,710 epoch 10 - iter 352/447 - loss 0.00512117 - time (sec): 23.54 - samples/sec: 2958.63 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 12:54:29,451 epoch 10 - iter 396/447 - loss 0.00514772 - time (sec): 26.28 - samples/sec: 2948.94 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-13 12:54:32,059 epoch 10 - iter 440/447 - loss 0.00469391 - time (sec): 28.89 - samples/sec: 2951.55 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-13 12:54:32,458 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-13 12:54:32,458 EPOCH 10 done: loss 0.0047 - lr: 0.000000
221
+ 2023-10-13 12:54:40,938 DEV : loss 0.23675945401191711 - f1-score (micro avg) 0.7819
222
+ 2023-10-13 12:54:41,310 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 12:54:41,311 Loading model from best epoch ...
224
+ 2023-10-13 12:54:42,795 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 12:54:47,671
226
+ Results:
227
+ - F-score (micro) 0.7527
228
+ - F-score (macro) 0.6738
229
+ - Accuracy 0.624
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8248 0.8607 0.8424 596
235
+ pers 0.6852 0.7387 0.7110 333
236
+ org 0.5635 0.5379 0.5504 132
237
+ prod 0.5962 0.4697 0.5254 66
238
+ time 0.7255 0.7551 0.7400 49
239
+
240
+ micro avg 0.7421 0.7636 0.7527 1176
241
+ macro avg 0.6790 0.6724 0.6738 1176
242
+ weighted avg 0.7390 0.7636 0.7503 1176
243
+
244
+ 2023-10-13 12:54:47,671 ----------------------------------------------------------------------------------------------------