Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbert-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
Dutch
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
7696267
•
1 Parent(s): f194fd7

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 +241 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af503bd466aeff3de7578b2801b2c06ec9681c40c5b9af7f8553d6990057c98
3
+ size 443311111
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 08:41:10 0.0000 0.3636 0.1605 0.4934 0.5837 0.5348 0.3862
3
+ 2 08:42:13 0.0000 0.1107 0.1036 0.8355 0.6085 0.7041 0.5536
4
+ 3 08:43:18 0.0000 0.0657 0.0926 0.7624 0.7593 0.7609 0.6402
5
+ 4 08:44:22 0.0000 0.0459 0.0913 0.8192 0.7862 0.8023 0.6856
6
+ 5 08:45:27 0.0000 0.0334 0.1509 0.8494 0.6932 0.7634 0.6289
7
+ 6 08:46:31 0.0000 0.0246 0.1339 0.8468 0.7593 0.8007 0.6787
8
+ 7 08:47:36 0.0000 0.0180 0.1574 0.8312 0.7882 0.8091 0.6917
9
+ 8 08:48:41 0.0000 0.0126 0.1644 0.8340 0.8048 0.8191 0.7108
10
+ 9 08:49:47 0.0000 0.0093 0.1972 0.8453 0.7510 0.7954 0.6744
11
+ 10 08:50:52 0.0000 0.0052 0.1938 0.8527 0.7655 0.8068 0.6899
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-14 08:40:07,077 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-14 08:40:07,078 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=13, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-14 08:40:07,078 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-14 08:40:07,078 MultiCorpus: 5777 train + 722 dev + 723 test sentences
52
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
53
+ 2023-10-14 08:40:07,078 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-14 08:40:07,078 Train: 5777 sentences
55
+ 2023-10-14 08:40:07,078 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-14 08:40:07,078 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-14 08:40:07,078 Training Params:
58
+ 2023-10-14 08:40:07,078 - learning_rate: "5e-05"
59
+ 2023-10-14 08:40:07,078 - mini_batch_size: "8"
60
+ 2023-10-14 08:40:07,078 - max_epochs: "10"
61
+ 2023-10-14 08:40:07,078 - shuffle: "True"
62
+ 2023-10-14 08:40:07,078 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-14 08:40:07,078 Plugins:
64
+ 2023-10-14 08:40:07,078 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-14 08:40:07,078 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-14 08:40:07,078 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-14 08:40:07,078 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-14 08:40:07,078 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-14 08:40:07,079 Computation:
70
+ 2023-10-14 08:40:07,079 - compute on device: cuda:0
71
+ 2023-10-14 08:40:07,079 - embedding storage: none
72
+ 2023-10-14 08:40:07,079 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-14 08:40:07,079 Model training base path: "hmbench-icdar/nl-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
74
+ 2023-10-14 08:40:07,079 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-14 08:40:07,079 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-14 08:40:12,831 epoch 1 - iter 72/723 - loss 2.05918268 - time (sec): 5.75 - samples/sec: 2946.51 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-14 08:40:18,424 epoch 1 - iter 144/723 - loss 1.16818121 - time (sec): 11.34 - samples/sec: 2978.79 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-14 08:40:24,479 epoch 1 - iter 216/723 - loss 0.82822698 - time (sec): 17.40 - samples/sec: 3002.20 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-14 08:40:30,235 epoch 1 - iter 288/723 - loss 0.66985125 - time (sec): 23.16 - samples/sec: 3016.41 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-14 08:40:35,853 epoch 1 - iter 360/723 - loss 0.57437342 - time (sec): 28.77 - samples/sec: 3014.67 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-14 08:40:41,454 epoch 1 - iter 432/723 - loss 0.51652129 - time (sec): 34.37 - samples/sec: 2973.95 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-14 08:40:47,515 epoch 1 - iter 504/723 - loss 0.46201015 - time (sec): 40.43 - samples/sec: 2987.94 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-14 08:40:53,810 epoch 1 - iter 576/723 - loss 0.42250578 - time (sec): 46.73 - samples/sec: 2971.37 - lr: 0.000040 - momentum: 0.000000
84
+ 2023-10-14 08:40:59,867 epoch 1 - iter 648/723 - loss 0.39178574 - time (sec): 52.79 - samples/sec: 2972.34 - lr: 0.000045 - momentum: 0.000000
85
+ 2023-10-14 08:41:05,871 epoch 1 - iter 720/723 - loss 0.36449097 - time (sec): 58.79 - samples/sec: 2986.16 - lr: 0.000050 - momentum: 0.000000
86
+ 2023-10-14 08:41:06,127 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-14 08:41:06,128 EPOCH 1 done: loss 0.3636 - lr: 0.000050
88
+ 2023-10-14 08:41:10,093 DEV : loss 0.16045822203159332 - f1-score (micro avg) 0.5348
89
+ 2023-10-14 08:41:10,116 saving best model
90
+ 2023-10-14 08:41:10,556 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-14 08:41:16,325 epoch 2 - iter 72/723 - loss 0.14172033 - time (sec): 5.77 - samples/sec: 3010.48 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-14 08:41:22,109 epoch 2 - iter 144/723 - loss 0.12806058 - time (sec): 11.55 - samples/sec: 2980.57 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-14 08:41:28,315 epoch 2 - iter 216/723 - loss 0.12803539 - time (sec): 17.76 - samples/sec: 2933.19 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-14 08:41:33,862 epoch 2 - iter 288/723 - loss 0.12202263 - time (sec): 23.31 - samples/sec: 2973.59 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-14 08:41:40,189 epoch 2 - iter 360/723 - loss 0.12080964 - time (sec): 29.63 - samples/sec: 2958.52 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-14 08:41:45,874 epoch 2 - iter 432/723 - loss 0.11694382 - time (sec): 35.32 - samples/sec: 2965.78 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-14 08:41:51,983 epoch 2 - iter 504/723 - loss 0.11733998 - time (sec): 41.43 - samples/sec: 2962.82 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-14 08:41:57,323 epoch 2 - iter 576/723 - loss 0.11441675 - time (sec): 46.77 - samples/sec: 2964.30 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-14 08:42:03,643 epoch 2 - iter 648/723 - loss 0.11224219 - time (sec): 53.09 - samples/sec: 2972.82 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-14 08:42:09,681 epoch 2 - iter 720/723 - loss 0.11078356 - time (sec): 59.12 - samples/sec: 2970.99 - lr: 0.000044 - momentum: 0.000000
101
+ 2023-10-14 08:42:09,901 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-14 08:42:09,902 EPOCH 2 done: loss 0.1107 - lr: 0.000044
103
+ 2023-10-14 08:42:13,440 DEV : loss 0.10363695025444031 - f1-score (micro avg) 0.7041
104
+ 2023-10-14 08:42:13,459 saving best model
105
+ 2023-10-14 08:42:13,965 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-14 08:42:20,064 epoch 3 - iter 72/723 - loss 0.07046006 - time (sec): 6.09 - samples/sec: 2907.60 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-14 08:42:26,285 epoch 3 - iter 144/723 - loss 0.06632641 - time (sec): 12.31 - samples/sec: 2888.10 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-14 08:42:32,534 epoch 3 - iter 216/723 - loss 0.06851821 - time (sec): 18.56 - samples/sec: 2865.87 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-14 08:42:38,432 epoch 3 - iter 288/723 - loss 0.06615459 - time (sec): 24.46 - samples/sec: 2895.34 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-14 08:42:44,260 epoch 3 - iter 360/723 - loss 0.06572883 - time (sec): 30.29 - samples/sec: 2923.03 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-14 08:42:49,881 epoch 3 - iter 432/723 - loss 0.06538057 - time (sec): 35.91 - samples/sec: 2954.69 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-14 08:42:56,024 epoch 3 - iter 504/723 - loss 0.06700951 - time (sec): 42.05 - samples/sec: 2925.32 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-14 08:43:02,061 epoch 3 - iter 576/723 - loss 0.06591234 - time (sec): 48.09 - samples/sec: 2936.96 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-14 08:43:07,986 epoch 3 - iter 648/723 - loss 0.06585569 - time (sec): 54.01 - samples/sec: 2941.72 - lr: 0.000039 - momentum: 0.000000
115
+ 2023-10-14 08:43:14,208 epoch 3 - iter 720/723 - loss 0.06567386 - time (sec): 60.24 - samples/sec: 2918.27 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-14 08:43:14,384 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-14 08:43:14,384 EPOCH 3 done: loss 0.0657 - lr: 0.000039
118
+ 2023-10-14 08:43:18,341 DEV : loss 0.09261729568243027 - f1-score (micro avg) 0.7609
119
+ 2023-10-14 08:43:18,361 saving best model
120
+ 2023-10-14 08:43:18,852 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-14 08:43:25,236 epoch 4 - iter 72/723 - loss 0.03634882 - time (sec): 6.38 - samples/sec: 2825.65 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-14 08:43:31,297 epoch 4 - iter 144/723 - loss 0.03662606 - time (sec): 12.44 - samples/sec: 2942.03 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-14 08:43:37,068 epoch 4 - iter 216/723 - loss 0.04038379 - time (sec): 18.21 - samples/sec: 2920.40 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-14 08:43:43,362 epoch 4 - iter 288/723 - loss 0.04257444 - time (sec): 24.51 - samples/sec: 2908.61 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-14 08:43:49,090 epoch 4 - iter 360/723 - loss 0.04462673 - time (sec): 30.24 - samples/sec: 2930.97 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-14 08:43:54,761 epoch 4 - iter 432/723 - loss 0.04482846 - time (sec): 35.91 - samples/sec: 2930.90 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-14 08:44:00,366 epoch 4 - iter 504/723 - loss 0.04395167 - time (sec): 41.51 - samples/sec: 2937.71 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-14 08:44:06,685 epoch 4 - iter 576/723 - loss 0.04429902 - time (sec): 47.83 - samples/sec: 2937.07 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-14 08:44:12,568 epoch 4 - iter 648/723 - loss 0.04540314 - time (sec): 53.72 - samples/sec: 2927.97 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-14 08:44:18,568 epoch 4 - iter 720/723 - loss 0.04549307 - time (sec): 59.71 - samples/sec: 2942.83 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-14 08:44:18,769 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-14 08:44:18,769 EPOCH 4 done: loss 0.0459 - lr: 0.000033
133
+ 2023-10-14 08:44:22,278 DEV : loss 0.0912981629371643 - f1-score (micro avg) 0.8023
134
+ 2023-10-14 08:44:22,302 saving best model
135
+ 2023-10-14 08:44:22,801 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-14 08:44:29,581 epoch 5 - iter 72/723 - loss 0.02994168 - time (sec): 6.78 - samples/sec: 2619.32 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-14 08:44:35,538 epoch 5 - iter 144/723 - loss 0.03265802 - time (sec): 12.73 - samples/sec: 2796.63 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-14 08:44:41,207 epoch 5 - iter 216/723 - loss 0.03167073 - time (sec): 18.40 - samples/sec: 2852.04 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-14 08:44:46,988 epoch 5 - iter 288/723 - loss 0.03339260 - time (sec): 24.18 - samples/sec: 2891.82 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-14 08:44:52,816 epoch 5 - iter 360/723 - loss 0.03182288 - time (sec): 30.01 - samples/sec: 2921.00 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-14 08:44:59,507 epoch 5 - iter 432/723 - loss 0.03101441 - time (sec): 36.70 - samples/sec: 2884.85 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-14 08:45:05,301 epoch 5 - iter 504/723 - loss 0.03178002 - time (sec): 42.50 - samples/sec: 2887.99 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-14 08:45:11,413 epoch 5 - iter 576/723 - loss 0.03195886 - time (sec): 48.61 - samples/sec: 2892.36 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-14 08:45:17,766 epoch 5 - iter 648/723 - loss 0.03371410 - time (sec): 54.96 - samples/sec: 2883.93 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-14 08:45:23,372 epoch 5 - iter 720/723 - loss 0.03353303 - time (sec): 60.57 - samples/sec: 2897.64 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-14 08:45:23,707 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-14 08:45:23,707 EPOCH 5 done: loss 0.0334 - lr: 0.000028
148
+ 2023-10-14 08:45:27,341 DEV : loss 0.15092381834983826 - f1-score (micro avg) 0.7634
149
+ 2023-10-14 08:45:27,363 ----------------------------------------------------------------------------------------------------
150
+ 2023-10-14 08:45:33,495 epoch 6 - iter 72/723 - loss 0.02383597 - time (sec): 6.13 - samples/sec: 2932.56 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-14 08:45:39,895 epoch 6 - iter 144/723 - loss 0.02275131 - time (sec): 12.53 - samples/sec: 2885.29 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-14 08:45:45,901 epoch 6 - iter 216/723 - loss 0.02559205 - time (sec): 18.54 - samples/sec: 2912.43 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-14 08:45:52,387 epoch 6 - iter 288/723 - loss 0.02648482 - time (sec): 25.02 - samples/sec: 2872.80 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-14 08:45:57,924 epoch 6 - iter 360/723 - loss 0.02538316 - time (sec): 30.56 - samples/sec: 2900.53 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-14 08:46:03,765 epoch 6 - iter 432/723 - loss 0.02448723 - time (sec): 36.40 - samples/sec: 2901.17 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-14 08:46:09,811 epoch 6 - iter 504/723 - loss 0.02458171 - time (sec): 42.45 - samples/sec: 2906.03 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-14 08:46:16,026 epoch 6 - iter 576/723 - loss 0.02508343 - time (sec): 48.66 - samples/sec: 2911.09 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-14 08:46:21,790 epoch 6 - iter 648/723 - loss 0.02441954 - time (sec): 54.43 - samples/sec: 2909.44 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-14 08:46:27,487 epoch 6 - iter 720/723 - loss 0.02461414 - time (sec): 60.12 - samples/sec: 2921.93 - lr: 0.000022 - momentum: 0.000000
160
+ 2023-10-14 08:46:27,706 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-14 08:46:27,706 EPOCH 6 done: loss 0.0246 - lr: 0.000022
162
+ 2023-10-14 08:46:31,624 DEV : loss 0.13394637405872345 - f1-score (micro avg) 0.8007
163
+ 2023-10-14 08:46:31,640 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-14 08:46:37,789 epoch 7 - iter 72/723 - loss 0.01052973 - time (sec): 6.15 - samples/sec: 2831.45 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-14 08:46:43,883 epoch 7 - iter 144/723 - loss 0.01534049 - time (sec): 12.24 - samples/sec: 2788.45 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-14 08:46:50,266 epoch 7 - iter 216/723 - loss 0.01640192 - time (sec): 18.62 - samples/sec: 2816.89 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-14 08:46:56,437 epoch 7 - iter 288/723 - loss 0.01582983 - time (sec): 24.79 - samples/sec: 2843.68 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-14 08:47:02,511 epoch 7 - iter 360/723 - loss 0.01684897 - time (sec): 30.87 - samples/sec: 2851.30 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-14 08:47:08,860 epoch 7 - iter 432/723 - loss 0.01771060 - time (sec): 37.22 - samples/sec: 2861.05 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-14 08:47:14,726 epoch 7 - iter 504/723 - loss 0.01806623 - time (sec): 43.08 - samples/sec: 2860.00 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-14 08:47:20,914 epoch 7 - iter 576/723 - loss 0.01763909 - time (sec): 49.27 - samples/sec: 2870.54 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-14 08:47:26,694 epoch 7 - iter 648/723 - loss 0.01807010 - time (sec): 55.05 - samples/sec: 2870.39 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-14 08:47:32,584 epoch 7 - iter 720/723 - loss 0.01793967 - time (sec): 60.94 - samples/sec: 2882.95 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-14 08:47:32,768 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-14 08:47:32,768 EPOCH 7 done: loss 0.0180 - lr: 0.000017
176
+ 2023-10-14 08:47:36,309 DEV : loss 0.15739385783672333 - f1-score (micro avg) 0.8091
177
+ 2023-10-14 08:47:36,330 saving best model
178
+ 2023-10-14 08:47:36,972 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-14 08:47:42,658 epoch 8 - iter 72/723 - loss 0.00886684 - time (sec): 5.68 - samples/sec: 3068.63 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-14 08:47:49,383 epoch 8 - iter 144/723 - loss 0.00889193 - time (sec): 12.41 - samples/sec: 2843.55 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-14 08:47:55,741 epoch 8 - iter 216/723 - loss 0.01045971 - time (sec): 18.77 - samples/sec: 2819.84 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-14 08:48:01,528 epoch 8 - iter 288/723 - loss 0.01209747 - time (sec): 24.55 - samples/sec: 2858.09 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-14 08:48:07,734 epoch 8 - iter 360/723 - loss 0.01220357 - time (sec): 30.76 - samples/sec: 2896.09 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-14 08:48:13,536 epoch 8 - iter 432/723 - loss 0.01156847 - time (sec): 36.56 - samples/sec: 2896.66 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-14 08:48:19,226 epoch 8 - iter 504/723 - loss 0.01200927 - time (sec): 42.25 - samples/sec: 2924.08 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-14 08:48:24,682 epoch 8 - iter 576/723 - loss 0.01257051 - time (sec): 47.71 - samples/sec: 2936.85 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-14 08:48:31,135 epoch 8 - iter 648/723 - loss 0.01301488 - time (sec): 54.16 - samples/sec: 2925.42 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-14 08:48:37,310 epoch 8 - iter 720/723 - loss 0.01265192 - time (sec): 60.34 - samples/sec: 2914.65 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-14 08:48:37,477 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-14 08:48:37,477 EPOCH 8 done: loss 0.0126 - lr: 0.000011
191
+ 2023-10-14 08:48:41,031 DEV : loss 0.16435782611370087 - f1-score (micro avg) 0.8191
192
+ 2023-10-14 08:48:41,057 saving best model
193
+ 2023-10-14 08:48:41,555 ----------------------------------------------------------------------------------------------------
194
+ 2023-10-14 08:48:47,795 epoch 9 - iter 72/723 - loss 0.01070952 - time (sec): 6.24 - samples/sec: 2923.12 - lr: 0.000011 - momentum: 0.000000
195
+ 2023-10-14 08:48:54,609 epoch 9 - iter 144/723 - loss 0.01060093 - time (sec): 13.05 - samples/sec: 2817.51 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-14 08:49:00,950 epoch 9 - iter 216/723 - loss 0.01086091 - time (sec): 19.39 - samples/sec: 2884.36 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-14 08:49:06,724 epoch 9 - iter 288/723 - loss 0.01001855 - time (sec): 25.17 - samples/sec: 2866.40 - lr: 0.000009 - momentum: 0.000000
198
+ 2023-10-14 08:49:13,184 epoch 9 - iter 360/723 - loss 0.00908806 - time (sec): 31.63 - samples/sec: 2871.35 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-14 08:49:18,726 epoch 9 - iter 432/723 - loss 0.00884104 - time (sec): 37.17 - samples/sec: 2881.99 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-14 08:49:24,886 epoch 9 - iter 504/723 - loss 0.00923270 - time (sec): 43.33 - samples/sec: 2865.04 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-14 08:49:30,450 epoch 9 - iter 576/723 - loss 0.00934944 - time (sec): 48.89 - samples/sec: 2866.48 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-14 08:49:36,426 epoch 9 - iter 648/723 - loss 0.00957257 - time (sec): 54.87 - samples/sec: 2870.69 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-14 08:49:42,770 epoch 9 - iter 720/723 - loss 0.00929602 - time (sec): 61.21 - samples/sec: 2869.96 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-14 08:49:42,966 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-14 08:49:42,966 EPOCH 9 done: loss 0.0093 - lr: 0.000006
206
+ 2023-10-14 08:49:47,108 DEV : loss 0.19722115993499756 - f1-score (micro avg) 0.7954
207
+ 2023-10-14 08:49:47,126 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-14 08:49:53,385 epoch 10 - iter 72/723 - loss 0.00259989 - time (sec): 6.26 - samples/sec: 2936.21 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-14 08:49:59,031 epoch 10 - iter 144/723 - loss 0.00417789 - time (sec): 11.90 - samples/sec: 2913.46 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-14 08:50:05,446 epoch 10 - iter 216/723 - loss 0.00571543 - time (sec): 18.32 - samples/sec: 2873.95 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-14 08:50:11,774 epoch 10 - iter 288/723 - loss 0.00605918 - time (sec): 24.65 - samples/sec: 2877.11 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-14 08:50:17,626 epoch 10 - iter 360/723 - loss 0.00556952 - time (sec): 30.50 - samples/sec: 2880.45 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-14 08:50:24,462 epoch 10 - iter 432/723 - loss 0.00569447 - time (sec): 37.33 - samples/sec: 2868.44 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-14 08:50:30,331 epoch 10 - iter 504/723 - loss 0.00564912 - time (sec): 43.20 - samples/sec: 2872.78 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-14 08:50:36,276 epoch 10 - iter 576/723 - loss 0.00551211 - time (sec): 49.15 - samples/sec: 2871.73 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-14 08:50:42,081 epoch 10 - iter 648/723 - loss 0.00538978 - time (sec): 54.95 - samples/sec: 2871.64 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-14 08:50:48,575 epoch 10 - iter 720/723 - loss 0.00516187 - time (sec): 61.45 - samples/sec: 2862.03 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-14 08:50:48,765 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-14 08:50:48,765 EPOCH 10 done: loss 0.0052 - lr: 0.000000
220
+ 2023-10-14 08:50:52,276 DEV : loss 0.1937766820192337 - f1-score (micro avg) 0.8068
221
+ 2023-10-14 08:50:52,725 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-14 08:50:52,727 Loading model from best epoch ...
223
+ 2023-10-14 08:50:55,066 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
224
+ 2023-10-14 08:50:57,817
225
+ Results:
226
+ - F-score (micro) 0.8168
227
+ - F-score (macro) 0.7131
228
+ - Accuracy 0.7047
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ PER 0.8333 0.8195 0.8264 482
234
+ LOC 0.8821 0.8493 0.8654 458
235
+ ORG 0.4324 0.4638 0.4476 69
236
+
237
+ micro avg 0.8251 0.8087 0.8168 1009
238
+ macro avg 0.7160 0.7109 0.7131 1009
239
+ weighted avg 0.8280 0.8087 0.8182 1009
240
+
241
+ 2023-10-14 08:50:57,817 ----------------------------------------------------------------------------------------------------