Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
37e4d1b
·
1 Parent(s): 299de51

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +239 -0
training.log ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-25 17:40:41,801 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-25 17:40:41,802 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 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=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-25 17:40:41,803 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-25 17:40:41,803 MultiCorpus: 7142 train + 698 dev + 2570 test sentences
52
+ - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator
53
+ 2023-10-25 17:40:41,803 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-25 17:40:41,803 Train: 7142 sentences
55
+ 2023-10-25 17:40:41,803 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-25 17:40:41,803 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-25 17:40:41,803 Training Params:
58
+ 2023-10-25 17:40:41,803 - learning_rate: "5e-05"
59
+ 2023-10-25 17:40:41,803 - mini_batch_size: "4"
60
+ 2023-10-25 17:40:41,803 - max_epochs: "10"
61
+ 2023-10-25 17:40:41,803 - shuffle: "True"
62
+ 2023-10-25 17:40:41,803 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-25 17:40:41,803 Plugins:
64
+ 2023-10-25 17:40:41,803 - TensorboardLogger
65
+ 2023-10-25 17:40:41,803 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-25 17:40:41,804 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-25 17:40:41,804 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-25 17:40:41,804 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-25 17:40:41,804 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-25 17:40:41,804 Computation:
71
+ 2023-10-25 17:40:41,804 - compute on device: cuda:0
72
+ 2023-10-25 17:40:41,804 - embedding storage: none
73
+ 2023-10-25 17:40:41,804 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-25 17:40:41,804 Model training base path: "hmbench-newseye/fr-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-25 17:40:41,804 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-25 17:40:41,804 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-25 17:40:41,804 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-25 17:40:50,955 epoch 1 - iter 178/1786 - loss 1.58853441 - time (sec): 9.15 - samples/sec: 2759.97 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-25 17:41:00,502 epoch 1 - iter 356/1786 - loss 0.99897941 - time (sec): 18.70 - samples/sec: 2715.25 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-25 17:41:09,557 epoch 1 - iter 534/1786 - loss 0.76525204 - time (sec): 27.75 - samples/sec: 2694.36 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-25 17:41:19,183 epoch 1 - iter 712/1786 - loss 0.62348649 - time (sec): 37.38 - samples/sec: 2664.62 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-25 17:41:28,851 epoch 1 - iter 890/1786 - loss 0.53503427 - time (sec): 47.05 - samples/sec: 2623.35 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-25 17:41:38,395 epoch 1 - iter 1068/1786 - loss 0.47559714 - time (sec): 56.59 - samples/sec: 2616.57 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-25 17:41:47,552 epoch 1 - iter 1246/1786 - loss 0.42659811 - time (sec): 65.75 - samples/sec: 2630.38 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-25 17:41:56,676 epoch 1 - iter 1424/1786 - loss 0.38940151 - time (sec): 74.87 - samples/sec: 2655.77 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-25 17:42:05,934 epoch 1 - iter 1602/1786 - loss 0.36429511 - time (sec): 84.13 - samples/sec: 2661.40 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-25 17:42:15,347 epoch 1 - iter 1780/1786 - loss 0.34310581 - time (sec): 93.54 - samples/sec: 2647.80 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-25 17:42:15,681 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-25 17:42:15,682 EPOCH 1 done: loss 0.3421 - lr: 0.000050
90
+ 2023-10-25 17:42:19,928 DEV : loss 0.1157413125038147 - f1-score (micro avg) 0.7285
91
+ 2023-10-25 17:42:19,950 saving best model
92
+ 2023-10-25 17:42:20,426 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-25 17:42:29,891 epoch 2 - iter 178/1786 - loss 0.12357626 - time (sec): 9.46 - samples/sec: 2610.76 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-25 17:42:39,366 epoch 2 - iter 356/1786 - loss 0.11053146 - time (sec): 18.94 - samples/sec: 2592.84 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-25 17:42:48,328 epoch 2 - iter 534/1786 - loss 0.11602450 - time (sec): 27.90 - samples/sec: 2688.88 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-25 17:42:57,850 epoch 2 - iter 712/1786 - loss 0.12151005 - time (sec): 37.42 - samples/sec: 2704.31 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-25 17:43:07,312 epoch 2 - iter 890/1786 - loss 0.11913634 - time (sec): 46.88 - samples/sec: 2708.85 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-25 17:43:16,634 epoch 2 - iter 1068/1786 - loss 0.11991823 - time (sec): 56.21 - samples/sec: 2680.92 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-25 17:43:25,948 epoch 2 - iter 1246/1786 - loss 0.12175183 - time (sec): 65.52 - samples/sec: 2675.76 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-25 17:43:35,423 epoch 2 - iter 1424/1786 - loss 0.12168175 - time (sec): 74.99 - samples/sec: 2675.01 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-25 17:43:44,649 epoch 2 - iter 1602/1786 - loss 0.13188351 - time (sec): 84.22 - samples/sec: 2646.95 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-25 17:43:54,068 epoch 2 - iter 1780/1786 - loss 0.13323438 - time (sec): 93.64 - samples/sec: 2650.12 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-25 17:43:54,378 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-25 17:43:54,378 EPOCH 2 done: loss 0.1333 - lr: 0.000044
105
+ 2023-10-25 17:43:58,432 DEV : loss 0.15184670686721802 - f1-score (micro avg) 0.7035
106
+ 2023-10-25 17:43:58,453 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-25 17:44:07,709 epoch 3 - iter 178/1786 - loss 0.21881355 - time (sec): 9.25 - samples/sec: 2535.12 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-25 17:44:17,382 epoch 3 - iter 356/1786 - loss 0.20073433 - time (sec): 18.93 - samples/sec: 2609.87 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-25 17:44:27,124 epoch 3 - iter 534/1786 - loss 0.18404447 - time (sec): 28.67 - samples/sec: 2589.85 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-25 17:44:37,132 epoch 3 - iter 712/1786 - loss 0.17724145 - time (sec): 38.68 - samples/sec: 2561.69 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-25 17:44:46,907 epoch 3 - iter 890/1786 - loss 0.19591471 - time (sec): 48.45 - samples/sec: 2572.30 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-25 17:44:56,423 epoch 3 - iter 1068/1786 - loss 0.18778237 - time (sec): 57.97 - samples/sec: 2582.25 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-25 17:45:05,773 epoch 3 - iter 1246/1786 - loss 0.18107435 - time (sec): 67.32 - samples/sec: 2589.95 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-25 17:45:15,145 epoch 3 - iter 1424/1786 - loss 0.17531969 - time (sec): 76.69 - samples/sec: 2569.83 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-25 17:45:24,888 epoch 3 - iter 1602/1786 - loss 0.16986179 - time (sec): 86.43 - samples/sec: 2586.15 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-25 17:45:34,549 epoch 3 - iter 1780/1786 - loss 0.16572558 - time (sec): 96.09 - samples/sec: 2581.29 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-25 17:45:34,877 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-25 17:45:34,877 EPOCH 3 done: loss 0.1660 - lr: 0.000039
119
+ 2023-10-25 17:45:40,755 DEV : loss 0.15264961123466492 - f1-score (micro avg) 0.7182
120
+ 2023-10-25 17:45:40,792 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-25 17:45:50,505 epoch 4 - iter 178/1786 - loss 0.11257728 - time (sec): 9.71 - samples/sec: 2672.08 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-25 17:46:00,061 epoch 4 - iter 356/1786 - loss 0.11558938 - time (sec): 19.27 - samples/sec: 2676.90 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-25 17:46:09,578 epoch 4 - iter 534/1786 - loss 0.13851064 - time (sec): 28.78 - samples/sec: 2605.72 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-25 17:46:19,481 epoch 4 - iter 712/1786 - loss 0.15453780 - time (sec): 38.69 - samples/sec: 2558.64 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-25 17:46:29,206 epoch 4 - iter 890/1786 - loss 0.14125444 - time (sec): 48.41 - samples/sec: 2570.26 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-25 17:46:38,730 epoch 4 - iter 1068/1786 - loss 0.13716273 - time (sec): 57.94 - samples/sec: 2587.83 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-25 17:46:48,206 epoch 4 - iter 1246/1786 - loss 0.14399996 - time (sec): 67.41 - samples/sec: 2572.01 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-25 17:46:57,742 epoch 4 - iter 1424/1786 - loss 0.17221842 - time (sec): 76.95 - samples/sec: 2580.21 - lr: 0.000034 - momentum: 0.000000
129
+ 2023-10-25 17:47:07,350 epoch 4 - iter 1602/1786 - loss 0.17249056 - time (sec): 86.56 - samples/sec: 2587.00 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-25 17:47:16,796 epoch 4 - iter 1780/1786 - loss 0.16885428 - time (sec): 96.00 - samples/sec: 2576.19 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-25 17:47:17,169 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-25 17:47:17,169 EPOCH 4 done: loss 0.1682 - lr: 0.000033
133
+ 2023-10-25 17:47:22,574 DEV : loss 0.23014414310455322 - f1-score (micro avg) 0.5756
134
+ 2023-10-25 17:47:22,594 ----------------------------------------------------------------------------------------------------
135
+ 2023-10-25 17:47:32,020 epoch 5 - iter 178/1786 - loss 0.29969294 - time (sec): 9.42 - samples/sec: 2460.84 - lr: 0.000033 - momentum: 0.000000
136
+ 2023-10-25 17:47:41,252 epoch 5 - iter 356/1786 - loss 0.22538083 - time (sec): 18.66 - samples/sec: 2574.32 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-25 17:47:50,174 epoch 5 - iter 534/1786 - loss 0.20926340 - time (sec): 27.58 - samples/sec: 2640.98 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-25 17:47:59,234 epoch 5 - iter 712/1786 - loss 0.20575150 - time (sec): 36.64 - samples/sec: 2666.93 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-25 17:48:08,029 epoch 5 - iter 890/1786 - loss 0.22083787 - time (sec): 45.43 - samples/sec: 2706.86 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-25 17:48:16,892 epoch 5 - iter 1068/1786 - loss 0.21465786 - time (sec): 54.30 - samples/sec: 2727.67 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-25 17:48:25,710 epoch 5 - iter 1246/1786 - loss 0.21366312 - time (sec): 63.11 - samples/sec: 2731.67 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-25 17:48:35,316 epoch 5 - iter 1424/1786 - loss 0.22207378 - time (sec): 72.72 - samples/sec: 2705.78 - lr: 0.000029 - momentum: 0.000000
143
+ 2023-10-25 17:48:44,792 epoch 5 - iter 1602/1786 - loss 0.23504852 - time (sec): 82.20 - samples/sec: 2714.75 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-25 17:48:54,333 epoch 5 - iter 1780/1786 - loss 0.23556972 - time (sec): 91.74 - samples/sec: 2701.57 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-25 17:48:54,656 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-25 17:48:54,656 EPOCH 5 done: loss 0.2355 - lr: 0.000028
147
+ 2023-10-25 17:48:59,052 DEV : loss 0.28669020533561707 - f1-score (micro avg) 0.5224
148
+ 2023-10-25 17:48:59,075 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-25 17:49:08,475 epoch 6 - iter 178/1786 - loss 0.24088950 - time (sec): 9.40 - samples/sec: 2520.43 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-25 17:49:17,462 epoch 6 - iter 356/1786 - loss 0.24200171 - time (sec): 18.38 - samples/sec: 2532.60 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-25 17:49:26,516 epoch 6 - iter 534/1786 - loss 0.27544235 - time (sec): 27.44 - samples/sec: 2630.04 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-25 17:49:35,938 epoch 6 - iter 712/1786 - loss 0.25855806 - time (sec): 36.86 - samples/sec: 2635.62 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-25 17:49:45,704 epoch 6 - iter 890/1786 - loss 0.23023254 - time (sec): 46.63 - samples/sec: 2631.64 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-25 17:49:55,723 epoch 6 - iter 1068/1786 - loss 0.22549331 - time (sec): 56.65 - samples/sec: 2617.90 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-25 17:50:05,358 epoch 6 - iter 1246/1786 - loss 0.21674189 - time (sec): 66.28 - samples/sec: 2610.39 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-25 17:50:14,325 epoch 6 - iter 1424/1786 - loss 0.21006865 - time (sec): 75.25 - samples/sec: 2637.31 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-25 17:50:23,084 epoch 6 - iter 1602/1786 - loss 0.21109774 - time (sec): 84.01 - samples/sec: 2651.06 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-25 17:50:31,915 epoch 6 - iter 1780/1786 - loss 0.21038544 - time (sec): 92.84 - samples/sec: 2674.68 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-25 17:50:32,192 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-25 17:50:32,192 EPOCH 6 done: loss 0.2102 - lr: 0.000022
161
+ 2023-10-25 17:50:37,252 DEV : loss 0.2602541446685791 - f1-score (micro avg) 0.5308
162
+ 2023-10-25 17:50:37,275 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-25 17:50:47,039 epoch 7 - iter 178/1786 - loss 0.21794570 - time (sec): 9.76 - samples/sec: 2454.73 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-25 17:50:56,559 epoch 7 - iter 356/1786 - loss 0.22918461 - time (sec): 19.28 - samples/sec: 2520.76 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-25 17:51:06,346 epoch 7 - iter 534/1786 - loss 0.25171027 - time (sec): 29.07 - samples/sec: 2568.53 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-25 17:51:15,990 epoch 7 - iter 712/1786 - loss 0.25397016 - time (sec): 38.71 - samples/sec: 2568.60 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-25 17:51:25,702 epoch 7 - iter 890/1786 - loss 0.26391332 - time (sec): 48.42 - samples/sec: 2586.64 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-25 17:51:35,331 epoch 7 - iter 1068/1786 - loss 0.27186244 - time (sec): 58.05 - samples/sec: 2599.54 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-25 17:51:44,934 epoch 7 - iter 1246/1786 - loss 0.27158031 - time (sec): 67.66 - samples/sec: 2592.94 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-25 17:51:54,043 epoch 7 - iter 1424/1786 - loss 0.27319462 - time (sec): 76.77 - samples/sec: 2581.14 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-25 17:52:03,313 epoch 7 - iter 1602/1786 - loss 0.28007902 - time (sec): 86.04 - samples/sec: 2589.45 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-25 17:52:12,749 epoch 7 - iter 1780/1786 - loss 0.28680135 - time (sec): 95.47 - samples/sec: 2600.07 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-25 17:52:13,056 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-25 17:52:13,057 EPOCH 7 done: loss 0.2869 - lr: 0.000017
175
+ 2023-10-25 17:52:17,998 DEV : loss 0.33920225501060486 - f1-score (micro avg) 0.0764
176
+ 2023-10-25 17:52:18,020 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-25 17:52:27,367 epoch 8 - iter 178/1786 - loss 0.36843742 - time (sec): 9.35 - samples/sec: 2758.41 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-25 17:52:36,777 epoch 8 - iter 356/1786 - loss 0.31028626 - time (sec): 18.76 - samples/sec: 2688.71 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-25 17:52:46,317 epoch 8 - iter 534/1786 - loss 0.27130704 - time (sec): 28.30 - samples/sec: 2643.81 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-25 17:52:56,058 epoch 8 - iter 712/1786 - loss 0.25513019 - time (sec): 38.04 - samples/sec: 2579.63 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-25 17:53:05,844 epoch 8 - iter 890/1786 - loss 0.24404946 - time (sec): 47.82 - samples/sec: 2555.74 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-25 17:53:14,963 epoch 8 - iter 1068/1786 - loss 0.23553099 - time (sec): 56.94 - samples/sec: 2591.77 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-25 17:53:23,953 epoch 8 - iter 1246/1786 - loss 0.22986010 - time (sec): 65.93 - samples/sec: 2608.09 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-25 17:53:34,180 epoch 8 - iter 1424/1786 - loss 0.22157961 - time (sec): 76.16 - samples/sec: 2575.16 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-25 17:53:44,033 epoch 8 - iter 1602/1786 - loss 0.22029122 - time (sec): 86.01 - samples/sec: 2578.42 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-25 17:53:53,158 epoch 8 - iter 1780/1786 - loss 0.22063290 - time (sec): 95.14 - samples/sec: 2606.86 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-25 17:53:53,440 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-25 17:53:53,440 EPOCH 8 done: loss 0.2206 - lr: 0.000011
189
+ 2023-10-25 17:53:57,704 DEV : loss 0.26614901423454285 - f1-score (micro avg) 0.2588
190
+ 2023-10-25 17:53:57,729 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-25 17:54:07,435 epoch 9 - iter 178/1786 - loss 0.22092430 - time (sec): 9.70 - samples/sec: 2608.61 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-25 17:54:16,932 epoch 9 - iter 356/1786 - loss 0.24817483 - time (sec): 19.20 - samples/sec: 2618.57 - lr: 0.000010 - momentum: 0.000000
193
+ 2023-10-25 17:54:26,445 epoch 9 - iter 534/1786 - loss 0.24992921 - time (sec): 28.71 - samples/sec: 2582.10 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-25 17:54:36,130 epoch 9 - iter 712/1786 - loss 0.23878804 - time (sec): 38.40 - samples/sec: 2606.59 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-25 17:54:45,779 epoch 9 - iter 890/1786 - loss 0.23615827 - time (sec): 48.05 - samples/sec: 2609.33 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-25 17:54:55,329 epoch 9 - iter 1068/1786 - loss 0.23293578 - time (sec): 57.60 - samples/sec: 2583.88 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-25 17:55:05,028 epoch 9 - iter 1246/1786 - loss 0.22847871 - time (sec): 67.30 - samples/sec: 2601.07 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-25 17:55:14,524 epoch 9 - iter 1424/1786 - loss 0.22861141 - time (sec): 76.79 - samples/sec: 2580.97 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-25 17:55:24,148 epoch 9 - iter 1602/1786 - loss 0.22425309 - time (sec): 86.42 - samples/sec: 2572.83 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-25 17:55:33,779 epoch 9 - iter 1780/1786 - loss 0.22106349 - time (sec): 96.05 - samples/sec: 2580.15 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-25 17:55:34,106 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-25 17:55:34,106 EPOCH 9 done: loss 0.2207 - lr: 0.000006
203
+ 2023-10-25 17:55:40,105 DEV : loss 0.23793765902519226 - f1-score (micro avg) 0.4396
204
+ 2023-10-25 17:55:40,130 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-25 17:55:49,679 epoch 10 - iter 178/1786 - loss 0.18894004 - time (sec): 9.55 - samples/sec: 2541.06 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-25 17:55:58,691 epoch 10 - iter 356/1786 - loss 0.18805572 - time (sec): 18.56 - samples/sec: 2552.08 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-25 17:56:07,838 epoch 10 - iter 534/1786 - loss 0.20022937 - time (sec): 27.71 - samples/sec: 2649.04 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-25 17:56:16,644 epoch 10 - iter 712/1786 - loss 0.21629891 - time (sec): 36.51 - samples/sec: 2700.37 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-25 17:56:25,835 epoch 10 - iter 890/1786 - loss 0.21744263 - time (sec): 45.70 - samples/sec: 2668.21 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-25 17:56:34,869 epoch 10 - iter 1068/1786 - loss 0.21847464 - time (sec): 54.74 - samples/sec: 2703.62 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-25 17:56:44,608 epoch 10 - iter 1246/1786 - loss 0.22124297 - time (sec): 64.48 - samples/sec: 2683.55 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-25 17:56:54,445 epoch 10 - iter 1424/1786 - loss 0.22346575 - time (sec): 74.31 - samples/sec: 2640.76 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-25 17:57:04,170 epoch 10 - iter 1602/1786 - loss 0.22696912 - time (sec): 84.04 - samples/sec: 2640.24 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-25 17:57:13,801 epoch 10 - iter 1780/1786 - loss 0.22705105 - time (sec): 93.67 - samples/sec: 2647.17 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-25 17:57:14,131 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-25 17:57:14,131 EPOCH 10 done: loss 0.2272 - lr: 0.000000
217
+ 2023-10-25 17:57:18,466 DEV : loss 0.2877625823020935 - f1-score (micro avg) 0.2472
218
+ 2023-10-25 17:57:18,976 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-25 17:57:18,978 Loading model from best epoch ...
220
+ 2023-10-25 17:57:20,828 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
221
+ 2023-10-25 17:57:33,683
222
+ Results:
223
+ - F-score (micro) 0.6059
224
+ - F-score (macro) 0.5138
225
+ - Accuracy 0.4467
226
+
227
+ By class:
228
+ precision recall f1-score support
229
+
230
+ LOC 0.5934 0.6356 0.6138 1095
231
+ PER 0.7320 0.6749 0.7023 1012
232
+ ORG 0.3383 0.3838 0.3596 357
233
+ HumanProd 0.3261 0.4545 0.3797 33
234
+
235
+ micro avg 0.5987 0.6131 0.6059 2497
236
+ macro avg 0.4974 0.5372 0.5138 2497
237
+ weighted avg 0.6096 0.6131 0.6102 2497
238
+
239
+ 2023-10-25 17:57:33,683 ----------------------------------------------------------------------------------------------------