Hugging Face's logo

stefan-it
/
hmbench-newseye-de-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
c03def7
•
1 Parent(s): c115963

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. runs/events.out.tfevents.1697581789.3ae7c61396a7.1160.13 +3 -0
  5. test.tsv +0 -0
  6. training.log +240 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9126aa1028995b0d3fd4c933762155600909b0cddd9a280924c60f1b00fdc7ab
3
+ size 440954373
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 22:34:32 0.0000 0.4278 0.1946 0.1970 0.6307 0.3003 0.1781
3
+ 2 22:39:22 0.0000 0.1643 0.1782 0.2232 0.5511 0.3177 0.1904
4
+ 3 22:44:16 0.0000 0.1164 0.1867 0.3195 0.4943 0.3881 0.2430
5
+ 4 22:49:04 0.0000 0.0840 0.2567 0.2923 0.6117 0.3956 0.2475
6
+ 5 22:53:55 0.0000 0.0585 0.2786 0.3244 0.5473 0.4073 0.2585
7
+ 6 22:58:45 0.0000 0.0455 0.3161 0.2639 0.5758 0.3619 0.2222
8
+ 7 23:03:35 0.0000 0.0299 0.4404 0.2663 0.6250 0.3735 0.2313
9
+ 8 23:08:26 0.0000 0.0227 0.4419 0.2718 0.6326 0.3802 0.2360
10
+ 9 23:13:18 0.0000 0.0151 0.4639 0.3010 0.6458 0.4106 0.2597
11
+ 10 23:18:12 0.0000 0.0093 0.4872 0.2857 0.6326 0.3936 0.2465
runs/events.out.tfevents.1697581789.3ae7c61396a7.1160.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521969546f1d29ef3a089ab15388450935922ad1f78be8647bf2a6e1d6e7466e
3
+ size 1464420
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 22:29:49,087 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 22:29:49,089 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): ElectraModel(
5
+ (embeddings): ElectraEmbeddings(
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): ElectraEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x ElectraLayer(
15
+ (attention): ElectraAttention(
16
+ (self): ElectraSelfAttention(
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): ElectraSelfOutput(
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): ElectraIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): ElectraOutput(
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
+ )
41
+ )
42
+ (locked_dropout): LockedDropout(p=0.5)
43
+ (linear): Linear(in_features=768, out_features=17, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 22:29:49,089 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 22:29:49,089 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences
48
+ - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator
49
+ 2023-10-17 22:29:49,089 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 22:29:49,089 Train: 20847 sentences
51
+ 2023-10-17 22:29:49,089 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 22:29:49,089 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 22:29:49,089 Training Params:
54
+ 2023-10-17 22:29:49,089 - learning_rate: "5e-05"
55
+ 2023-10-17 22:29:49,089 - mini_batch_size: "8"
56
+ 2023-10-17 22:29:49,090 - max_epochs: "10"
57
+ 2023-10-17 22:29:49,090 - shuffle: "True"
58
+ 2023-10-17 22:29:49,090 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 22:29:49,090 Plugins:
60
+ 2023-10-17 22:29:49,090 - TensorboardLogger
61
+ 2023-10-17 22:29:49,090 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 22:29:49,090 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 22:29:49,090 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 22:29:49,090 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 22:29:49,090 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 22:29:49,090 Computation:
67
+ 2023-10-17 22:29:49,090 - compute on device: cuda:0
68
+ 2023-10-17 22:29:49,090 - embedding storage: none
69
+ 2023-10-17 22:29:49,090 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 22:29:49,090 Model training base path: "hmbench-newseye/de-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
71
+ 2023-10-17 22:29:49,091 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 22:29:49,091 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 22:29:49,091 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 22:30:17,028 epoch 1 - iter 260/2606 - loss 2.02848927 - time (sec): 27.94 - samples/sec: 1371.19 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 22:30:44,429 epoch 1 - iter 520/2606 - loss 1.21844947 - time (sec): 55.34 - samples/sec: 1346.96 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 22:31:12,228 epoch 1 - iter 780/2606 - loss 0.91990652 - time (sec): 83.14 - samples/sec: 1318.02 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 22:31:40,051 epoch 1 - iter 1040/2606 - loss 0.74718680 - time (sec): 110.96 - samples/sec: 1326.72 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 22:32:06,348 epoch 1 - iter 1300/2606 - loss 0.64893783 - time (sec): 137.26 - samples/sec: 1328.81 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 22:32:33,330 epoch 1 - iter 1560/2606 - loss 0.57578103 - time (sec): 164.24 - samples/sec: 1328.85 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 22:32:59,917 epoch 1 - iter 1820/2606 - loss 0.52157619 - time (sec): 190.82 - samples/sec: 1348.16 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 22:33:28,070 epoch 1 - iter 2080/2606 - loss 0.48435644 - time (sec): 218.98 - samples/sec: 1347.86 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 22:33:56,168 epoch 1 - iter 2340/2606 - loss 0.45266046 - time (sec): 247.07 - samples/sec: 1341.87 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 22:34:23,642 epoch 1 - iter 2600/2606 - loss 0.42860811 - time (sec): 274.55 - samples/sec: 1334.20 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 22:34:24,375 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 22:34:24,375 EPOCH 1 done: loss 0.4278 - lr: 0.000050
86
+ 2023-10-17 22:34:31,962 DEV : loss 0.19458557665348053 - f1-score (micro avg) 0.3003
87
+ 2023-10-17 22:34:32,021 saving best model
88
+ 2023-10-17 22:34:32,611 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 22:35:00,780 epoch 2 - iter 260/2606 - loss 0.18573805 - time (sec): 28.17 - samples/sec: 1284.73 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 22:35:28,795 epoch 2 - iter 520/2606 - loss 0.17536530 - time (sec): 56.18 - samples/sec: 1294.10 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 22:35:57,211 epoch 2 - iter 780/2606 - loss 0.18464606 - time (sec): 84.60 - samples/sec: 1284.88 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 22:36:24,191 epoch 2 - iter 1040/2606 - loss 0.18572133 - time (sec): 111.58 - samples/sec: 1288.97 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 22:36:52,771 epoch 2 - iter 1300/2606 - loss 0.17573034 - time (sec): 140.16 - samples/sec: 1295.79 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 22:37:20,317 epoch 2 - iter 1560/2606 - loss 0.17431997 - time (sec): 167.70 - samples/sec: 1299.62 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 22:37:46,652 epoch 2 - iter 1820/2606 - loss 0.17276740 - time (sec): 194.04 - samples/sec: 1300.78 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 22:38:14,196 epoch 2 - iter 2080/2606 - loss 0.16921817 - time (sec): 221.58 - samples/sec: 1320.04 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 22:38:43,447 epoch 2 - iter 2340/2606 - loss 0.16736292 - time (sec): 250.83 - samples/sec: 1323.21 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 22:39:09,856 epoch 2 - iter 2600/2606 - loss 0.16436618 - time (sec): 277.24 - samples/sec: 1322.57 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 22:39:10,492 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 22:39:10,492 EPOCH 2 done: loss 0.1643 - lr: 0.000044
101
+ 2023-10-17 22:39:22,270 DEV : loss 0.17822161316871643 - f1-score (micro avg) 0.3177
102
+ 2023-10-17 22:39:22,322 saving best model
103
+ 2023-10-17 22:39:23,752 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 22:39:51,896 epoch 3 - iter 260/2606 - loss 0.12920206 - time (sec): 28.14 - samples/sec: 1282.36 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 22:40:20,405 epoch 3 - iter 520/2606 - loss 0.11453609 - time (sec): 56.64 - samples/sec: 1296.29 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 22:40:48,913 epoch 3 - iter 780/2606 - loss 0.11650277 - time (sec): 85.15 - samples/sec: 1267.04 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 22:41:17,273 epoch 3 - iter 1040/2606 - loss 0.12299209 - time (sec): 113.51 - samples/sec: 1291.79 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 22:41:44,017 epoch 3 - iter 1300/2606 - loss 0.12055576 - time (sec): 140.26 - samples/sec: 1302.55 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 22:42:10,968 epoch 3 - iter 1560/2606 - loss 0.11843686 - time (sec): 167.21 - samples/sec: 1311.30 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 22:42:39,419 epoch 3 - iter 1820/2606 - loss 0.11721896 - time (sec): 195.66 - samples/sec: 1315.84 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 22:43:07,827 epoch 3 - iter 2080/2606 - loss 0.11733893 - time (sec): 224.07 - samples/sec: 1312.43 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 22:43:34,880 epoch 3 - iter 2340/2606 - loss 0.11675506 - time (sec): 251.12 - samples/sec: 1309.40 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 22:44:03,157 epoch 3 - iter 2600/2606 - loss 0.11643558 - time (sec): 279.40 - samples/sec: 1311.26 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 22:44:03,732 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 22:44:03,733 EPOCH 3 done: loss 0.1164 - lr: 0.000039
116
+ 2023-10-17 22:44:16,079 DEV : loss 0.18669994175434113 - f1-score (micro avg) 0.3881
117
+ 2023-10-17 22:44:16,134 saving best model
118
+ 2023-10-17 22:44:17,540 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 22:44:44,788 epoch 4 - iter 260/2606 - loss 0.08494930 - time (sec): 27.24 - samples/sec: 1367.76 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 22:45:12,077 epoch 4 - iter 520/2606 - loss 0.07898452 - time (sec): 54.53 - samples/sec: 1348.42 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 22:45:39,790 epoch 4 - iter 780/2606 - loss 0.07898936 - time (sec): 82.25 - samples/sec: 1351.84 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 22:46:06,642 epoch 4 - iter 1040/2606 - loss 0.08216188 - time (sec): 109.10 - samples/sec: 1340.12 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 22:46:34,413 epoch 4 - iter 1300/2606 - loss 0.08359594 - time (sec): 136.87 - samples/sec: 1330.39 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 22:47:01,446 epoch 4 - iter 1560/2606 - loss 0.08486629 - time (sec): 163.90 - samples/sec: 1332.80 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 22:47:28,235 epoch 4 - iter 1820/2606 - loss 0.08429319 - time (sec): 190.69 - samples/sec: 1339.58 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 22:47:56,351 epoch 4 - iter 2080/2606 - loss 0.08455278 - time (sec): 218.81 - samples/sec: 1342.81 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 22:48:23,794 epoch 4 - iter 2340/2606 - loss 0.08431644 - time (sec): 246.25 - samples/sec: 1339.45 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 22:48:52,450 epoch 4 - iter 2600/2606 - loss 0.08411450 - time (sec): 274.91 - samples/sec: 1332.31 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 22:48:53,209 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 22:48:53,210 EPOCH 4 done: loss 0.0840 - lr: 0.000033
131
+ 2023-10-17 22:49:04,552 DEV : loss 0.2566596269607544 - f1-score (micro avg) 0.3956
132
+ 2023-10-17 22:49:04,607 saving best model
133
+ 2023-10-17 22:49:06,082 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 22:49:35,940 epoch 5 - iter 260/2606 - loss 0.04669936 - time (sec): 29.85 - samples/sec: 1205.57 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 22:50:03,138 epoch 5 - iter 520/2606 - loss 0.05345590 - time (sec): 57.05 - samples/sec: 1309.26 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 22:50:32,012 epoch 5 - iter 780/2606 - loss 0.05303634 - time (sec): 85.93 - samples/sec: 1325.22 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 22:50:59,501 epoch 5 - iter 1040/2606 - loss 0.05440153 - time (sec): 113.41 - samples/sec: 1314.75 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 22:51:27,926 epoch 5 - iter 1300/2606 - loss 0.05722889 - time (sec): 141.84 - samples/sec: 1310.04 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 22:51:55,765 epoch 5 - iter 1560/2606 - loss 0.05872981 - time (sec): 169.68 - samples/sec: 1319.28 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 22:52:23,788 epoch 5 - iter 1820/2606 - loss 0.05737820 - time (sec): 197.70 - samples/sec: 1316.82 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 22:52:51,093 epoch 5 - iter 2080/2606 - loss 0.05740010 - time (sec): 225.01 - samples/sec: 1321.20 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 22:53:17,507 epoch 5 - iter 2340/2606 - loss 0.05836892 - time (sec): 251.42 - samples/sec: 1323.52 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 22:53:43,210 epoch 5 - iter 2600/2606 - loss 0.05838649 - time (sec): 277.12 - samples/sec: 1323.20 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 22:53:43,761 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 22:53:43,761 EPOCH 5 done: loss 0.0585 - lr: 0.000028
146
+ 2023-10-17 22:53:55,674 DEV : loss 0.27858346700668335 - f1-score (micro avg) 0.4073
147
+ 2023-10-17 22:53:55,737 saving best model
148
+ 2023-10-17 22:53:57,184 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 22:54:24,007 epoch 6 - iter 260/2606 - loss 0.05343449 - time (sec): 26.82 - samples/sec: 1428.06 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 22:54:50,782 epoch 6 - iter 520/2606 - loss 0.05204942 - time (sec): 53.59 - samples/sec: 1383.52 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 22:55:17,857 epoch 6 - iter 780/2606 - loss 0.05156502 - time (sec): 80.67 - samples/sec: 1394.32 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 22:55:45,833 epoch 6 - iter 1040/2606 - loss 0.04980644 - time (sec): 108.65 - samples/sec: 1385.34 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 22:56:14,864 epoch 6 - iter 1300/2606 - loss 0.04934279 - time (sec): 137.68 - samples/sec: 1352.64 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 22:56:42,014 epoch 6 - iter 1560/2606 - loss 0.04831799 - time (sec): 164.83 - samples/sec: 1330.27 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 22:57:08,026 epoch 6 - iter 1820/2606 - loss 0.04711258 - time (sec): 190.84 - samples/sec: 1333.27 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 22:57:36,502 epoch 6 - iter 2080/2606 - loss 0.04700619 - time (sec): 219.31 - samples/sec: 1325.55 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 22:58:04,030 epoch 6 - iter 2340/2606 - loss 0.04631173 - time (sec): 246.84 - samples/sec: 1329.18 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 22:58:32,499 epoch 6 - iter 2600/2606 - loss 0.04553521 - time (sec): 275.31 - samples/sec: 1331.16 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 22:58:33,201 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 22:58:33,202 EPOCH 6 done: loss 0.0455 - lr: 0.000022
161
+ 2023-10-17 22:58:44,947 DEV : loss 0.31613317131996155 - f1-score (micro avg) 0.3619
162
+ 2023-10-17 22:58:45,011 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-17 22:59:13,685 epoch 7 - iter 260/2606 - loss 0.02491344 - time (sec): 28.67 - samples/sec: 1318.70 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-17 22:59:40,721 epoch 7 - iter 520/2606 - loss 0.02684154 - time (sec): 55.71 - samples/sec: 1329.26 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 23:00:09,079 epoch 7 - iter 780/2606 - loss 0.02766037 - time (sec): 84.07 - samples/sec: 1290.18 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 23:00:37,772 epoch 7 - iter 1040/2606 - loss 0.02974319 - time (sec): 112.76 - samples/sec: 1279.62 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-17 23:01:06,063 epoch 7 - iter 1300/2606 - loss 0.03074650 - time (sec): 141.05 - samples/sec: 1284.12 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-17 23:01:32,926 epoch 7 - iter 1560/2606 - loss 0.03182663 - time (sec): 167.91 - samples/sec: 1287.99 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 23:02:00,232 epoch 7 - iter 1820/2606 - loss 0.03187523 - time (sec): 195.22 - samples/sec: 1297.48 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 23:02:29,230 epoch 7 - iter 2080/2606 - loss 0.03088266 - time (sec): 224.22 - samples/sec: 1318.64 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 23:02:55,694 epoch 7 - iter 2340/2606 - loss 0.03076656 - time (sec): 250.68 - samples/sec: 1316.90 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 23:03:23,449 epoch 7 - iter 2600/2606 - loss 0.02992379 - time (sec): 278.44 - samples/sec: 1317.67 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 23:03:23,970 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-17 23:03:23,970 EPOCH 7 done: loss 0.0299 - lr: 0.000017
175
+ 2023-10-17 23:03:35,173 DEV : loss 0.4403761923313141 - f1-score (micro avg) 0.3735
176
+ 2023-10-17 23:03:35,238 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 23:04:03,459 epoch 8 - iter 260/2606 - loss 0.02142000 - time (sec): 28.22 - samples/sec: 1283.04 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 23:04:31,714 epoch 8 - iter 520/2606 - loss 0.01991354 - time (sec): 56.47 - samples/sec: 1294.22 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 23:04:58,892 epoch 8 - iter 780/2606 - loss 0.01931704 - time (sec): 83.65 - samples/sec: 1279.97 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-17 23:05:27,331 epoch 8 - iter 1040/2606 - loss 0.02006574 - time (sec): 112.09 - samples/sec: 1275.23 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 23:05:55,670 epoch 8 - iter 1300/2606 - loss 0.02078348 - time (sec): 140.43 - samples/sec: 1274.13 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 23:06:24,906 epoch 8 - iter 1560/2606 - loss 0.02167079 - time (sec): 169.67 - samples/sec: 1277.81 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 23:06:53,016 epoch 8 - iter 1820/2606 - loss 0.02190993 - time (sec): 197.78 - samples/sec: 1301.34 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 23:07:20,238 epoch 8 - iter 2080/2606 - loss 0.02313931 - time (sec): 225.00 - samples/sec: 1310.25 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 23:07:45,885 epoch 8 - iter 2340/2606 - loss 0.02250970 - time (sec): 250.64 - samples/sec: 1315.03 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 23:08:14,890 epoch 8 - iter 2600/2606 - loss 0.02273813 - time (sec): 279.65 - samples/sec: 1311.02 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-17 23:08:15,460 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 23:08:15,460 EPOCH 8 done: loss 0.0227 - lr: 0.000011
189
+ 2023-10-17 23:08:26,347 DEV : loss 0.44188764691352844 - f1-score (micro avg) 0.3802
190
+ 2023-10-17 23:08:26,402 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-17 23:08:55,086 epoch 9 - iter 260/2606 - loss 0.01290092 - time (sec): 28.68 - samples/sec: 1357.88 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-17 23:09:22,049 epoch 9 - iter 520/2606 - loss 0.01379589 - time (sec): 55.64 - samples/sec: 1348.29 - lr: 0.000010 - momentum: 0.000000
193
+ 2023-10-17 23:09:50,080 epoch 9 - iter 780/2606 - loss 0.01434365 - time (sec): 83.68 - samples/sec: 1312.48 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-17 23:10:18,063 epoch 9 - iter 1040/2606 - loss 0.01448784 - time (sec): 111.66 - samples/sec: 1292.94 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-17 23:10:45,062 epoch 9 - iter 1300/2606 - loss 0.01451714 - time (sec): 138.66 - samples/sec: 1293.96 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 23:11:13,160 epoch 9 - iter 1560/2606 - loss 0.01441414 - time (sec): 166.75 - samples/sec: 1300.35 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 23:11:40,264 epoch 9 - iter 1820/2606 - loss 0.01475688 - time (sec): 193.86 - samples/sec: 1310.23 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 23:12:08,004 epoch 9 - iter 2080/2606 - loss 0.01490181 - time (sec): 221.60 - samples/sec: 1320.90 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 23:12:36,041 epoch 9 - iter 2340/2606 - loss 0.01479776 - time (sec): 249.64 - samples/sec: 1321.83 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 23:13:05,286 epoch 9 - iter 2600/2606 - loss 0.01511359 - time (sec): 278.88 - samples/sec: 1314.75 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 23:13:05,943 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-17 23:13:05,944 EPOCH 9 done: loss 0.0151 - lr: 0.000006
203
+ 2023-10-17 23:13:18,078 DEV : loss 0.4638948440551758 - f1-score (micro avg) 0.4106
204
+ 2023-10-17 23:13:18,144 saving best model
205
+ 2023-10-17 23:13:19,694 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-17 23:13:50,439 epoch 10 - iter 260/2606 - loss 0.00890757 - time (sec): 30.74 - samples/sec: 1219.33 - lr: 0.000005 - momentum: 0.000000
207
+ 2023-10-17 23:14:18,832 epoch 10 - iter 520/2606 - loss 0.00864088 - time (sec): 59.14 - samples/sec: 1260.06 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 23:14:47,585 epoch 10 - iter 780/2606 - loss 0.01049821 - time (sec): 87.89 - samples/sec: 1243.94 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-17 23:15:14,969 epoch 10 - iter 1040/2606 - loss 0.01013399 - time (sec): 115.27 - samples/sec: 1247.17 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 23:15:42,175 epoch 10 - iter 1300/2606 - loss 0.00906366 - time (sec): 142.48 - samples/sec: 1286.90 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 23:16:09,614 epoch 10 - iter 1560/2606 - loss 0.00909100 - time (sec): 169.92 - samples/sec: 1297.96 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 23:16:39,396 epoch 10 - iter 1820/2606 - loss 0.00925267 - time (sec): 199.70 - samples/sec: 1299.91 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 23:17:07,503 epoch 10 - iter 2080/2606 - loss 0.00919351 - time (sec): 227.81 - samples/sec: 1297.14 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 23:17:33,875 epoch 10 - iter 2340/2606 - loss 0.00928314 - time (sec): 254.18 - samples/sec: 1298.02 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 23:17:59,956 epoch 10 - iter 2600/2606 - loss 0.00932223 - time (sec): 280.26 - samples/sec: 1308.39 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-17 23:18:00,484 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-17 23:18:00,484 EPOCH 10 done: loss 0.0093 - lr: 0.000000
218
+ 2023-10-17 23:18:12,656 DEV : loss 0.48719704151153564 - f1-score (micro avg) 0.3936
219
+ 2023-10-17 23:18:13,293 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-17 23:18:13,295 Loading model from best epoch ...
221
+ 2023-10-17 23:18:15,665 SequenceTagger predicts: Dictionary with 17 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, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
222
+ 2023-10-17 23:18:34,724
223
+ Results:
224
+ - F-score (micro) 0.4853
225
+ - F-score (macro) 0.3233
226
+ - Accuracy 0.3255
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ LOC 0.5263 0.6343 0.5753 1214
232
+ PER 0.3903 0.5087 0.4417 808
233
+ ORG 0.2745 0.2776 0.2761 353
234
+ HumanProd 0.0000 0.0000 0.0000 15
235
+
236
+ micro avg 0.4439 0.5351 0.4853 2390
237
+ macro avg 0.2978 0.3551 0.3233 2390
238
+ weighted avg 0.4398 0.5351 0.4823 2390
239
+
240
+ 2023-10-17 23:18:34,724 ----------------------------------------------------------------------------------------------------