Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmteams-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
f2d0eeb
•
1 Parent(s): 1e3fb07

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.1697549845.0468bd9609d6.7281.6 +3 -0
  5. test.tsv +0 -0
  6. training.log +238 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00722fce06f9cf6a7e8d102e0d18032ae8a4e5eab22be6d6c08d984259d9373d
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 13:38:57 0.0000 0.4990 0.1194 0.7564 0.7605 0.7585 0.6281
3
+ 2 13:40:32 0.0000 0.1195 0.1013 0.8111 0.8177 0.8144 0.7037
4
+ 3 13:42:06 0.0000 0.0818 0.1342 0.8101 0.7837 0.7967 0.6841
5
+ 4 13:43:41 0.0000 0.0589 0.1649 0.7868 0.8286 0.8072 0.6944
6
+ 5 13:45:15 0.0000 0.0427 0.1587 0.8081 0.8136 0.8108 0.6994
7
+ 6 13:46:47 0.0000 0.0315 0.1810 0.8159 0.8259 0.8208 0.7133
8
+ 7 13:48:22 0.0000 0.0240 0.1769 0.8322 0.8367 0.8345 0.7330
9
+ 8 13:49:56 0.0000 0.0177 0.1967 0.7984 0.8354 0.8165 0.7066
10
+ 9 13:51:31 0.0000 0.0126 0.2093 0.8166 0.8299 0.8232 0.7168
11
+ 10 13:53:06 0.0000 0.0086 0.2027 0.8239 0.8340 0.8289 0.7254
runs/events.out.tfevents.1697549845.0468bd9609d6.7281.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861c49d752324b64e98fd9b74e338b3442aa9605cbf3ffc75108fcc53906793d
3
+ size 999862
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,238 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 13:37:25,646 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 13:37:25,647 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 13:37:25,647 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 13:37:25,647 MultiCorpus: 7142 train + 698 dev + 2570 test sentences
48
+ - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator
49
+ 2023-10-17 13:37:25,647 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 13:37:25,648 Train: 7142 sentences
51
+ 2023-10-17 13:37:25,648 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 13:37:25,648 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 13:37:25,648 Training Params:
54
+ 2023-10-17 13:37:25,648 - learning_rate: "3e-05"
55
+ 2023-10-17 13:37:25,648 - mini_batch_size: "4"
56
+ 2023-10-17 13:37:25,648 - max_epochs: "10"
57
+ 2023-10-17 13:37:25,648 - shuffle: "True"
58
+ 2023-10-17 13:37:25,648 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 13:37:25,648 Plugins:
60
+ 2023-10-17 13:37:25,648 - TensorboardLogger
61
+ 2023-10-17 13:37:25,648 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 13:37:25,648 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 13:37:25,648 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 13:37:25,648 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 13:37:25,648 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 13:37:25,648 Computation:
67
+ 2023-10-17 13:37:25,648 - compute on device: cuda:0
68
+ 2023-10-17 13:37:25,648 - embedding storage: none
69
+ 2023-10-17 13:37:25,648 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 13:37:25,648 Model training base path: "hmbench-newseye/fr-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 13:37:25,648 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 13:37:25,648 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 13:37:25,648 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 13:37:34,100 epoch 1 - iter 178/1786 - loss 2.71850894 - time (sec): 8.45 - samples/sec: 2722.97 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 13:37:43,271 epoch 1 - iter 356/1786 - loss 1.55627930 - time (sec): 17.62 - samples/sec: 2818.11 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 13:37:52,167 epoch 1 - iter 534/1786 - loss 1.17692252 - time (sec): 26.52 - samples/sec: 2810.54 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 13:38:01,158 epoch 1 - iter 712/1786 - loss 0.95620126 - time (sec): 35.51 - samples/sec: 2847.03 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 13:38:09,947 epoch 1 - iter 890/1786 - loss 0.81990248 - time (sec): 44.30 - samples/sec: 2817.71 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 13:38:18,765 epoch 1 - iter 1068/1786 - loss 0.72732692 - time (sec): 53.12 - samples/sec: 2789.30 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 13:38:27,632 epoch 1 - iter 1246/1786 - loss 0.64882748 - time (sec): 61.98 - samples/sec: 2788.02 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 13:38:36,725 epoch 1 - iter 1424/1786 - loss 0.58363820 - time (sec): 71.08 - samples/sec: 2803.30 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 13:38:45,495 epoch 1 - iter 1602/1786 - loss 0.53997715 - time (sec): 79.85 - samples/sec: 2791.05 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 13:38:54,216 epoch 1 - iter 1780/1786 - loss 0.49959069 - time (sec): 88.57 - samples/sec: 2802.19 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 13:38:54,485 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 13:38:54,486 EPOCH 1 done: loss 0.4990 - lr: 0.000030
86
+ 2023-10-17 13:38:57,577 DEV : loss 0.11935114115476608 - f1-score (micro avg) 0.7585
87
+ 2023-10-17 13:38:57,593 saving best model
88
+ 2023-10-17 13:38:57,942 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 13:39:07,045 epoch 2 - iter 178/1786 - loss 0.14207407 - time (sec): 9.10 - samples/sec: 2671.63 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 13:39:15,919 epoch 2 - iter 356/1786 - loss 0.13038487 - time (sec): 17.98 - samples/sec: 2672.23 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 13:39:24,577 epoch 2 - iter 534/1786 - loss 0.12627094 - time (sec): 26.63 - samples/sec: 2624.39 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 13:39:33,752 epoch 2 - iter 712/1786 - loss 0.12554020 - time (sec): 35.81 - samples/sec: 2655.03 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 13:39:42,945 epoch 2 - iter 890/1786 - loss 0.12266313 - time (sec): 45.00 - samples/sec: 2698.72 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 13:39:52,042 epoch 2 - iter 1068/1786 - loss 0.12077729 - time (sec): 54.10 - samples/sec: 2723.97 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 13:40:01,199 epoch 2 - iter 1246/1786 - loss 0.11775653 - time (sec): 63.26 - samples/sec: 2764.92 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 13:40:09,971 epoch 2 - iter 1424/1786 - loss 0.12007377 - time (sec): 72.03 - samples/sec: 2776.20 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 13:40:18,872 epoch 2 - iter 1602/1786 - loss 0.11957108 - time (sec): 80.93 - samples/sec: 2773.10 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 13:40:27,656 epoch 2 - iter 1780/1786 - loss 0.11971143 - time (sec): 89.71 - samples/sec: 2765.64 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 13:40:27,939 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 13:40:27,940 EPOCH 2 done: loss 0.1195 - lr: 0.000027
101
+ 2023-10-17 13:40:32,630 DEV : loss 0.10125791281461716 - f1-score (micro avg) 0.8144
102
+ 2023-10-17 13:40:32,647 saving best model
103
+ 2023-10-17 13:40:33,095 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 13:40:41,901 epoch 3 - iter 178/1786 - loss 0.07418424 - time (sec): 8.80 - samples/sec: 2788.17 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 13:40:50,945 epoch 3 - iter 356/1786 - loss 0.07570841 - time (sec): 17.84 - samples/sec: 2768.58 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 13:40:59,866 epoch 3 - iter 534/1786 - loss 0.07399212 - time (sec): 26.77 - samples/sec: 2788.93 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 13:41:08,915 epoch 3 - iter 712/1786 - loss 0.07427751 - time (sec): 35.82 - samples/sec: 2747.68 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 13:41:17,929 epoch 3 - iter 890/1786 - loss 0.07471144 - time (sec): 44.83 - samples/sec: 2766.71 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 13:41:26,655 epoch 3 - iter 1068/1786 - loss 0.07885766 - time (sec): 53.56 - samples/sec: 2762.94 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 13:41:35,429 epoch 3 - iter 1246/1786 - loss 0.08022104 - time (sec): 62.33 - samples/sec: 2764.62 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 13:41:44,429 epoch 3 - iter 1424/1786 - loss 0.07990684 - time (sec): 71.33 - samples/sec: 2780.82 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 13:41:53,237 epoch 3 - iter 1602/1786 - loss 0.08236359 - time (sec): 80.14 - samples/sec: 2781.43 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 13:42:02,129 epoch 3 - iter 1780/1786 - loss 0.08175112 - time (sec): 89.03 - samples/sec: 2781.51 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 13:42:02,455 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 13:42:02,456 EPOCH 3 done: loss 0.0818 - lr: 0.000023
116
+ 2023-10-17 13:42:06,658 DEV : loss 0.13423609733581543 - f1-score (micro avg) 0.7967
117
+ 2023-10-17 13:42:06,675 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 13:42:15,751 epoch 4 - iter 178/1786 - loss 0.05237935 - time (sec): 9.07 - samples/sec: 2848.98 - lr: 0.000023 - momentum: 0.000000
119
+ 2023-10-17 13:42:24,779 epoch 4 - iter 356/1786 - loss 0.05659288 - time (sec): 18.10 - samples/sec: 2788.78 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 13:42:33,850 epoch 4 - iter 534/1786 - loss 0.05742020 - time (sec): 27.17 - samples/sec: 2798.72 - lr: 0.000022 - momentum: 0.000000
121
+ 2023-10-17 13:42:43,043 epoch 4 - iter 712/1786 - loss 0.05968286 - time (sec): 36.37 - samples/sec: 2804.23 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 13:42:51,955 epoch 4 - iter 890/1786 - loss 0.06046189 - time (sec): 45.28 - samples/sec: 2778.04 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 13:43:01,044 epoch 4 - iter 1068/1786 - loss 0.05955440 - time (sec): 54.37 - samples/sec: 2780.27 - lr: 0.000021 - momentum: 0.000000
124
+ 2023-10-17 13:43:10,485 epoch 4 - iter 1246/1786 - loss 0.06002902 - time (sec): 63.81 - samples/sec: 2761.07 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 13:43:19,111 epoch 4 - iter 1424/1786 - loss 0.05900004 - time (sec): 72.43 - samples/sec: 2757.94 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 13:43:27,980 epoch 4 - iter 1602/1786 - loss 0.05891783 - time (sec): 81.30 - samples/sec: 2755.96 - lr: 0.000020 - momentum: 0.000000
127
+ 2023-10-17 13:43:36,698 epoch 4 - iter 1780/1786 - loss 0.05878177 - time (sec): 90.02 - samples/sec: 2752.92 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 13:43:37,002 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 13:43:37,002 EPOCH 4 done: loss 0.0589 - lr: 0.000020
130
+ 2023-10-17 13:43:41,153 DEV : loss 0.16494163870811462 - f1-score (micro avg) 0.8072
131
+ 2023-10-17 13:43:41,170 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-17 13:43:50,053 epoch 5 - iter 178/1786 - loss 0.03097896 - time (sec): 8.88 - samples/sec: 2793.19 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-17 13:43:59,171 epoch 5 - iter 356/1786 - loss 0.04055098 - time (sec): 18.00 - samples/sec: 2843.10 - lr: 0.000019 - momentum: 0.000000
134
+ 2023-10-17 13:44:08,165 epoch 5 - iter 534/1786 - loss 0.04153062 - time (sec): 26.99 - samples/sec: 2845.05 - lr: 0.000019 - momentum: 0.000000
135
+ 2023-10-17 13:44:17,143 epoch 5 - iter 712/1786 - loss 0.04112747 - time (sec): 35.97 - samples/sec: 2818.48 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 13:44:25,980 epoch 5 - iter 890/1786 - loss 0.04124960 - time (sec): 44.81 - samples/sec: 2781.91 - lr: 0.000018 - momentum: 0.000000
137
+ 2023-10-17 13:44:34,928 epoch 5 - iter 1068/1786 - loss 0.04175525 - time (sec): 53.76 - samples/sec: 2789.27 - lr: 0.000018 - momentum: 0.000000
138
+ 2023-10-17 13:44:43,746 epoch 5 - iter 1246/1786 - loss 0.04113562 - time (sec): 62.57 - samples/sec: 2782.73 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 13:44:52,508 epoch 5 - iter 1424/1786 - loss 0.04207320 - time (sec): 71.34 - samples/sec: 2788.00 - lr: 0.000017 - momentum: 0.000000
140
+ 2023-10-17 13:45:01,198 epoch 5 - iter 1602/1786 - loss 0.04173442 - time (sec): 80.03 - samples/sec: 2765.43 - lr: 0.000017 - momentum: 0.000000
141
+ 2023-10-17 13:45:10,322 epoch 5 - iter 1780/1786 - loss 0.04286181 - time (sec): 89.15 - samples/sec: 2780.12 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 13:45:10,633 ----------------------------------------------------------------------------------------------------
143
+ 2023-10-17 13:45:10,633 EPOCH 5 done: loss 0.0427 - lr: 0.000017
144
+ 2023-10-17 13:45:15,433 DEV : loss 0.1587299257516861 - f1-score (micro avg) 0.8108
145
+ 2023-10-17 13:45:15,450 ----------------------------------------------------------------------------------------------------
146
+ 2023-10-17 13:45:24,076 epoch 6 - iter 178/1786 - loss 0.03579067 - time (sec): 8.62 - samples/sec: 2905.87 - lr: 0.000016 - momentum: 0.000000
147
+ 2023-10-17 13:45:33,127 epoch 6 - iter 356/1786 - loss 0.02738996 - time (sec): 17.68 - samples/sec: 2901.45 - lr: 0.000016 - momentum: 0.000000
148
+ 2023-10-17 13:45:42,026 epoch 6 - iter 534/1786 - loss 0.02902765 - time (sec): 26.57 - samples/sec: 2826.40 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-17 13:45:51,006 epoch 6 - iter 712/1786 - loss 0.02908652 - time (sec): 35.56 - samples/sec: 2805.29 - lr: 0.000015 - momentum: 0.000000
150
+ 2023-10-17 13:45:59,947 epoch 6 - iter 890/1786 - loss 0.02990502 - time (sec): 44.50 - samples/sec: 2780.47 - lr: 0.000015 - momentum: 0.000000
151
+ 2023-10-17 13:46:08,899 epoch 6 - iter 1068/1786 - loss 0.02956431 - time (sec): 53.45 - samples/sec: 2767.16 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-17 13:46:17,597 epoch 6 - iter 1246/1786 - loss 0.03095708 - time (sec): 62.15 - samples/sec: 2779.68 - lr: 0.000014 - momentum: 0.000000
153
+ 2023-10-17 13:46:26,112 epoch 6 - iter 1424/1786 - loss 0.03171714 - time (sec): 70.66 - samples/sec: 2810.15 - lr: 0.000014 - momentum: 0.000000
154
+ 2023-10-17 13:46:34,499 epoch 6 - iter 1602/1786 - loss 0.03200171 - time (sec): 79.05 - samples/sec: 2818.22 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-17 13:46:42,973 epoch 6 - iter 1780/1786 - loss 0.03147805 - time (sec): 87.52 - samples/sec: 2831.86 - lr: 0.000013 - momentum: 0.000000
156
+ 2023-10-17 13:46:43,268 ----------------------------------------------------------------------------------------------------
157
+ 2023-10-17 13:46:43,269 EPOCH 6 done: loss 0.0315 - lr: 0.000013
158
+ 2023-10-17 13:46:47,415 DEV : loss 0.1810143142938614 - f1-score (micro avg) 0.8208
159
+ 2023-10-17 13:46:47,432 saving best model
160
+ 2023-10-17 13:46:47,883 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 13:46:57,010 epoch 7 - iter 178/1786 - loss 0.02252211 - time (sec): 9.12 - samples/sec: 2815.32 - lr: 0.000013 - momentum: 0.000000
162
+ 2023-10-17 13:47:06,046 epoch 7 - iter 356/1786 - loss 0.02178416 - time (sec): 18.16 - samples/sec: 2798.52 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-17 13:47:14,788 epoch 7 - iter 534/1786 - loss 0.02234988 - time (sec): 26.90 - samples/sec: 2783.93 - lr: 0.000012 - momentum: 0.000000
164
+ 2023-10-17 13:47:23,746 epoch 7 - iter 712/1786 - loss 0.02071319 - time (sec): 35.86 - samples/sec: 2801.18 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-17 13:47:32,861 epoch 7 - iter 890/1786 - loss 0.02322136 - time (sec): 44.97 - samples/sec: 2795.86 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-17 13:47:41,641 epoch 7 - iter 1068/1786 - loss 0.02464583 - time (sec): 53.75 - samples/sec: 2781.24 - lr: 0.000011 - momentum: 0.000000
167
+ 2023-10-17 13:47:50,621 epoch 7 - iter 1246/1786 - loss 0.02371729 - time (sec): 62.73 - samples/sec: 2796.27 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-17 13:47:59,715 epoch 7 - iter 1424/1786 - loss 0.02337745 - time (sec): 71.83 - samples/sec: 2785.17 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-17 13:48:08,615 epoch 7 - iter 1602/1786 - loss 0.02344878 - time (sec): 80.73 - samples/sec: 2757.92 - lr: 0.000010 - momentum: 0.000000
170
+ 2023-10-17 13:48:17,579 epoch 7 - iter 1780/1786 - loss 0.02410208 - time (sec): 89.69 - samples/sec: 2758.99 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-17 13:48:17,888 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 13:48:17,889 EPOCH 7 done: loss 0.0240 - lr: 0.000010
173
+ 2023-10-17 13:48:22,557 DEV : loss 0.1769118458032608 - f1-score (micro avg) 0.8345
174
+ 2023-10-17 13:48:22,574 saving best model
175
+ 2023-10-17 13:48:23,039 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 13:48:31,997 epoch 8 - iter 178/1786 - loss 0.01978668 - time (sec): 8.95 - samples/sec: 2710.28 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-17 13:48:40,923 epoch 8 - iter 356/1786 - loss 0.01795202 - time (sec): 17.88 - samples/sec: 2730.53 - lr: 0.000009 - momentum: 0.000000
178
+ 2023-10-17 13:48:49,838 epoch 8 - iter 534/1786 - loss 0.01682048 - time (sec): 26.80 - samples/sec: 2732.43 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-17 13:48:58,809 epoch 8 - iter 712/1786 - loss 0.01706732 - time (sec): 35.77 - samples/sec: 2726.67 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 13:49:07,606 epoch 8 - iter 890/1786 - loss 0.01709347 - time (sec): 44.56 - samples/sec: 2745.57 - lr: 0.000008 - momentum: 0.000000
181
+ 2023-10-17 13:49:16,512 epoch 8 - iter 1068/1786 - loss 0.01748776 - time (sec): 53.47 - samples/sec: 2735.99 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-17 13:49:25,400 epoch 8 - iter 1246/1786 - loss 0.01730659 - time (sec): 62.36 - samples/sec: 2751.55 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 13:49:34,658 epoch 8 - iter 1424/1786 - loss 0.01760562 - time (sec): 71.62 - samples/sec: 2770.82 - lr: 0.000007 - momentum: 0.000000
184
+ 2023-10-17 13:49:43,429 epoch 8 - iter 1602/1786 - loss 0.01761039 - time (sec): 80.39 - samples/sec: 2768.58 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-17 13:49:52,395 epoch 8 - iter 1780/1786 - loss 0.01754475 - time (sec): 89.35 - samples/sec: 2776.92 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 13:49:52,677 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 13:49:52,677 EPOCH 8 done: loss 0.0177 - lr: 0.000007
188
+ 2023-10-17 13:49:56,898 DEV : loss 0.196747824549675 - f1-score (micro avg) 0.8165
189
+ 2023-10-17 13:49:56,915 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 13:50:06,356 epoch 9 - iter 178/1786 - loss 0.01085864 - time (sec): 9.44 - samples/sec: 2704.82 - lr: 0.000006 - momentum: 0.000000
191
+ 2023-10-17 13:50:15,176 epoch 9 - iter 356/1786 - loss 0.01281656 - time (sec): 18.26 - samples/sec: 2792.68 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-17 13:50:24,105 epoch 9 - iter 534/1786 - loss 0.01358075 - time (sec): 27.19 - samples/sec: 2767.01 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 13:50:33,067 epoch 9 - iter 712/1786 - loss 0.01366083 - time (sec): 36.15 - samples/sec: 2736.04 - lr: 0.000005 - momentum: 0.000000
194
+ 2023-10-17 13:50:41,994 epoch 9 - iter 890/1786 - loss 0.01227376 - time (sec): 45.08 - samples/sec: 2741.15 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-17 13:50:50,756 epoch 9 - iter 1068/1786 - loss 0.01291585 - time (sec): 53.84 - samples/sec: 2748.82 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 13:51:00,405 epoch 9 - iter 1246/1786 - loss 0.01335982 - time (sec): 63.49 - samples/sec: 2696.12 - lr: 0.000004 - momentum: 0.000000
197
+ 2023-10-17 13:51:09,305 epoch 9 - iter 1424/1786 - loss 0.01331987 - time (sec): 72.39 - samples/sec: 2709.60 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-17 13:51:18,256 epoch 9 - iter 1602/1786 - loss 0.01337922 - time (sec): 81.34 - samples/sec: 2723.43 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 13:51:27,315 epoch 9 - iter 1780/1786 - loss 0.01258706 - time (sec): 90.40 - samples/sec: 2745.83 - lr: 0.000003 - momentum: 0.000000
200
+ 2023-10-17 13:51:27,587 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-17 13:51:27,587 EPOCH 9 done: loss 0.0126 - lr: 0.000003
202
+ 2023-10-17 13:51:31,855 DEV : loss 0.20930074155330658 - f1-score (micro avg) 0.8232
203
+ 2023-10-17 13:51:31,872 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 13:51:40,887 epoch 10 - iter 178/1786 - loss 0.00609129 - time (sec): 9.01 - samples/sec: 2824.04 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-17 13:51:50,023 epoch 10 - iter 356/1786 - loss 0.00715017 - time (sec): 18.15 - samples/sec: 2816.42 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-17 13:51:58,978 epoch 10 - iter 534/1786 - loss 0.00851154 - time (sec): 27.10 - samples/sec: 2809.81 - lr: 0.000002 - momentum: 0.000000
207
+ 2023-10-17 13:52:07,808 epoch 10 - iter 712/1786 - loss 0.00825487 - time (sec): 35.93 - samples/sec: 2767.77 - lr: 0.000002 - momentum: 0.000000
208
+ 2023-10-17 13:52:17,310 epoch 10 - iter 890/1786 - loss 0.00855273 - time (sec): 45.44 - samples/sec: 2755.18 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 13:52:26,532 epoch 10 - iter 1068/1786 - loss 0.00838603 - time (sec): 54.66 - samples/sec: 2739.98 - lr: 0.000001 - momentum: 0.000000
210
+ 2023-10-17 13:52:35,578 epoch 10 - iter 1246/1786 - loss 0.00840932 - time (sec): 63.70 - samples/sec: 2727.41 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-17 13:52:44,438 epoch 10 - iter 1424/1786 - loss 0.00809426 - time (sec): 72.56 - samples/sec: 2745.31 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 13:52:53,121 epoch 10 - iter 1602/1786 - loss 0.00816111 - time (sec): 81.25 - samples/sec: 2749.63 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-17 13:53:01,991 epoch 10 - iter 1780/1786 - loss 0.00858460 - time (sec): 90.12 - samples/sec: 2750.90 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-17 13:53:02,263 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-17 13:53:02,263 EPOCH 10 done: loss 0.0086 - lr: 0.000000
216
+ 2023-10-17 13:53:06,932 DEV : loss 0.20266954600811005 - f1-score (micro avg) 0.8289
217
+ 2023-10-17 13:53:07,291 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 13:53:07,292 Loading model from best epoch ...
219
+ 2023-10-17 13:53:08,632 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
220
+ 2023-10-17 13:53:18,265
221
+ Results:
222
+ - F-score (micro) 0.705
223
+ - F-score (macro) 0.6364
224
+ - Accuracy 0.5623
225
+
226
+ By class:
227
+ precision recall f1-score support
228
+
229
+ LOC 0.7285 0.6959 0.7118 1095
230
+ PER 0.7944 0.7787 0.7864 1012
231
+ ORG 0.4503 0.5714 0.5037 357
232
+ HumanProd 0.4237 0.7576 0.5435 33
233
+
234
+ micro avg 0.6976 0.7125 0.7050 2497
235
+ macro avg 0.5992 0.7009 0.6364 2497
236
+ weighted avg 0.7114 0.7125 0.7101 2497
237
+
238
+ 2023-10-17 13:53:18,265 ----------------------------------------------------------------------------------------------------