Hugging Face's logo

stefan-it
/
hmbench-icdar-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
a903ec3
·
1 Parent(s): 9ea04f0

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.1697541700.bce904bcef33.2023.3 +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:b12f9af4e50d19bc655e5dda57475e7d60886ce01450b1a4fb5b36bdf1377ab1
3
+ size 440941957
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 11:22:41 0.0000 0.3674 0.0927 0.7095 0.7489 0.7287 0.5916
3
+ 2 11:23:45 0.0000 0.1053 0.0796 0.7224 0.7771 0.7488 0.6167
4
+ 3 11:24:48 0.0000 0.0761 0.0918 0.7558 0.7421 0.7489 0.6137
5
+ 4 11:25:51 0.0000 0.0544 0.1407 0.7265 0.7964 0.7598 0.6320
6
+ 5 11:26:55 0.0000 0.0429 0.1663 0.7622 0.7941 0.7778 0.6555
7
+ 6 11:27:59 0.0000 0.0312 0.1633 0.7467 0.7704 0.7584 0.6271
8
+ 7 11:29:02 0.0000 0.0219 0.1899 0.7468 0.7873 0.7665 0.6391
9
+ 8 11:30:05 0.0000 0.0156 0.2174 0.7521 0.7964 0.7736 0.6477
10
+ 9 11:31:09 0.0000 0.0107 0.2290 0.7342 0.7873 0.7598 0.6322
11
+ 10 11:32:15 0.0000 0.0080 0.2330 0.7436 0.7873 0.7648 0.6356
runs/events.out.tfevents.1697541700.bce904bcef33.2023.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148cb5ad17a0b28c04dce410539ff44c81ae6fb4cd95707e345f3610005de453
3
+ size 556612
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 11:21:40,050 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 11:21:40,051 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=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 11:21:40,051 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 11:21:40,051 MultiCorpus: 7936 train + 992 dev + 992 test sentences
48
+ - NER_ICDAR_EUROPEANA Corpus: 7936 train + 992 dev + 992 test sentences - /root/.flair/datasets/ner_icdar_europeana/fr
49
+ 2023-10-17 11:21:40,051 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 11:21:40,052 Train: 7936 sentences
51
+ 2023-10-17 11:21:40,052 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 11:21:40,052 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 11:21:40,052 Training Params:
54
+ 2023-10-17 11:21:40,052 - learning_rate: "5e-05"
55
+ 2023-10-17 11:21:40,052 - mini_batch_size: "8"
56
+ 2023-10-17 11:21:40,052 - max_epochs: "10"
57
+ 2023-10-17 11:21:40,052 - shuffle: "True"
58
+ 2023-10-17 11:21:40,052 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 11:21:40,052 Plugins:
60
+ 2023-10-17 11:21:40,052 - TensorboardLogger
61
+ 2023-10-17 11:21:40,052 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 11:21:40,052 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 11:21:40,052 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 11:21:40,052 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 11:21:40,052 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 11:21:40,052 Computation:
67
+ 2023-10-17 11:21:40,052 - compute on device: cuda:0
68
+ 2023-10-17 11:21:40,052 - embedding storage: none
69
+ 2023-10-17 11:21:40,052 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 11:21:40,052 Model training base path: "hmbench-icdar/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
71
+ 2023-10-17 11:21:40,052 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 11:21:40,052 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 11:21:40,052 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 11:21:45,743 epoch 1 - iter 99/992 - loss 2.00752470 - time (sec): 5.69 - samples/sec: 2843.79 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 11:21:51,606 epoch 1 - iter 198/992 - loss 1.16110239 - time (sec): 11.55 - samples/sec: 2877.04 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 11:21:57,730 epoch 1 - iter 297/992 - loss 0.86009292 - time (sec): 17.68 - samples/sec: 2807.08 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 11:22:03,344 epoch 1 - iter 396/992 - loss 0.70056867 - time (sec): 23.29 - samples/sec: 2807.69 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 11:22:09,204 epoch 1 - iter 495/992 - loss 0.59290102 - time (sec): 29.15 - samples/sec: 2807.40 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 11:22:15,182 epoch 1 - iter 594/992 - loss 0.51678549 - time (sec): 35.13 - samples/sec: 2808.16 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 11:22:20,959 epoch 1 - iter 693/992 - loss 0.46411643 - time (sec): 40.91 - samples/sec: 2806.30 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 11:22:26,973 epoch 1 - iter 792/992 - loss 0.42507693 - time (sec): 46.92 - samples/sec: 2798.32 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 11:22:32,888 epoch 1 - iter 891/992 - loss 0.39307524 - time (sec): 52.83 - samples/sec: 2786.92 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 11:22:38,704 epoch 1 - iter 990/992 - loss 0.36782772 - time (sec): 58.65 - samples/sec: 2790.32 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 11:22:38,823 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 11:22:38,823 EPOCH 1 done: loss 0.3674 - lr: 0.000050
86
+ 2023-10-17 11:22:41,920 DEV : loss 0.09267440438270569 - f1-score (micro avg) 0.7287
87
+ 2023-10-17 11:22:41,943 saving best model
88
+ 2023-10-17 11:22:42,310 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 11:22:48,213 epoch 2 - iter 99/992 - loss 0.11596098 - time (sec): 5.90 - samples/sec: 2864.40 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 11:22:54,188 epoch 2 - iter 198/992 - loss 0.11376424 - time (sec): 11.88 - samples/sec: 2788.50 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 11:23:00,295 epoch 2 - iter 297/992 - loss 0.11209663 - time (sec): 17.98 - samples/sec: 2759.41 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 11:23:06,316 epoch 2 - iter 396/992 - loss 0.11161254 - time (sec): 24.00 - samples/sec: 2767.95 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 11:23:12,200 epoch 2 - iter 495/992 - loss 0.10962236 - time (sec): 29.89 - samples/sec: 2762.55 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 11:23:18,445 epoch 2 - iter 594/992 - loss 0.10658082 - time (sec): 36.13 - samples/sec: 2749.28 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 11:23:24,452 epoch 2 - iter 693/992 - loss 0.10590489 - time (sec): 42.14 - samples/sec: 2752.00 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 11:23:30,157 epoch 2 - iter 792/992 - loss 0.10554854 - time (sec): 47.85 - samples/sec: 2752.16 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 11:23:35,744 epoch 2 - iter 891/992 - loss 0.10485385 - time (sec): 53.43 - samples/sec: 2756.15 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 11:23:41,651 epoch 2 - iter 990/992 - loss 0.10541228 - time (sec): 59.34 - samples/sec: 2757.92 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 11:23:41,762 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 11:23:41,763 EPOCH 2 done: loss 0.1053 - lr: 0.000044
101
+ 2023-10-17 11:23:45,546 DEV : loss 0.07957779616117477 - f1-score (micro avg) 0.7488
102
+ 2023-10-17 11:23:45,567 saving best model
103
+ 2023-10-17 11:23:46,062 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 11:23:51,998 epoch 3 - iter 99/992 - loss 0.07399883 - time (sec): 5.93 - samples/sec: 2792.44 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 11:23:57,894 epoch 3 - iter 198/992 - loss 0.07782338 - time (sec): 11.83 - samples/sec: 2777.78 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 11:24:03,807 epoch 3 - iter 297/992 - loss 0.07965927 - time (sec): 17.74 - samples/sec: 2795.99 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 11:24:09,711 epoch 3 - iter 396/992 - loss 0.07595699 - time (sec): 23.65 - samples/sec: 2808.81 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 11:24:15,396 epoch 3 - iter 495/992 - loss 0.07484677 - time (sec): 29.33 - samples/sec: 2819.60 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 11:24:21,231 epoch 3 - iter 594/992 - loss 0.07449912 - time (sec): 35.17 - samples/sec: 2800.02 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 11:24:27,126 epoch 3 - iter 693/992 - loss 0.07526423 - time (sec): 41.06 - samples/sec: 2795.76 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 11:24:33,067 epoch 3 - iter 792/992 - loss 0.07578093 - time (sec): 47.00 - samples/sec: 2790.69 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 11:24:39,214 epoch 3 - iter 891/992 - loss 0.07554286 - time (sec): 53.15 - samples/sec: 2782.60 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 11:24:45,213 epoch 3 - iter 990/992 - loss 0.07580919 - time (sec): 59.15 - samples/sec: 2766.04 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 11:24:45,340 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 11:24:45,340 EPOCH 3 done: loss 0.0761 - lr: 0.000039
116
+ 2023-10-17 11:24:48,746 DEV : loss 0.09182097762823105 - f1-score (micro avg) 0.7489
117
+ 2023-10-17 11:24:48,769 saving best model
118
+ 2023-10-17 11:24:49,263 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 11:24:55,170 epoch 4 - iter 99/992 - loss 0.05468852 - time (sec): 5.90 - samples/sec: 2780.10 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 11:25:01,487 epoch 4 - iter 198/992 - loss 0.05293064 - time (sec): 12.22 - samples/sec: 2794.12 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 11:25:07,607 epoch 4 - iter 297/992 - loss 0.05364317 - time (sec): 18.34 - samples/sec: 2776.94 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 11:25:13,550 epoch 4 - iter 396/992 - loss 0.05402008 - time (sec): 24.28 - samples/sec: 2777.04 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 11:25:19,296 epoch 4 - iter 495/992 - loss 0.05392577 - time (sec): 30.03 - samples/sec: 2786.92 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 11:25:24,951 epoch 4 - iter 594/992 - loss 0.05443890 - time (sec): 35.69 - samples/sec: 2782.91 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 11:25:30,557 epoch 4 - iter 693/992 - loss 0.05350202 - time (sec): 41.29 - samples/sec: 2783.23 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 11:25:36,431 epoch 4 - iter 792/992 - loss 0.05357310 - time (sec): 47.17 - samples/sec: 2777.82 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 11:25:42,388 epoch 4 - iter 891/992 - loss 0.05445889 - time (sec): 53.12 - samples/sec: 2780.60 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 11:25:48,076 epoch 4 - iter 990/992 - loss 0.05431231 - time (sec): 58.81 - samples/sec: 2784.57 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 11:25:48,189 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 11:25:48,190 EPOCH 4 done: loss 0.0544 - lr: 0.000033
131
+ 2023-10-17 11:25:51,644 DEV : loss 0.1407020390033722 - f1-score (micro avg) 0.7598
132
+ 2023-10-17 11:25:51,666 saving best model
133
+ 2023-10-17 11:25:52,143 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 11:25:58,088 epoch 5 - iter 99/992 - loss 0.04345102 - time (sec): 5.94 - samples/sec: 2737.20 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 11:26:04,229 epoch 5 - iter 198/992 - loss 0.04013191 - time (sec): 12.08 - samples/sec: 2773.50 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 11:26:10,153 epoch 5 - iter 297/992 - loss 0.04013654 - time (sec): 18.01 - samples/sec: 2788.59 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 11:26:16,359 epoch 5 - iter 396/992 - loss 0.04153776 - time (sec): 24.21 - samples/sec: 2797.16 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 11:26:22,273 epoch 5 - iter 495/992 - loss 0.04178549 - time (sec): 30.13 - samples/sec: 2793.12 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 11:26:27,904 epoch 5 - iter 594/992 - loss 0.04313324 - time (sec): 35.76 - samples/sec: 2796.33 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 11:26:34,115 epoch 5 - iter 693/992 - loss 0.04394145 - time (sec): 41.97 - samples/sec: 2773.35 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 11:26:40,034 epoch 5 - iter 792/992 - loss 0.04428695 - time (sec): 47.89 - samples/sec: 2761.16 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 11:26:45,880 epoch 5 - iter 891/992 - loss 0.04347387 - time (sec): 53.73 - samples/sec: 2758.23 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 11:26:51,571 epoch 5 - iter 990/992 - loss 0.04302101 - time (sec): 59.42 - samples/sec: 2753.59 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 11:26:51,696 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 11:26:51,696 EPOCH 5 done: loss 0.0429 - lr: 0.000028
146
+ 2023-10-17 11:26:55,092 DEV : loss 0.1663055419921875 - f1-score (micro avg) 0.7778
147
+ 2023-10-17 11:26:55,113 saving best model
148
+ 2023-10-17 11:26:55,582 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 11:27:01,664 epoch 6 - iter 99/992 - loss 0.03345702 - time (sec): 6.08 - samples/sec: 2705.79 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 11:27:07,592 epoch 6 - iter 198/992 - loss 0.03258281 - time (sec): 12.01 - samples/sec: 2720.35 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 11:27:13,856 epoch 6 - iter 297/992 - loss 0.03031919 - time (sec): 18.27 - samples/sec: 2750.49 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 11:27:19,774 epoch 6 - iter 396/992 - loss 0.03089649 - time (sec): 24.19 - samples/sec: 2754.91 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 11:27:25,776 epoch 6 - iter 495/992 - loss 0.02999409 - time (sec): 30.19 - samples/sec: 2762.61 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 11:27:31,638 epoch 6 - iter 594/992 - loss 0.03070964 - time (sec): 36.05 - samples/sec: 2765.56 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 11:27:37,231 epoch 6 - iter 693/992 - loss 0.03109293 - time (sec): 41.65 - samples/sec: 2769.11 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 11:27:42,876 epoch 6 - iter 792/992 - loss 0.03056361 - time (sec): 47.29 - samples/sec: 2773.64 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 11:27:48,608 epoch 6 - iter 891/992 - loss 0.03117794 - time (sec): 53.02 - samples/sec: 2778.13 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 11:27:54,391 epoch 6 - iter 990/992 - loss 0.03126223 - time (sec): 58.80 - samples/sec: 2781.63 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 11:27:54,511 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 11:27:54,511 EPOCH 6 done: loss 0.0312 - lr: 0.000022
161
+ 2023-10-17 11:27:59,227 DEV : loss 0.1633480340242386 - f1-score (micro avg) 0.7584
162
+ 2023-10-17 11:27:59,263 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-17 11:28:05,215 epoch 7 - iter 99/992 - loss 0.01789778 - time (sec): 5.95 - samples/sec: 2739.15 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-17 11:28:11,218 epoch 7 - iter 198/992 - loss 0.01724841 - time (sec): 11.95 - samples/sec: 2745.60 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 11:28:17,621 epoch 7 - iter 297/992 - loss 0.01961745 - time (sec): 18.36 - samples/sec: 2700.02 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 11:28:23,473 epoch 7 - iter 396/992 - loss 0.01992616 - time (sec): 24.21 - samples/sec: 2712.23 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-17 11:28:29,388 epoch 7 - iter 495/992 - loss 0.02094923 - time (sec): 30.12 - samples/sec: 2720.79 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-17 11:28:35,340 epoch 7 - iter 594/992 - loss 0.01985550 - time (sec): 36.08 - samples/sec: 2728.57 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 11:28:41,393 epoch 7 - iter 693/992 - loss 0.02067558 - time (sec): 42.13 - samples/sec: 2724.08 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 11:28:47,206 epoch 7 - iter 792/992 - loss 0.02093216 - time (sec): 47.94 - samples/sec: 2718.22 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 11:28:53,073 epoch 7 - iter 891/992 - loss 0.02197206 - time (sec): 53.81 - samples/sec: 2739.75 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 11:28:58,840 epoch 7 - iter 990/992 - loss 0.02197388 - time (sec): 59.58 - samples/sec: 2747.71 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 11:28:58,961 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-17 11:28:58,961 EPOCH 7 done: loss 0.0219 - lr: 0.000017
175
+ 2023-10-17 11:29:02,566 DEV : loss 0.1898750215768814 - f1-score (micro avg) 0.7665
176
+ 2023-10-17 11:29:02,594 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 11:29:08,347 epoch 8 - iter 99/992 - loss 0.00858606 - time (sec): 5.75 - samples/sec: 2846.11 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 11:29:14,064 epoch 8 - iter 198/992 - loss 0.01171469 - time (sec): 11.47 - samples/sec: 2824.80 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 11:29:20,281 epoch 8 - iter 297/992 - loss 0.01211733 - time (sec): 17.69 - samples/sec: 2828.38 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-17 11:29:26,152 epoch 8 - iter 396/992 - loss 0.01169790 - time (sec): 23.56 - samples/sec: 2805.84 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 11:29:32,084 epoch 8 - iter 495/992 - loss 0.01211186 - time (sec): 29.49 - samples/sec: 2821.28 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 11:29:38,180 epoch 8 - iter 594/992 - loss 0.01413340 - time (sec): 35.58 - samples/sec: 2807.68 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 11:29:43,898 epoch 8 - iter 693/992 - loss 0.01436134 - time (sec): 41.30 - samples/sec: 2798.96 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 11:29:49,496 epoch 8 - iter 792/992 - loss 0.01496934 - time (sec): 46.90 - samples/sec: 2784.54 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 11:29:55,299 epoch 8 - iter 891/992 - loss 0.01507510 - time (sec): 52.70 - samples/sec: 2793.17 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 11:30:01,345 epoch 8 - iter 990/992 - loss 0.01559016 - time (sec): 58.75 - samples/sec: 2785.33 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-17 11:30:01,478 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 11:30:01,478 EPOCH 8 done: loss 0.0156 - lr: 0.000011
189
+ 2023-10-17 11:30:05,096 DEV : loss 0.21736501157283783 - f1-score (micro avg) 0.7736
190
+ 2023-10-17 11:30:05,127 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-17 11:30:11,217 epoch 9 - iter 99/992 - loss 0.01189736 - time (sec): 6.09 - samples/sec: 2601.72 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-17 11:30:17,689 epoch 9 - iter 198/992 - loss 0.01120784 - time (sec): 12.56 - samples/sec: 2643.77 - lr: 0.000010 - momentum: 0.000000
193
+ 2023-10-17 11:30:23,899 epoch 9 - iter 297/992 - loss 0.01112974 - time (sec): 18.77 - samples/sec: 2685.89 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-17 11:30:29,897 epoch 9 - iter 396/992 - loss 0.00969053 - time (sec): 24.77 - samples/sec: 2692.32 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-17 11:30:35,679 epoch 9 - iter 495/992 - loss 0.00960030 - time (sec): 30.55 - samples/sec: 2702.51 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 11:30:41,692 epoch 9 - iter 594/992 - loss 0.00957094 - time (sec): 36.56 - samples/sec: 2700.06 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 11:30:47,567 epoch 9 - iter 693/992 - loss 0.00941102 - time (sec): 42.44 - samples/sec: 2704.48 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 11:30:53,670 epoch 9 - iter 792/992 - loss 0.01010825 - time (sec): 48.54 - samples/sec: 2709.90 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 11:30:59,631 epoch 9 - iter 891/992 - loss 0.01035941 - time (sec): 54.50 - samples/sec: 2710.26 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 11:31:05,562 epoch 9 - iter 990/992 - loss 0.01067263 - time (sec): 60.43 - samples/sec: 2708.56 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 11:31:05,685 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-17 11:31:05,685 EPOCH 9 done: loss 0.0107 - lr: 0.000006
203
+ 2023-10-17 11:31:09,296 DEV : loss 0.2289990335702896 - f1-score (micro avg) 0.7598
204
+ 2023-10-17 11:31:09,320 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-17 11:31:15,610 epoch 10 - iter 99/992 - loss 0.00433310 - time (sec): 6.29 - samples/sec: 2625.70 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-17 11:31:21,873 epoch 10 - iter 198/992 - loss 0.00533994 - time (sec): 12.55 - samples/sec: 2561.60 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 11:31:28,202 epoch 10 - iter 297/992 - loss 0.00637622 - time (sec): 18.88 - samples/sec: 2575.30 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 11:31:34,426 epoch 10 - iter 396/992 - loss 0.00717457 - time (sec): 25.10 - samples/sec: 2581.66 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 11:31:40,384 epoch 10 - iter 495/992 - loss 0.00716627 - time (sec): 31.06 - samples/sec: 2593.97 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 11:31:46,392 epoch 10 - iter 594/992 - loss 0.00678007 - time (sec): 37.07 - samples/sec: 2628.76 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 11:31:52,420 epoch 10 - iter 693/992 - loss 0.00705269 - time (sec): 43.10 - samples/sec: 2659.76 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 11:31:58,173 epoch 10 - iter 792/992 - loss 0.00695957 - time (sec): 48.85 - samples/sec: 2683.39 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 11:32:04,222 epoch 10 - iter 891/992 - loss 0.00746367 - time (sec): 54.90 - samples/sec: 2676.79 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 11:32:10,346 epoch 10 - iter 990/992 - loss 0.00797105 - time (sec): 61.02 - samples/sec: 2682.68 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 11:32:10,450 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-17 11:32:10,450 EPOCH 10 done: loss 0.0080 - lr: 0.000000
217
+ 2023-10-17 11:32:15,038 DEV : loss 0.23297961056232452 - f1-score (micro avg) 0.7648
218
+ 2023-10-17 11:32:15,550 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 11:32:15,552 Loading model from best epoch ...
220
+ 2023-10-17 11:32:17,148 SequenceTagger predicts: Dictionary with 13 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
221
+ 2023-10-17 11:32:21,019
222
+ Results:
223
+ - F-score (micro) 0.7587
224
+ - F-score (macro) 0.6925
225
+ - Accuracy 0.6447
226
+
227
+ By class:
228
+ precision recall f1-score support
229
+
230
+ LOC 0.8560 0.7893 0.8213 655
231
+ PER 0.6335 0.7982 0.7063 223
232
+ ORG 0.5565 0.5433 0.5498 127
233
+
234
+ micro avg 0.7572 0.7602 0.7587 1005
235
+ macro avg 0.6820 0.7103 0.6925 1005
236
+ weighted avg 0.7687 0.7602 0.7615 1005
237
+
238
+ 2023-10-17 11:32:21,020 ----------------------------------------------------------------------------------------------------