Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmteams-bs8-wsFalse-e10-lr5e-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
265141b
•
1 Parent(s): 14d8b1a

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.1697547442.4aef72135bc5.1113.7 +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 sha256:3bf0d90ffa994b3c1a18897d8ff0b4f3c7974dbb7dbe5660a27f7b0fdc56291c
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 12:59:45 0.0000 0.3042 0.1024 0.4787 0.7597 0.5874 0.4224
3
+ 2 13:02:11 0.0000 0.0879 0.1295 0.5251 0.8124 0.6379 0.4778
4
+ 3 13:04:35 0.0000 0.0652 0.1395 0.5587 0.7185 0.6286 0.4655
5
+ 4 13:07:00 0.0000 0.0498 0.1887 0.5226 0.7803 0.6260 0.4630
6
+ 5 13:09:24 0.0000 0.0351 0.2784 0.5374 0.7975 0.6421 0.4817
7
+ 6 13:11:52 0.0000 0.0251 0.2776 0.5726 0.7265 0.6404 0.4774
8
+ 7 13:14:13 0.0000 0.0169 0.3382 0.5559 0.7735 0.6469 0.4877
9
+ 8 13:16:40 0.0000 0.0112 0.3760 0.5633 0.7838 0.6555 0.4942
10
+ 9 13:19:07 0.0000 0.0070 0.3953 0.5655 0.7700 0.6521 0.4927
11
+ 10 13:21:34 0.0000 0.0047 0.4053 0.5648 0.7780 0.6545 0.4956
runs/events.out.tfevents.1697547442.4aef72135bc5.1113.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dac0c80c8738932b3c121b94f5d9f3a62f0a55b55380cbf29716a9bf478b095a
3
+ size 1018100
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 12:57:22,959 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 12:57:22,960 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 12:57:22,960 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 12:57:22,961 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
48
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
49
+ 2023-10-17 12:57:22,961 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 12:57:22,961 Train: 14465 sentences
51
+ 2023-10-17 12:57:22,961 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 12:57:22,961 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 12:57:22,961 Training Params:
54
+ 2023-10-17 12:57:22,961 - learning_rate: "5e-05"
55
+ 2023-10-17 12:57:22,961 - mini_batch_size: "8"
56
+ 2023-10-17 12:57:22,961 - max_epochs: "10"
57
+ 2023-10-17 12:57:22,961 - shuffle: "True"
58
+ 2023-10-17 12:57:22,961 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 12:57:22,961 Plugins:
60
+ 2023-10-17 12:57:22,961 - TensorboardLogger
61
+ 2023-10-17 12:57:22,961 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 12:57:22,961 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 12:57:22,962 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 12:57:22,962 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 12:57:22,962 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 12:57:22,962 Computation:
67
+ 2023-10-17 12:57:22,962 - compute on device: cuda:0
68
+ 2023-10-17 12:57:22,962 - embedding storage: none
69
+ 2023-10-17 12:57:22,962 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 12:57:22,962 Model training base path: "hmbench-letemps/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 12:57:22,962 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 12:57:22,962 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 12:57:22,962 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 12:57:37,220 epoch 1 - iter 180/1809 - loss 1.84340706 - time (sec): 14.26 - samples/sec: 2648.39 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 12:57:50,903 epoch 1 - iter 360/1809 - loss 1.05150880 - time (sec): 27.94 - samples/sec: 2653.99 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 12:58:04,641 epoch 1 - iter 540/1809 - loss 0.74172731 - time (sec): 41.68 - samples/sec: 2727.46 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 12:58:17,857 epoch 1 - iter 720/1809 - loss 0.58928040 - time (sec): 54.89 - samples/sec: 2771.98 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 12:58:32,073 epoch 1 - iter 900/1809 - loss 0.49921402 - time (sec): 69.11 - samples/sec: 2758.24 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 12:58:45,617 epoch 1 - iter 1080/1809 - loss 0.43657646 - time (sec): 82.65 - samples/sec: 2755.99 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 12:58:59,176 epoch 1 - iter 1260/1809 - loss 0.38919295 - time (sec): 96.21 - samples/sec: 2764.35 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 12:59:12,317 epoch 1 - iter 1440/1809 - loss 0.35301689 - time (sec): 109.35 - samples/sec: 2791.91 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 12:59:25,395 epoch 1 - iter 1620/1809 - loss 0.32539419 - time (sec): 122.43 - samples/sec: 2797.97 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 12:59:39,241 epoch 1 - iter 1800/1809 - loss 0.30517417 - time (sec): 136.28 - samples/sec: 2775.15 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 12:59:39,970 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 12:59:39,971 EPOCH 1 done: loss 0.3042 - lr: 0.000050
86
+ 2023-10-17 12:59:45,481 DEV : loss 0.10241620242595673 - f1-score (micro avg) 0.5874
87
+ 2023-10-17 12:59:45,529 saving best model
88
+ 2023-10-17 12:59:46,074 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 13:00:00,358 epoch 2 - iter 180/1809 - loss 0.08999612 - time (sec): 14.28 - samples/sec: 2712.94 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 13:00:14,189 epoch 2 - iter 360/1809 - loss 0.08860684 - time (sec): 28.11 - samples/sec: 2740.96 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 13:00:27,501 epoch 2 - iter 540/1809 - loss 0.09064747 - time (sec): 41.43 - samples/sec: 2748.69 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 13:00:40,822 epoch 2 - iter 720/1809 - loss 0.08986173 - time (sec): 54.75 - samples/sec: 2763.03 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 13:00:55,054 epoch 2 - iter 900/1809 - loss 0.08846040 - time (sec): 68.98 - samples/sec: 2726.01 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 13:01:08,830 epoch 2 - iter 1080/1809 - loss 0.09011922 - time (sec): 82.75 - samples/sec: 2736.28 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 13:01:23,268 epoch 2 - iter 1260/1809 - loss 0.08854167 - time (sec): 97.19 - samples/sec: 2728.15 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 13:01:36,733 epoch 2 - iter 1440/1809 - loss 0.08789492 - time (sec): 110.66 - samples/sec: 2735.03 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 13:01:50,720 epoch 2 - iter 1620/1809 - loss 0.08789901 - time (sec): 124.64 - samples/sec: 2739.18 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 13:02:04,249 epoch 2 - iter 1800/1809 - loss 0.08798538 - time (sec): 138.17 - samples/sec: 2737.08 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 13:02:04,931 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 13:02:04,931 EPOCH 2 done: loss 0.0879 - lr: 0.000044
101
+ 2023-10-17 13:02:11,312 DEV : loss 0.12951047718524933 - f1-score (micro avg) 0.6379
102
+ 2023-10-17 13:02:11,354 saving best model
103
+ 2023-10-17 13:02:11,954 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 13:02:24,999 epoch 3 - iter 180/1809 - loss 0.06500996 - time (sec): 13.04 - samples/sec: 2812.60 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 13:02:38,194 epoch 3 - iter 360/1809 - loss 0.06343791 - time (sec): 26.24 - samples/sec: 2858.92 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 13:02:51,465 epoch 3 - iter 540/1809 - loss 0.06422061 - time (sec): 39.51 - samples/sec: 2860.97 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 13:03:04,781 epoch 3 - iter 720/1809 - loss 0.06581941 - time (sec): 52.83 - samples/sec: 2856.71 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 13:03:17,851 epoch 3 - iter 900/1809 - loss 0.06424567 - time (sec): 65.90 - samples/sec: 2859.91 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 13:03:30,944 epoch 3 - iter 1080/1809 - loss 0.06446192 - time (sec): 78.99 - samples/sec: 2881.71 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 13:03:45,032 epoch 3 - iter 1260/1809 - loss 0.06498763 - time (sec): 93.08 - samples/sec: 2836.00 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 13:03:59,459 epoch 3 - iter 1440/1809 - loss 0.06557827 - time (sec): 107.50 - samples/sec: 2808.10 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 13:04:13,201 epoch 3 - iter 1620/1809 - loss 0.06535863 - time (sec): 121.25 - samples/sec: 2813.72 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 13:04:27,131 epoch 3 - iter 1800/1809 - loss 0.06527467 - time (sec): 135.18 - samples/sec: 2798.04 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 13:04:27,823 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 13:04:27,824 EPOCH 3 done: loss 0.0652 - lr: 0.000039
116
+ 2023-10-17 13:04:35,091 DEV : loss 0.1395214945077896 - f1-score (micro avg) 0.6286
117
+ 2023-10-17 13:04:35,137 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 13:04:49,427 epoch 4 - iter 180/1809 - loss 0.04607623 - time (sec): 14.29 - samples/sec: 2694.03 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 13:05:02,656 epoch 4 - iter 360/1809 - loss 0.04930480 - time (sec): 27.52 - samples/sec: 2765.32 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 13:05:16,122 epoch 4 - iter 540/1809 - loss 0.04969251 - time (sec): 40.98 - samples/sec: 2809.11 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 13:05:29,916 epoch 4 - iter 720/1809 - loss 0.04875287 - time (sec): 54.78 - samples/sec: 2789.29 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 13:05:43,863 epoch 4 - iter 900/1809 - loss 0.05042701 - time (sec): 68.72 - samples/sec: 2772.42 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 13:05:57,328 epoch 4 - iter 1080/1809 - loss 0.05094849 - time (sec): 82.19 - samples/sec: 2774.64 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 13:06:10,958 epoch 4 - iter 1260/1809 - loss 0.05022295 - time (sec): 95.82 - samples/sec: 2775.40 - lr: 0.000035 - momentum: 0.000000
125
+ 2023-10-17 13:06:25,227 epoch 4 - iter 1440/1809 - loss 0.04918643 - time (sec): 110.09 - samples/sec: 2767.92 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 13:06:39,187 epoch 4 - iter 1620/1809 - loss 0.04981270 - time (sec): 124.05 - samples/sec: 2756.38 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 13:06:52,930 epoch 4 - iter 1800/1809 - loss 0.04985632 - time (sec): 137.79 - samples/sec: 2744.58 - lr: 0.000033 - momentum: 0.000000
128
+ 2023-10-17 13:06:53,562 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 13:06:53,562 EPOCH 4 done: loss 0.0498 - lr: 0.000033
130
+ 2023-10-17 13:06:59,958 DEV : loss 0.18873652815818787 - f1-score (micro avg) 0.626
131
+ 2023-10-17 13:07:00,003 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-17 13:07:13,048 epoch 5 - iter 180/1809 - loss 0.02718902 - time (sec): 13.04 - samples/sec: 2906.08 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-17 13:07:26,269 epoch 5 - iter 360/1809 - loss 0.03344726 - time (sec): 26.26 - samples/sec: 2908.88 - lr: 0.000032 - momentum: 0.000000
134
+ 2023-10-17 13:07:39,729 epoch 5 - iter 540/1809 - loss 0.03538346 - time (sec): 39.72 - samples/sec: 2867.24 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 13:07:54,013 epoch 5 - iter 720/1809 - loss 0.03597454 - time (sec): 54.01 - samples/sec: 2815.92 - lr: 0.000031 - momentum: 0.000000
136
+ 2023-10-17 13:08:08,507 epoch 5 - iter 900/1809 - loss 0.03415119 - time (sec): 68.50 - samples/sec: 2788.45 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 13:08:23,258 epoch 5 - iter 1080/1809 - loss 0.03530280 - time (sec): 83.25 - samples/sec: 2762.73 - lr: 0.000030 - momentum: 0.000000
138
+ 2023-10-17 13:08:37,149 epoch 5 - iter 1260/1809 - loss 0.03588608 - time (sec): 97.14 - samples/sec: 2742.58 - lr: 0.000029 - momentum: 0.000000
139
+ 2023-10-17 13:08:50,110 epoch 5 - iter 1440/1809 - loss 0.03547127 - time (sec): 110.10 - samples/sec: 2743.26 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 13:09:03,929 epoch 5 - iter 1620/1809 - loss 0.03474216 - time (sec): 123.92 - samples/sec: 2746.59 - lr: 0.000028 - momentum: 0.000000
141
+ 2023-10-17 13:09:17,457 epoch 5 - iter 1800/1809 - loss 0.03509614 - time (sec): 137.45 - samples/sec: 2747.44 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 13:09:18,174 ----------------------------------------------------------------------------------------------------
143
+ 2023-10-17 13:09:18,175 EPOCH 5 done: loss 0.0351 - lr: 0.000028
144
+ 2023-10-17 13:09:24,764 DEV : loss 0.27836063504219055 - f1-score (micro avg) 0.6421
145
+ 2023-10-17 13:09:24,810 saving best model
146
+ 2023-10-17 13:09:25,455 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 13:09:38,637 epoch 6 - iter 180/1809 - loss 0.01695260 - time (sec): 13.18 - samples/sec: 2838.54 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 13:09:51,844 epoch 6 - iter 360/1809 - loss 0.02022091 - time (sec): 26.39 - samples/sec: 2824.39 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 13:10:05,970 epoch 6 - iter 540/1809 - loss 0.02183610 - time (sec): 40.51 - samples/sec: 2778.30 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 13:10:19,993 epoch 6 - iter 720/1809 - loss 0.02350031 - time (sec): 54.54 - samples/sec: 2766.70 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 13:10:34,760 epoch 6 - iter 900/1809 - loss 0.02331272 - time (sec): 69.30 - samples/sec: 2735.54 - lr: 0.000025 - momentum: 0.000000
152
+ 2023-10-17 13:10:49,638 epoch 6 - iter 1080/1809 - loss 0.02398290 - time (sec): 84.18 - samples/sec: 2701.31 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 13:11:03,946 epoch 6 - iter 1260/1809 - loss 0.02353897 - time (sec): 98.49 - samples/sec: 2695.72 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 13:11:18,525 epoch 6 - iter 1440/1809 - loss 0.02441370 - time (sec): 113.07 - samples/sec: 2683.06 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 13:11:31,815 epoch 6 - iter 1620/1809 - loss 0.02434786 - time (sec): 126.36 - samples/sec: 2690.79 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 13:11:45,166 epoch 6 - iter 1800/1809 - loss 0.02504313 - time (sec): 139.71 - samples/sec: 2709.69 - lr: 0.000022 - momentum: 0.000000
157
+ 2023-10-17 13:11:45,767 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 13:11:45,768 EPOCH 6 done: loss 0.0251 - lr: 0.000022
159
+ 2023-10-17 13:11:52,868 DEV : loss 0.277566134929657 - f1-score (micro avg) 0.6404
160
+ 2023-10-17 13:11:52,914 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 13:12:05,939 epoch 7 - iter 180/1809 - loss 0.01703639 - time (sec): 13.02 - samples/sec: 2899.01 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 13:12:19,089 epoch 7 - iter 360/1809 - loss 0.01419929 - time (sec): 26.17 - samples/sec: 2873.27 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 13:12:32,766 epoch 7 - iter 540/1809 - loss 0.01520086 - time (sec): 39.85 - samples/sec: 2833.52 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 13:12:46,111 epoch 7 - iter 720/1809 - loss 0.01636940 - time (sec): 53.19 - samples/sec: 2830.28 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 13:12:59,075 epoch 7 - iter 900/1809 - loss 0.01631353 - time (sec): 66.16 - samples/sec: 2854.63 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 13:13:11,932 epoch 7 - iter 1080/1809 - loss 0.01710760 - time (sec): 79.02 - samples/sec: 2863.60 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 13:13:25,576 epoch 7 - iter 1260/1809 - loss 0.01653770 - time (sec): 92.66 - samples/sec: 2857.00 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 13:13:39,118 epoch 7 - iter 1440/1809 - loss 0.01635189 - time (sec): 106.20 - samples/sec: 2850.78 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 13:13:52,416 epoch 7 - iter 1620/1809 - loss 0.01664859 - time (sec): 119.50 - samples/sec: 2856.40 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 13:14:06,491 epoch 7 - iter 1800/1809 - loss 0.01683251 - time (sec): 133.58 - samples/sec: 2830.35 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 13:14:07,203 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 13:14:07,204 EPOCH 7 done: loss 0.0169 - lr: 0.000017
173
+ 2023-10-17 13:14:13,444 DEV : loss 0.3381885588169098 - f1-score (micro avg) 0.6469
174
+ 2023-10-17 13:14:13,488 saving best model
175
+ 2023-10-17 13:14:14,083 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 13:14:27,601 epoch 8 - iter 180/1809 - loss 0.00784746 - time (sec): 13.52 - samples/sec: 2779.74 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 13:14:41,110 epoch 8 - iter 360/1809 - loss 0.00992790 - time (sec): 27.02 - samples/sec: 2761.80 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 13:14:55,394 epoch 8 - iter 540/1809 - loss 0.01010784 - time (sec): 41.31 - samples/sec: 2720.81 - lr: 0.000015 - momentum: 0.000000
179
+ 2023-10-17 13:15:09,732 epoch 8 - iter 720/1809 - loss 0.01077941 - time (sec): 55.65 - samples/sec: 2718.87 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 13:15:24,528 epoch 8 - iter 900/1809 - loss 0.01023506 - time (sec): 70.44 - samples/sec: 2672.41 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 13:15:38,345 epoch 8 - iter 1080/1809 - loss 0.01066822 - time (sec): 84.26 - samples/sec: 2675.84 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 13:15:52,277 epoch 8 - iter 1260/1809 - loss 0.01068226 - time (sec): 98.19 - samples/sec: 2673.63 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 13:16:05,434 epoch 8 - iter 1440/1809 - loss 0.01011548 - time (sec): 111.35 - samples/sec: 2708.59 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 13:16:19,175 epoch 8 - iter 1620/1809 - loss 0.01069293 - time (sec): 125.09 - samples/sec: 2718.77 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 13:16:33,216 epoch 8 - iter 1800/1809 - loss 0.01129507 - time (sec): 139.13 - samples/sec: 2717.14 - lr: 0.000011 - momentum: 0.000000
186
+ 2023-10-17 13:16:33,918 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 13:16:33,918 EPOCH 8 done: loss 0.0112 - lr: 0.000011
188
+ 2023-10-17 13:16:40,422 DEV : loss 0.3760252892971039 - f1-score (micro avg) 0.6555
189
+ 2023-10-17 13:16:40,466 saving best model
190
+ 2023-10-17 13:16:41,076 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-17 13:16:55,165 epoch 9 - iter 180/1809 - loss 0.00699473 - time (sec): 14.09 - samples/sec: 2692.27 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-17 13:17:08,854 epoch 9 - iter 360/1809 - loss 0.00800011 - time (sec): 27.78 - samples/sec: 2673.76 - lr: 0.000010 - momentum: 0.000000
193
+ 2023-10-17 13:17:21,927 epoch 9 - iter 540/1809 - loss 0.00784076 - time (sec): 40.85 - samples/sec: 2716.11 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-17 13:17:35,991 epoch 9 - iter 720/1809 - loss 0.00811916 - time (sec): 54.91 - samples/sec: 2707.86 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-17 13:17:49,737 epoch 9 - iter 900/1809 - loss 0.00811360 - time (sec): 68.66 - samples/sec: 2730.47 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 13:18:03,967 epoch 9 - iter 1080/1809 - loss 0.00795283 - time (sec): 82.89 - samples/sec: 2716.52 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 13:18:17,621 epoch 9 - iter 1260/1809 - loss 0.00770312 - time (sec): 96.54 - samples/sec: 2730.38 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 13:18:31,453 epoch 9 - iter 1440/1809 - loss 0.00743409 - time (sec): 110.38 - samples/sec: 2732.91 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 13:18:45,298 epoch 9 - iter 1620/1809 - loss 0.00731569 - time (sec): 124.22 - samples/sec: 2730.15 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 13:18:59,691 epoch 9 - iter 1800/1809 - loss 0.00705202 - time (sec): 138.61 - samples/sec: 2727.78 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 13:19:00,353 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-17 13:19:00,353 EPOCH 9 done: loss 0.0070 - lr: 0.000006
203
+ 2023-10-17 13:19:07,562 DEV : loss 0.3952539563179016 - f1-score (micro avg) 0.6521
204
+ 2023-10-17 13:19:07,604 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-17 13:19:21,606 epoch 10 - iter 180/1809 - loss 0.00511638 - time (sec): 14.00 - samples/sec: 2613.91 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-17 13:19:35,721 epoch 10 - iter 360/1809 - loss 0.00478079 - time (sec): 28.11 - samples/sec: 2677.95 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 13:19:50,649 epoch 10 - iter 540/1809 - loss 0.00426938 - time (sec): 43.04 - samples/sec: 2589.12 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 13:20:05,350 epoch 10 - iter 720/1809 - loss 0.00500865 - time (sec): 57.74 - samples/sec: 2598.57 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 13:20:19,311 epoch 10 - iter 900/1809 - loss 0.00515276 - time (sec): 71.70 - samples/sec: 2610.81 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 13:20:32,388 epoch 10 - iter 1080/1809 - loss 0.00512569 - time (sec): 84.78 - samples/sec: 2661.62 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 13:20:46,110 epoch 10 - iter 1260/1809 - loss 0.00480815 - time (sec): 98.50 - samples/sec: 2662.33 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 13:21:00,221 epoch 10 - iter 1440/1809 - loss 0.00509895 - time (sec): 112.61 - samples/sec: 2676.30 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 13:21:13,711 epoch 10 - iter 1620/1809 - loss 0.00479092 - time (sec): 126.10 - samples/sec: 2701.50 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 13:21:27,421 epoch 10 - iter 1800/1809 - loss 0.00470773 - time (sec): 139.82 - samples/sec: 2705.31 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 13:21:28,066 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-17 13:21:28,066 EPOCH 10 done: loss 0.0047 - lr: 0.000000
217
+ 2023-10-17 13:21:34,505 DEV : loss 0.4053354859352112 - f1-score (micro avg) 0.6545
218
+ 2023-10-17 13:21:35,063 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 13:21:35,065 Loading model from best epoch ...
220
+ 2023-10-17 13:21:37,585 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org
221
+ 2023-10-17 13:21:45,770
222
+ Results:
223
+ - F-score (micro) 0.6646
224
+ - F-score (macro) 0.5118
225
+ - Accuracy 0.5075
226
+
227
+ By class:
228
+ precision recall f1-score support
229
+
230
+ loc 0.6667 0.7682 0.7138 591
231
+ pers 0.5948 0.7731 0.6724 357
232
+ org 0.1818 0.1266 0.1493 79
233
+
234
+ micro avg 0.6167 0.7205 0.6646 1027
235
+ macro avg 0.4811 0.5560 0.5118 1027
236
+ weighted avg 0.6044 0.7205 0.6560 1027
237
+
238
+ 2023-10-17 13:21:45,770 ----------------------------------------------------------------------------------------------------