Hugging Face's logo

stefan-it
/
hmbench-letemps-fr-hmteams-bs8-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
3753aca
·
1 Parent(s): 0a0119a

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.1697545948.4aef72135bc5.1113.6 +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 sha256:070a796a81ea1b610a12b462eb590ecd17206b7325f7c730e2bca737096c77f4
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 12:34:54 0.0000 0.3567 0.1121 0.4857 0.7963 0.6034 0.4397
3
+ 2 12:37:19 0.0000 0.0849 0.1311 0.5073 0.8375 0.6319 0.4701
4
+ 3 12:39:49 0.0000 0.0627 0.1326 0.5627 0.7654 0.6486 0.4873
5
+ 4 12:42:13 0.0000 0.0466 0.2112 0.5459 0.7414 0.6288 0.4662
6
+ 5 12:44:40 0.0000 0.0337 0.2863 0.5369 0.8238 0.6501 0.4891
7
+ 6 12:47:04 0.0000 0.0232 0.3231 0.5594 0.7757 0.6500 0.4888
8
+ 7 12:49:31 0.0000 0.0168 0.3526 0.5447 0.7872 0.6439 0.4838
9
+ 8 12:51:54 0.0000 0.0106 0.3538 0.5608 0.7494 0.6415 0.4795
10
+ 9 12:54:18 0.0000 0.0071 0.3797 0.5583 0.7780 0.6501 0.4892
11
+ 10 12:56:41 0.0000 0.0051 0.3881 0.5632 0.7803 0.6542 0.4928
runs/events.out.tfevents.1697545948.4aef72135bc5.1113.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf235d40a16a7d6bb8a94dc6e8550fef119d205fc2921b076e4dff6968e906b
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 12:32:28,665 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 12:32:28,667 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 12:32:28,667 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 12:32:28,667 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 12:32:28,667 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 12:32:28,667 Train: 14465 sentences
51
+ 2023-10-17 12:32:28,667 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 12:32:28,667 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 12:32:28,667 Training Params:
54
+ 2023-10-17 12:32:28,667 - learning_rate: "3e-05"
55
+ 2023-10-17 12:32:28,667 - mini_batch_size: "8"
56
+ 2023-10-17 12:32:28,667 - max_epochs: "10"
57
+ 2023-10-17 12:32:28,667 - shuffle: "True"
58
+ 2023-10-17 12:32:28,667 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 12:32:28,667 Plugins:
60
+ 2023-10-17 12:32:28,667 - TensorboardLogger
61
+ 2023-10-17 12:32:28,668 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 12:32:28,668 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 12:32:28,668 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 12:32:28,668 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 12:32:28,668 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 12:32:28,668 Computation:
67
+ 2023-10-17 12:32:28,668 - compute on device: cuda:0
68
+ 2023-10-17 12:32:28,668 - embedding storage: none
69
+ 2023-10-17 12:32:28,668 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 12:32:28,668 Model training base path: "hmbench-letemps/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 12:32:28,668 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 12:32:28,668 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 12:32:28,668 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 12:32:42,334 epoch 1 - iter 180/1809 - loss 2.27370058 - time (sec): 13.66 - samples/sec: 2763.04 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 12:32:56,352 epoch 1 - iter 360/1809 - loss 1.28858365 - time (sec): 27.68 - samples/sec: 2678.53 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 12:33:10,517 epoch 1 - iter 540/1809 - loss 0.90451008 - time (sec): 41.85 - samples/sec: 2716.33 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 12:33:25,236 epoch 1 - iter 720/1809 - loss 0.71533264 - time (sec): 56.57 - samples/sec: 2689.99 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 12:33:39,270 epoch 1 - iter 900/1809 - loss 0.60199015 - time (sec): 70.60 - samples/sec: 2699.97 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 12:33:53,669 epoch 1 - iter 1080/1809 - loss 0.52415435 - time (sec): 85.00 - samples/sec: 2679.90 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 12:34:07,164 epoch 1 - iter 1260/1809 - loss 0.46467647 - time (sec): 98.49 - samples/sec: 2700.29 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 12:34:20,887 epoch 1 - iter 1440/1809 - loss 0.41906400 - time (sec): 112.22 - samples/sec: 2720.64 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 12:34:33,995 epoch 1 - iter 1620/1809 - loss 0.38402725 - time (sec): 125.33 - samples/sec: 2733.35 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 12:34:48,030 epoch 1 - iter 1800/1809 - loss 0.35784435 - time (sec): 139.36 - samples/sec: 2713.76 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 12:34:48,688 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 12:34:48,688 EPOCH 1 done: loss 0.3567 - lr: 0.000030
86
+ 2023-10-17 12:34:54,087 DEV : loss 0.11208685487508774 - f1-score (micro avg) 0.6034
87
+ 2023-10-17 12:34:54,132 saving best model
88
+ 2023-10-17 12:34:54,619 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 12:35:07,905 epoch 2 - iter 180/1809 - loss 0.08803213 - time (sec): 13.28 - samples/sec: 2916.72 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 12:35:21,947 epoch 2 - iter 360/1809 - loss 0.08583051 - time (sec): 27.33 - samples/sec: 2819.84 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 12:35:36,781 epoch 2 - iter 540/1809 - loss 0.08742910 - time (sec): 42.16 - samples/sec: 2700.81 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 12:35:50,394 epoch 2 - iter 720/1809 - loss 0.08626529 - time (sec): 55.77 - samples/sec: 2712.15 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 12:36:04,316 epoch 2 - iter 900/1809 - loss 0.08537028 - time (sec): 69.70 - samples/sec: 2697.95 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 12:36:18,551 epoch 2 - iter 1080/1809 - loss 0.08696357 - time (sec): 83.93 - samples/sec: 2697.94 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 12:36:32,949 epoch 2 - iter 1260/1809 - loss 0.08563682 - time (sec): 98.33 - samples/sec: 2696.63 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 12:36:46,311 epoch 2 - iter 1440/1809 - loss 0.08480444 - time (sec): 111.69 - samples/sec: 2709.71 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 12:36:59,255 epoch 2 - iter 1620/1809 - loss 0.08486256 - time (sec): 124.63 - samples/sec: 2739.39 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 12:37:12,524 epoch 2 - iter 1800/1809 - loss 0.08496792 - time (sec): 137.90 - samples/sec: 2742.44 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 12:37:13,215 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 12:37:13,215 EPOCH 2 done: loss 0.0849 - lr: 0.000027
101
+ 2023-10-17 12:37:19,694 DEV : loss 0.13111227750778198 - f1-score (micro avg) 0.6319
102
+ 2023-10-17 12:37:19,739 saving best model
103
+ 2023-10-17 12:37:20,330 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 12:37:34,636 epoch 3 - iter 180/1809 - loss 0.05902844 - time (sec): 14.30 - samples/sec: 2564.53 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 12:37:49,112 epoch 3 - iter 360/1809 - loss 0.05895939 - time (sec): 28.78 - samples/sec: 2606.39 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 12:38:03,624 epoch 3 - iter 540/1809 - loss 0.05969344 - time (sec): 43.29 - samples/sec: 2610.92 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 12:38:17,930 epoch 3 - iter 720/1809 - loss 0.06212207 - time (sec): 57.60 - samples/sec: 2619.96 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 12:38:31,816 epoch 3 - iter 900/1809 - loss 0.06110739 - time (sec): 71.48 - samples/sec: 2636.30 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 12:38:46,100 epoch 3 - iter 1080/1809 - loss 0.06175488 - time (sec): 85.77 - samples/sec: 2653.88 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 12:39:00,267 epoch 3 - iter 1260/1809 - loss 0.06303296 - time (sec): 99.94 - samples/sec: 2641.35 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 12:39:14,535 epoch 3 - iter 1440/1809 - loss 0.06273772 - time (sec): 114.20 - samples/sec: 2643.35 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 12:39:28,429 epoch 3 - iter 1620/1809 - loss 0.06267906 - time (sec): 128.10 - samples/sec: 2663.21 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 12:39:41,756 epoch 3 - iter 1800/1809 - loss 0.06278456 - time (sec): 141.42 - samples/sec: 2674.41 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 12:39:42,507 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 12:39:42,507 EPOCH 3 done: loss 0.0627 - lr: 0.000023
116
+ 2023-10-17 12:39:49,880 DEV : loss 0.13264159858226776 - f1-score (micro avg) 0.6486
117
+ 2023-10-17 12:39:49,924 saving best model
118
+ 2023-10-17 12:39:50,549 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 12:40:04,418 epoch 4 - iter 180/1809 - loss 0.04494956 - time (sec): 13.87 - samples/sec: 2775.70 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 12:40:17,827 epoch 4 - iter 360/1809 - loss 0.04469307 - time (sec): 27.28 - samples/sec: 2789.65 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 12:40:31,565 epoch 4 - iter 540/1809 - loss 0.04599527 - time (sec): 41.01 - samples/sec: 2806.92 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 12:40:44,876 epoch 4 - iter 720/1809 - loss 0.04655565 - time (sec): 54.33 - samples/sec: 2812.46 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 12:40:56,786 epoch 4 - iter 900/1809 - loss 0.04659306 - time (sec): 66.24 - samples/sec: 2876.60 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 12:41:10,776 epoch 4 - iter 1080/1809 - loss 0.04661371 - time (sec): 80.23 - samples/sec: 2842.54 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 12:41:25,311 epoch 4 - iter 1260/1809 - loss 0.04625491 - time (sec): 94.76 - samples/sec: 2806.39 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 12:41:38,618 epoch 4 - iter 1440/1809 - loss 0.04567270 - time (sec): 108.07 - samples/sec: 2819.66 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 12:41:52,411 epoch 4 - iter 1620/1809 - loss 0.04632141 - time (sec): 121.86 - samples/sec: 2805.86 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 12:42:06,435 epoch 4 - iter 1800/1809 - loss 0.04660214 - time (sec): 135.88 - samples/sec: 2783.09 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 12:42:07,048 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 12:42:07,048 EPOCH 4 done: loss 0.0466 - lr: 0.000020
131
+ 2023-10-17 12:42:13,395 DEV : loss 0.2111847847700119 - f1-score (micro avg) 0.6288
132
+ 2023-10-17 12:42:13,438 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 12:42:27,715 epoch 5 - iter 180/1809 - loss 0.02684447 - time (sec): 14.28 - samples/sec: 2655.18 - lr: 0.000020 - momentum: 0.000000
134
+ 2023-10-17 12:42:43,306 epoch 5 - iter 360/1809 - loss 0.03299146 - time (sec): 29.87 - samples/sec: 2557.94 - lr: 0.000019 - momentum: 0.000000
135
+ 2023-10-17 12:42:56,547 epoch 5 - iter 540/1809 - loss 0.03398210 - time (sec): 43.11 - samples/sec: 2642.20 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 12:43:10,122 epoch 5 - iter 720/1809 - loss 0.03396815 - time (sec): 56.68 - samples/sec: 2683.01 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 12:43:24,271 epoch 5 - iter 900/1809 - loss 0.03181056 - time (sec): 70.83 - samples/sec: 2696.72 - lr: 0.000018 - momentum: 0.000000
138
+ 2023-10-17 12:43:38,412 epoch 5 - iter 1080/1809 - loss 0.03248635 - time (sec): 84.97 - samples/sec: 2706.81 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 12:43:52,925 epoch 5 - iter 1260/1809 - loss 0.03349930 - time (sec): 99.49 - samples/sec: 2678.03 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 12:44:06,516 epoch 5 - iter 1440/1809 - loss 0.03382517 - time (sec): 113.08 - samples/sec: 2671.17 - lr: 0.000017 - momentum: 0.000000
141
+ 2023-10-17 12:44:20,244 epoch 5 - iter 1620/1809 - loss 0.03364689 - time (sec): 126.80 - samples/sec: 2684.20 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 12:44:33,805 epoch 5 - iter 1800/1809 - loss 0.03378464 - time (sec): 140.37 - samples/sec: 2690.40 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 12:44:34,521 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 12:44:34,522 EPOCH 5 done: loss 0.0337 - lr: 0.000017
145
+ 2023-10-17 12:44:40,805 DEV : loss 0.2863040864467621 - f1-score (micro avg) 0.6501
146
+ 2023-10-17 12:44:40,849 saving best model
147
+ 2023-10-17 12:44:41,466 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 12:44:54,520 epoch 6 - iter 180/1809 - loss 0.01746924 - time (sec): 13.05 - samples/sec: 2866.05 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-17 12:45:07,394 epoch 6 - iter 360/1809 - loss 0.02167689 - time (sec): 25.93 - samples/sec: 2874.50 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 12:45:20,713 epoch 6 - iter 540/1809 - loss 0.02243785 - time (sec): 39.25 - samples/sec: 2867.99 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 12:45:34,006 epoch 6 - iter 720/1809 - loss 0.02310060 - time (sec): 52.54 - samples/sec: 2871.80 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-17 12:45:47,441 epoch 6 - iter 900/1809 - loss 0.02291002 - time (sec): 65.97 - samples/sec: 2873.58 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 12:46:01,611 epoch 6 - iter 1080/1809 - loss 0.02368605 - time (sec): 80.14 - samples/sec: 2837.37 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 12:46:15,084 epoch 6 - iter 1260/1809 - loss 0.02295485 - time (sec): 93.62 - samples/sec: 2836.00 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-17 12:46:29,634 epoch 6 - iter 1440/1809 - loss 0.02348442 - time (sec): 108.17 - samples/sec: 2804.62 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 12:46:42,680 epoch 6 - iter 1620/1809 - loss 0.02284877 - time (sec): 121.21 - samples/sec: 2804.99 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 12:46:57,034 epoch 6 - iter 1800/1809 - loss 0.02323254 - time (sec): 135.57 - samples/sec: 2792.48 - lr: 0.000013 - momentum: 0.000000
158
+ 2023-10-17 12:46:57,702 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 12:46:57,702 EPOCH 6 done: loss 0.0232 - lr: 0.000013
160
+ 2023-10-17 12:47:04,321 DEV : loss 0.3231387138366699 - f1-score (micro avg) 0.65
161
+ 2023-10-17 12:47:04,371 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-17 12:47:18,159 epoch 7 - iter 180/1809 - loss 0.01193593 - time (sec): 13.79 - samples/sec: 2738.61 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-17 12:47:32,406 epoch 7 - iter 360/1809 - loss 0.01319722 - time (sec): 28.03 - samples/sec: 2682.64 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-17 12:47:46,524 epoch 7 - iter 540/1809 - loss 0.01435567 - time (sec): 42.15 - samples/sec: 2678.86 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-17 12:48:00,344 epoch 7 - iter 720/1809 - loss 0.01621888 - time (sec): 55.97 - samples/sec: 2689.90 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-17 12:48:14,114 epoch 7 - iter 900/1809 - loss 0.01659162 - time (sec): 69.74 - samples/sec: 2708.00 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 12:48:27,599 epoch 7 - iter 1080/1809 - loss 0.01715533 - time (sec): 83.23 - samples/sec: 2718.74 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-17 12:48:41,211 epoch 7 - iter 1260/1809 - loss 0.01681447 - time (sec): 96.84 - samples/sec: 2733.74 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-17 12:48:55,627 epoch 7 - iter 1440/1809 - loss 0.01623294 - time (sec): 111.25 - samples/sec: 2721.32 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 12:49:09,921 epoch 7 - iter 1620/1809 - loss 0.01669798 - time (sec): 125.55 - samples/sec: 2718.79 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-17 12:49:23,765 epoch 7 - iter 1800/1809 - loss 0.01666121 - time (sec): 139.39 - samples/sec: 2712.25 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-17 12:49:24,402 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-17 12:49:24,402 EPOCH 7 done: loss 0.0168 - lr: 0.000010
174
+ 2023-10-17 12:49:31,552 DEV : loss 0.3526480197906494 - f1-score (micro avg) 0.6439
175
+ 2023-10-17 12:49:31,596 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 12:49:45,322 epoch 8 - iter 180/1809 - loss 0.00687072 - time (sec): 13.72 - samples/sec: 2737.57 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-17 12:49:59,159 epoch 8 - iter 360/1809 - loss 0.00878289 - time (sec): 27.56 - samples/sec: 2708.04 - lr: 0.000009 - momentum: 0.000000
178
+ 2023-10-17 12:50:13,458 epoch 8 - iter 540/1809 - loss 0.01005585 - time (sec): 41.86 - samples/sec: 2685.02 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-17 12:50:27,285 epoch 8 - iter 720/1809 - loss 0.01102532 - time (sec): 55.69 - samples/sec: 2716.91 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 12:50:40,196 epoch 8 - iter 900/1809 - loss 0.01076944 - time (sec): 68.60 - samples/sec: 2744.28 - lr: 0.000008 - momentum: 0.000000
181
+ 2023-10-17 12:50:53,170 epoch 8 - iter 1080/1809 - loss 0.01115779 - time (sec): 81.57 - samples/sec: 2764.02 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-17 12:51:06,244 epoch 8 - iter 1260/1809 - loss 0.01098807 - time (sec): 94.65 - samples/sec: 2773.77 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 12:51:20,217 epoch 8 - iter 1440/1809 - loss 0.01054582 - time (sec): 108.62 - samples/sec: 2776.65 - lr: 0.000007 - momentum: 0.000000
184
+ 2023-10-17 12:51:34,049 epoch 8 - iter 1620/1809 - loss 0.01049241 - time (sec): 122.45 - samples/sec: 2777.35 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-17 12:51:47,519 epoch 8 - iter 1800/1809 - loss 0.01064423 - time (sec): 135.92 - samples/sec: 2781.31 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 12:51:48,170 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 12:51:48,171 EPOCH 8 done: loss 0.0106 - lr: 0.000007
188
+ 2023-10-17 12:51:54,537 DEV : loss 0.3538384437561035 - f1-score (micro avg) 0.6415
189
+ 2023-10-17 12:51:54,580 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 12:52:08,026 epoch 9 - iter 180/1809 - loss 0.00555717 - time (sec): 13.44 - samples/sec: 2820.99 - lr: 0.000006 - momentum: 0.000000
191
+ 2023-10-17 12:52:21,823 epoch 9 - iter 360/1809 - loss 0.00577815 - time (sec): 27.24 - samples/sec: 2726.32 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-17 12:52:35,707 epoch 9 - iter 540/1809 - loss 0.00650262 - time (sec): 41.12 - samples/sec: 2697.90 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 12:52:49,710 epoch 9 - iter 720/1809 - loss 0.00752309 - time (sec): 55.13 - samples/sec: 2697.30 - lr: 0.000005 - momentum: 0.000000
194
+ 2023-10-17 12:53:03,890 epoch 9 - iter 900/1809 - loss 0.00758994 - time (sec): 69.31 - samples/sec: 2704.92 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-17 12:53:17,416 epoch 9 - iter 1080/1809 - loss 0.00725976 - time (sec): 82.83 - samples/sec: 2718.32 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 12:53:30,619 epoch 9 - iter 1260/1809 - loss 0.00716453 - time (sec): 96.04 - samples/sec: 2744.77 - lr: 0.000004 - momentum: 0.000000
197
+ 2023-10-17 12:53:44,086 epoch 9 - iter 1440/1809 - loss 0.00712254 - time (sec): 109.50 - samples/sec: 2754.65 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-17 12:53:57,433 epoch 9 - iter 1620/1809 - loss 0.00683275 - time (sec): 122.85 - samples/sec: 2760.59 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 12:54:11,195 epoch 9 - iter 1800/1809 - loss 0.00715118 - time (sec): 136.61 - samples/sec: 2767.71 - lr: 0.000003 - momentum: 0.000000
200
+ 2023-10-17 12:54:11,739 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-17 12:54:11,740 EPOCH 9 done: loss 0.0071 - lr: 0.000003
202
+ 2023-10-17 12:54:18,770 DEV : loss 0.3797404170036316 - f1-score (micro avg) 0.6501
203
+ 2023-10-17 12:54:18,820 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 12:54:32,197 epoch 10 - iter 180/1809 - loss 0.00573911 - time (sec): 13.37 - samples/sec: 2736.20 - lr: 0.000003 - momentum: 0.000000
205
+ 2023-10-17 12:54:44,132 epoch 10 - iter 360/1809 - loss 0.00501062 - time (sec): 25.31 - samples/sec: 2974.73 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-17 12:54:56,554 epoch 10 - iter 540/1809 - loss 0.00477005 - time (sec): 37.73 - samples/sec: 2953.57 - lr: 0.000002 - momentum: 0.000000
207
+ 2023-10-17 12:55:10,406 epoch 10 - iter 720/1809 - loss 0.00521171 - time (sec): 51.58 - samples/sec: 2908.90 - lr: 0.000002 - momentum: 0.000000
208
+ 2023-10-17 12:55:24,658 epoch 10 - iter 900/1809 - loss 0.00520448 - time (sec): 65.84 - samples/sec: 2843.55 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 12:55:38,667 epoch 10 - iter 1080/1809 - loss 0.00525655 - time (sec): 79.84 - samples/sec: 2826.21 - lr: 0.000001 - momentum: 0.000000
210
+ 2023-10-17 12:55:52,431 epoch 10 - iter 1260/1809 - loss 0.00501805 - time (sec): 93.61 - samples/sec: 2801.56 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-17 12:56:06,542 epoch 10 - iter 1440/1809 - loss 0.00517881 - time (sec): 107.72 - samples/sec: 2797.91 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 12:56:20,815 epoch 10 - iter 1620/1809 - loss 0.00493116 - time (sec): 121.99 - samples/sec: 2792.57 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-17 12:56:34,050 epoch 10 - iter 1800/1809 - loss 0.00508429 - time (sec): 135.23 - samples/sec: 2797.09 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-17 12:56:34,710 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-17 12:56:34,710 EPOCH 10 done: loss 0.0051 - lr: 0.000000
216
+ 2023-10-17 12:56:41,156 DEV : loss 0.38813158869743347 - f1-score (micro avg) 0.6542
217
+ 2023-10-17 12:56:41,200 saving best model
218
+ 2023-10-17 12:56:43,010 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 12:56:43,011 Loading model from best epoch ...
220
+ 2023-10-17 12:56:44,822 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 12:56:52,675
222
+ Results:
223
+ - F-score (micro) 0.6583
224
+ - F-score (macro) 0.4964
225
+ - Accuracy 0.5028
226
+
227
+ By class:
228
+ precision recall f1-score support
229
+
230
+ loc 0.6676 0.7817 0.7202 591
231
+ pers 0.5817 0.7283 0.6468 357
232
+ org 0.1538 0.1013 0.1221 79
233
+
234
+ micro avg 0.6129 0.7108 0.6583 1027
235
+ macro avg 0.4677 0.5371 0.4964 1027
236
+ weighted avg 0.5982 0.7108 0.6487 1027
237
+
238
+ 2023-10-17 12:56:52,676 ----------------------------------------------------------------------------------------------------