Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
7ef46ac
·
1 Parent(s): f1d215b

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.1697656570.46dc0c540dd0.3108.7 +3 -0
  5. test.tsv +0 -0
  6. training.log +247 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e43c1c843fb8e14b946685e023a47a1686f4502dd3021429a9591ff1c995309
3
+ size 19050210
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 19:16:31 0.0000 1.1698 0.3899 0.2194 0.1151 0.1510 0.0853
3
+ 2 19:16:56 0.0000 0.4258 0.3044 0.3675 0.4009 0.3835 0.2542
4
+ 3 19:17:21 0.0000 0.3546 0.2698 0.4204 0.4582 0.4385 0.3043
5
+ 4 19:17:46 0.0000 0.3105 0.2499 0.4380 0.5160 0.4738 0.3364
6
+ 5 19:18:11 0.0000 0.2819 0.2401 0.4800 0.5281 0.5029 0.3631
7
+ 6 19:18:37 0.0000 0.2592 0.2316 0.5044 0.5641 0.5326 0.3898
8
+ 7 19:19:02 0.0000 0.2448 0.2260 0.4937 0.5619 0.5256 0.3828
9
+ 8 19:19:27 0.0000 0.2311 0.2259 0.5085 0.5808 0.5422 0.3981
10
+ 9 19:19:52 0.0000 0.2240 0.2262 0.5040 0.5727 0.5362 0.3925
11
+ 10 19:20:17 0.0000 0.2207 0.2269 0.5175 0.5773 0.5457 0.4014
runs/events.out.tfevents.1697656570.46dc0c540dd0.3108.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978a56f42236f0870ad718e9c2157627e3a5a57b9dd081347c5104e3d10a86a6
3
+ size 415388
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 19:16:10,441 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 19:16:10,441 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(32001, 128)
7
+ (position_embeddings): Embedding(512, 128)
8
+ (token_type_embeddings): Embedding(2, 128)
9
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
10
+ (dropout): Dropout(p=0.1, inplace=False)
11
+ )
12
+ (encoder): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-1): 2 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
17
+ (query): Linear(in_features=128, out_features=128, bias=True)
18
+ (key): Linear(in_features=128, out_features=128, bias=True)
19
+ (value): Linear(in_features=128, out_features=128, bias=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (output): BertSelfOutput(
23
+ (dense): Linear(in_features=128, out_features=128, bias=True)
24
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
25
+ (dropout): Dropout(p=0.1, inplace=False)
26
+ )
27
+ )
28
+ (intermediate): BertIntermediate(
29
+ (dense): Linear(in_features=128, out_features=512, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
33
+ (dense): Linear(in_features=512, out_features=128, bias=True)
34
+ (LayerNorm): LayerNorm((128,), eps=1e-12, elementwise_affine=True)
35
+ (dropout): Dropout(p=0.1, inplace=False)
36
+ )
37
+ )
38
+ )
39
+ )
40
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=128, out_features=128, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=128, out_features=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-18 19:16:10,441 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 19:16:10,442 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
52
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
53
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 19:16:10,442 Train: 5901 sentences
55
+ 2023-10-18 19:16:10,442 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 19:16:10,442 Training Params:
58
+ 2023-10-18 19:16:10,442 - learning_rate: "5e-05"
59
+ 2023-10-18 19:16:10,442 - mini_batch_size: "8"
60
+ 2023-10-18 19:16:10,442 - max_epochs: "10"
61
+ 2023-10-18 19:16:10,442 - shuffle: "True"
62
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 19:16:10,442 Plugins:
64
+ 2023-10-18 19:16:10,442 - TensorboardLogger
65
+ 2023-10-18 19:16:10,442 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 19:16:10,442 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 19:16:10,442 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 19:16:10,442 Computation:
71
+ 2023-10-18 19:16:10,442 - compute on device: cuda:0
72
+ 2023-10-18 19:16:10,442 - embedding storage: none
73
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 19:16:10,442 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 19:16:10,442 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 19:16:10,442 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 19:16:12,152 epoch 1 - iter 73/738 - loss 3.07586690 - time (sec): 1.71 - samples/sec: 8803.91 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 19:16:14,385 epoch 1 - iter 146/738 - loss 2.77274838 - time (sec): 3.94 - samples/sec: 8359.91 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 19:16:16,258 epoch 1 - iter 219/738 - loss 2.37894957 - time (sec): 5.82 - samples/sec: 8573.50 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 19:16:18,002 epoch 1 - iter 292/738 - loss 2.02832146 - time (sec): 7.56 - samples/sec: 8683.64 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 19:16:19,668 epoch 1 - iter 365/738 - loss 1.77711491 - time (sec): 9.23 - samples/sec: 8794.98 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-18 19:16:21,343 epoch 1 - iter 438/738 - loss 1.59379009 - time (sec): 10.90 - samples/sec: 8915.26 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-18 19:16:23,048 epoch 1 - iter 511/738 - loss 1.46113750 - time (sec): 12.60 - samples/sec: 8930.48 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-18 19:16:24,891 epoch 1 - iter 584/738 - loss 1.33512940 - time (sec): 14.45 - samples/sec: 9118.78 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-18 19:16:26,602 epoch 1 - iter 657/738 - loss 1.24694827 - time (sec): 16.16 - samples/sec: 9194.50 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-18 19:16:28,278 epoch 1 - iter 730/738 - loss 1.18415498 - time (sec): 17.84 - samples/sec: 9146.63 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-18 19:16:28,542 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 19:16:28,542 EPOCH 1 done: loss 1.1698 - lr: 0.000049
90
+ 2023-10-18 19:16:31,032 DEV : loss 0.3898785710334778 - f1-score (micro avg) 0.151
91
+ 2023-10-18 19:16:31,060 saving best model
92
+ 2023-10-18 19:16:31,087 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-18 19:16:32,754 epoch 2 - iter 73/738 - loss 0.44379610 - time (sec): 1.67 - samples/sec: 8957.60 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 19:16:34,463 epoch 2 - iter 146/738 - loss 0.45149541 - time (sec): 3.38 - samples/sec: 9164.70 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-18 19:16:36,377 epoch 2 - iter 219/738 - loss 0.44816036 - time (sec): 5.29 - samples/sec: 9320.47 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 19:16:38,107 epoch 2 - iter 292/738 - loss 0.44332964 - time (sec): 7.02 - samples/sec: 9149.40 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-18 19:16:39,802 epoch 2 - iter 365/738 - loss 0.44861383 - time (sec): 8.71 - samples/sec: 9231.97 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 19:16:41,523 epoch 2 - iter 438/738 - loss 0.44417937 - time (sec): 10.44 - samples/sec: 9186.53 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-18 19:16:43,310 epoch 2 - iter 511/738 - loss 0.43943622 - time (sec): 12.22 - samples/sec: 9272.15 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 19:16:45,089 epoch 2 - iter 584/738 - loss 0.43496346 - time (sec): 14.00 - samples/sec: 9296.38 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-18 19:16:47,412 epoch 2 - iter 657/738 - loss 0.42916078 - time (sec): 16.32 - samples/sec: 9104.09 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 19:16:49,139 epoch 2 - iter 730/738 - loss 0.42612713 - time (sec): 18.05 - samples/sec: 9107.29 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-18 19:16:49,331 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-18 19:16:49,331 EPOCH 2 done: loss 0.4258 - lr: 0.000045
105
+ 2023-10-18 19:16:56,554 DEV : loss 0.30439963936805725 - f1-score (micro avg) 0.3835
106
+ 2023-10-18 19:16:56,582 saving best model
107
+ 2023-10-18 19:16:56,615 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-18 19:16:58,341 epoch 3 - iter 73/738 - loss 0.38212163 - time (sec): 1.73 - samples/sec: 9041.67 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-18 19:17:00,082 epoch 3 - iter 146/738 - loss 0.37123255 - time (sec): 3.47 - samples/sec: 8893.99 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 19:17:01,813 epoch 3 - iter 219/738 - loss 0.38122082 - time (sec): 5.20 - samples/sec: 8881.29 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-18 19:17:03,613 epoch 3 - iter 292/738 - loss 0.37054219 - time (sec): 7.00 - samples/sec: 9093.43 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 19:17:05,407 epoch 3 - iter 365/738 - loss 0.36975075 - time (sec): 8.79 - samples/sec: 9310.43 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-18 19:17:07,251 epoch 3 - iter 438/738 - loss 0.36348837 - time (sec): 10.64 - samples/sec: 9318.23 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 19:17:09,105 epoch 3 - iter 511/738 - loss 0.35957823 - time (sec): 12.49 - samples/sec: 9327.22 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-18 19:17:10,798 epoch 3 - iter 584/738 - loss 0.35718051 - time (sec): 14.18 - samples/sec: 9308.65 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 19:17:12,488 epoch 3 - iter 657/738 - loss 0.35703417 - time (sec): 15.87 - samples/sec: 9334.93 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-18 19:17:14,156 epoch 3 - iter 730/738 - loss 0.35392752 - time (sec): 17.54 - samples/sec: 9316.96 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-18 19:17:14,395 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-18 19:17:14,395 EPOCH 3 done: loss 0.3546 - lr: 0.000039
120
+ 2023-10-18 19:17:21,627 DEV : loss 0.2697567641735077 - f1-score (micro avg) 0.4385
121
+ 2023-10-18 19:17:21,654 saving best model
122
+ 2023-10-18 19:17:21,689 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-18 19:17:23,414 epoch 4 - iter 73/738 - loss 0.31534660 - time (sec): 1.72 - samples/sec: 9312.37 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 19:17:25,190 epoch 4 - iter 146/738 - loss 0.31583539 - time (sec): 3.50 - samples/sec: 9459.36 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-18 19:17:26,931 epoch 4 - iter 219/738 - loss 0.31563059 - time (sec): 5.24 - samples/sec: 9568.13 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 19:17:28,602 epoch 4 - iter 292/738 - loss 0.32238830 - time (sec): 6.91 - samples/sec: 9481.86 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-18 19:17:30,332 epoch 4 - iter 365/738 - loss 0.32299176 - time (sec): 8.64 - samples/sec: 9408.69 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 19:17:32,244 epoch 4 - iter 438/738 - loss 0.32181537 - time (sec): 10.55 - samples/sec: 9483.55 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-18 19:17:33,999 epoch 4 - iter 511/738 - loss 0.31852674 - time (sec): 12.31 - samples/sec: 9396.46 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 19:17:35,735 epoch 4 - iter 584/738 - loss 0.31761959 - time (sec): 14.05 - samples/sec: 9372.05 - lr: 0.000035 - momentum: 0.000000
131
+ 2023-10-18 19:17:37,460 epoch 4 - iter 657/738 - loss 0.31666181 - time (sec): 15.77 - samples/sec: 9381.59 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-18 19:17:39,337 epoch 4 - iter 730/738 - loss 0.31100660 - time (sec): 17.65 - samples/sec: 9344.17 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-18 19:17:39,517 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-18 19:17:39,518 EPOCH 4 done: loss 0.3105 - lr: 0.000033
135
+ 2023-10-18 19:17:46,781 DEV : loss 0.24989160895347595 - f1-score (micro avg) 0.4738
136
+ 2023-10-18 19:17:46,809 saving best model
137
+ 2023-10-18 19:17:46,842 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-18 19:17:48,549 epoch 5 - iter 73/738 - loss 0.33889059 - time (sec): 1.71 - samples/sec: 9758.31 - lr: 0.000033 - momentum: 0.000000
139
+ 2023-10-18 19:17:50,329 epoch 5 - iter 146/738 - loss 0.30240545 - time (sec): 3.49 - samples/sec: 9865.12 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 19:17:52,054 epoch 5 - iter 219/738 - loss 0.29939293 - time (sec): 5.21 - samples/sec: 9604.33 - lr: 0.000032 - momentum: 0.000000
141
+ 2023-10-18 19:17:53,799 epoch 5 - iter 292/738 - loss 0.29440439 - time (sec): 6.96 - samples/sec: 9486.80 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 19:17:55,494 epoch 5 - iter 365/738 - loss 0.29326400 - time (sec): 8.65 - samples/sec: 9425.14 - lr: 0.000031 - momentum: 0.000000
143
+ 2023-10-18 19:17:57,245 epoch 5 - iter 438/738 - loss 0.29384822 - time (sec): 10.40 - samples/sec: 9429.18 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 19:17:58,964 epoch 5 - iter 511/738 - loss 0.29217563 - time (sec): 12.12 - samples/sec: 9447.95 - lr: 0.000030 - momentum: 0.000000
145
+ 2023-10-18 19:18:00,728 epoch 5 - iter 584/738 - loss 0.28778672 - time (sec): 13.89 - samples/sec: 9410.97 - lr: 0.000029 - momentum: 0.000000
146
+ 2023-10-18 19:18:02,548 epoch 5 - iter 657/738 - loss 0.28493520 - time (sec): 15.71 - samples/sec: 9352.08 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 19:18:04,328 epoch 5 - iter 730/738 - loss 0.28263463 - time (sec): 17.49 - samples/sec: 9403.28 - lr: 0.000028 - momentum: 0.000000
148
+ 2023-10-18 19:18:04,519 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-18 19:18:04,519 EPOCH 5 done: loss 0.2819 - lr: 0.000028
150
+ 2023-10-18 19:18:11,788 DEV : loss 0.24010828137397766 - f1-score (micro avg) 0.5029
151
+ 2023-10-18 19:18:11,815 saving best model
152
+ 2023-10-18 19:18:11,849 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-18 19:18:13,695 epoch 6 - iter 73/738 - loss 0.29763220 - time (sec): 1.85 - samples/sec: 9990.87 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 19:18:15,418 epoch 6 - iter 146/738 - loss 0.28553332 - time (sec): 3.57 - samples/sec: 9318.60 - lr: 0.000027 - momentum: 0.000000
155
+ 2023-10-18 19:18:17,163 epoch 6 - iter 219/738 - loss 0.27904513 - time (sec): 5.31 - samples/sec: 9345.50 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 19:18:18,941 epoch 6 - iter 292/738 - loss 0.26679853 - time (sec): 7.09 - samples/sec: 9280.39 - lr: 0.000026 - momentum: 0.000000
157
+ 2023-10-18 19:18:21,255 epoch 6 - iter 365/738 - loss 0.26616402 - time (sec): 9.41 - samples/sec: 8894.81 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 19:18:23,013 epoch 6 - iter 438/738 - loss 0.26698244 - time (sec): 11.16 - samples/sec: 8904.33 - lr: 0.000025 - momentum: 0.000000
159
+ 2023-10-18 19:18:24,785 epoch 6 - iter 511/738 - loss 0.26719563 - time (sec): 12.94 - samples/sec: 8828.95 - lr: 0.000024 - momentum: 0.000000
160
+ 2023-10-18 19:18:26,509 epoch 6 - iter 584/738 - loss 0.26332397 - time (sec): 14.66 - samples/sec: 8892.33 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 19:18:28,257 epoch 6 - iter 657/738 - loss 0.26303038 - time (sec): 16.41 - samples/sec: 8972.92 - lr: 0.000023 - momentum: 0.000000
162
+ 2023-10-18 19:18:29,999 epoch 6 - iter 730/738 - loss 0.26036240 - time (sec): 18.15 - samples/sec: 9064.22 - lr: 0.000022 - momentum: 0.000000
163
+ 2023-10-18 19:18:30,189 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-18 19:18:30,189 EPOCH 6 done: loss 0.2592 - lr: 0.000022
165
+ 2023-10-18 19:18:37,482 DEV : loss 0.23162847757339478 - f1-score (micro avg) 0.5326
166
+ 2023-10-18 19:18:37,509 saving best model
167
+ 2023-10-18 19:18:37,542 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-18 19:18:39,340 epoch 7 - iter 73/738 - loss 0.26477648 - time (sec): 1.80 - samples/sec: 8805.94 - lr: 0.000022 - momentum: 0.000000
169
+ 2023-10-18 19:18:41,055 epoch 7 - iter 146/738 - loss 0.25666080 - time (sec): 3.51 - samples/sec: 9218.25 - lr: 0.000021 - momentum: 0.000000
170
+ 2023-10-18 19:18:42,803 epoch 7 - iter 219/738 - loss 0.25357439 - time (sec): 5.26 - samples/sec: 9349.12 - lr: 0.000021 - momentum: 0.000000
171
+ 2023-10-18 19:18:44,536 epoch 7 - iter 292/738 - loss 0.25298532 - time (sec): 6.99 - samples/sec: 9290.53 - lr: 0.000020 - momentum: 0.000000
172
+ 2023-10-18 19:18:46,336 epoch 7 - iter 365/738 - loss 0.24890974 - time (sec): 8.79 - samples/sec: 9295.19 - lr: 0.000020 - momentum: 0.000000
173
+ 2023-10-18 19:18:48,116 epoch 7 - iter 438/738 - loss 0.24820722 - time (sec): 10.57 - samples/sec: 9226.06 - lr: 0.000019 - momentum: 0.000000
174
+ 2023-10-18 19:18:49,919 epoch 7 - iter 511/738 - loss 0.25007629 - time (sec): 12.38 - samples/sec: 9260.81 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-18 19:18:51,614 epoch 7 - iter 584/738 - loss 0.25047113 - time (sec): 14.07 - samples/sec: 9270.02 - lr: 0.000018 - momentum: 0.000000
176
+ 2023-10-18 19:18:53,422 epoch 7 - iter 657/738 - loss 0.24687633 - time (sec): 15.88 - samples/sec: 9360.24 - lr: 0.000017 - momentum: 0.000000
177
+ 2023-10-18 19:18:55,163 epoch 7 - iter 730/738 - loss 0.24542372 - time (sec): 17.62 - samples/sec: 9350.51 - lr: 0.000017 - momentum: 0.000000
178
+ 2023-10-18 19:18:55,353 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-18 19:18:55,353 EPOCH 7 done: loss 0.2448 - lr: 0.000017
180
+ 2023-10-18 19:19:02,608 DEV : loss 0.22602201998233795 - f1-score (micro avg) 0.5256
181
+ 2023-10-18 19:19:02,637 ----------------------------------------------------------------------------------------------------
182
+ 2023-10-18 19:19:04,311 epoch 8 - iter 73/738 - loss 0.24423595 - time (sec): 1.67 - samples/sec: 9745.79 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-18 19:19:06,038 epoch 8 - iter 146/738 - loss 0.23121395 - time (sec): 3.40 - samples/sec: 9164.06 - lr: 0.000016 - momentum: 0.000000
184
+ 2023-10-18 19:19:07,781 epoch 8 - iter 219/738 - loss 0.22578664 - time (sec): 5.14 - samples/sec: 9300.66 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-18 19:19:09,520 epoch 8 - iter 292/738 - loss 0.22931143 - time (sec): 6.88 - samples/sec: 9270.00 - lr: 0.000015 - momentum: 0.000000
186
+ 2023-10-18 19:19:11,191 epoch 8 - iter 365/738 - loss 0.23131383 - time (sec): 8.55 - samples/sec: 9206.24 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-18 19:19:13,033 epoch 8 - iter 438/738 - loss 0.23177533 - time (sec): 10.39 - samples/sec: 9213.72 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-18 19:19:14,746 epoch 8 - iter 511/738 - loss 0.23071403 - time (sec): 12.11 - samples/sec: 9212.74 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-18 19:19:16,470 epoch 8 - iter 584/738 - loss 0.22836249 - time (sec): 13.83 - samples/sec: 9299.07 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-18 19:19:18,250 epoch 8 - iter 657/738 - loss 0.22818409 - time (sec): 15.61 - samples/sec: 9358.07 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-18 19:19:20,147 epoch 8 - iter 730/738 - loss 0.23096993 - time (sec): 17.51 - samples/sec: 9427.60 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-18 19:19:20,335 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-18 19:19:20,335 EPOCH 8 done: loss 0.2311 - lr: 0.000011
194
+ 2023-10-18 19:19:27,642 DEV : loss 0.22594498097896576 - f1-score (micro avg) 0.5422
195
+ 2023-10-18 19:19:27,671 saving best model
196
+ 2023-10-18 19:19:27,703 ----------------------------------------------------------------------------------------------------
197
+ 2023-10-18 19:19:29,484 epoch 9 - iter 73/738 - loss 0.18455478 - time (sec): 1.78 - samples/sec: 8727.95 - lr: 0.000011 - momentum: 0.000000
198
+ 2023-10-18 19:19:31,203 epoch 9 - iter 146/738 - loss 0.20931099 - time (sec): 3.50 - samples/sec: 9088.75 - lr: 0.000010 - momentum: 0.000000
199
+ 2023-10-18 19:19:32,887 epoch 9 - iter 219/738 - loss 0.20975404 - time (sec): 5.18 - samples/sec: 9297.14 - lr: 0.000010 - momentum: 0.000000
200
+ 2023-10-18 19:19:34,653 epoch 9 - iter 292/738 - loss 0.22411280 - time (sec): 6.95 - samples/sec: 9389.15 - lr: 0.000009 - momentum: 0.000000
201
+ 2023-10-18 19:19:36,405 epoch 9 - iter 365/738 - loss 0.22562147 - time (sec): 8.70 - samples/sec: 9441.59 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-18 19:19:38,076 epoch 9 - iter 438/738 - loss 0.22642686 - time (sec): 10.37 - samples/sec: 9345.82 - lr: 0.000008 - momentum: 0.000000
203
+ 2023-10-18 19:19:39,738 epoch 9 - iter 511/738 - loss 0.22750691 - time (sec): 12.03 - samples/sec: 9401.08 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-18 19:19:41,543 epoch 9 - iter 584/738 - loss 0.22803447 - time (sec): 13.84 - samples/sec: 9450.52 - lr: 0.000007 - momentum: 0.000000
205
+ 2023-10-18 19:19:43,400 epoch 9 - iter 657/738 - loss 0.22389397 - time (sec): 15.70 - samples/sec: 9480.63 - lr: 0.000006 - momentum: 0.000000
206
+ 2023-10-18 19:19:45,138 epoch 9 - iter 730/738 - loss 0.22337068 - time (sec): 17.43 - samples/sec: 9453.91 - lr: 0.000006 - momentum: 0.000000
207
+ 2023-10-18 19:19:45,332 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-18 19:19:45,332 EPOCH 9 done: loss 0.2240 - lr: 0.000006
209
+ 2023-10-18 19:19:52,605 DEV : loss 0.22624309360980988 - f1-score (micro avg) 0.5362
210
+ 2023-10-18 19:19:52,632 ----------------------------------------------------------------------------------------------------
211
+ 2023-10-18 19:19:54,345 epoch 10 - iter 73/738 - loss 0.24146970 - time (sec): 1.71 - samples/sec: 9516.11 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-18 19:19:56,147 epoch 10 - iter 146/738 - loss 0.23503637 - time (sec): 3.51 - samples/sec: 9734.76 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-18 19:19:57,897 epoch 10 - iter 219/738 - loss 0.23583201 - time (sec): 5.26 - samples/sec: 9531.90 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-18 19:20:00,098 epoch 10 - iter 292/738 - loss 0.22826275 - time (sec): 7.47 - samples/sec: 9052.37 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-18 19:20:01,827 epoch 10 - iter 365/738 - loss 0.22769440 - time (sec): 9.19 - samples/sec: 8993.55 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-18 19:20:03,517 epoch 10 - iter 438/738 - loss 0.22412354 - time (sec): 10.88 - samples/sec: 8956.87 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-18 19:20:05,191 epoch 10 - iter 511/738 - loss 0.22446585 - time (sec): 12.56 - samples/sec: 9001.05 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-18 19:20:06,948 epoch 10 - iter 584/738 - loss 0.22796532 - time (sec): 14.31 - samples/sec: 9050.23 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-18 19:20:08,702 epoch 10 - iter 657/738 - loss 0.22207363 - time (sec): 16.07 - samples/sec: 9167.06 - lr: 0.000001 - momentum: 0.000000
220
+ 2023-10-18 19:20:10,373 epoch 10 - iter 730/738 - loss 0.22025921 - time (sec): 17.74 - samples/sec: 9298.67 - lr: 0.000000 - momentum: 0.000000
221
+ 2023-10-18 19:20:10,543 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-18 19:20:10,543 EPOCH 10 done: loss 0.2207 - lr: 0.000000
223
+ 2023-10-18 19:20:17,848 DEV : loss 0.2269122153520584 - f1-score (micro avg) 0.5457
224
+ 2023-10-18 19:20:17,877 saving best model
225
+ 2023-10-18 19:20:17,943 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-18 19:20:17,943 Loading model from best epoch ...
227
+ 2023-10-18 19:20:18,024 SequenceTagger predicts: Dictionary with 21 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, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
228
+ 2023-10-18 19:20:20,721
229
+ Results:
230
+ - F-score (micro) 0.5456
231
+ - F-score (macro) 0.3348
232
+ - Accuracy 0.3993
233
+
234
+ By class:
235
+ precision recall f1-score support
236
+
237
+ loc 0.5688 0.7657 0.6528 858
238
+ pers 0.4237 0.5121 0.4637 537
239
+ org 0.2000 0.0530 0.0838 132
240
+ time 0.4500 0.5000 0.4737 54
241
+ prod 0.0000 0.0000 0.0000 61
242
+
243
+ micro avg 0.5087 0.5883 0.5456 1642
244
+ macro avg 0.3285 0.3662 0.3348 1642
245
+ weighted avg 0.4667 0.5883 0.5151 1642
246
+
247
+ 2023-10-18 19:20:20,721 ----------------------------------------------------------------------------------------------------