Hugging Face's logo

stefan-it
/
hmbench-hipe2020-de-hmbert_tiny-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
29c0390
·
1 Parent(s): 5b28aca

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.1697653303.46dc0c540dd0.2878.15 +3 -0
  5. test.tsv +0 -0
  6. training.log +245 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891f2f7de79b7853a3e73835cb5df5ea84cc009e4ef3bc42eeec38c548c2d807
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 18:21:55 0.0000 1.8109 0.4488 0.0000 0.0000 0.0000 0.0000
3
+ 2 18:22:11 0.0000 0.4835 0.3287 0.3274 0.1446 0.2007 0.1145
4
+ 3 18:22:26 0.0000 0.3996 0.3115 0.3528 0.2455 0.2895 0.1763
5
+ 4 18:22:41 0.0000 0.3601 0.3031 0.3847 0.2830 0.3261 0.2034
6
+ 5 18:22:56 0.0000 0.3314 0.2967 0.3694 0.3206 0.3432 0.2180
7
+ 6 18:23:12 0.0000 0.3076 0.2882 0.3548 0.3315 0.3428 0.2177
8
+ 7 18:23:27 0.0000 0.2978 0.2950 0.3780 0.3221 0.3478 0.2213
9
+ 8 18:23:43 0.0000 0.2878 0.2947 0.3706 0.3268 0.3473 0.2207
10
+ 9 18:23:59 0.0000 0.2753 0.2968 0.3769 0.3182 0.3451 0.2182
11
+ 10 18:24:14 0.0000 0.2761 0.2940 0.3741 0.3299 0.3506 0.2230
runs/events.out.tfevents.1697653303.46dc0c540dd0.2878.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a01e4613ecd61a9f5d7ab61e4c61a1debd06588fdb6e69e36c1dfa8b2e811234
3
+ size 253592
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-18 18:21:43,173 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-18 18:21:43,173 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 18:21:43,173 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-18 18:21:43,173 MultiCorpus: 3575 train + 1235 dev + 1266 test sentences
52
+ - NER_HIPE_2022 Corpus: 3575 train + 1235 dev + 1266 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/de/with_doc_seperator
53
+ 2023-10-18 18:21:43,173 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-18 18:21:43,173 Train: 3575 sentences
55
+ 2023-10-18 18:21:43,173 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-18 18:21:43,173 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-18 18:21:43,173 Training Params:
58
+ 2023-10-18 18:21:43,173 - learning_rate: "5e-05"
59
+ 2023-10-18 18:21:43,173 - mini_batch_size: "8"
60
+ 2023-10-18 18:21:43,173 - max_epochs: "10"
61
+ 2023-10-18 18:21:43,173 - shuffle: "True"
62
+ 2023-10-18 18:21:43,173 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-18 18:21:43,173 Plugins:
64
+ 2023-10-18 18:21:43,173 - TensorboardLogger
65
+ 2023-10-18 18:21:43,173 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-18 18:21:43,174 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-18 18:21:43,174 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-18 18:21:43,174 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-18 18:21:43,174 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-18 18:21:43,174 Computation:
71
+ 2023-10-18 18:21:43,174 - compute on device: cuda:0
72
+ 2023-10-18 18:21:43,174 - embedding storage: none
73
+ 2023-10-18 18:21:43,174 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-18 18:21:43,174 Model training base path: "hmbench-hipe2020/de-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
75
+ 2023-10-18 18:21:43,174 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-18 18:21:43,174 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-18 18:21:43,174 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-18 18:21:44,063 epoch 1 - iter 44/447 - loss 4.23649821 - time (sec): 0.89 - samples/sec: 9205.03 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-18 18:21:45,001 epoch 1 - iter 88/447 - loss 4.09913748 - time (sec): 1.83 - samples/sec: 9161.65 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-18 18:21:46,122 epoch 1 - iter 132/447 - loss 3.70752803 - time (sec): 2.95 - samples/sec: 8885.41 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-18 18:21:47,135 epoch 1 - iter 176/447 - loss 3.33851307 - time (sec): 3.96 - samples/sec: 8897.63 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-18 18:21:48,153 epoch 1 - iter 220/447 - loss 2.91921810 - time (sec): 4.98 - samples/sec: 8929.24 - lr: 0.000024 - momentum: 0.000000
83
+ 2023-10-18 18:21:49,138 epoch 1 - iter 264/447 - loss 2.57172108 - time (sec): 5.96 - samples/sec: 8897.72 - lr: 0.000029 - momentum: 0.000000
84
+ 2023-10-18 18:21:50,118 epoch 1 - iter 308/447 - loss 2.32138092 - time (sec): 6.94 - samples/sec: 8782.67 - lr: 0.000034 - momentum: 0.000000
85
+ 2023-10-18 18:21:51,110 epoch 1 - iter 352/447 - loss 2.12444880 - time (sec): 7.94 - samples/sec: 8684.37 - lr: 0.000039 - momentum: 0.000000
86
+ 2023-10-18 18:21:52,115 epoch 1 - iter 396/447 - loss 1.96997781 - time (sec): 8.94 - samples/sec: 8592.80 - lr: 0.000044 - momentum: 0.000000
87
+ 2023-10-18 18:21:53,135 epoch 1 - iter 440/447 - loss 1.83051644 - time (sec): 9.96 - samples/sec: 8560.53 - lr: 0.000049 - momentum: 0.000000
88
+ 2023-10-18 18:21:53,279 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-18 18:21:53,280 EPOCH 1 done: loss 1.8109 - lr: 0.000049
90
+ 2023-10-18 18:21:55,566 DEV : loss 0.44877171516418457 - f1-score (micro avg) 0.0
91
+ 2023-10-18 18:21:55,589 ----------------------------------------------------------------------------------------------------
92
+ 2023-10-18 18:21:56,612 epoch 2 - iter 44/447 - loss 0.60155493 - time (sec): 1.02 - samples/sec: 8574.38 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-18 18:21:57,597 epoch 2 - iter 88/447 - loss 0.56142538 - time (sec): 2.01 - samples/sec: 8504.11 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-18 18:21:58,565 epoch 2 - iter 132/447 - loss 0.55726995 - time (sec): 2.98 - samples/sec: 8469.91 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-18 18:21:59,547 epoch 2 - iter 176/447 - loss 0.54406916 - time (sec): 3.96 - samples/sec: 8495.52 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-18 18:22:00,547 epoch 2 - iter 220/447 - loss 0.53559205 - time (sec): 4.96 - samples/sec: 8474.13 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-18 18:22:01,542 epoch 2 - iter 264/447 - loss 0.52587561 - time (sec): 5.95 - samples/sec: 8323.02 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-18 18:22:02,554 epoch 2 - iter 308/447 - loss 0.51234790 - time (sec): 6.96 - samples/sec: 8349.78 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-18 18:22:03,602 epoch 2 - iter 352/447 - loss 0.49579329 - time (sec): 8.01 - samples/sec: 8484.55 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-18 18:22:04,613 epoch 2 - iter 396/447 - loss 0.49021091 - time (sec): 9.02 - samples/sec: 8540.08 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-18 18:22:05,637 epoch 2 - iter 440/447 - loss 0.48330812 - time (sec): 10.05 - samples/sec: 8495.76 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-18 18:22:05,784 ----------------------------------------------------------------------------------------------------
103
+ 2023-10-18 18:22:05,784 EPOCH 2 done: loss 0.4835 - lr: 0.000045
104
+ 2023-10-18 18:22:11,082 DEV : loss 0.32866111397743225 - f1-score (micro avg) 0.2007
105
+ 2023-10-18 18:22:11,105 saving best model
106
+ 2023-10-18 18:22:11,142 ----------------------------------------------------------------------------------------------------
107
+ 2023-10-18 18:22:12,115 epoch 3 - iter 44/447 - loss 0.40849086 - time (sec): 0.97 - samples/sec: 9093.83 - lr: 0.000044 - momentum: 0.000000
108
+ 2023-10-18 18:22:13,082 epoch 3 - iter 88/447 - loss 0.39700437 - time (sec): 1.94 - samples/sec: 8792.81 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-18 18:22:14,073 epoch 3 - iter 132/447 - loss 0.41180397 - time (sec): 2.93 - samples/sec: 8767.84 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-18 18:22:15,057 epoch 3 - iter 176/447 - loss 0.41517633 - time (sec): 3.91 - samples/sec: 8603.19 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-18 18:22:16,077 epoch 3 - iter 220/447 - loss 0.40697778 - time (sec): 4.93 - samples/sec: 8582.36 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-18 18:22:17,133 epoch 3 - iter 264/447 - loss 0.40336023 - time (sec): 5.99 - samples/sec: 8712.21 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-18 18:22:18,123 epoch 3 - iter 308/447 - loss 0.40473996 - time (sec): 6.98 - samples/sec: 8727.05 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-18 18:22:19,105 epoch 3 - iter 352/447 - loss 0.40234530 - time (sec): 7.96 - samples/sec: 8674.70 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-18 18:22:20,067 epoch 3 - iter 396/447 - loss 0.40175952 - time (sec): 8.92 - samples/sec: 8624.41 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-18 18:22:21,055 epoch 3 - iter 440/447 - loss 0.40155202 - time (sec): 9.91 - samples/sec: 8597.01 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-18 18:22:21,214 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-18 18:22:21,214 EPOCH 3 done: loss 0.3996 - lr: 0.000039
119
+ 2023-10-18 18:22:26,494 DEV : loss 0.31150904297828674 - f1-score (micro avg) 0.2895
120
+ 2023-10-18 18:22:26,518 saving best model
121
+ 2023-10-18 18:22:26,553 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-18 18:22:27,547 epoch 4 - iter 44/447 - loss 0.31938505 - time (sec): 0.99 - samples/sec: 7768.01 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-18 18:22:28,522 epoch 4 - iter 88/447 - loss 0.35629034 - time (sec): 1.97 - samples/sec: 8020.00 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-18 18:22:29,360 epoch 4 - iter 132/447 - loss 0.37841602 - time (sec): 2.81 - samples/sec: 8550.59 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-18 18:22:30,205 epoch 4 - iter 176/447 - loss 0.37884124 - time (sec): 3.65 - samples/sec: 8816.64 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-18 18:22:31,154 epoch 4 - iter 220/447 - loss 0.36800228 - time (sec): 4.60 - samples/sec: 9070.98 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-18 18:22:32,140 epoch 4 - iter 264/447 - loss 0.35905570 - time (sec): 5.59 - samples/sec: 9038.17 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-18 18:22:33,228 epoch 4 - iter 308/447 - loss 0.35834364 - time (sec): 6.68 - samples/sec: 8997.15 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-18 18:22:34,223 epoch 4 - iter 352/447 - loss 0.35753489 - time (sec): 7.67 - samples/sec: 8989.30 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-18 18:22:35,209 epoch 4 - iter 396/447 - loss 0.35399316 - time (sec): 8.66 - samples/sec: 8900.47 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-18 18:22:36,209 epoch 4 - iter 440/447 - loss 0.35960244 - time (sec): 9.66 - samples/sec: 8828.74 - lr: 0.000033 - momentum: 0.000000
132
+ 2023-10-18 18:22:36,366 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-18 18:22:36,366 EPOCH 4 done: loss 0.3601 - lr: 0.000033
134
+ 2023-10-18 18:22:41,343 DEV : loss 0.3030697703361511 - f1-score (micro avg) 0.3261
135
+ 2023-10-18 18:22:41,367 saving best model
136
+ 2023-10-18 18:22:41,411 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-18 18:22:42,431 epoch 5 - iter 44/447 - loss 0.32935993 - time (sec): 1.02 - samples/sec: 8650.32 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-18 18:22:43,415 epoch 5 - iter 88/447 - loss 0.31978926 - time (sec): 2.00 - samples/sec: 8326.37 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-18 18:22:44,768 epoch 5 - iter 132/447 - loss 0.32434382 - time (sec): 3.36 - samples/sec: 7570.99 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-18 18:22:45,779 epoch 5 - iter 176/447 - loss 0.32626966 - time (sec): 4.37 - samples/sec: 7906.10 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-18 18:22:46,731 epoch 5 - iter 220/447 - loss 0.32079104 - time (sec): 5.32 - samples/sec: 8117.80 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-18 18:22:47,707 epoch 5 - iter 264/447 - loss 0.32647442 - time (sec): 6.30 - samples/sec: 8199.87 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-18 18:22:48,633 epoch 5 - iter 308/447 - loss 0.33184709 - time (sec): 7.22 - samples/sec: 8204.55 - lr: 0.000030 - momentum: 0.000000
144
+ 2023-10-18 18:22:49,467 epoch 5 - iter 352/447 - loss 0.33135495 - time (sec): 8.06 - samples/sec: 8350.69 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-18 18:22:50,382 epoch 5 - iter 396/447 - loss 0.32921133 - time (sec): 8.97 - samples/sec: 8431.60 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-18 18:22:51,434 epoch 5 - iter 440/447 - loss 0.33252622 - time (sec): 10.02 - samples/sec: 8520.37 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-18 18:22:51,599 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-18 18:22:51,599 EPOCH 5 done: loss 0.3314 - lr: 0.000028
149
+ 2023-10-18 18:22:56,580 DEV : loss 0.2966790497303009 - f1-score (micro avg) 0.3432
150
+ 2023-10-18 18:22:56,605 saving best model
151
+ 2023-10-18 18:22:56,646 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-18 18:22:57,639 epoch 6 - iter 44/447 - loss 0.32205009 - time (sec): 0.99 - samples/sec: 7882.22 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-18 18:22:58,675 epoch 6 - iter 88/447 - loss 0.28851192 - time (sec): 2.03 - samples/sec: 8518.03 - lr: 0.000027 - momentum: 0.000000
154
+ 2023-10-18 18:22:59,657 epoch 6 - iter 132/447 - loss 0.27935474 - time (sec): 3.01 - samples/sec: 8308.57 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-18 18:23:00,674 epoch 6 - iter 176/447 - loss 0.29305316 - time (sec): 4.03 - samples/sec: 8517.53 - lr: 0.000026 - momentum: 0.000000
156
+ 2023-10-18 18:23:01,689 epoch 6 - iter 220/447 - loss 0.29344782 - time (sec): 5.04 - samples/sec: 8600.65 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-18 18:23:02,693 epoch 6 - iter 264/447 - loss 0.29557160 - time (sec): 6.05 - samples/sec: 8512.17 - lr: 0.000025 - momentum: 0.000000
158
+ 2023-10-18 18:23:03,653 epoch 6 - iter 308/447 - loss 0.29555013 - time (sec): 7.01 - samples/sec: 8482.76 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-18 18:23:04,667 epoch 6 - iter 352/447 - loss 0.29649384 - time (sec): 8.02 - samples/sec: 8570.31 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-18 18:23:05,648 epoch 6 - iter 396/447 - loss 0.29505917 - time (sec): 9.00 - samples/sec: 8570.39 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-18 18:23:06,640 epoch 6 - iter 440/447 - loss 0.30654783 - time (sec): 9.99 - samples/sec: 8556.98 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-18 18:23:06,794 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-18 18:23:06,794 EPOCH 6 done: loss 0.3076 - lr: 0.000022
164
+ 2023-10-18 18:23:12,104 DEV : loss 0.2881721258163452 - f1-score (micro avg) 0.3428
165
+ 2023-10-18 18:23:12,130 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-18 18:23:13,173 epoch 7 - iter 44/447 - loss 0.24532264 - time (sec): 1.04 - samples/sec: 8882.55 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-18 18:23:14,184 epoch 7 - iter 88/447 - loss 0.27568476 - time (sec): 2.05 - samples/sec: 8486.80 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-18 18:23:15,283 epoch 7 - iter 132/447 - loss 0.29794749 - time (sec): 3.15 - samples/sec: 8599.07 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-18 18:23:16,312 epoch 7 - iter 176/447 - loss 0.29956954 - time (sec): 4.18 - samples/sec: 8565.70 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-18 18:23:17,376 epoch 7 - iter 220/447 - loss 0.30213892 - time (sec): 5.25 - samples/sec: 8384.24 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-18 18:23:18,349 epoch 7 - iter 264/447 - loss 0.30357337 - time (sec): 6.22 - samples/sec: 8377.41 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-18 18:23:19,377 epoch 7 - iter 308/447 - loss 0.29758405 - time (sec): 7.25 - samples/sec: 8318.63 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-18 18:23:20,358 epoch 7 - iter 352/447 - loss 0.29898433 - time (sec): 8.23 - samples/sec: 8353.32 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-18 18:23:21,384 epoch 7 - iter 396/447 - loss 0.29612803 - time (sec): 9.25 - samples/sec: 8325.21 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-18 18:23:22,424 epoch 7 - iter 440/447 - loss 0.29754448 - time (sec): 10.29 - samples/sec: 8276.01 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-18 18:23:22,589 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-18 18:23:22,589 EPOCH 7 done: loss 0.2978 - lr: 0.000017
178
+ 2023-10-18 18:23:27,857 DEV : loss 0.2950444519519806 - f1-score (micro avg) 0.3478
179
+ 2023-10-18 18:23:27,881 saving best model
180
+ 2023-10-18 18:23:27,915 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-18 18:23:28,944 epoch 8 - iter 44/447 - loss 0.29022344 - time (sec): 1.03 - samples/sec: 9194.27 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-18 18:23:29,939 epoch 8 - iter 88/447 - loss 0.27818831 - time (sec): 2.02 - samples/sec: 8694.64 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-18 18:23:30,925 epoch 8 - iter 132/447 - loss 0.29183782 - time (sec): 3.01 - samples/sec: 8683.21 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-18 18:23:31,934 epoch 8 - iter 176/447 - loss 0.29768575 - time (sec): 4.02 - samples/sec: 8511.47 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-18 18:23:32,961 epoch 8 - iter 220/447 - loss 0.30091732 - time (sec): 5.05 - samples/sec: 8435.25 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-18 18:23:33,943 epoch 8 - iter 264/447 - loss 0.29597312 - time (sec): 6.03 - samples/sec: 8442.64 - lr: 0.000013 - momentum: 0.000000
187
+ 2023-10-18 18:23:34,941 epoch 8 - iter 308/447 - loss 0.29271218 - time (sec): 7.03 - samples/sec: 8347.80 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-18 18:23:35,941 epoch 8 - iter 352/447 - loss 0.29100478 - time (sec): 8.03 - samples/sec: 8386.27 - lr: 0.000012 - momentum: 0.000000
189
+ 2023-10-18 18:23:36,957 epoch 8 - iter 396/447 - loss 0.28742095 - time (sec): 9.04 - samples/sec: 8390.58 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-18 18:23:38,050 epoch 8 - iter 440/447 - loss 0.28930722 - time (sec): 10.13 - samples/sec: 8390.30 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-18 18:23:38,225 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-18 18:23:38,225 EPOCH 8 done: loss 0.2878 - lr: 0.000011
193
+ 2023-10-18 18:23:43,523 DEV : loss 0.29474112391471863 - f1-score (micro avg) 0.3473
194
+ 2023-10-18 18:23:43,547 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-18 18:23:44,548 epoch 9 - iter 44/447 - loss 0.25740795 - time (sec): 1.00 - samples/sec: 8141.93 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-18 18:23:45,525 epoch 9 - iter 88/447 - loss 0.27278712 - time (sec): 1.98 - samples/sec: 7858.76 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-18 18:23:46,560 epoch 9 - iter 132/447 - loss 0.26541675 - time (sec): 3.01 - samples/sec: 8036.26 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-18 18:23:47,629 epoch 9 - iter 176/447 - loss 0.27555671 - time (sec): 4.08 - samples/sec: 7930.21 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-18 18:23:48,717 epoch 9 - iter 220/447 - loss 0.27547894 - time (sec): 5.17 - samples/sec: 8030.67 - lr: 0.000008 - momentum: 0.000000
200
+ 2023-10-18 18:23:49,774 epoch 9 - iter 264/447 - loss 0.27439270 - time (sec): 6.23 - samples/sec: 8141.15 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-18 18:23:50,822 epoch 9 - iter 308/447 - loss 0.27018164 - time (sec): 7.27 - samples/sec: 8134.64 - lr: 0.000007 - momentum: 0.000000
202
+ 2023-10-18 18:23:51,870 epoch 9 - iter 352/447 - loss 0.26807567 - time (sec): 8.32 - samples/sec: 8095.54 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-18 18:23:52,962 epoch 9 - iter 396/447 - loss 0.27305200 - time (sec): 9.41 - samples/sec: 8151.44 - lr: 0.000006 - momentum: 0.000000
204
+ 2023-10-18 18:23:53,986 epoch 9 - iter 440/447 - loss 0.27534298 - time (sec): 10.44 - samples/sec: 8199.93 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-18 18:23:54,132 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-18 18:23:54,133 EPOCH 9 done: loss 0.2753 - lr: 0.000006
207
+ 2023-10-18 18:23:59,472 DEV : loss 0.2967955470085144 - f1-score (micro avg) 0.3451
208
+ 2023-10-18 18:23:59,496 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-18 18:24:00,570 epoch 10 - iter 44/447 - loss 0.31147788 - time (sec): 1.07 - samples/sec: 7567.81 - lr: 0.000005 - momentum: 0.000000
210
+ 2023-10-18 18:24:01,581 epoch 10 - iter 88/447 - loss 0.29350164 - time (sec): 2.08 - samples/sec: 7864.46 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-18 18:24:02,585 epoch 10 - iter 132/447 - loss 0.27414972 - time (sec): 3.09 - samples/sec: 7968.43 - lr: 0.000004 - momentum: 0.000000
212
+ 2023-10-18 18:24:03,541 epoch 10 - iter 176/447 - loss 0.27134812 - time (sec): 4.05 - samples/sec: 8107.61 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-18 18:24:04,542 epoch 10 - iter 220/447 - loss 0.27511632 - time (sec): 5.05 - samples/sec: 8012.55 - lr: 0.000003 - momentum: 0.000000
214
+ 2023-10-18 18:24:05,574 epoch 10 - iter 264/447 - loss 0.26854414 - time (sec): 6.08 - samples/sec: 8070.76 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-18 18:24:06,537 epoch 10 - iter 308/447 - loss 0.27296262 - time (sec): 7.04 - samples/sec: 8110.53 - lr: 0.000002 - momentum: 0.000000
216
+ 2023-10-18 18:24:07,641 epoch 10 - iter 352/447 - loss 0.27183740 - time (sec): 8.14 - samples/sec: 8302.87 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-18 18:24:08,693 epoch 10 - iter 396/447 - loss 0.27614075 - time (sec): 9.20 - samples/sec: 8270.70 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-18 18:24:09,741 epoch 10 - iter 440/447 - loss 0.27640189 - time (sec): 10.24 - samples/sec: 8271.79 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-18 18:24:09,932 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-18 18:24:09,932 EPOCH 10 done: loss 0.2761 - lr: 0.000000
221
+ 2023-10-18 18:24:14,905 DEV : loss 0.2940215766429901 - f1-score (micro avg) 0.3506
222
+ 2023-10-18 18:24:14,929 saving best model
223
+ 2023-10-18 18:24:14,992 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-18 18:24:14,992 Loading model from best epoch ...
225
+ 2023-10-18 18:24:15,067 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-prod, B-prod, E-prod, I-prod, S-time, B-time, E-time, I-time
226
+ 2023-10-18 18:24:17,305
227
+ Results:
228
+ - F-score (micro) 0.3601
229
+ - F-score (macro) 0.1639
230
+ - Accuracy 0.2303
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ loc 0.5196 0.5554 0.5369 596
236
+ pers 0.1712 0.2282 0.1956 333
237
+ org 0.0000 0.0000 0.0000 132
238
+ time 0.1500 0.0612 0.0870 49
239
+ prod 0.0000 0.0000 0.0000 66
240
+
241
+ micro avg 0.3724 0.3486 0.3601 1176
242
+ macro avg 0.1682 0.1690 0.1639 1176
243
+ weighted avg 0.3181 0.3486 0.3311 1176
244
+
245
+ 2023-10-18 18:24:17,305 ----------------------------------------------------------------------------------------------------