Hugging Face's logo

hmbert-tiny
/
flair-hipe-2022-newseye-de

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
76c99fb
•
1 Parent(s): 6781f46

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.1697711216.46dc0c540dd0.4319.3 +3 -0
  5. test.tsv +0 -0
  6. training.log +241 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e377980b53e56f7a60373a4788cecb775938c102a970c711e90541f09224315c
3
+ size 19048098
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 10:28:01 0.0000 0.8801 0.1375 0.3320 0.1553 0.2116 0.1187
3
+ 2 10:29:07 0.0000 0.3258 0.1231 0.3564 0.2538 0.2965 0.1740
4
+ 3 10:30:14 0.0000 0.2681 0.1242 0.2974 0.3087 0.3030 0.1785
5
+ 4 10:31:21 0.0000 0.2379 0.1483 0.2257 0.4223 0.2942 0.1735
6
+ 5 10:32:28 0.0000 0.2159 0.1355 0.2507 0.3617 0.2961 0.1743
7
+ 6 10:33:34 0.0000 0.1977 0.1463 0.2445 0.3352 0.2827 0.1653
8
+ 7 10:34:41 0.0000 0.1859 0.1627 0.2324 0.4261 0.3008 0.1776
9
+ 8 10:35:48 0.0000 0.1731 0.1696 0.2160 0.3826 0.2761 0.1607
10
+ 9 10:36:55 0.0000 0.1687 0.1792 0.2210 0.4299 0.2920 0.1717
11
+ 10 10:38:02 0.0000 0.1635 0.1842 0.2163 0.4261 0.2870 0.1685
runs/events.out.tfevents.1697711216.46dc0c540dd0.4319.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b46a6af3d776ba7667e5af21bc1292642bcb2dfd06178524c161b2f41e04973a
3
+ size 1464420
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-19 10:26:56,941 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-19 10:26:56,941 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=17, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-19 10:26:56,941 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-19 10:26:56,941 MultiCorpus: 20847 train + 1123 dev + 3350 test sentences
52
+ - NER_HIPE_2022 Corpus: 20847 train + 1123 dev + 3350 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/de/with_doc_seperator
53
+ 2023-10-19 10:26:56,941 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-19 10:26:56,941 Train: 20847 sentences
55
+ 2023-10-19 10:26:56,941 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-19 10:26:56,941 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-19 10:26:56,941 Training Params:
58
+ 2023-10-19 10:26:56,941 - learning_rate: "5e-05"
59
+ 2023-10-19 10:26:56,941 - mini_batch_size: "8"
60
+ 2023-10-19 10:26:56,941 - max_epochs: "10"
61
+ 2023-10-19 10:26:56,941 - shuffle: "True"
62
+ 2023-10-19 10:26:56,941 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-19 10:26:56,941 Plugins:
64
+ 2023-10-19 10:26:56,941 - TensorboardLogger
65
+ 2023-10-19 10:26:56,941 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-19 10:26:56,941 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-19 10:26:56,942 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-19 10:26:56,942 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-19 10:26:56,942 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-19 10:26:56,942 Computation:
71
+ 2023-10-19 10:26:56,942 - compute on device: cuda:0
72
+ 2023-10-19 10:26:56,942 - embedding storage: none
73
+ 2023-10-19 10:26:56,942 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-19 10:26:56,942 Model training base path: "hmbench-newseye/de-dbmdz/bert-tiny-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1"
75
+ 2023-10-19 10:26:56,942 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-19 10:26:56,942 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-19 10:26:56,942 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-19 10:27:03,158 epoch 1 - iter 260/2606 - loss 3.11893094 - time (sec): 6.22 - samples/sec: 5861.68 - lr: 0.000005 - momentum: 0.000000
79
+ 2023-10-19 10:27:09,222 epoch 1 - iter 520/2606 - loss 2.45662908 - time (sec): 12.28 - samples/sec: 5832.63 - lr: 0.000010 - momentum: 0.000000
80
+ 2023-10-19 10:27:15,610 epoch 1 - iter 780/2606 - loss 1.81424223 - time (sec): 18.67 - samples/sec: 6026.34 - lr: 0.000015 - momentum: 0.000000
81
+ 2023-10-19 10:27:21,740 epoch 1 - iter 1040/2606 - loss 1.50115032 - time (sec): 24.80 - samples/sec: 5987.58 - lr: 0.000020 - momentum: 0.000000
82
+ 2023-10-19 10:27:27,811 epoch 1 - iter 1300/2606 - loss 1.33359036 - time (sec): 30.87 - samples/sec: 5875.91 - lr: 0.000025 - momentum: 0.000000
83
+ 2023-10-19 10:27:34,064 epoch 1 - iter 1560/2606 - loss 1.18442141 - time (sec): 37.12 - samples/sec: 5907.76 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-19 10:27:40,175 epoch 1 - iter 1820/2606 - loss 1.07763140 - time (sec): 43.23 - samples/sec: 5919.80 - lr: 0.000035 - momentum: 0.000000
85
+ 2023-10-19 10:27:47,178 epoch 1 - iter 2080/2606 - loss 0.99105876 - time (sec): 50.24 - samples/sec: 5878.65 - lr: 0.000040 - momentum: 0.000000
86
+ 2023-10-19 10:27:53,271 epoch 1 - iter 2340/2606 - loss 0.93099772 - time (sec): 56.33 - samples/sec: 5900.79 - lr: 0.000045 - momentum: 0.000000
87
+ 2023-10-19 10:27:59,502 epoch 1 - iter 2600/2606 - loss 0.88085087 - time (sec): 62.56 - samples/sec: 5863.64 - lr: 0.000050 - momentum: 0.000000
88
+ 2023-10-19 10:27:59,628 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-19 10:27:59,629 EPOCH 1 done: loss 0.8801 - lr: 0.000050
90
+ 2023-10-19 10:28:01,912 DEV : loss 0.13753747940063477 - f1-score (micro avg) 0.2116
91
+ 2023-10-19 10:28:01,936 saving best model
92
+ 2023-10-19 10:28:01,964 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-19 10:28:08,109 epoch 2 - iter 260/2606 - loss 0.42374739 - time (sec): 6.14 - samples/sec: 5818.81 - lr: 0.000049 - momentum: 0.000000
94
+ 2023-10-19 10:28:14,214 epoch 2 - iter 520/2606 - loss 0.40655630 - time (sec): 12.25 - samples/sec: 5937.03 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-19 10:28:20,349 epoch 2 - iter 780/2606 - loss 0.38998511 - time (sec): 18.38 - samples/sec: 5993.86 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-19 10:28:26,415 epoch 2 - iter 1040/2606 - loss 0.37158150 - time (sec): 24.45 - samples/sec: 5925.55 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-19 10:28:32,653 epoch 2 - iter 1300/2606 - loss 0.35862543 - time (sec): 30.69 - samples/sec: 5952.53 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-19 10:28:38,675 epoch 2 - iter 1560/2606 - loss 0.35173504 - time (sec): 36.71 - samples/sec: 5989.35 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-19 10:28:44,715 epoch 2 - iter 1820/2606 - loss 0.34322686 - time (sec): 42.75 - samples/sec: 5938.37 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-19 10:28:50,907 epoch 2 - iter 2080/2606 - loss 0.33733039 - time (sec): 48.94 - samples/sec: 5962.65 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-19 10:28:57,064 epoch 2 - iter 2340/2606 - loss 0.33269201 - time (sec): 55.10 - samples/sec: 5945.67 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-19 10:29:03,285 epoch 2 - iter 2600/2606 - loss 0.32557472 - time (sec): 61.32 - samples/sec: 5979.13 - lr: 0.000044 - momentum: 0.000000
103
+ 2023-10-19 10:29:03,427 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-19 10:29:03,428 EPOCH 2 done: loss 0.3258 - lr: 0.000044
105
+ 2023-10-19 10:29:07,968 DEV : loss 0.12312041968107224 - f1-score (micro avg) 0.2965
106
+ 2023-10-19 10:29:07,990 saving best model
107
+ 2023-10-19 10:29:08,021 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-19 10:29:14,860 epoch 3 - iter 260/2606 - loss 0.26992693 - time (sec): 6.84 - samples/sec: 5253.15 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-19 10:29:20,959 epoch 3 - iter 520/2606 - loss 0.27143201 - time (sec): 12.94 - samples/sec: 5426.17 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-19 10:29:27,212 epoch 3 - iter 780/2606 - loss 0.28917169 - time (sec): 19.19 - samples/sec: 5584.66 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-19 10:29:33,343 epoch 3 - iter 1040/2606 - loss 0.27927986 - time (sec): 25.32 - samples/sec: 5644.03 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-19 10:29:39,332 epoch 3 - iter 1300/2606 - loss 0.27479024 - time (sec): 31.31 - samples/sec: 5666.91 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-19 10:29:45,461 epoch 3 - iter 1560/2606 - loss 0.27799701 - time (sec): 37.44 - samples/sec: 5709.66 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-19 10:29:51,294 epoch 3 - iter 1820/2606 - loss 0.27344105 - time (sec): 43.27 - samples/sec: 5735.62 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-19 10:29:57,408 epoch 3 - iter 2080/2606 - loss 0.27372467 - time (sec): 49.39 - samples/sec: 5863.20 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-19 10:30:03,653 epoch 3 - iter 2340/2606 - loss 0.27074986 - time (sec): 55.63 - samples/sec: 5899.95 - lr: 0.000039 - momentum: 0.000000
117
+ 2023-10-19 10:30:09,900 epoch 3 - iter 2600/2606 - loss 0.26787206 - time (sec): 61.88 - samples/sec: 5925.07 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-19 10:30:10,035 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-19 10:30:10,035 EPOCH 3 done: loss 0.2681 - lr: 0.000039
120
+ 2023-10-19 10:30:14,548 DEV : loss 0.12417197227478027 - f1-score (micro avg) 0.303
121
+ 2023-10-19 10:30:14,571 saving best model
122
+ 2023-10-19 10:30:14,604 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-19 10:30:20,857 epoch 4 - iter 260/2606 - loss 0.23462566 - time (sec): 6.25 - samples/sec: 6095.08 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-19 10:30:27,021 epoch 4 - iter 520/2606 - loss 0.23856366 - time (sec): 12.42 - samples/sec: 5956.74 - lr: 0.000038 - momentum: 0.000000
125
+ 2023-10-19 10:30:33,016 epoch 4 - iter 780/2606 - loss 0.24865085 - time (sec): 18.41 - samples/sec: 5808.11 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-19 10:30:39,248 epoch 4 - iter 1040/2606 - loss 0.23899456 - time (sec): 24.64 - samples/sec: 5891.22 - lr: 0.000037 - momentum: 0.000000
127
+ 2023-10-19 10:30:46,210 epoch 4 - iter 1300/2606 - loss 0.23494139 - time (sec): 31.61 - samples/sec: 5868.53 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-19 10:30:52,318 epoch 4 - iter 1560/2606 - loss 0.23793258 - time (sec): 37.71 - samples/sec: 5842.14 - lr: 0.000036 - momentum: 0.000000
129
+ 2023-10-19 10:30:58,462 epoch 4 - iter 1820/2606 - loss 0.23925018 - time (sec): 43.86 - samples/sec: 5872.72 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-19 10:31:04,747 epoch 4 - iter 2080/2606 - loss 0.24063825 - time (sec): 50.14 - samples/sec: 5899.49 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-19 10:31:10,663 epoch 4 - iter 2340/2606 - loss 0.24108957 - time (sec): 56.06 - samples/sec: 5878.16 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-19 10:31:16,822 epoch 4 - iter 2600/2606 - loss 0.23788664 - time (sec): 62.22 - samples/sec: 5892.69 - lr: 0.000033 - momentum: 0.000000
133
+ 2023-10-19 10:31:16,960 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-19 10:31:16,960 EPOCH 4 done: loss 0.2379 - lr: 0.000033
135
+ 2023-10-19 10:31:21,461 DEV : loss 0.14830529689788818 - f1-score (micro avg) 0.2942
136
+ 2023-10-19 10:31:21,484 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-19 10:31:27,504 epoch 5 - iter 260/2606 - loss 0.21632271 - time (sec): 6.02 - samples/sec: 5700.59 - lr: 0.000033 - momentum: 0.000000
138
+ 2023-10-19 10:31:33,543 epoch 5 - iter 520/2606 - loss 0.20875397 - time (sec): 12.06 - samples/sec: 5799.10 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-19 10:31:39,695 epoch 5 - iter 780/2606 - loss 0.21727693 - time (sec): 18.21 - samples/sec: 5795.11 - lr: 0.000032 - momentum: 0.000000
140
+ 2023-10-19 10:31:45,911 epoch 5 - iter 1040/2606 - loss 0.21610880 - time (sec): 24.43 - samples/sec: 5961.70 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-19 10:31:52,195 epoch 5 - iter 1300/2606 - loss 0.21362450 - time (sec): 30.71 - samples/sec: 5917.59 - lr: 0.000031 - momentum: 0.000000
142
+ 2023-10-19 10:31:58,206 epoch 5 - iter 1560/2606 - loss 0.21468184 - time (sec): 36.72 - samples/sec: 5940.53 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-19 10:32:04,312 epoch 5 - iter 1820/2606 - loss 0.21378284 - time (sec): 42.83 - samples/sec: 5963.13 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-19 10:32:11,150 epoch 5 - iter 2080/2606 - loss 0.21569807 - time (sec): 49.66 - samples/sec: 5919.65 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-19 10:32:17,262 epoch 5 - iter 2340/2606 - loss 0.21694641 - time (sec): 55.78 - samples/sec: 5892.62 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-19 10:32:23,462 epoch 5 - iter 2600/2606 - loss 0.21590122 - time (sec): 61.98 - samples/sec: 5913.56 - lr: 0.000028 - momentum: 0.000000
147
+ 2023-10-19 10:32:23,608 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-19 10:32:23,608 EPOCH 5 done: loss 0.2159 - lr: 0.000028
149
+ 2023-10-19 10:32:28,124 DEV : loss 0.13548018038272858 - f1-score (micro avg) 0.2961
150
+ 2023-10-19 10:32:28,148 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-19 10:32:34,136 epoch 6 - iter 260/2606 - loss 0.19425732 - time (sec): 5.99 - samples/sec: 6445.66 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-19 10:32:40,053 epoch 6 - iter 520/2606 - loss 0.20229066 - time (sec): 11.90 - samples/sec: 6274.72 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-19 10:32:46,105 epoch 6 - iter 780/2606 - loss 0.20201165 - time (sec): 17.96 - samples/sec: 6216.67 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-19 10:32:52,101 epoch 6 - iter 1040/2606 - loss 0.19912505 - time (sec): 23.95 - samples/sec: 6199.07 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-19 10:32:58,306 epoch 6 - iter 1300/2606 - loss 0.20082645 - time (sec): 30.16 - samples/sec: 6168.82 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-19 10:33:04,202 epoch 6 - iter 1560/2606 - loss 0.19897949 - time (sec): 36.05 - samples/sec: 6086.20 - lr: 0.000024 - momentum: 0.000000
157
+ 2023-10-19 10:33:10,249 epoch 6 - iter 1820/2606 - loss 0.19908713 - time (sec): 42.10 - samples/sec: 6031.05 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-19 10:33:16,477 epoch 6 - iter 2080/2606 - loss 0.19567788 - time (sec): 48.33 - samples/sec: 6073.86 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-19 10:33:22,717 epoch 6 - iter 2340/2606 - loss 0.19369496 - time (sec): 54.57 - samples/sec: 6090.00 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-19 10:33:28,844 epoch 6 - iter 2600/2606 - loss 0.19757153 - time (sec): 60.70 - samples/sec: 6043.76 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-19 10:33:28,988 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-19 10:33:28,989 EPOCH 6 done: loss 0.1977 - lr: 0.000022
163
+ 2023-10-19 10:33:34,156 DEV : loss 0.1463058739900589 - f1-score (micro avg) 0.2827
164
+ 2023-10-19 10:33:34,179 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-19 10:33:40,498 epoch 7 - iter 260/2606 - loss 0.18497675 - time (sec): 6.32 - samples/sec: 5665.48 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-19 10:33:46,641 epoch 7 - iter 520/2606 - loss 0.18548242 - time (sec): 12.46 - samples/sec: 5965.82 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-19 10:33:52,751 epoch 7 - iter 780/2606 - loss 0.18017411 - time (sec): 18.57 - samples/sec: 6010.61 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-19 10:33:58,890 epoch 7 - iter 1040/2606 - loss 0.18483920 - time (sec): 24.71 - samples/sec: 5890.98 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-19 10:34:05,274 epoch 7 - iter 1300/2606 - loss 0.18558021 - time (sec): 31.09 - samples/sec: 5864.86 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-19 10:34:11,422 epoch 7 - iter 1560/2606 - loss 0.18791905 - time (sec): 37.24 - samples/sec: 5917.49 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-19 10:34:17,694 epoch 7 - iter 1820/2606 - loss 0.18434786 - time (sec): 43.51 - samples/sec: 5929.83 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-19 10:34:23,763 epoch 7 - iter 2080/2606 - loss 0.18656303 - time (sec): 49.58 - samples/sec: 5913.72 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-19 10:34:30,010 epoch 7 - iter 2340/2606 - loss 0.18578748 - time (sec): 55.83 - samples/sec: 5918.57 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-19 10:34:36,238 epoch 7 - iter 2600/2606 - loss 0.18558486 - time (sec): 62.06 - samples/sec: 5906.60 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-19 10:34:36,388 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-19 10:34:36,388 EPOCH 7 done: loss 0.1859 - lr: 0.000017
177
+ 2023-10-19 10:34:41,622 DEV : loss 0.1627039760351181 - f1-score (micro avg) 0.3008
178
+ 2023-10-19 10:34:41,644 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-19 10:34:47,971 epoch 8 - iter 260/2606 - loss 0.18111838 - time (sec): 6.33 - samples/sec: 5775.54 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-19 10:34:54,080 epoch 8 - iter 520/2606 - loss 0.18137979 - time (sec): 12.44 - samples/sec: 5959.36 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-19 10:35:00,107 epoch 8 - iter 780/2606 - loss 0.17816738 - time (sec): 18.46 - samples/sec: 5880.44 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-19 10:35:06,288 epoch 8 - iter 1040/2606 - loss 0.17712968 - time (sec): 24.64 - samples/sec: 6001.89 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-19 10:35:12,317 epoch 8 - iter 1300/2606 - loss 0.17233100 - time (sec): 30.67 - samples/sec: 5979.56 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-19 10:35:18,311 epoch 8 - iter 1560/2606 - loss 0.17193540 - time (sec): 36.67 - samples/sec: 5914.70 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-19 10:35:24,459 epoch 8 - iter 1820/2606 - loss 0.17667085 - time (sec): 42.81 - samples/sec: 5954.85 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-19 10:35:30,561 epoch 8 - iter 2080/2606 - loss 0.17442414 - time (sec): 48.92 - samples/sec: 5950.78 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-19 10:35:36,623 epoch 8 - iter 2340/2606 - loss 0.17322645 - time (sec): 54.98 - samples/sec: 5977.27 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-19 10:35:42,807 epoch 8 - iter 2600/2606 - loss 0.17314424 - time (sec): 61.16 - samples/sec: 5996.05 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-19 10:35:42,940 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-19 10:35:42,941 EPOCH 8 done: loss 0.1731 - lr: 0.000011
191
+ 2023-10-19 10:35:48,166 DEV : loss 0.16963887214660645 - f1-score (micro avg) 0.2761
192
+ 2023-10-19 10:35:48,191 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-19 10:35:54,315 epoch 9 - iter 260/2606 - loss 0.14720245 - time (sec): 6.12 - samples/sec: 5984.96 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-19 10:36:00,503 epoch 9 - iter 520/2606 - loss 0.14323789 - time (sec): 12.31 - samples/sec: 6004.62 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-19 10:36:06,788 epoch 9 - iter 780/2606 - loss 0.15143859 - time (sec): 18.60 - samples/sec: 5925.32 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-19 10:36:13,033 epoch 9 - iter 1040/2606 - loss 0.15467000 - time (sec): 24.84 - samples/sec: 5826.48 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-19 10:36:19,209 epoch 9 - iter 1300/2606 - loss 0.16182122 - time (sec): 31.02 - samples/sec: 5895.96 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-19 10:36:25,386 epoch 9 - iter 1560/2606 - loss 0.16198334 - time (sec): 37.19 - samples/sec: 5907.62 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-19 10:36:31,525 epoch 9 - iter 1820/2606 - loss 0.16864382 - time (sec): 43.33 - samples/sec: 5904.81 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-19 10:36:37,662 epoch 9 - iter 2080/2606 - loss 0.16802225 - time (sec): 49.47 - samples/sec: 5890.69 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-19 10:36:43,833 epoch 9 - iter 2340/2606 - loss 0.16935804 - time (sec): 55.64 - samples/sec: 5932.50 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-19 10:36:49,940 epoch 9 - iter 2600/2606 - loss 0.16889534 - time (sec): 61.75 - samples/sec: 5931.99 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-19 10:36:50,092 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-19 10:36:50,092 EPOCH 9 done: loss 0.1687 - lr: 0.000006
205
+ 2023-10-19 10:36:55,314 DEV : loss 0.17923599481582642 - f1-score (micro avg) 0.292
206
+ 2023-10-19 10:36:55,338 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-19 10:37:01,470 epoch 10 - iter 260/2606 - loss 0.16670870 - time (sec): 6.13 - samples/sec: 6043.12 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-19 10:37:08,006 epoch 10 - iter 520/2606 - loss 0.17291448 - time (sec): 12.67 - samples/sec: 5812.79 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-19 10:37:14,177 epoch 10 - iter 780/2606 - loss 0.16212646 - time (sec): 18.84 - samples/sec: 5895.13 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-19 10:37:20,303 epoch 10 - iter 1040/2606 - loss 0.16389360 - time (sec): 24.96 - samples/sec: 5847.20 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-19 10:37:26,591 epoch 10 - iter 1300/2606 - loss 0.16609968 - time (sec): 31.25 - samples/sec: 5920.88 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-19 10:37:32,767 epoch 10 - iter 1560/2606 - loss 0.16761010 - time (sec): 37.43 - samples/sec: 5920.04 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-19 10:37:38,766 epoch 10 - iter 1820/2606 - loss 0.16561236 - time (sec): 43.43 - samples/sec: 5920.44 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-19 10:37:44,938 epoch 10 - iter 2080/2606 - loss 0.16463496 - time (sec): 49.60 - samples/sec: 5903.12 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-19 10:37:51,157 epoch 10 - iter 2340/2606 - loss 0.16348950 - time (sec): 55.82 - samples/sec: 5870.39 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-19 10:37:57,513 epoch 10 - iter 2600/2606 - loss 0.16347898 - time (sec): 62.17 - samples/sec: 5899.09 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-19 10:37:57,656 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-19 10:37:57,656 EPOCH 10 done: loss 0.1635 - lr: 0.000000
219
+ 2023-10-19 10:38:02,888 DEV : loss 0.18416452407836914 - f1-score (micro avg) 0.287
220
+ 2023-10-19 10:38:02,942 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-19 10:38:02,942 Loading model from best epoch ...
222
+ 2023-10-19 10:38:03,021 SequenceTagger predicts: Dictionary with 17 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
223
+ 2023-10-19 10:38:09,420
224
+ Results:
225
+ - F-score (micro) 0.2335
226
+ - F-score (macro) 0.1202
227
+ - Accuracy 0.1328
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ LOC 0.4412 0.3089 0.3634 1214
233
+ PER 0.1569 0.0792 0.1053 808
234
+ ORG 0.0217 0.0085 0.0122 353
235
+ HumanProd 0.0000 0.0000 0.0000 15
236
+
237
+ micro avg 0.3166 0.1849 0.2335 2390
238
+ macro avg 0.1549 0.0992 0.1202 2390
239
+ weighted avg 0.2803 0.1849 0.2220 2390
240
+
241
+ 2023-10-19 10:38:09,420 ----------------------------------------------------------------------------------------------------