Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmteams-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
1330b5f
•
1 Parent(s): b84f4a6

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.1697562295.bce904bcef33.2251.9 +3 -0
  5. test.tsv +0 -0
  6. training.log +236 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41b6df2c4e8a9e27c4bd8eff88f5c5d1efd066b5d147a8b8271ab0c97ed04b65
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 17:06:09 0.0000 0.3318 0.0947 0.8494 0.7107 0.7739 0.6394
3
+ 2 17:07:24 0.0000 0.1132 0.1042 0.8881 0.7293 0.8009 0.6756
4
+ 3 17:08:39 0.0000 0.0740 0.0772 0.8847 0.8399 0.8617 0.7699
5
+ 4 17:09:54 0.0000 0.0554 0.1105 0.8697 0.8275 0.8481 0.7521
6
+ 5 17:11:11 0.0000 0.0389 0.1349 0.8964 0.7955 0.8429 0.7397
7
+ 6 17:12:24 0.0000 0.0290 0.1452 0.8980 0.8275 0.8613 0.7672
8
+ 7 17:13:39 0.0000 0.0196 0.1649 0.8952 0.8027 0.8464 0.7443
9
+ 8 17:14:53 0.0000 0.0128 0.1513 0.8976 0.8244 0.8595 0.7636
10
+ 9 17:16:08 0.0000 0.0087 0.1677 0.8867 0.8244 0.8544 0.7571
11
+ 10 17:17:22 0.0000 0.0055 0.1754 0.8873 0.8130 0.8485 0.7474
runs/events.out.tfevents.1697562295.bce904bcef33.2251.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a020163b946ea456aad9dfbdf127b237d5666170f9defa9c005e4ad8e3f352
3
+ size 808480
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,236 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 17:04:55,524 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 17:04:55,525 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 17:04:55,525 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 17:04:55,525 MultiCorpus: 5777 train + 722 dev + 723 test sentences
48
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
49
+ 2023-10-17 17:04:55,525 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 17:04:55,525 Train: 5777 sentences
51
+ 2023-10-17 17:04:55,525 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 17:04:55,525 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 17:04:55,525 Training Params:
54
+ 2023-10-17 17:04:55,525 - learning_rate: "5e-05"
55
+ 2023-10-17 17:04:55,525 - mini_batch_size: "4"
56
+ 2023-10-17 17:04:55,525 - max_epochs: "10"
57
+ 2023-10-17 17:04:55,525 - shuffle: "True"
58
+ 2023-10-17 17:04:55,525 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 17:04:55,525 Plugins:
60
+ 2023-10-17 17:04:55,525 - TensorboardLogger
61
+ 2023-10-17 17:04:55,525 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 17:04:55,525 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 17:04:55,525 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 17:04:55,525 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 17:04:55,525 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 17:04:55,525 Computation:
67
+ 2023-10-17 17:04:55,525 - compute on device: cuda:0
68
+ 2023-10-17 17:04:55,525 - embedding storage: none
69
+ 2023-10-17 17:04:55,525 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 17:04:55,526 Model training base path: "hmbench-icdar/nl-hmteams/teams-base-historic-multilingual-discriminator-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
71
+ 2023-10-17 17:04:55,526 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 17:04:55,526 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 17:04:55,526 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 17:05:02,906 epoch 1 - iter 144/1445 - loss 2.04744536 - time (sec): 7.38 - samples/sec: 2328.00 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 17:05:10,040 epoch 1 - iter 288/1445 - loss 1.16515708 - time (sec): 14.51 - samples/sec: 2345.32 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 17:05:16,936 epoch 1 - iter 432/1445 - loss 0.82511112 - time (sec): 21.41 - samples/sec: 2415.80 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 17:05:24,122 epoch 1 - iter 576/1445 - loss 0.66268920 - time (sec): 28.60 - samples/sec: 2430.47 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 17:05:31,275 epoch 1 - iter 720/1445 - loss 0.54957029 - time (sec): 35.75 - samples/sec: 2467.67 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 17:05:38,463 epoch 1 - iter 864/1445 - loss 0.47492151 - time (sec): 42.94 - samples/sec: 2480.51 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 17:05:45,429 epoch 1 - iter 1008/1445 - loss 0.42416443 - time (sec): 49.90 - samples/sec: 2480.63 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 17:05:52,469 epoch 1 - iter 1152/1445 - loss 0.38566918 - time (sec): 56.94 - samples/sec: 2483.33 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 17:05:59,365 epoch 1 - iter 1296/1445 - loss 0.36046029 - time (sec): 63.84 - samples/sec: 2459.71 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 17:06:06,401 epoch 1 - iter 1440/1445 - loss 0.33304682 - time (sec): 70.87 - samples/sec: 2475.30 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 17:06:06,673 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 17:06:06,673 EPOCH 1 done: loss 0.3318 - lr: 0.000050
86
+ 2023-10-17 17:06:09,347 DEV : loss 0.09467300027608871 - f1-score (micro avg) 0.7739
87
+ 2023-10-17 17:06:09,364 saving best model
88
+ 2023-10-17 17:06:09,696 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 17:06:16,645 epoch 2 - iter 144/1445 - loss 0.08876150 - time (sec): 6.95 - samples/sec: 2497.71 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 17:06:23,663 epoch 2 - iter 288/1445 - loss 0.09747449 - time (sec): 13.97 - samples/sec: 2491.11 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 17:06:30,614 epoch 2 - iter 432/1445 - loss 0.10608025 - time (sec): 20.92 - samples/sec: 2475.55 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 17:06:37,529 epoch 2 - iter 576/1445 - loss 0.10270502 - time (sec): 27.83 - samples/sec: 2482.27 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 17:06:44,828 epoch 2 - iter 720/1445 - loss 0.09945147 - time (sec): 35.13 - samples/sec: 2501.83 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 17:06:52,376 epoch 2 - iter 864/1445 - loss 0.09821080 - time (sec): 42.68 - samples/sec: 2521.14 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 17:06:59,408 epoch 2 - iter 1008/1445 - loss 0.09698307 - time (sec): 49.71 - samples/sec: 2519.44 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 17:07:06,366 epoch 2 - iter 1152/1445 - loss 0.09459084 - time (sec): 56.67 - samples/sec: 2507.92 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 17:07:13,360 epoch 2 - iter 1296/1445 - loss 0.11694060 - time (sec): 63.66 - samples/sec: 2492.28 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 17:07:20,514 epoch 2 - iter 1440/1445 - loss 0.11332756 - time (sec): 70.82 - samples/sec: 2478.69 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 17:07:20,745 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 17:07:20,745 EPOCH 2 done: loss 0.1132 - lr: 0.000044
101
+ 2023-10-17 17:07:24,308 DEV : loss 0.10420767962932587 - f1-score (micro avg) 0.8009
102
+ 2023-10-17 17:07:24,324 saving best model
103
+ 2023-10-17 17:07:24,783 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 17:07:31,927 epoch 3 - iter 144/1445 - loss 0.08470755 - time (sec): 7.14 - samples/sec: 2435.17 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 17:07:39,197 epoch 3 - iter 288/1445 - loss 0.07396372 - time (sec): 14.41 - samples/sec: 2489.97 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 17:07:46,305 epoch 3 - iter 432/1445 - loss 0.07383465 - time (sec): 21.52 - samples/sec: 2520.38 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 17:07:53,470 epoch 3 - iter 576/1445 - loss 0.06831722 - time (sec): 28.68 - samples/sec: 2509.82 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 17:08:00,420 epoch 3 - iter 720/1445 - loss 0.06838521 - time (sec): 35.63 - samples/sec: 2481.69 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 17:08:07,496 epoch 3 - iter 864/1445 - loss 0.07099289 - time (sec): 42.71 - samples/sec: 2495.14 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 17:08:14,716 epoch 3 - iter 1008/1445 - loss 0.07256253 - time (sec): 49.93 - samples/sec: 2493.61 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 17:08:21,813 epoch 3 - iter 1152/1445 - loss 0.07227280 - time (sec): 57.02 - samples/sec: 2475.20 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 17:08:28,856 epoch 3 - iter 1296/1445 - loss 0.07185740 - time (sec): 64.07 - samples/sec: 2470.54 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 17:08:35,964 epoch 3 - iter 1440/1445 - loss 0.07400816 - time (sec): 71.18 - samples/sec: 2471.75 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 17:08:36,192 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 17:08:36,192 EPOCH 3 done: loss 0.0740 - lr: 0.000039
116
+ 2023-10-17 17:08:39,376 DEV : loss 0.07721319794654846 - f1-score (micro avg) 0.8617
117
+ 2023-10-17 17:08:39,393 saving best model
118
+ 2023-10-17 17:08:39,828 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 17:08:46,820 epoch 4 - iter 144/1445 - loss 0.05757716 - time (sec): 6.99 - samples/sec: 2389.26 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 17:08:54,123 epoch 4 - iter 288/1445 - loss 0.05567864 - time (sec): 14.29 - samples/sec: 2423.78 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 17:09:01,229 epoch 4 - iter 432/1445 - loss 0.05284901 - time (sec): 21.40 - samples/sec: 2418.66 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 17:09:08,705 epoch 4 - iter 576/1445 - loss 0.05592908 - time (sec): 28.87 - samples/sec: 2397.87 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 17:09:15,661 epoch 4 - iter 720/1445 - loss 0.05517652 - time (sec): 35.83 - samples/sec: 2408.47 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 17:09:22,687 epoch 4 - iter 864/1445 - loss 0.05536967 - time (sec): 42.86 - samples/sec: 2424.10 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 17:09:29,787 epoch 4 - iter 1008/1445 - loss 0.05543565 - time (sec): 49.96 - samples/sec: 2437.22 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 17:09:37,137 epoch 4 - iter 1152/1445 - loss 0.05526822 - time (sec): 57.31 - samples/sec: 2459.94 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 17:09:44,260 epoch 4 - iter 1296/1445 - loss 0.05451781 - time (sec): 64.43 - samples/sec: 2451.52 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 17:09:51,253 epoch 4 - iter 1440/1445 - loss 0.05521212 - time (sec): 71.42 - samples/sec: 2460.69 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 17:09:51,478 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 17:09:51,478 EPOCH 4 done: loss 0.0554 - lr: 0.000033
131
+ 2023-10-17 17:09:54,822 DEV : loss 0.1105174869298935 - f1-score (micro avg) 0.8481
132
+ 2023-10-17 17:09:54,845 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 17:10:02,920 epoch 5 - iter 144/1445 - loss 0.03691405 - time (sec): 8.07 - samples/sec: 2224.21 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 17:10:10,045 epoch 5 - iter 288/1445 - loss 0.03176100 - time (sec): 15.20 - samples/sec: 2304.05 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 17:10:17,602 epoch 5 - iter 432/1445 - loss 0.03932322 - time (sec): 22.75 - samples/sec: 2329.78 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 17:10:24,977 epoch 5 - iter 576/1445 - loss 0.03671770 - time (sec): 30.13 - samples/sec: 2360.90 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 17:10:32,045 epoch 5 - iter 720/1445 - loss 0.03597991 - time (sec): 37.20 - samples/sec: 2364.69 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 17:10:39,156 epoch 5 - iter 864/1445 - loss 0.03800795 - time (sec): 44.31 - samples/sec: 2393.05 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 17:10:46,424 epoch 5 - iter 1008/1445 - loss 0.03888293 - time (sec): 51.58 - samples/sec: 2404.57 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 17:10:53,392 epoch 5 - iter 1152/1445 - loss 0.04005684 - time (sec): 58.55 - samples/sec: 2405.04 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 17:11:00,395 epoch 5 - iter 1296/1445 - loss 0.03964899 - time (sec): 65.55 - samples/sec: 2408.75 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 17:11:07,736 epoch 5 - iter 1440/1445 - loss 0.03902191 - time (sec): 72.89 - samples/sec: 2410.31 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 17:11:07,980 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 17:11:07,980 EPOCH 5 done: loss 0.0389 - lr: 0.000028
145
+ 2023-10-17 17:11:11,203 DEV : loss 0.1348668783903122 - f1-score (micro avg) 0.8429
146
+ 2023-10-17 17:11:11,220 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 17:11:18,313 epoch 6 - iter 144/1445 - loss 0.02667685 - time (sec): 7.09 - samples/sec: 2642.82 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 17:11:25,407 epoch 6 - iter 288/1445 - loss 0.02437191 - time (sec): 14.19 - samples/sec: 2520.07 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 17:11:32,591 epoch 6 - iter 432/1445 - loss 0.02572777 - time (sec): 21.37 - samples/sec: 2541.33 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 17:11:39,608 epoch 6 - iter 576/1445 - loss 0.02873206 - time (sec): 28.39 - samples/sec: 2556.68 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 17:11:46,265 epoch 6 - iter 720/1445 - loss 0.02986499 - time (sec): 35.04 - samples/sec: 2557.72 - lr: 0.000025 - momentum: 0.000000
152
+ 2023-10-17 17:11:53,395 epoch 6 - iter 864/1445 - loss 0.02883648 - time (sec): 42.17 - samples/sec: 2553.96 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 17:12:00,334 epoch 6 - iter 1008/1445 - loss 0.02974928 - time (sec): 49.11 - samples/sec: 2533.59 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 17:12:07,379 epoch 6 - iter 1152/1445 - loss 0.03018321 - time (sec): 56.16 - samples/sec: 2528.82 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 17:12:14,362 epoch 6 - iter 1296/1445 - loss 0.02977708 - time (sec): 63.14 - samples/sec: 2512.31 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 17:12:21,234 epoch 6 - iter 1440/1445 - loss 0.02903161 - time (sec): 70.01 - samples/sec: 2510.34 - lr: 0.000022 - momentum: 0.000000
157
+ 2023-10-17 17:12:21,461 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 17:12:21,461 EPOCH 6 done: loss 0.0290 - lr: 0.000022
159
+ 2023-10-17 17:12:24,802 DEV : loss 0.1451694220304489 - f1-score (micro avg) 0.8613
160
+ 2023-10-17 17:12:24,825 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 17:12:31,930 epoch 7 - iter 144/1445 - loss 0.02087668 - time (sec): 7.10 - samples/sec: 2417.93 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 17:12:39,148 epoch 7 - iter 288/1445 - loss 0.02185794 - time (sec): 14.32 - samples/sec: 2409.26 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 17:12:46,500 epoch 7 - iter 432/1445 - loss 0.02175364 - time (sec): 21.67 - samples/sec: 2411.87 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 17:12:53,739 epoch 7 - iter 576/1445 - loss 0.02252627 - time (sec): 28.91 - samples/sec: 2435.17 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 17:13:01,179 epoch 7 - iter 720/1445 - loss 0.02077423 - time (sec): 36.35 - samples/sec: 2411.62 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 17:13:08,331 epoch 7 - iter 864/1445 - loss 0.02175611 - time (sec): 43.50 - samples/sec: 2439.32 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 17:13:15,291 epoch 7 - iter 1008/1445 - loss 0.02053015 - time (sec): 50.46 - samples/sec: 2465.32 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 17:13:22,299 epoch 7 - iter 1152/1445 - loss 0.02076891 - time (sec): 57.47 - samples/sec: 2463.50 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 17:13:29,333 epoch 7 - iter 1296/1445 - loss 0.01993760 - time (sec): 64.51 - samples/sec: 2453.37 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 17:13:36,373 epoch 7 - iter 1440/1445 - loss 0.01965177 - time (sec): 71.55 - samples/sec: 2451.17 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 17:13:36,727 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 17:13:36,727 EPOCH 7 done: loss 0.0196 - lr: 0.000017
173
+ 2023-10-17 17:13:39,963 DEV : loss 0.16489093005657196 - f1-score (micro avg) 0.8464
174
+ 2023-10-17 17:13:39,982 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 17:13:46,885 epoch 8 - iter 144/1445 - loss 0.01306226 - time (sec): 6.90 - samples/sec: 2419.95 - lr: 0.000016 - momentum: 0.000000
176
+ 2023-10-17 17:13:54,119 epoch 8 - iter 288/1445 - loss 0.01102787 - time (sec): 14.14 - samples/sec: 2401.83 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 17:14:01,225 epoch 8 - iter 432/1445 - loss 0.01344659 - time (sec): 21.24 - samples/sec: 2410.46 - lr: 0.000015 - momentum: 0.000000
178
+ 2023-10-17 17:14:08,409 epoch 8 - iter 576/1445 - loss 0.01269442 - time (sec): 28.43 - samples/sec: 2425.31 - lr: 0.000014 - momentum: 0.000000
179
+ 2023-10-17 17:14:15,556 epoch 8 - iter 720/1445 - loss 0.01377224 - time (sec): 35.57 - samples/sec: 2433.65 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 17:14:22,489 epoch 8 - iter 864/1445 - loss 0.01260199 - time (sec): 42.51 - samples/sec: 2444.68 - lr: 0.000013 - momentum: 0.000000
181
+ 2023-10-17 17:14:29,499 epoch 8 - iter 1008/1445 - loss 0.01260952 - time (sec): 49.52 - samples/sec: 2461.06 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 17:14:36,438 epoch 8 - iter 1152/1445 - loss 0.01357834 - time (sec): 56.46 - samples/sec: 2471.67 - lr: 0.000012 - momentum: 0.000000
183
+ 2023-10-17 17:14:43,638 epoch 8 - iter 1296/1445 - loss 0.01319581 - time (sec): 63.65 - samples/sec: 2498.23 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 17:14:50,513 epoch 8 - iter 1440/1445 - loss 0.01282748 - time (sec): 70.53 - samples/sec: 2489.90 - lr: 0.000011 - momentum: 0.000000
185
+ 2023-10-17 17:14:50,738 ----------------------------------------------------------------------------------------------------
186
+ 2023-10-17 17:14:50,738 EPOCH 8 done: loss 0.0128 - lr: 0.000011
187
+ 2023-10-17 17:14:53,961 DEV : loss 0.1513351947069168 - f1-score (micro avg) 0.8595
188
+ 2023-10-17 17:14:53,979 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 17:15:00,976 epoch 9 - iter 144/1445 - loss 0.01099181 - time (sec): 7.00 - samples/sec: 2449.62 - lr: 0.000011 - momentum: 0.000000
190
+ 2023-10-17 17:15:08,090 epoch 9 - iter 288/1445 - loss 0.01019344 - time (sec): 14.11 - samples/sec: 2481.99 - lr: 0.000010 - momentum: 0.000000
191
+ 2023-10-17 17:15:15,251 epoch 9 - iter 432/1445 - loss 0.00967362 - time (sec): 21.27 - samples/sec: 2468.37 - lr: 0.000009 - momentum: 0.000000
192
+ 2023-10-17 17:15:22,506 epoch 9 - iter 576/1445 - loss 0.01035916 - time (sec): 28.53 - samples/sec: 2485.88 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-17 17:15:29,912 epoch 9 - iter 720/1445 - loss 0.01031149 - time (sec): 35.93 - samples/sec: 2484.21 - lr: 0.000008 - momentum: 0.000000
194
+ 2023-10-17 17:15:36,953 epoch 9 - iter 864/1445 - loss 0.01001435 - time (sec): 42.97 - samples/sec: 2486.28 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-17 17:15:43,984 epoch 9 - iter 1008/1445 - loss 0.00920076 - time (sec): 50.00 - samples/sec: 2468.52 - lr: 0.000007 - momentum: 0.000000
196
+ 2023-10-17 17:15:50,879 epoch 9 - iter 1152/1445 - loss 0.00875804 - time (sec): 56.90 - samples/sec: 2453.39 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-17 17:15:57,895 epoch 9 - iter 1296/1445 - loss 0.00852447 - time (sec): 63.91 - samples/sec: 2472.25 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-17 17:16:04,969 epoch 9 - iter 1440/1445 - loss 0.00877198 - time (sec): 70.99 - samples/sec: 2474.67 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-17 17:16:05,199 ----------------------------------------------------------------------------------------------------
200
+ 2023-10-17 17:16:05,199 EPOCH 9 done: loss 0.0087 - lr: 0.000006
201
+ 2023-10-17 17:16:08,771 DEV : loss 0.16765910387039185 - f1-score (micro avg) 0.8544
202
+ 2023-10-17 17:16:08,787 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 17:16:15,817 epoch 10 - iter 144/1445 - loss 0.00253582 - time (sec): 7.03 - samples/sec: 2563.59 - lr: 0.000005 - momentum: 0.000000
204
+ 2023-10-17 17:16:22,833 epoch 10 - iter 288/1445 - loss 0.00331327 - time (sec): 14.04 - samples/sec: 2473.08 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-17 17:16:30,060 epoch 10 - iter 432/1445 - loss 0.00410042 - time (sec): 21.27 - samples/sec: 2497.27 - lr: 0.000004 - momentum: 0.000000
206
+ 2023-10-17 17:16:37,212 epoch 10 - iter 576/1445 - loss 0.00431306 - time (sec): 28.42 - samples/sec: 2504.09 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-17 17:16:44,188 epoch 10 - iter 720/1445 - loss 0.00416941 - time (sec): 35.40 - samples/sec: 2507.58 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 17:16:51,345 epoch 10 - iter 864/1445 - loss 0.00456723 - time (sec): 42.56 - samples/sec: 2499.03 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 17:16:58,231 epoch 10 - iter 1008/1445 - loss 0.00492998 - time (sec): 49.44 - samples/sec: 2497.08 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 17:17:05,259 epoch 10 - iter 1152/1445 - loss 0.00486200 - time (sec): 56.47 - samples/sec: 2496.94 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-17 17:17:12,327 epoch 10 - iter 1296/1445 - loss 0.00520572 - time (sec): 63.54 - samples/sec: 2500.58 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 17:17:19,331 epoch 10 - iter 1440/1445 - loss 0.00554479 - time (sec): 70.54 - samples/sec: 2492.72 - lr: 0.000000 - momentum: 0.000000
213
+ 2023-10-17 17:17:19,547 ----------------------------------------------------------------------------------------------------
214
+ 2023-10-17 17:17:19,547 EPOCH 10 done: loss 0.0055 - lr: 0.000000
215
+ 2023-10-17 17:17:22,759 DEV : loss 0.1753772795200348 - f1-score (micro avg) 0.8485
216
+ 2023-10-17 17:17:23,144 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-17 17:17:23,145 Loading model from best epoch ...
218
+ 2023-10-17 17:17:24,487 SequenceTagger predicts: Dictionary with 13 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
219
+ 2023-10-17 17:17:27,289
220
+ Results:
221
+ - F-score (micro) 0.8245
222
+ - F-score (macro) 0.7277
223
+ - Accuracy 0.7118
224
+
225
+ By class:
226
+ precision recall f1-score support
227
+
228
+ PER 0.8133 0.8402 0.8265 482
229
+ LOC 0.9221 0.8275 0.8723 458
230
+ ORG 0.5254 0.4493 0.4844 69
231
+
232
+ micro avg 0.8419 0.8077 0.8245 1009
233
+ macro avg 0.7536 0.7057 0.7277 1009
234
+ weighted avg 0.8430 0.8077 0.8239 1009
235
+
236
+ 2023-10-17 17:17:27,289 ----------------------------------------------------------------------------------------------------