Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
4b880cc
•
1 Parent(s): 0fc05cf

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.1697544751.0468bd9609d6.7281.0 +3 -0
  5. test.tsv +0 -0
  6. training.log +240 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ec46f020c190e117dea7572747885e5f7e1d1e67d77dacf55b99293793f2e42
3
+ size 440954373
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
loss.tsv ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ EPOCH TIMESTAMP LEARNING_RATE TRAIN_LOSS DEV_LOSS DEV_PRECISION DEV_RECALL DEV_F1 DEV_ACCURACY
2
+ 1 12:13:43 0.0000 0.5723 0.1070 0.6959 0.7660 0.7293 0.5945
3
+ 2 12:14:58 0.0000 0.1084 0.1125 0.7574 0.8327 0.7933 0.6718
4
+ 3 12:16:13 0.0000 0.0670 0.1134 0.7826 0.8082 0.7952 0.6742
5
+ 4 12:17:28 0.0000 0.0487 0.1193 0.7927 0.8218 0.8069 0.6935
6
+ 5 12:18:43 0.0000 0.0364 0.1610 0.7966 0.8313 0.8136 0.7007
7
+ 6 12:19:58 0.0000 0.0284 0.1765 0.8073 0.8435 0.8250 0.7168
8
+ 7 12:21:12 0.0000 0.0219 0.1844 0.7984 0.8299 0.8139 0.7011
9
+ 8 12:22:27 0.0000 0.0173 0.1963 0.8024 0.8286 0.8153 0.7040
10
+ 9 12:23:42 0.0000 0.0135 0.2013 0.8032 0.8218 0.8124 0.7007
11
+ 10 12:24:56 0.0000 0.0099 0.1995 0.8123 0.8299 0.8210 0.7101
runs/events.out.tfevents.1697544751.0468bd9609d6.7281.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1ab38546899d314baf7f80af3cd530007e9131de8b0888e94411cc477bc4c04
3
+ size 502461
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 12:12:31,861 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 12:12:31,862 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=17, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 12:12:31,862 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 12:12:31,862 MultiCorpus: 7142 train + 698 dev + 2570 test sentences
48
+ - NER_HIPE_2022 Corpus: 7142 train + 698 dev + 2570 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/newseye/fr/with_doc_seperator
49
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 12:12:31,863 Train: 7142 sentences
51
+ 2023-10-17 12:12:31,863 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 12:12:31,863 Training Params:
54
+ 2023-10-17 12:12:31,863 - learning_rate: "3e-05"
55
+ 2023-10-17 12:12:31,863 - mini_batch_size: "8"
56
+ 2023-10-17 12:12:31,863 - max_epochs: "10"
57
+ 2023-10-17 12:12:31,863 - shuffle: "True"
58
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 12:12:31,863 Plugins:
60
+ 2023-10-17 12:12:31,863 - TensorboardLogger
61
+ 2023-10-17 12:12:31,863 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 12:12:31,863 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 12:12:31,863 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 12:12:31,863 Computation:
67
+ 2023-10-17 12:12:31,863 - compute on device: cuda:0
68
+ 2023-10-17 12:12:31,863 - embedding storage: none
69
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 12:12:31,863 Model training base path: "hmbench-newseye/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1"
71
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 12:12:31,863 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 12:12:31,863 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 12:12:39,868 epoch 1 - iter 89/893 - loss 2.85730488 - time (sec): 8.00 - samples/sec: 3061.44 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 12:12:46,421 epoch 1 - iter 178/893 - loss 1.85506791 - time (sec): 14.56 - samples/sec: 3412.31 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 12:12:53,180 epoch 1 - iter 267/893 - loss 1.38732665 - time (sec): 21.32 - samples/sec: 3522.46 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 12:12:59,540 epoch 1 - iter 356/893 - loss 1.14478631 - time (sec): 27.68 - samples/sec: 3551.80 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 12:13:06,415 epoch 1 - iter 445/893 - loss 0.97261226 - time (sec): 34.55 - samples/sec: 3563.18 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 12:13:13,098 epoch 1 - iter 534/893 - loss 0.84652087 - time (sec): 41.23 - samples/sec: 3596.87 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 12:13:19,594 epoch 1 - iter 623/893 - loss 0.75591951 - time (sec): 47.73 - samples/sec: 3616.65 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 12:13:26,521 epoch 1 - iter 712/893 - loss 0.67732184 - time (sec): 54.66 - samples/sec: 3626.52 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 12:13:33,467 epoch 1 - iter 801/893 - loss 0.62183579 - time (sec): 61.60 - samples/sec: 3611.56 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 12:13:40,480 epoch 1 - iter 890/893 - loss 0.57352952 - time (sec): 68.62 - samples/sec: 3614.04 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 12:13:40,670 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 12:13:40,670 EPOCH 1 done: loss 0.5723 - lr: 0.000030
86
+ 2023-10-17 12:13:43,232 DEV : loss 0.10704871267080307 - f1-score (micro avg) 0.7293
87
+ 2023-10-17 12:13:43,247 saving best model
88
+ 2023-10-17 12:13:43,637 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 12:13:49,896 epoch 2 - iter 89/893 - loss 0.14146838 - time (sec): 6.26 - samples/sec: 3762.41 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 12:13:56,876 epoch 2 - iter 178/893 - loss 0.12893578 - time (sec): 13.24 - samples/sec: 3673.48 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 12:14:04,692 epoch 2 - iter 267/893 - loss 0.12429957 - time (sec): 21.05 - samples/sec: 3507.13 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 12:14:11,624 epoch 2 - iter 356/893 - loss 0.11841667 - time (sec): 27.99 - samples/sec: 3523.08 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 12:14:18,414 epoch 2 - iter 445/893 - loss 0.11401166 - time (sec): 34.78 - samples/sec: 3542.53 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 12:14:25,667 epoch 2 - iter 534/893 - loss 0.11386573 - time (sec): 42.03 - samples/sec: 3530.67 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 12:14:33,129 epoch 2 - iter 623/893 - loss 0.11214322 - time (sec): 49.49 - samples/sec: 3481.58 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 12:14:40,204 epoch 2 - iter 712/893 - loss 0.11040463 - time (sec): 56.57 - samples/sec: 3489.52 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 12:14:47,394 epoch 2 - iter 801/893 - loss 0.10936323 - time (sec): 63.76 - samples/sec: 3527.43 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 12:14:54,130 epoch 2 - iter 890/893 - loss 0.10834170 - time (sec): 70.49 - samples/sec: 3517.52 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 12:14:54,385 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 12:14:54,385 EPOCH 2 done: loss 0.1084 - lr: 0.000027
101
+ 2023-10-17 12:14:58,657 DEV : loss 0.11247449368238449 - f1-score (micro avg) 0.7933
102
+ 2023-10-17 12:14:58,676 saving best model
103
+ 2023-10-17 12:14:59,276 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 12:15:06,504 epoch 3 - iter 89/893 - loss 0.06805108 - time (sec): 7.23 - samples/sec: 3598.82 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 12:15:13,326 epoch 3 - iter 178/893 - loss 0.06757782 - time (sec): 14.05 - samples/sec: 3596.86 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 12:15:20,879 epoch 3 - iter 267/893 - loss 0.06379743 - time (sec): 21.60 - samples/sec: 3528.07 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 12:15:27,864 epoch 3 - iter 356/893 - loss 0.06406541 - time (sec): 28.59 - samples/sec: 3600.32 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 12:15:35,036 epoch 3 - iter 445/893 - loss 0.06439386 - time (sec): 35.76 - samples/sec: 3585.04 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 12:15:41,504 epoch 3 - iter 534/893 - loss 0.06566818 - time (sec): 42.23 - samples/sec: 3602.45 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 12:15:48,277 epoch 3 - iter 623/893 - loss 0.06775661 - time (sec): 49.00 - samples/sec: 3606.18 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 12:15:55,000 epoch 3 - iter 712/893 - loss 0.06644627 - time (sec): 55.72 - samples/sec: 3600.94 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 12:16:02,106 epoch 3 - iter 801/893 - loss 0.06548290 - time (sec): 62.83 - samples/sec: 3580.94 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 12:16:08,494 epoch 3 - iter 890/893 - loss 0.06710688 - time (sec): 69.22 - samples/sec: 3582.96 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 12:16:08,721 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 12:16:08,721 EPOCH 3 done: loss 0.0670 - lr: 0.000023
116
+ 2023-10-17 12:16:13,362 DEV : loss 0.11337490379810333 - f1-score (micro avg) 0.7952
117
+ 2023-10-17 12:16:13,379 saving best model
118
+ 2023-10-17 12:16:13,968 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 12:16:20,824 epoch 4 - iter 89/893 - loss 0.04583453 - time (sec): 6.85 - samples/sec: 3653.77 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 12:16:27,871 epoch 4 - iter 178/893 - loss 0.04916381 - time (sec): 13.90 - samples/sec: 3586.20 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 12:16:34,875 epoch 4 - iter 267/893 - loss 0.05184043 - time (sec): 20.90 - samples/sec: 3610.33 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 12:16:41,602 epoch 4 - iter 356/893 - loss 0.05199944 - time (sec): 27.63 - samples/sec: 3611.42 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 12:16:48,916 epoch 4 - iter 445/893 - loss 0.05051620 - time (sec): 34.95 - samples/sec: 3572.32 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 12:16:55,985 epoch 4 - iter 534/893 - loss 0.05017704 - time (sec): 42.02 - samples/sec: 3584.24 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 12:17:03,148 epoch 4 - iter 623/893 - loss 0.04874093 - time (sec): 49.18 - samples/sec: 3571.97 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 12:17:09,673 epoch 4 - iter 712/893 - loss 0.04824195 - time (sec): 55.70 - samples/sec: 3566.08 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 12:17:16,445 epoch 4 - iter 801/893 - loss 0.04854874 - time (sec): 62.48 - samples/sec: 3565.23 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 12:17:23,534 epoch 4 - iter 890/893 - loss 0.04877570 - time (sec): 69.56 - samples/sec: 3566.84 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 12:17:23,743 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 12:17:23,744 EPOCH 4 done: loss 0.0487 - lr: 0.000020
131
+ 2023-10-17 12:17:28,138 DEV : loss 0.11932364106178284 - f1-score (micro avg) 0.8069
132
+ 2023-10-17 12:17:28,161 saving best model
133
+ 2023-10-17 12:17:28,790 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 12:17:35,379 epoch 5 - iter 89/893 - loss 0.03497413 - time (sec): 6.59 - samples/sec: 3716.09 - lr: 0.000020 - momentum: 0.000000
135
+ 2023-10-17 12:17:41,734 epoch 5 - iter 178/893 - loss 0.03718769 - time (sec): 12.94 - samples/sec: 3685.55 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 12:17:48,871 epoch 5 - iter 267/893 - loss 0.04142280 - time (sec): 20.08 - samples/sec: 3620.04 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 12:17:55,949 epoch 5 - iter 356/893 - loss 0.04142570 - time (sec): 27.16 - samples/sec: 3600.69 - lr: 0.000019 - momentum: 0.000000
138
+ 2023-10-17 12:18:03,278 epoch 5 - iter 445/893 - loss 0.04248257 - time (sec): 34.49 - samples/sec: 3609.75 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 12:18:10,953 epoch 5 - iter 534/893 - loss 0.03963812 - time (sec): 42.16 - samples/sec: 3538.91 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 12:18:18,355 epoch 5 - iter 623/893 - loss 0.03809248 - time (sec): 49.56 - samples/sec: 3529.55 - lr: 0.000018 - momentum: 0.000000
141
+ 2023-10-17 12:18:25,313 epoch 5 - iter 712/893 - loss 0.03706784 - time (sec): 56.52 - samples/sec: 3533.29 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 12:18:32,665 epoch 5 - iter 801/893 - loss 0.03669771 - time (sec): 63.87 - samples/sec: 3520.70 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 12:18:39,249 epoch 5 - iter 890/893 - loss 0.03631606 - time (sec): 70.46 - samples/sec: 3521.70 - lr: 0.000017 - momentum: 0.000000
144
+ 2023-10-17 12:18:39,413 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 12:18:39,414 EPOCH 5 done: loss 0.0364 - lr: 0.000017
146
+ 2023-10-17 12:18:43,607 DEV : loss 0.16096670925617218 - f1-score (micro avg) 0.8136
147
+ 2023-10-17 12:18:43,623 saving best model
148
+ 2023-10-17 12:18:44,144 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 12:18:51,235 epoch 6 - iter 89/893 - loss 0.02863753 - time (sec): 7.09 - samples/sec: 3547.53 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 12:18:58,307 epoch 6 - iter 178/893 - loss 0.02897778 - time (sec): 14.16 - samples/sec: 3604.65 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 12:19:04,998 epoch 6 - iter 267/893 - loss 0.02773578 - time (sec): 20.85 - samples/sec: 3623.07 - lr: 0.000016 - momentum: 0.000000
152
+ 2023-10-17 12:19:12,035 epoch 6 - iter 356/893 - loss 0.02766024 - time (sec): 27.89 - samples/sec: 3589.23 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 12:19:19,390 epoch 6 - iter 445/893 - loss 0.02785857 - time (sec): 35.24 - samples/sec: 3561.86 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 12:19:26,563 epoch 6 - iter 534/893 - loss 0.02883310 - time (sec): 42.42 - samples/sec: 3582.11 - lr: 0.000015 - momentum: 0.000000
155
+ 2023-10-17 12:19:33,390 epoch 6 - iter 623/893 - loss 0.02939347 - time (sec): 49.24 - samples/sec: 3581.27 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 12:19:39,932 epoch 6 - iter 712/893 - loss 0.02855559 - time (sec): 55.79 - samples/sec: 3587.29 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 12:19:46,666 epoch 6 - iter 801/893 - loss 0.02814727 - time (sec): 62.52 - samples/sec: 3576.11 - lr: 0.000014 - momentum: 0.000000
158
+ 2023-10-17 12:19:53,610 epoch 6 - iter 890/893 - loss 0.02837280 - time (sec): 69.46 - samples/sec: 3570.30 - lr: 0.000013 - momentum: 0.000000
159
+ 2023-10-17 12:19:53,808 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 12:19:53,808 EPOCH 6 done: loss 0.0284 - lr: 0.000013
161
+ 2023-10-17 12:19:58,395 DEV : loss 0.17645598948001862 - f1-score (micro avg) 0.825
162
+ 2023-10-17 12:19:58,410 saving best model
163
+ 2023-10-17 12:19:58,989 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 12:20:05,580 epoch 7 - iter 89/893 - loss 0.01795184 - time (sec): 6.59 - samples/sec: 3538.78 - lr: 0.000013 - momentum: 0.000000
165
+ 2023-10-17 12:20:12,912 epoch 7 - iter 178/893 - loss 0.01923215 - time (sec): 13.92 - samples/sec: 3578.32 - lr: 0.000013 - momentum: 0.000000
166
+ 2023-10-17 12:20:19,698 epoch 7 - iter 267/893 - loss 0.02233022 - time (sec): 20.71 - samples/sec: 3564.31 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 12:20:27,160 epoch 7 - iter 356/893 - loss 0.02153127 - time (sec): 28.17 - samples/sec: 3573.60 - lr: 0.000012 - momentum: 0.000000
168
+ 2023-10-17 12:20:33,937 epoch 7 - iter 445/893 - loss 0.02333590 - time (sec): 34.95 - samples/sec: 3609.86 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-17 12:20:40,375 epoch 7 - iter 534/893 - loss 0.02295462 - time (sec): 41.38 - samples/sec: 3589.92 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 12:20:47,236 epoch 7 - iter 623/893 - loss 0.02344317 - time (sec): 48.25 - samples/sec: 3565.25 - lr: 0.000011 - momentum: 0.000000
171
+ 2023-10-17 12:20:54,043 epoch 7 - iter 712/893 - loss 0.02321907 - time (sec): 55.05 - samples/sec: 3563.67 - lr: 0.000011 - momentum: 0.000000
172
+ 2023-10-17 12:21:01,460 epoch 7 - iter 801/893 - loss 0.02240865 - time (sec): 62.47 - samples/sec: 3556.31 - lr: 0.000010 - momentum: 0.000000
173
+ 2023-10-17 12:21:08,547 epoch 7 - iter 890/893 - loss 0.02194327 - time (sec): 69.56 - samples/sec: 3567.55 - lr: 0.000010 - momentum: 0.000000
174
+ 2023-10-17 12:21:08,733 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 12:21:08,733 EPOCH 7 done: loss 0.0219 - lr: 0.000010
176
+ 2023-10-17 12:21:12,882 DEV : loss 0.1844026744365692 - f1-score (micro avg) 0.8139
177
+ 2023-10-17 12:21:12,898 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-17 12:21:20,744 epoch 8 - iter 89/893 - loss 0.01255689 - time (sec): 7.85 - samples/sec: 3339.00 - lr: 0.000010 - momentum: 0.000000
179
+ 2023-10-17 12:21:28,038 epoch 8 - iter 178/893 - loss 0.01548700 - time (sec): 15.14 - samples/sec: 3389.82 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 12:21:34,919 epoch 8 - iter 267/893 - loss 0.01594896 - time (sec): 22.02 - samples/sec: 3458.08 - lr: 0.000009 - momentum: 0.000000
181
+ 2023-10-17 12:21:41,668 epoch 8 - iter 356/893 - loss 0.01712178 - time (sec): 28.77 - samples/sec: 3468.64 - lr: 0.000009 - momentum: 0.000000
182
+ 2023-10-17 12:21:48,918 epoch 8 - iter 445/893 - loss 0.01789972 - time (sec): 36.02 - samples/sec: 3464.56 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 12:21:56,104 epoch 8 - iter 534/893 - loss 0.01905710 - time (sec): 43.20 - samples/sec: 3475.53 - lr: 0.000008 - momentum: 0.000000
184
+ 2023-10-17 12:22:03,342 epoch 8 - iter 623/893 - loss 0.01767420 - time (sec): 50.44 - samples/sec: 3483.39 - lr: 0.000008 - momentum: 0.000000
185
+ 2023-10-17 12:22:10,713 epoch 8 - iter 712/893 - loss 0.01702791 - time (sec): 57.81 - samples/sec: 3501.71 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 12:22:17,326 epoch 8 - iter 801/893 - loss 0.01763268 - time (sec): 64.43 - samples/sec: 3507.31 - lr: 0.000007 - momentum: 0.000000
187
+ 2023-10-17 12:22:23,553 epoch 8 - iter 890/893 - loss 0.01731707 - time (sec): 70.65 - samples/sec: 3511.06 - lr: 0.000007 - momentum: 0.000000
188
+ 2023-10-17 12:22:23,766 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 12:22:23,766 EPOCH 8 done: loss 0.0173 - lr: 0.000007
190
+ 2023-10-17 12:22:27,877 DEV : loss 0.19628190994262695 - f1-score (micro avg) 0.8153
191
+ 2023-10-17 12:22:27,893 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-17 12:22:35,088 epoch 9 - iter 89/893 - loss 0.01038174 - time (sec): 7.19 - samples/sec: 3555.84 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 12:22:42,202 epoch 9 - iter 178/893 - loss 0.01419247 - time (sec): 14.31 - samples/sec: 3556.98 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 12:22:49,188 epoch 9 - iter 267/893 - loss 0.01418667 - time (sec): 21.29 - samples/sec: 3594.57 - lr: 0.000006 - momentum: 0.000000
195
+ 2023-10-17 12:22:56,073 epoch 9 - iter 356/893 - loss 0.01361146 - time (sec): 28.18 - samples/sec: 3566.67 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 12:23:02,914 epoch 9 - iter 445/893 - loss 0.01423414 - time (sec): 35.02 - samples/sec: 3581.62 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 12:23:09,495 epoch 9 - iter 534/893 - loss 0.01463469 - time (sec): 41.60 - samples/sec: 3606.77 - lr: 0.000005 - momentum: 0.000000
198
+ 2023-10-17 12:23:16,280 epoch 9 - iter 623/893 - loss 0.01461206 - time (sec): 48.39 - samples/sec: 3605.21 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 12:23:22,944 epoch 9 - iter 712/893 - loss 0.01414789 - time (sec): 55.05 - samples/sec: 3593.53 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 12:23:29,888 epoch 9 - iter 801/893 - loss 0.01360551 - time (sec): 61.99 - samples/sec: 3598.82 - lr: 0.000004 - momentum: 0.000000
201
+ 2023-10-17 12:23:37,203 epoch 9 - iter 890/893 - loss 0.01349250 - time (sec): 69.31 - samples/sec: 3579.73 - lr: 0.000003 - momentum: 0.000000
202
+ 2023-10-17 12:23:37,405 ----------------------------------------------------------------------------------------------------
203
+ 2023-10-17 12:23:37,406 EPOCH 9 done: loss 0.0135 - lr: 0.000003
204
+ 2023-10-17 12:23:42,085 DEV : loss 0.2013043463230133 - f1-score (micro avg) 0.8124
205
+ 2023-10-17 12:23:42,102 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-17 12:23:49,278 epoch 10 - iter 89/893 - loss 0.01244930 - time (sec): 7.17 - samples/sec: 3525.80 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-17 12:23:56,454 epoch 10 - iter 178/893 - loss 0.01214030 - time (sec): 14.35 - samples/sec: 3488.04 - lr: 0.000003 - momentum: 0.000000
208
+ 2023-10-17 12:24:03,245 epoch 10 - iter 267/893 - loss 0.01122784 - time (sec): 21.14 - samples/sec: 3515.99 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 12:24:10,345 epoch 10 - iter 356/893 - loss 0.01032258 - time (sec): 28.24 - samples/sec: 3545.28 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 12:24:17,003 epoch 10 - iter 445/893 - loss 0.01111884 - time (sec): 34.90 - samples/sec: 3575.90 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 12:24:24,085 epoch 10 - iter 534/893 - loss 0.01106441 - time (sec): 41.98 - samples/sec: 3536.02 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 12:24:30,739 epoch 10 - iter 623/893 - loss 0.01038407 - time (sec): 48.64 - samples/sec: 3544.80 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 12:24:37,750 epoch 10 - iter 712/893 - loss 0.01024039 - time (sec): 55.65 - samples/sec: 3529.60 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 12:24:44,628 epoch 10 - iter 801/893 - loss 0.00986859 - time (sec): 62.52 - samples/sec: 3541.25 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 12:24:51,860 epoch 10 - iter 890/893 - loss 0.00988030 - time (sec): 69.76 - samples/sec: 3556.93 - lr: 0.000000 - momentum: 0.000000
216
+ 2023-10-17 12:24:52,068 ----------------------------------------------------------------------------------------------------
217
+ 2023-10-17 12:24:52,068 EPOCH 10 done: loss 0.0099 - lr: 0.000000
218
+ 2023-10-17 12:24:56,699 DEV : loss 0.1994680017232895 - f1-score (micro avg) 0.821
219
+ 2023-10-17 12:24:57,112 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-17 12:24:57,113 Loading model from best epoch ...
221
+ 2023-10-17 12:24:59,004 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
222
+ 2023-10-17 12:25:08,749
223
+ Results:
224
+ - F-score (micro) 0.7033
225
+ - F-score (macro) 0.638
226
+ - Accuracy 0.5639
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ LOC 0.7209 0.7242 0.7226 1095
232
+ PER 0.7767 0.7836 0.7801 1012
233
+ ORG 0.4123 0.6190 0.4950 357
234
+ HumanProd 0.4600 0.6970 0.5542 33
235
+
236
+ micro avg 0.6760 0.7329 0.7033 2497
237
+ macro avg 0.5925 0.7060 0.6380 2497
238
+ weighted avg 0.6959 0.7329 0.7111 2497
239
+
240
+ 2023-10-17 12:25:08,749 ----------------------------------------------------------------------------------------------------