Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
f08205b
·
1 Parent(s): b21f156

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.1697551811.0468bd9609d6.7281.8 +3 -0
  5. test.tsv +0 -0
  6. training.log +239 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28b97851aabcbfa85907dd0bb51aa8acea49ae52afa657930efa18fa9add2f61
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 14:11:23 0.0000 0.6024 0.1049 0.6762 0.7728 0.7213 0.5904
3
+ 2 14:12:37 0.0000 0.1051 0.1065 0.7263 0.8122 0.7669 0.6412
4
+ 3 14:13:52 0.0000 0.0643 0.1115 0.7908 0.8231 0.8067 0.6899
5
+ 4 14:15:07 0.0000 0.0457 0.1470 0.7721 0.8204 0.7955 0.6783
6
+ 5 14:16:21 0.0000 0.0350 0.1706 0.8047 0.8299 0.8171 0.7068
7
+ 6 14:17:36 0.0000 0.0283 0.1936 0.7891 0.8299 0.8090 0.6948
8
+ 7 14:18:51 0.0000 0.0238 0.1905 0.7918 0.8435 0.8169 0.7078
9
+ 8 14:20:05 0.0000 0.0177 0.1925 0.8211 0.8367 0.8288 0.7244
10
+ 9 14:21:20 0.0000 0.0122 0.2041 0.8068 0.8354 0.8209 0.7131
11
+ 10 14:22:35 0.0000 0.0094 0.2141 0.7987 0.8367 0.8173 0.7077
runs/events.out.tfevents.1697551811.0468bd9609d6.7281.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972b7ed09b695be9955cec4451f38251fd4052d0d3798ad702e12fdc7b8449d6
3
+ size 502461
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 14:10:11,532 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 14:10:11,533 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 14:10:11,533 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 14:10:11,533 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 14:10:11,533 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 14:10:11,533 Train: 7142 sentences
51
+ 2023-10-17 14:10:11,533 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 14:10:11,533 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 14:10:11,534 Training Params:
54
+ 2023-10-17 14:10:11,534 - learning_rate: "3e-05"
55
+ 2023-10-17 14:10:11,534 - mini_batch_size: "8"
56
+ 2023-10-17 14:10:11,534 - max_epochs: "10"
57
+ 2023-10-17 14:10:11,534 - shuffle: "True"
58
+ 2023-10-17 14:10:11,534 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 14:10:11,534 Plugins:
60
+ 2023-10-17 14:10:11,534 - TensorboardLogger
61
+ 2023-10-17 14:10:11,534 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 14:10:11,534 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 14:10:11,534 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 14:10:11,534 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 14:10:11,534 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 14:10:11,534 Computation:
67
+ 2023-10-17 14:10:11,534 - compute on device: cuda:0
68
+ 2023-10-17 14:10:11,534 - embedding storage: none
69
+ 2023-10-17 14:10:11,534 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 14:10:11,534 Model training base path: "hmbench-newseye/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3"
71
+ 2023-10-17 14:10:11,534 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 14:10:11,534 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 14:10:11,534 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 14:10:18,101 epoch 1 - iter 89/893 - loss 3.18821826 - time (sec): 6.57 - samples/sec: 3663.50 - lr: 0.000003 - momentum: 0.000000
75
+ 2023-10-17 14:10:24,900 epoch 1 - iter 178/893 - loss 2.02730331 - time (sec): 13.37 - samples/sec: 3655.29 - lr: 0.000006 - momentum: 0.000000
76
+ 2023-10-17 14:10:31,279 epoch 1 - iter 267/893 - loss 1.54250315 - time (sec): 19.74 - samples/sec: 3620.84 - lr: 0.000009 - momentum: 0.000000
77
+ 2023-10-17 14:10:38,176 epoch 1 - iter 356/893 - loss 1.22936425 - time (sec): 26.64 - samples/sec: 3648.31 - lr: 0.000012 - momentum: 0.000000
78
+ 2023-10-17 14:10:45,399 epoch 1 - iter 445/893 - loss 1.03366668 - time (sec): 33.86 - samples/sec: 3618.90 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-17 14:10:52,409 epoch 1 - iter 534/893 - loss 0.90453755 - time (sec): 40.87 - samples/sec: 3593.88 - lr: 0.000018 - momentum: 0.000000
80
+ 2023-10-17 14:10:59,662 epoch 1 - iter 623/893 - loss 0.79689601 - time (sec): 48.13 - samples/sec: 3580.57 - lr: 0.000021 - momentum: 0.000000
81
+ 2023-10-17 14:11:06,903 epoch 1 - iter 712/893 - loss 0.71218918 - time (sec): 55.37 - samples/sec: 3595.84 - lr: 0.000024 - momentum: 0.000000
82
+ 2023-10-17 14:11:13,804 epoch 1 - iter 801/893 - loss 0.65097764 - time (sec): 62.27 - samples/sec: 3605.59 - lr: 0.000027 - momentum: 0.000000
83
+ 2023-10-17 14:11:20,259 epoch 1 - iter 890/893 - loss 0.60396316 - time (sec): 68.72 - samples/sec: 3607.87 - lr: 0.000030 - momentum: 0.000000
84
+ 2023-10-17 14:11:20,494 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 14:11:20,494 EPOCH 1 done: loss 0.6024 - lr: 0.000030
86
+ 2023-10-17 14:11:23,692 DEV : loss 0.10485294461250305 - f1-score (micro avg) 0.7213
87
+ 2023-10-17 14:11:23,708 saving best model
88
+ 2023-10-17 14:11:24,047 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 14:11:30,654 epoch 2 - iter 89/893 - loss 0.12053920 - time (sec): 6.61 - samples/sec: 3623.05 - lr: 0.000030 - momentum: 0.000000
90
+ 2023-10-17 14:11:37,814 epoch 2 - iter 178/893 - loss 0.12089620 - time (sec): 13.77 - samples/sec: 3633.53 - lr: 0.000029 - momentum: 0.000000
91
+ 2023-10-17 14:11:44,955 epoch 2 - iter 267/893 - loss 0.11493666 - time (sec): 20.91 - samples/sec: 3580.12 - lr: 0.000029 - momentum: 0.000000
92
+ 2023-10-17 14:11:51,723 epoch 2 - iter 356/893 - loss 0.11530044 - time (sec): 27.67 - samples/sec: 3604.47 - lr: 0.000029 - momentum: 0.000000
93
+ 2023-10-17 14:11:58,309 epoch 2 - iter 445/893 - loss 0.11276770 - time (sec): 34.26 - samples/sec: 3603.94 - lr: 0.000028 - momentum: 0.000000
94
+ 2023-10-17 14:12:05,445 epoch 2 - iter 534/893 - loss 0.10981634 - time (sec): 41.40 - samples/sec: 3593.09 - lr: 0.000028 - momentum: 0.000000
95
+ 2023-10-17 14:12:12,466 epoch 2 - iter 623/893 - loss 0.11043125 - time (sec): 48.42 - samples/sec: 3564.81 - lr: 0.000028 - momentum: 0.000000
96
+ 2023-10-17 14:12:19,698 epoch 2 - iter 712/893 - loss 0.10651423 - time (sec): 55.65 - samples/sec: 3564.13 - lr: 0.000027 - momentum: 0.000000
97
+ 2023-10-17 14:12:26,705 epoch 2 - iter 801/893 - loss 0.10556302 - time (sec): 62.66 - samples/sec: 3571.07 - lr: 0.000027 - momentum: 0.000000
98
+ 2023-10-17 14:12:33,493 epoch 2 - iter 890/893 - loss 0.10507616 - time (sec): 69.44 - samples/sec: 3571.62 - lr: 0.000027 - momentum: 0.000000
99
+ 2023-10-17 14:12:33,703 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 14:12:33,703 EPOCH 2 done: loss 0.1051 - lr: 0.000027
101
+ 2023-10-17 14:12:37,950 DEV : loss 0.10654985904693604 - f1-score (micro avg) 0.7669
102
+ 2023-10-17 14:12:37,967 saving best model
103
+ 2023-10-17 14:12:38,428 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 14:12:45,119 epoch 3 - iter 89/893 - loss 0.06949100 - time (sec): 6.69 - samples/sec: 3371.75 - lr: 0.000026 - momentum: 0.000000
105
+ 2023-10-17 14:12:51,956 epoch 3 - iter 178/893 - loss 0.06461281 - time (sec): 13.53 - samples/sec: 3555.66 - lr: 0.000026 - momentum: 0.000000
106
+ 2023-10-17 14:12:58,796 epoch 3 - iter 267/893 - loss 0.06349975 - time (sec): 20.37 - samples/sec: 3594.82 - lr: 0.000026 - momentum: 0.000000
107
+ 2023-10-17 14:13:05,526 epoch 3 - iter 356/893 - loss 0.06379984 - time (sec): 27.10 - samples/sec: 3608.99 - lr: 0.000025 - momentum: 0.000000
108
+ 2023-10-17 14:13:12,774 epoch 3 - iter 445/893 - loss 0.06225707 - time (sec): 34.34 - samples/sec: 3558.57 - lr: 0.000025 - momentum: 0.000000
109
+ 2023-10-17 14:13:19,621 epoch 3 - iter 534/893 - loss 0.06365270 - time (sec): 41.19 - samples/sec: 3538.11 - lr: 0.000025 - momentum: 0.000000
110
+ 2023-10-17 14:13:26,744 epoch 3 - iter 623/893 - loss 0.06442220 - time (sec): 48.31 - samples/sec: 3563.22 - lr: 0.000024 - momentum: 0.000000
111
+ 2023-10-17 14:13:33,715 epoch 3 - iter 712/893 - loss 0.06324340 - time (sec): 55.29 - samples/sec: 3579.46 - lr: 0.000024 - momentum: 0.000000
112
+ 2023-10-17 14:13:40,729 epoch 3 - iter 801/893 - loss 0.06243522 - time (sec): 62.30 - samples/sec: 3596.74 - lr: 0.000024 - momentum: 0.000000
113
+ 2023-10-17 14:13:48,068 epoch 3 - iter 890/893 - loss 0.06421146 - time (sec): 69.64 - samples/sec: 3560.36 - lr: 0.000023 - momentum: 0.000000
114
+ 2023-10-17 14:13:48,284 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 14:13:48,285 EPOCH 3 done: loss 0.0643 - lr: 0.000023
116
+ 2023-10-17 14:13:52,398 DEV : loss 0.11152768135070801 - f1-score (micro avg) 0.8067
117
+ 2023-10-17 14:13:52,414 saving best model
118
+ 2023-10-17 14:13:52,855 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 14:13:59,746 epoch 4 - iter 89/893 - loss 0.03606401 - time (sec): 6.89 - samples/sec: 3522.41 - lr: 0.000023 - momentum: 0.000000
120
+ 2023-10-17 14:14:07,251 epoch 4 - iter 178/893 - loss 0.04211063 - time (sec): 14.39 - samples/sec: 3545.46 - lr: 0.000023 - momentum: 0.000000
121
+ 2023-10-17 14:14:14,390 epoch 4 - iter 267/893 - loss 0.04187109 - time (sec): 21.53 - samples/sec: 3547.94 - lr: 0.000022 - momentum: 0.000000
122
+ 2023-10-17 14:14:21,377 epoch 4 - iter 356/893 - loss 0.04455749 - time (sec): 28.52 - samples/sec: 3538.29 - lr: 0.000022 - momentum: 0.000000
123
+ 2023-10-17 14:14:28,045 epoch 4 - iter 445/893 - loss 0.04511641 - time (sec): 35.19 - samples/sec: 3562.25 - lr: 0.000022 - momentum: 0.000000
124
+ 2023-10-17 14:14:34,935 epoch 4 - iter 534/893 - loss 0.04363248 - time (sec): 42.08 - samples/sec: 3561.73 - lr: 0.000021 - momentum: 0.000000
125
+ 2023-10-17 14:14:41,614 epoch 4 - iter 623/893 - loss 0.04457538 - time (sec): 48.75 - samples/sec: 3544.96 - lr: 0.000021 - momentum: 0.000000
126
+ 2023-10-17 14:14:48,764 epoch 4 - iter 712/893 - loss 0.04527644 - time (sec): 55.90 - samples/sec: 3539.53 - lr: 0.000021 - momentum: 0.000000
127
+ 2023-10-17 14:14:55,674 epoch 4 - iter 801/893 - loss 0.04599751 - time (sec): 62.81 - samples/sec: 3548.10 - lr: 0.000020 - momentum: 0.000000
128
+ 2023-10-17 14:15:02,549 epoch 4 - iter 890/893 - loss 0.04579098 - time (sec): 69.69 - samples/sec: 3559.69 - lr: 0.000020 - momentum: 0.000000
129
+ 2023-10-17 14:15:02,749 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 14:15:02,749 EPOCH 4 done: loss 0.0457 - lr: 0.000020
131
+ 2023-10-17 14:15:07,472 DEV : loss 0.14700356125831604 - f1-score (micro avg) 0.7955
132
+ 2023-10-17 14:15:07,490 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 14:15:14,548 epoch 5 - iter 89/893 - loss 0.02159756 - time (sec): 7.06 - samples/sec: 3494.49 - lr: 0.000020 - momentum: 0.000000
134
+ 2023-10-17 14:15:21,637 epoch 5 - iter 178/893 - loss 0.02588404 - time (sec): 14.15 - samples/sec: 3591.19 - lr: 0.000019 - momentum: 0.000000
135
+ 2023-10-17 14:15:28,996 epoch 5 - iter 267/893 - loss 0.03084829 - time (sec): 21.51 - samples/sec: 3568.58 - lr: 0.000019 - momentum: 0.000000
136
+ 2023-10-17 14:15:35,859 epoch 5 - iter 356/893 - loss 0.03225333 - time (sec): 28.37 - samples/sec: 3579.62 - lr: 0.000019 - momentum: 0.000000
137
+ 2023-10-17 14:15:42,592 epoch 5 - iter 445/893 - loss 0.03370496 - time (sec): 35.10 - samples/sec: 3573.10 - lr: 0.000018 - momentum: 0.000000
138
+ 2023-10-17 14:15:49,750 epoch 5 - iter 534/893 - loss 0.03350192 - time (sec): 42.26 - samples/sec: 3586.11 - lr: 0.000018 - momentum: 0.000000
139
+ 2023-10-17 14:15:56,643 epoch 5 - iter 623/893 - loss 0.03401656 - time (sec): 49.15 - samples/sec: 3578.04 - lr: 0.000018 - momentum: 0.000000
140
+ 2023-10-17 14:16:03,722 epoch 5 - iter 712/893 - loss 0.03477601 - time (sec): 56.23 - samples/sec: 3560.67 - lr: 0.000017 - momentum: 0.000000
141
+ 2023-10-17 14:16:10,505 epoch 5 - iter 801/893 - loss 0.03446752 - time (sec): 63.01 - samples/sec: 3563.60 - lr: 0.000017 - momentum: 0.000000
142
+ 2023-10-17 14:16:17,059 epoch 5 - iter 890/893 - loss 0.03506799 - time (sec): 69.57 - samples/sec: 3566.78 - lr: 0.000017 - momentum: 0.000000
143
+ 2023-10-17 14:16:17,273 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 14:16:17,273 EPOCH 5 done: loss 0.0350 - lr: 0.000017
145
+ 2023-10-17 14:16:21,422 DEV : loss 0.17064201831817627 - f1-score (micro avg) 0.8171
146
+ 2023-10-17 14:16:21,439 saving best model
147
+ 2023-10-17 14:16:21,902 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 14:16:28,780 epoch 6 - iter 89/893 - loss 0.01857424 - time (sec): 6.88 - samples/sec: 3577.99 - lr: 0.000016 - momentum: 0.000000
149
+ 2023-10-17 14:16:35,905 epoch 6 - iter 178/893 - loss 0.02937566 - time (sec): 14.00 - samples/sec: 3638.01 - lr: 0.000016 - momentum: 0.000000
150
+ 2023-10-17 14:16:42,905 epoch 6 - iter 267/893 - loss 0.02608151 - time (sec): 21.00 - samples/sec: 3592.78 - lr: 0.000016 - momentum: 0.000000
151
+ 2023-10-17 14:16:49,575 epoch 6 - iter 356/893 - loss 0.02657817 - time (sec): 27.67 - samples/sec: 3595.01 - lr: 0.000015 - momentum: 0.000000
152
+ 2023-10-17 14:16:56,500 epoch 6 - iter 445/893 - loss 0.02885372 - time (sec): 34.60 - samples/sec: 3573.37 - lr: 0.000015 - momentum: 0.000000
153
+ 2023-10-17 14:17:03,373 epoch 6 - iter 534/893 - loss 0.02838909 - time (sec): 41.47 - samples/sec: 3571.61 - lr: 0.000015 - momentum: 0.000000
154
+ 2023-10-17 14:17:10,284 epoch 6 - iter 623/893 - loss 0.02811999 - time (sec): 48.38 - samples/sec: 3578.24 - lr: 0.000014 - momentum: 0.000000
155
+ 2023-10-17 14:17:17,204 epoch 6 - iter 712/893 - loss 0.02761914 - time (sec): 55.30 - samples/sec: 3581.39 - lr: 0.000014 - momentum: 0.000000
156
+ 2023-10-17 14:17:24,288 epoch 6 - iter 801/893 - loss 0.02780382 - time (sec): 62.38 - samples/sec: 3579.86 - lr: 0.000014 - momentum: 0.000000
157
+ 2023-10-17 14:17:31,228 epoch 6 - iter 890/893 - loss 0.02839401 - time (sec): 69.32 - samples/sec: 3578.28 - lr: 0.000013 - momentum: 0.000000
158
+ 2023-10-17 14:17:31,447 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 14:17:31,447 EPOCH 6 done: loss 0.0283 - lr: 0.000013
160
+ 2023-10-17 14:17:36,227 DEV : loss 0.1936318576335907 - f1-score (micro avg) 0.809
161
+ 2023-10-17 14:17:36,243 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-17 14:17:43,564 epoch 7 - iter 89/893 - loss 0.02232161 - time (sec): 7.32 - samples/sec: 3518.53 - lr: 0.000013 - momentum: 0.000000
163
+ 2023-10-17 14:17:50,393 epoch 7 - iter 178/893 - loss 0.02338449 - time (sec): 14.15 - samples/sec: 3547.67 - lr: 0.000013 - momentum: 0.000000
164
+ 2023-10-17 14:17:57,533 epoch 7 - iter 267/893 - loss 0.02202040 - time (sec): 21.29 - samples/sec: 3505.95 - lr: 0.000012 - momentum: 0.000000
165
+ 2023-10-17 14:18:04,965 epoch 7 - iter 356/893 - loss 0.02401679 - time (sec): 28.72 - samples/sec: 3515.78 - lr: 0.000012 - momentum: 0.000000
166
+ 2023-10-17 14:18:11,827 epoch 7 - iter 445/893 - loss 0.02427825 - time (sec): 35.58 - samples/sec: 3528.34 - lr: 0.000012 - momentum: 0.000000
167
+ 2023-10-17 14:18:19,045 epoch 7 - iter 534/893 - loss 0.02405158 - time (sec): 42.80 - samples/sec: 3525.53 - lr: 0.000011 - momentum: 0.000000
168
+ 2023-10-17 14:18:25,907 epoch 7 - iter 623/893 - loss 0.02394111 - time (sec): 49.66 - samples/sec: 3532.13 - lr: 0.000011 - momentum: 0.000000
169
+ 2023-10-17 14:18:32,477 epoch 7 - iter 712/893 - loss 0.02434482 - time (sec): 56.23 - samples/sec: 3531.54 - lr: 0.000011 - momentum: 0.000000
170
+ 2023-10-17 14:18:39,111 epoch 7 - iter 801/893 - loss 0.02382729 - time (sec): 62.87 - samples/sec: 3549.30 - lr: 0.000010 - momentum: 0.000000
171
+ 2023-10-17 14:18:46,127 epoch 7 - iter 890/893 - loss 0.02377225 - time (sec): 69.88 - samples/sec: 3552.15 - lr: 0.000010 - momentum: 0.000000
172
+ 2023-10-17 14:18:46,297 ----------------------------------------------------------------------------------------------------
173
+ 2023-10-17 14:18:46,298 EPOCH 7 done: loss 0.0238 - lr: 0.000010
174
+ 2023-10-17 14:18:51,143 DEV : loss 0.19045308232307434 - f1-score (micro avg) 0.8169
175
+ 2023-10-17 14:18:51,161 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 14:18:58,365 epoch 8 - iter 89/893 - loss 0.01688687 - time (sec): 7.20 - samples/sec: 3308.59 - lr: 0.000010 - momentum: 0.000000
177
+ 2023-10-17 14:19:05,754 epoch 8 - iter 178/893 - loss 0.01507813 - time (sec): 14.59 - samples/sec: 3414.28 - lr: 0.000009 - momentum: 0.000000
178
+ 2023-10-17 14:19:12,379 epoch 8 - iter 267/893 - loss 0.01659736 - time (sec): 21.22 - samples/sec: 3411.65 - lr: 0.000009 - momentum: 0.000000
179
+ 2023-10-17 14:19:19,722 epoch 8 - iter 356/893 - loss 0.01634020 - time (sec): 28.56 - samples/sec: 3417.32 - lr: 0.000009 - momentum: 0.000000
180
+ 2023-10-17 14:19:26,948 epoch 8 - iter 445/893 - loss 0.01807096 - time (sec): 35.79 - samples/sec: 3447.89 - lr: 0.000008 - momentum: 0.000000
181
+ 2023-10-17 14:19:33,565 epoch 8 - iter 534/893 - loss 0.01770225 - time (sec): 42.40 - samples/sec: 3499.20 - lr: 0.000008 - momentum: 0.000000
182
+ 2023-10-17 14:19:40,128 epoch 8 - iter 623/893 - loss 0.01823384 - time (sec): 48.97 - samples/sec: 3525.85 - lr: 0.000008 - momentum: 0.000000
183
+ 2023-10-17 14:19:46,969 epoch 8 - iter 712/893 - loss 0.01825900 - time (sec): 55.81 - samples/sec: 3519.18 - lr: 0.000007 - momentum: 0.000000
184
+ 2023-10-17 14:19:53,671 epoch 8 - iter 801/893 - loss 0.01738740 - time (sec): 62.51 - samples/sec: 3527.35 - lr: 0.000007 - momentum: 0.000000
185
+ 2023-10-17 14:20:01,160 epoch 8 - iter 890/893 - loss 0.01771823 - time (sec): 70.00 - samples/sec: 3541.43 - lr: 0.000007 - momentum: 0.000000
186
+ 2023-10-17 14:20:01,398 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 14:20:01,398 EPOCH 8 done: loss 0.0177 - lr: 0.000007
188
+ 2023-10-17 14:20:05,566 DEV : loss 0.192477285861969 - f1-score (micro avg) 0.8288
189
+ 2023-10-17 14:20:05,583 saving best model
190
+ 2023-10-17 14:20:06,038 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-17 14:20:13,064 epoch 9 - iter 89/893 - loss 0.01801821 - time (sec): 7.02 - samples/sec: 3548.33 - lr: 0.000006 - momentum: 0.000000
192
+ 2023-10-17 14:20:20,095 epoch 9 - iter 178/893 - loss 0.01400252 - time (sec): 14.05 - samples/sec: 3497.31 - lr: 0.000006 - momentum: 0.000000
193
+ 2023-10-17 14:20:27,466 epoch 9 - iter 267/893 - loss 0.01241543 - time (sec): 21.43 - samples/sec: 3498.11 - lr: 0.000006 - momentum: 0.000000
194
+ 2023-10-17 14:20:34,094 epoch 9 - iter 356/893 - loss 0.01183902 - time (sec): 28.05 - samples/sec: 3533.40 - lr: 0.000005 - momentum: 0.000000
195
+ 2023-10-17 14:20:40,711 epoch 9 - iter 445/893 - loss 0.01202647 - time (sec): 34.67 - samples/sec: 3546.02 - lr: 0.000005 - momentum: 0.000000
196
+ 2023-10-17 14:20:47,463 epoch 9 - iter 534/893 - loss 0.01194551 - time (sec): 41.42 - samples/sec: 3584.17 - lr: 0.000005 - momentum: 0.000000
197
+ 2023-10-17 14:20:54,584 epoch 9 - iter 623/893 - loss 0.01167993 - time (sec): 48.54 - samples/sec: 3589.57 - lr: 0.000004 - momentum: 0.000000
198
+ 2023-10-17 14:21:01,573 epoch 9 - iter 712/893 - loss 0.01218580 - time (sec): 55.53 - samples/sec: 3591.70 - lr: 0.000004 - momentum: 0.000000
199
+ 2023-10-17 14:21:08,429 epoch 9 - iter 801/893 - loss 0.01218316 - time (sec): 62.39 - samples/sec: 3573.44 - lr: 0.000004 - momentum: 0.000000
200
+ 2023-10-17 14:21:15,572 epoch 9 - iter 890/893 - loss 0.01221895 - time (sec): 69.53 - samples/sec: 3566.01 - lr: 0.000003 - momentum: 0.000000
201
+ 2023-10-17 14:21:15,802 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-17 14:21:15,802 EPOCH 9 done: loss 0.0122 - lr: 0.000003
203
+ 2023-10-17 14:21:20,642 DEV : loss 0.20407408475875854 - f1-score (micro avg) 0.8209
204
+ 2023-10-17 14:21:20,661 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-17 14:21:27,776 epoch 10 - iter 89/893 - loss 0.00971997 - time (sec): 7.11 - samples/sec: 3615.69 - lr: 0.000003 - momentum: 0.000000
206
+ 2023-10-17 14:21:34,502 epoch 10 - iter 178/893 - loss 0.00955405 - time (sec): 13.84 - samples/sec: 3536.48 - lr: 0.000003 - momentum: 0.000000
207
+ 2023-10-17 14:21:41,337 epoch 10 - iter 267/893 - loss 0.00944326 - time (sec): 20.68 - samples/sec: 3600.81 - lr: 0.000002 - momentum: 0.000000
208
+ 2023-10-17 14:21:47,925 epoch 10 - iter 356/893 - loss 0.00930071 - time (sec): 27.26 - samples/sec: 3574.09 - lr: 0.000002 - momentum: 0.000000
209
+ 2023-10-17 14:21:55,162 epoch 10 - iter 445/893 - loss 0.00925717 - time (sec): 34.50 - samples/sec: 3549.48 - lr: 0.000002 - momentum: 0.000000
210
+ 2023-10-17 14:22:01,938 epoch 10 - iter 534/893 - loss 0.00902192 - time (sec): 41.28 - samples/sec: 3535.95 - lr: 0.000001 - momentum: 0.000000
211
+ 2023-10-17 14:22:09,683 epoch 10 - iter 623/893 - loss 0.00924880 - time (sec): 49.02 - samples/sec: 3531.34 - lr: 0.000001 - momentum: 0.000000
212
+ 2023-10-17 14:22:16,544 epoch 10 - iter 712/893 - loss 0.00949301 - time (sec): 55.88 - samples/sec: 3530.79 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 14:22:23,898 epoch 10 - iter 801/893 - loss 0.00974846 - time (sec): 63.24 - samples/sec: 3537.12 - lr: 0.000000 - momentum: 0.000000
214
+ 2023-10-17 14:22:30,922 epoch 10 - iter 890/893 - loss 0.00937198 - time (sec): 70.26 - samples/sec: 3530.47 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 14:22:31,113 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-17 14:22:31,113 EPOCH 10 done: loss 0.0094 - lr: 0.000000
217
+ 2023-10-17 14:22:35,808 DEV : loss 0.21412597596645355 - f1-score (micro avg) 0.8173
218
+ 2023-10-17 14:22:36,161 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 14:22:36,162 Loading model from best epoch ...
220
+ 2023-10-17 14:22:37,524 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
221
+ 2023-10-17 14:22:47,325
222
+ Results:
223
+ - F-score (micro) 0.7081
224
+ - F-score (macro) 0.6378
225
+ - Accuracy 0.5674
226
+
227
+ By class:
228
+ precision recall f1-score support
229
+
230
+ LOC 0.7379 0.6941 0.7153 1095
231
+ PER 0.8155 0.7777 0.7962 1012
232
+ ORG 0.4339 0.6162 0.5093 357
233
+ HumanProd 0.4000 0.7879 0.5306 33
234
+
235
+ micro avg 0.6985 0.7181 0.7081 2497
236
+ macro avg 0.5968 0.7190 0.6378 2497
237
+ weighted avg 0.7214 0.7181 0.7162 2497
238
+
239
+ 2023-10-17 14:22:47,325 ----------------------------------------------------------------------------------------------------