Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
379dffb
•
1 Parent(s): 868055b

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.1697584848.bce904bcef33.2482.17 +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:a5a53f0a8ec834209b161861c7470444b656eb7e4b610e7676cc6cdc8bffce26
3
+ size 440966725
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 23:21:46 0.0000 0.5687 0.1068 0.7435 0.7818 0.7621 0.6337
3
+ 2 23:22:49 0.0000 0.1178 0.1396 0.7474 0.8202 0.7821 0.6593
4
+ 3 23:23:52 0.0000 0.0737 0.1246 0.8038 0.8236 0.8136 0.7080
5
+ 4 23:24:56 0.0000 0.0506 0.1510 0.8133 0.8310 0.8221 0.7212
6
+ 5 23:25:59 0.0000 0.0357 0.1606 0.8235 0.8763 0.8491 0.7552
7
+ 6 23:27:03 0.0000 0.0247 0.1865 0.8171 0.8522 0.8343 0.7388
8
+ 7 23:28:06 0.0000 0.0161 0.1937 0.8231 0.8499 0.8363 0.7409
9
+ 8 23:29:08 0.0000 0.0099 0.2119 0.8470 0.8431 0.8450 0.7491
10
+ 9 23:30:11 0.0000 0.0072 0.2077 0.8336 0.8608 0.8470 0.7511
11
+ 10 23:31:14 0.0000 0.0047 0.2188 0.8459 0.8551 0.8505 0.7575
runs/events.out.tfevents.1697584848.bce904bcef33.2482.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53d956387d01676cc50cd9f1be83a296520da17033eda57d1b3103d04cf15a8
3
+ size 415388
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 23:20:48,607 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 23:20:48,608 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=21, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 23:20:48,608 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 23:20:48,609 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
48
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
49
+ 2023-10-17 23:20:48,609 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 23:20:48,609 Train: 5901 sentences
51
+ 2023-10-17 23:20:48,609 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 23:20:48,609 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 23:20:48,609 Training Params:
54
+ 2023-10-17 23:20:48,609 - learning_rate: "5e-05"
55
+ 2023-10-17 23:20:48,609 - mini_batch_size: "8"
56
+ 2023-10-17 23:20:48,609 - max_epochs: "10"
57
+ 2023-10-17 23:20:48,609 - shuffle: "True"
58
+ 2023-10-17 23:20:48,609 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 23:20:48,609 Plugins:
60
+ 2023-10-17 23:20:48,609 - TensorboardLogger
61
+ 2023-10-17 23:20:48,609 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 23:20:48,609 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 23:20:48,609 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 23:20:48,609 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 23:20:48,609 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 23:20:48,609 Computation:
67
+ 2023-10-17 23:20:48,610 - compute on device: cuda:0
68
+ 2023-10-17 23:20:48,610 - embedding storage: none
69
+ 2023-10-17 23:20:48,610 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 23:20:48,610 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
71
+ 2023-10-17 23:20:48,610 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 23:20:48,610 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 23:20:48,610 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 23:20:53,860 epoch 1 - iter 73/738 - loss 2.85474195 - time (sec): 5.25 - samples/sec: 3208.60 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 23:20:59,150 epoch 1 - iter 146/738 - loss 1.78283901 - time (sec): 10.54 - samples/sec: 3224.58 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 23:21:04,724 epoch 1 - iter 219/738 - loss 1.30841453 - time (sec): 16.11 - samples/sec: 3226.08 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 23:21:09,914 epoch 1 - iter 292/738 - loss 1.06896886 - time (sec): 21.30 - samples/sec: 3231.26 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 23:21:15,039 epoch 1 - iter 365/738 - loss 0.91894998 - time (sec): 26.43 - samples/sec: 3222.58 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 23:21:19,675 epoch 1 - iter 438/738 - loss 0.81887551 - time (sec): 31.06 - samples/sec: 3219.41 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 23:21:24,221 epoch 1 - iter 511/738 - loss 0.73797567 - time (sec): 35.61 - samples/sec: 3237.14 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 23:21:29,755 epoch 1 - iter 584/738 - loss 0.66529868 - time (sec): 41.14 - samples/sec: 3255.58 - lr: 0.000039 - momentum: 0.000000
82
+ 2023-10-17 23:21:34,453 epoch 1 - iter 657/738 - loss 0.61811551 - time (sec): 45.84 - samples/sec: 3244.08 - lr: 0.000044 - momentum: 0.000000
83
+ 2023-10-17 23:21:39,299 epoch 1 - iter 730/738 - loss 0.57233422 - time (sec): 50.69 - samples/sec: 3252.08 - lr: 0.000049 - momentum: 0.000000
84
+ 2023-10-17 23:21:39,786 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 23:21:39,786 EPOCH 1 done: loss 0.5687 - lr: 0.000049
86
+ 2023-10-17 23:21:46,270 DEV : loss 0.10680218786001205 - f1-score (micro avg) 0.7621
87
+ 2023-10-17 23:21:46,307 saving best model
88
+ 2023-10-17 23:21:46,722 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 23:21:52,044 epoch 2 - iter 73/738 - loss 0.12994419 - time (sec): 5.32 - samples/sec: 3181.55 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 23:21:57,252 epoch 2 - iter 146/738 - loss 0.11822578 - time (sec): 10.53 - samples/sec: 3134.72 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 23:22:02,033 epoch 2 - iter 219/738 - loss 0.11707730 - time (sec): 15.31 - samples/sec: 3223.08 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 23:22:06,854 epoch 2 - iter 292/738 - loss 0.12130436 - time (sec): 20.13 - samples/sec: 3238.62 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 23:22:11,419 epoch 2 - iter 365/738 - loss 0.12325461 - time (sec): 24.70 - samples/sec: 3254.74 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 23:22:16,413 epoch 2 - iter 438/738 - loss 0.12007044 - time (sec): 29.69 - samples/sec: 3274.88 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 23:22:21,264 epoch 2 - iter 511/738 - loss 0.11944053 - time (sec): 34.54 - samples/sec: 3296.37 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 23:22:27,327 epoch 2 - iter 584/738 - loss 0.11685937 - time (sec): 40.60 - samples/sec: 3287.09 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 23:22:32,387 epoch 2 - iter 657/738 - loss 0.11755883 - time (sec): 45.66 - samples/sec: 3277.59 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 23:22:36,985 epoch 2 - iter 730/738 - loss 0.11821850 - time (sec): 50.26 - samples/sec: 3280.65 - lr: 0.000045 - momentum: 0.000000
99
+ 2023-10-17 23:22:37,406 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 23:22:37,406 EPOCH 2 done: loss 0.1178 - lr: 0.000045
101
+ 2023-10-17 23:22:49,212 DEV : loss 0.13957878947257996 - f1-score (micro avg) 0.7821
102
+ 2023-10-17 23:22:49,247 saving best model
103
+ 2023-10-17 23:22:49,771 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 23:22:54,738 epoch 3 - iter 73/738 - loss 0.06730250 - time (sec): 4.96 - samples/sec: 3249.69 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 23:22:59,596 epoch 3 - iter 146/738 - loss 0.06639160 - time (sec): 9.82 - samples/sec: 3249.10 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 23:23:04,665 epoch 3 - iter 219/738 - loss 0.06940105 - time (sec): 14.89 - samples/sec: 3211.31 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 23:23:09,789 epoch 3 - iter 292/738 - loss 0.07344307 - time (sec): 20.02 - samples/sec: 3212.38 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 23:23:15,097 epoch 3 - iter 365/738 - loss 0.07364186 - time (sec): 25.32 - samples/sec: 3235.78 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 23:23:19,723 epoch 3 - iter 438/738 - loss 0.07290238 - time (sec): 29.95 - samples/sec: 3255.49 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 23:23:25,283 epoch 3 - iter 511/738 - loss 0.07401442 - time (sec): 35.51 - samples/sec: 3264.76 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 23:23:30,236 epoch 3 - iter 584/738 - loss 0.07353939 - time (sec): 40.46 - samples/sec: 3251.95 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 23:23:35,032 epoch 3 - iter 657/738 - loss 0.07127111 - time (sec): 45.26 - samples/sec: 3266.17 - lr: 0.000040 - momentum: 0.000000
113
+ 2023-10-17 23:23:40,375 epoch 3 - iter 730/738 - loss 0.07266252 - time (sec): 50.60 - samples/sec: 3260.30 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 23:23:40,800 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 23:23:40,800 EPOCH 3 done: loss 0.0737 - lr: 0.000039
116
+ 2023-10-17 23:23:52,463 DEV : loss 0.12460250407457352 - f1-score (micro avg) 0.8136
117
+ 2023-10-17 23:23:52,497 saving best model
118
+ 2023-10-17 23:23:53,038 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 23:23:58,038 epoch 4 - iter 73/738 - loss 0.03370323 - time (sec): 5.00 - samples/sec: 3418.52 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 23:24:02,660 epoch 4 - iter 146/738 - loss 0.04562321 - time (sec): 9.62 - samples/sec: 3364.30 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 23:24:08,381 epoch 4 - iter 219/738 - loss 0.04852262 - time (sec): 15.34 - samples/sec: 3309.97 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 23:24:13,478 epoch 4 - iter 292/738 - loss 0.05147819 - time (sec): 20.44 - samples/sec: 3325.35 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 23:24:18,159 epoch 4 - iter 365/738 - loss 0.04853046 - time (sec): 25.12 - samples/sec: 3315.02 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 23:24:22,760 epoch 4 - iter 438/738 - loss 0.04928914 - time (sec): 29.72 - samples/sec: 3294.20 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 23:24:27,929 epoch 4 - iter 511/738 - loss 0.04904117 - time (sec): 34.89 - samples/sec: 3290.30 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 23:24:33,404 epoch 4 - iter 584/738 - loss 0.04995549 - time (sec): 40.36 - samples/sec: 3262.97 - lr: 0.000035 - momentum: 0.000000
127
+ 2023-10-17 23:24:38,303 epoch 4 - iter 657/738 - loss 0.04972125 - time (sec): 45.26 - samples/sec: 3252.44 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 23:24:43,566 epoch 4 - iter 730/738 - loss 0.05043296 - time (sec): 50.53 - samples/sec: 3250.06 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 23:24:44,260 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 23:24:44,260 EPOCH 4 done: loss 0.0506 - lr: 0.000033
131
+ 2023-10-17 23:24:55,980 DEV : loss 0.15104417502880096 - f1-score (micro avg) 0.8221
132
+ 2023-10-17 23:24:56,015 saving best model
133
+ 2023-10-17 23:24:56,592 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 23:25:01,650 epoch 5 - iter 73/738 - loss 0.03956590 - time (sec): 5.06 - samples/sec: 3136.97 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 23:25:06,581 epoch 5 - iter 146/738 - loss 0.03562984 - time (sec): 9.99 - samples/sec: 3167.84 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 23:25:11,371 epoch 5 - iter 219/738 - loss 0.03556496 - time (sec): 14.78 - samples/sec: 3244.94 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 23:25:16,291 epoch 5 - iter 292/738 - loss 0.03548706 - time (sec): 19.70 - samples/sec: 3287.46 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 23:25:21,008 epoch 5 - iter 365/738 - loss 0.03604989 - time (sec): 24.41 - samples/sec: 3289.09 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 23:25:27,506 epoch 5 - iter 438/738 - loss 0.03712954 - time (sec): 30.91 - samples/sec: 3245.75 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 23:25:32,944 epoch 5 - iter 511/738 - loss 0.03554041 - time (sec): 36.35 - samples/sec: 3245.90 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-17 23:25:37,745 epoch 5 - iter 584/738 - loss 0.03576331 - time (sec): 41.15 - samples/sec: 3231.39 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 23:25:42,074 epoch 5 - iter 657/738 - loss 0.03519494 - time (sec): 45.48 - samples/sec: 3234.17 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 23:25:47,319 epoch 5 - iter 730/738 - loss 0.03557902 - time (sec): 50.73 - samples/sec: 3247.21 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 23:25:47,884 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 23:25:47,884 EPOCH 5 done: loss 0.0357 - lr: 0.000028
146
+ 2023-10-17 23:25:59,681 DEV : loss 0.16061857342720032 - f1-score (micro avg) 0.8491
147
+ 2023-10-17 23:25:59,713 saving best model
148
+ 2023-10-17 23:26:00,283 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 23:26:05,830 epoch 6 - iter 73/738 - loss 0.03118785 - time (sec): 5.55 - samples/sec: 3271.74 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 23:26:11,069 epoch 6 - iter 146/738 - loss 0.02616507 - time (sec): 10.78 - samples/sec: 3173.32 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 23:26:15,848 epoch 6 - iter 219/738 - loss 0.02339505 - time (sec): 15.56 - samples/sec: 3211.29 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 23:26:21,924 epoch 6 - iter 292/738 - loss 0.02435022 - time (sec): 21.64 - samples/sec: 3228.36 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 23:26:26,608 epoch 6 - iter 365/738 - loss 0.02549636 - time (sec): 26.32 - samples/sec: 3239.19 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 23:26:31,540 epoch 6 - iter 438/738 - loss 0.02512432 - time (sec): 31.26 - samples/sec: 3223.33 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-17 23:26:36,807 epoch 6 - iter 511/738 - loss 0.02472183 - time (sec): 36.52 - samples/sec: 3223.08 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 23:26:41,722 epoch 6 - iter 584/738 - loss 0.02355624 - time (sec): 41.44 - samples/sec: 3212.31 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 23:26:46,324 epoch 6 - iter 657/738 - loss 0.02348594 - time (sec): 46.04 - samples/sec: 3228.99 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 23:26:51,137 epoch 6 - iter 730/738 - loss 0.02428917 - time (sec): 50.85 - samples/sec: 3239.02 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 23:26:51,631 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 23:26:51,631 EPOCH 6 done: loss 0.0247 - lr: 0.000022
161
+ 2023-10-17 23:27:03,285 DEV : loss 0.1864573210477829 - f1-score (micro avg) 0.8343
162
+ 2023-10-17 23:27:03,320 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-17 23:27:07,808 epoch 7 - iter 73/738 - loss 0.01908871 - time (sec): 4.49 - samples/sec: 3418.41 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-17 23:27:12,781 epoch 7 - iter 146/738 - loss 0.01731582 - time (sec): 9.46 - samples/sec: 3340.36 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 23:27:17,560 epoch 7 - iter 219/738 - loss 0.01576750 - time (sec): 14.24 - samples/sec: 3300.59 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 23:27:22,548 epoch 7 - iter 292/738 - loss 0.01585694 - time (sec): 19.23 - samples/sec: 3243.91 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-17 23:27:28,246 epoch 7 - iter 365/738 - loss 0.01552307 - time (sec): 24.93 - samples/sec: 3245.65 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-17 23:27:32,869 epoch 7 - iter 438/738 - loss 0.01447850 - time (sec): 29.55 - samples/sec: 3246.80 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 23:27:38,122 epoch 7 - iter 511/738 - loss 0.01650421 - time (sec): 34.80 - samples/sec: 3231.68 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 23:27:43,410 epoch 7 - iter 584/738 - loss 0.01625634 - time (sec): 40.09 - samples/sec: 3243.21 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 23:27:48,588 epoch 7 - iter 657/738 - loss 0.01672479 - time (sec): 45.27 - samples/sec: 3244.29 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 23:27:53,986 epoch 7 - iter 730/738 - loss 0.01610283 - time (sec): 50.67 - samples/sec: 3246.76 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 23:27:54,602 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-17 23:27:54,602 EPOCH 7 done: loss 0.0161 - lr: 0.000017
175
+ 2023-10-17 23:28:06,282 DEV : loss 0.1937481015920639 - f1-score (micro avg) 0.8363
176
+ 2023-10-17 23:28:06,316 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-17 23:28:11,106 epoch 8 - iter 73/738 - loss 0.00650832 - time (sec): 4.79 - samples/sec: 3384.54 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 23:28:15,525 epoch 8 - iter 146/738 - loss 0.00609167 - time (sec): 9.21 - samples/sec: 3324.21 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 23:28:21,030 epoch 8 - iter 219/738 - loss 0.00649774 - time (sec): 14.71 - samples/sec: 3312.05 - lr: 0.000015 - momentum: 0.000000
180
+ 2023-10-17 23:28:25,843 epoch 8 - iter 292/738 - loss 0.00738941 - time (sec): 19.53 - samples/sec: 3261.54 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-17 23:28:31,461 epoch 8 - iter 365/738 - loss 0.00922834 - time (sec): 25.14 - samples/sec: 3260.92 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 23:28:36,767 epoch 8 - iter 438/738 - loss 0.01058127 - time (sec): 30.45 - samples/sec: 3229.20 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 23:28:41,311 epoch 8 - iter 511/738 - loss 0.01038329 - time (sec): 34.99 - samples/sec: 3244.01 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 23:28:45,794 epoch 8 - iter 584/738 - loss 0.01003015 - time (sec): 39.48 - samples/sec: 3265.71 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 23:28:50,264 epoch 8 - iter 657/738 - loss 0.01016964 - time (sec): 43.95 - samples/sec: 3276.86 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 23:28:55,761 epoch 8 - iter 730/738 - loss 0.00979342 - time (sec): 49.44 - samples/sec: 3287.76 - lr: 0.000011 - momentum: 0.000000
187
+ 2023-10-17 23:28:56,757 ----------------------------------------------------------------------------------------------------
188
+ 2023-10-17 23:28:56,757 EPOCH 8 done: loss 0.0099 - lr: 0.000011
189
+ 2023-10-17 23:29:08,393 DEV : loss 0.21192434430122375 - f1-score (micro avg) 0.845
190
+ 2023-10-17 23:29:08,437 ----------------------------------------------------------------------------------------------------
191
+ 2023-10-17 23:29:13,398 epoch 9 - iter 73/738 - loss 0.00572354 - time (sec): 4.96 - samples/sec: 3245.85 - lr: 0.000011 - momentum: 0.000000
192
+ 2023-10-17 23:29:18,282 epoch 9 - iter 146/738 - loss 0.00771689 - time (sec): 9.84 - samples/sec: 3246.31 - lr: 0.000010 - momentum: 0.000000
193
+ 2023-10-17 23:29:23,619 epoch 9 - iter 219/738 - loss 0.00686114 - time (sec): 15.18 - samples/sec: 3276.24 - lr: 0.000010 - momentum: 0.000000
194
+ 2023-10-17 23:29:28,492 epoch 9 - iter 292/738 - loss 0.00626330 - time (sec): 20.05 - samples/sec: 3267.08 - lr: 0.000009 - momentum: 0.000000
195
+ 2023-10-17 23:29:33,568 epoch 9 - iter 365/738 - loss 0.00726506 - time (sec): 25.13 - samples/sec: 3305.24 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 23:29:38,439 epoch 9 - iter 438/738 - loss 0.00887684 - time (sec): 30.00 - samples/sec: 3289.80 - lr: 0.000008 - momentum: 0.000000
197
+ 2023-10-17 23:29:43,087 epoch 9 - iter 511/738 - loss 0.00852118 - time (sec): 34.65 - samples/sec: 3285.43 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 23:29:48,690 epoch 9 - iter 584/738 - loss 0.00774901 - time (sec): 40.25 - samples/sec: 3261.36 - lr: 0.000007 - momentum: 0.000000
199
+ 2023-10-17 23:29:53,636 epoch 9 - iter 657/738 - loss 0.00716142 - time (sec): 45.20 - samples/sec: 3264.88 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 23:29:58,790 epoch 9 - iter 730/738 - loss 0.00709577 - time (sec): 50.35 - samples/sec: 3260.45 - lr: 0.000006 - momentum: 0.000000
201
+ 2023-10-17 23:29:59,499 ----------------------------------------------------------------------------------------------------
202
+ 2023-10-17 23:29:59,499 EPOCH 9 done: loss 0.0072 - lr: 0.000006
203
+ 2023-10-17 23:30:11,248 DEV : loss 0.20770353078842163 - f1-score (micro avg) 0.847
204
+ 2023-10-17 23:30:11,286 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-17 23:30:16,877 epoch 10 - iter 73/738 - loss 0.00364011 - time (sec): 5.59 - samples/sec: 3144.56 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-17 23:30:22,277 epoch 10 - iter 146/738 - loss 0.00694055 - time (sec): 10.99 - samples/sec: 3114.55 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 23:30:27,427 epoch 10 - iter 219/738 - loss 0.00565523 - time (sec): 16.14 - samples/sec: 3115.09 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 23:30:32,962 epoch 10 - iter 292/738 - loss 0.00642647 - time (sec): 21.67 - samples/sec: 3158.25 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 23:30:37,900 epoch 10 - iter 365/738 - loss 0.00548506 - time (sec): 26.61 - samples/sec: 3171.74 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 23:30:42,656 epoch 10 - iter 438/738 - loss 0.00523018 - time (sec): 31.37 - samples/sec: 3217.05 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 23:30:47,193 epoch 10 - iter 511/738 - loss 0.00494489 - time (sec): 35.91 - samples/sec: 3233.06 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 23:30:52,200 epoch 10 - iter 584/738 - loss 0.00451099 - time (sec): 40.91 - samples/sec: 3227.12 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 23:30:57,205 epoch 10 - iter 657/738 - loss 0.00453998 - time (sec): 45.92 - samples/sec: 3232.95 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 23:31:02,184 epoch 10 - iter 730/738 - loss 0.00471051 - time (sec): 50.90 - samples/sec: 3232.14 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 23:31:02,735 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-17 23:31:02,736 EPOCH 10 done: loss 0.0047 - lr: 0.000000
217
+ 2023-10-17 23:31:14,954 DEV : loss 0.21875163912773132 - f1-score (micro avg) 0.8505
218
+ 2023-10-17 23:31:14,994 saving best model
219
+ 2023-10-17 23:31:15,959 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-17 23:31:15,960 Loading model from best epoch ...
221
+ 2023-10-17 23:31:17,507 SequenceTagger predicts: Dictionary with 21 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
222
+ 2023-10-17 23:31:24,230
223
+ Results:
224
+ - F-score (micro) 0.8068
225
+ - F-score (macro) 0.7197
226
+ - Accuracy 0.6964
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ loc 0.8642 0.8753 0.8697 858
232
+ pers 0.7603 0.8212 0.7896 537
233
+ org 0.5846 0.5758 0.5802 132
234
+ prod 0.7213 0.7213 0.7213 61
235
+ time 0.5968 0.6852 0.6379 54
236
+
237
+ micro avg 0.7926 0.8216 0.8068 1642
238
+ macro avg 0.7055 0.7358 0.7197 1642
239
+ weighted avg 0.7937 0.8216 0.8071 1642
240
+
241
+ 2023-10-17 23:31:24,230 ----------------------------------------------------------------------------------------------------