Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
a4a6bbb
·
1 Parent(s): 6c3fecc

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.1697578653.bce904bcef33.2482.9 +3 -0
  5. test.tsv +0 -0
  6. training.log +243 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b103e39c2637ece9e17e4e91d73df7152210c8a0fa05e745c9082bcefeeb66
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 21:38:29 0.0000 0.5934 0.1129 0.7516 0.8058 0.7778 0.6631
3
+ 2 21:39:32 0.0000 0.1223 0.1003 0.7689 0.8385 0.8022 0.6935
4
+ 3 21:40:35 0.0000 0.0690 0.1238 0.8132 0.8179 0.8155 0.7126
5
+ 4 21:41:39 0.0000 0.0492 0.1606 0.8028 0.8442 0.8230 0.7187
6
+ 5 21:42:42 0.0000 0.0359 0.1835 0.8336 0.8265 0.8300 0.7332
7
+ 6 21:43:45 0.0000 0.0239 0.1739 0.8476 0.8316 0.8395 0.7446
8
+ 7 21:44:51 0.0000 0.0171 0.1982 0.8424 0.8540 0.8481 0.7596
9
+ 8 21:45:56 0.0000 0.0103 0.2016 0.8468 0.8482 0.8475 0.7548
10
+ 9 21:46:59 0.0000 0.0067 0.2172 0.8564 0.8505 0.8534 0.7635
11
+ 10 21:48:05 0.0000 0.0040 0.2140 0.8474 0.8585 0.8529 0.7636
runs/events.out.tfevents.1697578653.bce904bcef33.2482.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643d466e707fb3313149c69c331cdb137c88a7d1f70b1b28a9948ad11fe84f5a
3
+ size 415388
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 21:37:33,205 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 21:37:33,206 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 21:37:33,207 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 21:37:33,207 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 21:37:33,207 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 21:37:33,207 Train: 5901 sentences
51
+ 2023-10-17 21:37:33,207 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 21:37:33,207 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 21:37:33,207 Training Params:
54
+ 2023-10-17 21:37:33,207 - learning_rate: "5e-05"
55
+ 2023-10-17 21:37:33,207 - mini_batch_size: "8"
56
+ 2023-10-17 21:37:33,207 - max_epochs: "10"
57
+ 2023-10-17 21:37:33,207 - shuffle: "True"
58
+ 2023-10-17 21:37:33,207 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 21:37:33,207 Plugins:
60
+ 2023-10-17 21:37:33,207 - TensorboardLogger
61
+ 2023-10-17 21:37:33,207 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 21:37:33,207 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 21:37:33,207 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 21:37:33,207 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 21:37:33,207 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 21:37:33,207 Computation:
67
+ 2023-10-17 21:37:33,207 - compute on device: cuda:0
68
+ 2023-10-17 21:37:33,207 - embedding storage: none
69
+ 2023-10-17 21:37:33,207 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 21:37:33,207 Model training base path: "hmbench-hipe2020/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3"
71
+ 2023-10-17 21:37:33,207 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 21:37:33,207 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 21:37:33,208 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 21:37:38,054 epoch 1 - iter 73/738 - loss 3.20466009 - time (sec): 4.85 - samples/sec: 3325.72 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 21:37:44,393 epoch 1 - iter 146/738 - loss 1.82822506 - time (sec): 11.18 - samples/sec: 3213.03 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 21:37:49,357 epoch 1 - iter 219/738 - loss 1.39660502 - time (sec): 16.15 - samples/sec: 3206.33 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 21:37:53,696 epoch 1 - iter 292/738 - loss 1.16544068 - time (sec): 20.49 - samples/sec: 3251.24 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 21:37:58,432 epoch 1 - iter 365/738 - loss 0.99315566 - time (sec): 25.22 - samples/sec: 3273.37 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 21:38:03,790 epoch 1 - iter 438/738 - loss 0.86323967 - time (sec): 30.58 - samples/sec: 3287.68 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 21:38:08,863 epoch 1 - iter 511/738 - loss 0.76774990 - time (sec): 35.65 - samples/sec: 3270.74 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 21:38:13,703 epoch 1 - iter 584/738 - loss 0.70024884 - time (sec): 40.49 - samples/sec: 3268.58 - lr: 0.000039 - momentum: 0.000000
82
+ 2023-10-17 21:38:18,394 epoch 1 - iter 657/738 - loss 0.64669515 - time (sec): 45.19 - samples/sec: 3276.62 - lr: 0.000044 - momentum: 0.000000
83
+ 2023-10-17 21:38:23,326 epoch 1 - iter 730/738 - loss 0.59939081 - time (sec): 50.12 - samples/sec: 3278.78 - lr: 0.000049 - momentum: 0.000000
84
+ 2023-10-17 21:38:23,856 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 21:38:23,856 EPOCH 1 done: loss 0.5934 - lr: 0.000049
86
+ 2023-10-17 21:38:29,633 DEV : loss 0.1128801703453064 - f1-score (micro avg) 0.7778
87
+ 2023-10-17 21:38:29,661 saving best model
88
+ 2023-10-17 21:38:30,004 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 21:38:34,995 epoch 2 - iter 73/738 - loss 0.13929752 - time (sec): 4.99 - samples/sec: 3221.31 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 21:38:40,210 epoch 2 - iter 146/738 - loss 0.14514716 - time (sec): 10.20 - samples/sec: 3360.68 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 21:38:45,427 epoch 2 - iter 219/738 - loss 0.13839134 - time (sec): 15.42 - samples/sec: 3294.50 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 21:38:50,124 epoch 2 - iter 292/738 - loss 0.13536477 - time (sec): 20.12 - samples/sec: 3306.95 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 21:38:55,052 epoch 2 - iter 365/738 - loss 0.12836567 - time (sec): 25.05 - samples/sec: 3344.41 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 21:39:00,343 epoch 2 - iter 438/738 - loss 0.12889574 - time (sec): 30.34 - samples/sec: 3319.06 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 21:39:05,285 epoch 2 - iter 511/738 - loss 0.12679776 - time (sec): 35.28 - samples/sec: 3319.49 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 21:39:10,668 epoch 2 - iter 584/738 - loss 0.12274550 - time (sec): 40.66 - samples/sec: 3290.55 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 21:39:15,345 epoch 2 - iter 657/738 - loss 0.12120563 - time (sec): 45.34 - samples/sec: 3306.09 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 21:39:20,421 epoch 2 - iter 730/738 - loss 0.12260627 - time (sec): 50.42 - samples/sec: 3269.78 - lr: 0.000045 - momentum: 0.000000
99
+ 2023-10-17 21:39:20,875 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 21:39:20,875 EPOCH 2 done: loss 0.1223 - lr: 0.000045
101
+ 2023-10-17 21:39:32,645 DEV : loss 0.10028773546218872 - f1-score (micro avg) 0.8022
102
+ 2023-10-17 21:39:32,675 saving best model
103
+ 2023-10-17 21:39:33,124 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 21:39:38,060 epoch 3 - iter 73/738 - loss 0.06628436 - time (sec): 4.93 - samples/sec: 3238.96 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 21:39:43,294 epoch 3 - iter 146/738 - loss 0.07394815 - time (sec): 10.17 - samples/sec: 3211.88 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 21:39:48,350 epoch 3 - iter 219/738 - loss 0.07202732 - time (sec): 15.22 - samples/sec: 3228.17 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 21:39:53,503 epoch 3 - iter 292/738 - loss 0.07142235 - time (sec): 20.37 - samples/sec: 3236.87 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 21:39:58,868 epoch 3 - iter 365/738 - loss 0.06979816 - time (sec): 25.74 - samples/sec: 3245.87 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 21:40:03,908 epoch 3 - iter 438/738 - loss 0.07197892 - time (sec): 30.78 - samples/sec: 3244.65 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 21:40:08,536 epoch 3 - iter 511/738 - loss 0.07091128 - time (sec): 35.41 - samples/sec: 3250.71 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 21:40:13,933 epoch 3 - iter 584/738 - loss 0.06898470 - time (sec): 40.80 - samples/sec: 3255.13 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 21:40:18,862 epoch 3 - iter 657/738 - loss 0.06930859 - time (sec): 45.73 - samples/sec: 3264.70 - lr: 0.000040 - momentum: 0.000000
113
+ 2023-10-17 21:40:23,347 epoch 3 - iter 730/738 - loss 0.06898062 - time (sec): 50.22 - samples/sec: 3281.86 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 21:40:23,828 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 21:40:23,829 EPOCH 3 done: loss 0.0690 - lr: 0.000039
116
+ 2023-10-17 21:40:35,285 DEV : loss 0.12378295511007309 - f1-score (micro avg) 0.8155
117
+ 2023-10-17 21:40:35,332 saving best model
118
+ 2023-10-17 21:40:35,886 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 21:40:41,150 epoch 4 - iter 73/738 - loss 0.03928514 - time (sec): 5.26 - samples/sec: 2980.34 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 21:40:46,260 epoch 4 - iter 146/738 - loss 0.03986666 - time (sec): 10.37 - samples/sec: 3124.89 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 21:40:51,918 epoch 4 - iter 219/738 - loss 0.03995194 - time (sec): 16.03 - samples/sec: 3121.47 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 21:40:56,907 epoch 4 - iter 292/738 - loss 0.04267289 - time (sec): 21.02 - samples/sec: 3124.52 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 21:41:01,164 epoch 4 - iter 365/738 - loss 0.04347795 - time (sec): 25.27 - samples/sec: 3165.12 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 21:41:06,088 epoch 4 - iter 438/738 - loss 0.04539882 - time (sec): 30.20 - samples/sec: 3164.80 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 21:41:11,676 epoch 4 - iter 511/738 - loss 0.04802091 - time (sec): 35.79 - samples/sec: 3209.92 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 21:41:16,315 epoch 4 - iter 584/738 - loss 0.04880702 - time (sec): 40.43 - samples/sec: 3223.06 - lr: 0.000035 - momentum: 0.000000
127
+ 2023-10-17 21:41:21,818 epoch 4 - iter 657/738 - loss 0.04821365 - time (sec): 45.93 - samples/sec: 3223.49 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 21:41:26,489 epoch 4 - iter 730/738 - loss 0.04880709 - time (sec): 50.60 - samples/sec: 3245.95 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 21:41:27,147 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 21:41:27,148 EPOCH 4 done: loss 0.0492 - lr: 0.000033
131
+ 2023-10-17 21:41:39,246 DEV : loss 0.16061200201511383 - f1-score (micro avg) 0.823
132
+ 2023-10-17 21:41:39,286 saving best model
133
+ 2023-10-17 21:41:39,987 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 21:41:44,741 epoch 5 - iter 73/738 - loss 0.03400326 - time (sec): 4.75 - samples/sec: 3223.80 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 21:41:49,497 epoch 5 - iter 146/738 - loss 0.02962038 - time (sec): 9.51 - samples/sec: 3270.97 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 21:41:54,630 epoch 5 - iter 219/738 - loss 0.03062328 - time (sec): 14.64 - samples/sec: 3293.76 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 21:41:59,518 epoch 5 - iter 292/738 - loss 0.03152666 - time (sec): 19.53 - samples/sec: 3233.15 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 21:42:04,821 epoch 5 - iter 365/738 - loss 0.03434371 - time (sec): 24.83 - samples/sec: 3238.22 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 21:42:10,677 epoch 5 - iter 438/738 - loss 0.03615567 - time (sec): 30.69 - samples/sec: 3275.49 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 21:42:15,421 epoch 5 - iter 511/738 - loss 0.03672734 - time (sec): 35.43 - samples/sec: 3267.84 - lr: 0.000030 - momentum: 0.000000
141
+ 2023-10-17 21:42:20,277 epoch 5 - iter 584/738 - loss 0.03595696 - time (sec): 40.29 - samples/sec: 3276.06 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 21:42:25,356 epoch 5 - iter 657/738 - loss 0.03716307 - time (sec): 45.37 - samples/sec: 3268.76 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 21:42:30,298 epoch 5 - iter 730/738 - loss 0.03608514 - time (sec): 50.31 - samples/sec: 3275.76 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 21:42:30,739 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 21:42:30,739 EPOCH 5 done: loss 0.0359 - lr: 0.000028
146
+ 2023-10-17 21:42:42,269 DEV : loss 0.18349634110927582 - f1-score (micro avg) 0.83
147
+ 2023-10-17 21:42:42,304 saving best model
148
+ 2023-10-17 21:42:42,866 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 21:42:48,143 epoch 6 - iter 73/738 - loss 0.01719025 - time (sec): 5.27 - samples/sec: 3243.63 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 21:42:52,544 epoch 6 - iter 146/738 - loss 0.02317490 - time (sec): 9.68 - samples/sec: 3296.96 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 21:42:57,644 epoch 6 - iter 219/738 - loss 0.02165752 - time (sec): 14.78 - samples/sec: 3245.12 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 21:43:02,338 epoch 6 - iter 292/738 - loss 0.02166477 - time (sec): 19.47 - samples/sec: 3249.25 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 21:43:07,148 epoch 6 - iter 365/738 - loss 0.01993618 - time (sec): 24.28 - samples/sec: 3273.45 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 21:43:12,403 epoch 6 - iter 438/738 - loss 0.02125273 - time (sec): 29.54 - samples/sec: 3261.84 - lr: 0.000025 - momentum: 0.000000
155
+ 2023-10-17 21:43:17,663 epoch 6 - iter 511/738 - loss 0.02155343 - time (sec): 34.80 - samples/sec: 3253.02 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 21:43:22,464 epoch 6 - iter 584/738 - loss 0.02332337 - time (sec): 39.60 - samples/sec: 3274.24 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 21:43:27,582 epoch 6 - iter 657/738 - loss 0.02370338 - time (sec): 44.71 - samples/sec: 3279.43 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 21:43:32,708 epoch 6 - iter 730/738 - loss 0.02350382 - time (sec): 49.84 - samples/sec: 3265.56 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 21:43:33,635 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 21:43:33,635 EPOCH 6 done: loss 0.0239 - lr: 0.000022
161
+ 2023-10-17 21:43:45,183 DEV : loss 0.17387224733829498 - f1-score (micro avg) 0.8395
162
+ 2023-10-17 21:43:45,243 saving best model
163
+ 2023-10-17 21:43:45,817 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 21:43:51,153 epoch 7 - iter 73/738 - loss 0.01770805 - time (sec): 5.33 - samples/sec: 3090.79 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-17 21:43:56,557 epoch 7 - iter 146/738 - loss 0.01453465 - time (sec): 10.74 - samples/sec: 3102.10 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 21:44:01,664 epoch 7 - iter 219/738 - loss 0.01699714 - time (sec): 15.84 - samples/sec: 3070.56 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-17 21:44:07,217 epoch 7 - iter 292/738 - loss 0.01728090 - time (sec): 21.40 - samples/sec: 3103.41 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-17 21:44:12,420 epoch 7 - iter 365/738 - loss 0.01724780 - time (sec): 26.60 - samples/sec: 3110.67 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-17 21:44:17,427 epoch 7 - iter 438/738 - loss 0.01762499 - time (sec): 31.61 - samples/sec: 3114.74 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-17 21:44:22,662 epoch 7 - iter 511/738 - loss 0.01628760 - time (sec): 36.84 - samples/sec: 3133.30 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 21:44:28,079 epoch 7 - iter 584/738 - loss 0.01702390 - time (sec): 42.26 - samples/sec: 3117.45 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-17 21:44:33,704 epoch 7 - iter 657/738 - loss 0.01773960 - time (sec): 47.88 - samples/sec: 3118.01 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 21:44:38,587 epoch 7 - iter 730/738 - loss 0.01735761 - time (sec): 52.77 - samples/sec: 3114.22 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-17 21:44:39,275 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 21:44:39,276 EPOCH 7 done: loss 0.0171 - lr: 0.000017
176
+ 2023-10-17 21:44:51,205 DEV : loss 0.1981659084558487 - f1-score (micro avg) 0.8481
177
+ 2023-10-17 21:44:51,238 saving best model
178
+ 2023-10-17 21:44:51,768 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-17 21:44:57,754 epoch 8 - iter 73/738 - loss 0.00924025 - time (sec): 5.98 - samples/sec: 2774.48 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-17 21:45:02,807 epoch 8 - iter 146/738 - loss 0.00948333 - time (sec): 11.04 - samples/sec: 3084.60 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-17 21:45:08,045 epoch 8 - iter 219/738 - loss 0.01219250 - time (sec): 16.27 - samples/sec: 3162.88 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-17 21:45:13,266 epoch 8 - iter 292/738 - loss 0.01081484 - time (sec): 21.49 - samples/sec: 3190.17 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-17 21:45:18,175 epoch 8 - iter 365/738 - loss 0.01151200 - time (sec): 26.40 - samples/sec: 3178.76 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-17 21:45:23,016 epoch 8 - iter 438/738 - loss 0.01023420 - time (sec): 31.24 - samples/sec: 3180.17 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-17 21:45:28,075 epoch 8 - iter 511/738 - loss 0.00995113 - time (sec): 36.30 - samples/sec: 3186.42 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-17 21:45:32,793 epoch 8 - iter 584/738 - loss 0.01005037 - time (sec): 41.02 - samples/sec: 3199.15 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-17 21:45:37,561 epoch 8 - iter 657/738 - loss 0.01027859 - time (sec): 45.79 - samples/sec: 3203.17 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-17 21:45:43,215 epoch 8 - iter 730/738 - loss 0.01038533 - time (sec): 51.44 - samples/sec: 3195.43 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-17 21:45:43,866 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 21:45:43,866 EPOCH 8 done: loss 0.0103 - lr: 0.000011
191
+ 2023-10-17 21:45:56,168 DEV : loss 0.20160594582557678 - f1-score (micro avg) 0.8475
192
+ 2023-10-17 21:45:56,209 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 21:46:01,451 epoch 9 - iter 73/738 - loss 0.00534004 - time (sec): 5.24 - samples/sec: 3180.64 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-17 21:46:07,288 epoch 9 - iter 146/738 - loss 0.00466241 - time (sec): 11.08 - samples/sec: 3151.55 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-17 21:46:12,817 epoch 9 - iter 219/738 - loss 0.00509846 - time (sec): 16.61 - samples/sec: 3222.48 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-17 21:46:18,104 epoch 9 - iter 292/738 - loss 0.00566526 - time (sec): 21.89 - samples/sec: 3272.78 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-17 21:46:23,049 epoch 9 - iter 365/738 - loss 0.00719356 - time (sec): 26.84 - samples/sec: 3275.40 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 21:46:27,879 epoch 9 - iter 438/738 - loss 0.00730734 - time (sec): 31.67 - samples/sec: 3266.02 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-17 21:46:33,072 epoch 9 - iter 511/738 - loss 0.00730646 - time (sec): 36.86 - samples/sec: 3247.54 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 21:46:37,908 epoch 9 - iter 584/738 - loss 0.00715416 - time (sec): 41.70 - samples/sec: 3231.88 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-17 21:46:42,593 epoch 9 - iter 657/738 - loss 0.00700237 - time (sec): 46.38 - samples/sec: 3230.20 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 21:46:47,097 epoch 9 - iter 730/738 - loss 0.00673335 - time (sec): 50.89 - samples/sec: 3240.15 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-17 21:46:47,566 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 21:46:47,567 EPOCH 9 done: loss 0.0067 - lr: 0.000006
205
+ 2023-10-17 21:46:59,772 DEV : loss 0.21716605126857758 - f1-score (micro avg) 0.8534
206
+ 2023-10-17 21:46:59,811 saving best model
207
+ 2023-10-17 21:47:00,341 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-17 21:47:05,574 epoch 10 - iter 73/738 - loss 0.00481027 - time (sec): 5.23 - samples/sec: 3251.80 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-17 21:47:11,081 epoch 10 - iter 146/738 - loss 0.00430328 - time (sec): 10.74 - samples/sec: 3182.28 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-17 21:47:16,234 epoch 10 - iter 219/738 - loss 0.00324077 - time (sec): 15.89 - samples/sec: 3165.96 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-17 21:47:21,507 epoch 10 - iter 292/738 - loss 0.00333845 - time (sec): 21.16 - samples/sec: 3112.76 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 21:47:26,804 epoch 10 - iter 365/738 - loss 0.00348861 - time (sec): 26.46 - samples/sec: 3130.00 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-17 21:47:31,700 epoch 10 - iter 438/738 - loss 0.00328087 - time (sec): 31.36 - samples/sec: 3130.23 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 21:47:36,917 epoch 10 - iter 511/738 - loss 0.00299330 - time (sec): 36.57 - samples/sec: 3131.52 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-17 21:47:41,775 epoch 10 - iter 584/738 - loss 0.00299401 - time (sec): 41.43 - samples/sec: 3129.59 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 21:47:47,900 epoch 10 - iter 657/738 - loss 0.00311008 - time (sec): 47.56 - samples/sec: 3156.52 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-17 21:47:52,887 epoch 10 - iter 730/738 - loss 0.00401652 - time (sec): 52.54 - samples/sec: 3141.65 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-17 21:47:53,401 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-17 21:47:53,401 EPOCH 10 done: loss 0.0040 - lr: 0.000000
220
+ 2023-10-17 21:48:05,276 DEV : loss 0.2139635980129242 - f1-score (micro avg) 0.8529
221
+ 2023-10-17 21:48:05,723 ----------------------------------------------------------------------------------------------------
222
+ 2023-10-17 21:48:05,724 Loading model from best epoch ...
223
+ 2023-10-17 21:48:07,454 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
224
+ 2023-10-17 21:48:13,905
225
+ Results:
226
+ - F-score (micro) 0.8099
227
+ - F-score (macro) 0.7115
228
+ - Accuracy 0.7022
229
+
230
+ By class:
231
+ precision recall f1-score support
232
+
233
+ loc 0.8768 0.8706 0.8737 858
234
+ pers 0.7727 0.8231 0.7971 537
235
+ org 0.5985 0.5985 0.5985 132
236
+ time 0.5312 0.6296 0.5763 54
237
+ prod 0.7368 0.6885 0.7119 61
238
+
239
+ micro avg 0.8014 0.8185 0.8099 1642
240
+ macro avg 0.7032 0.7221 0.7115 1642
241
+ weighted avg 0.8038 0.8185 0.8107 1642
242
+
243
+ 2023-10-17 21:48:13,906 ----------------------------------------------------------------------------------------------------