Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
4f292fe
•
1 Parent(s): a2a6052

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.1697556160.0468bd9609d6.7281.13 +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 sha256:913aea9de4c9d005b8bcc77b33ebca4ffdef732805900a26de83435784623931
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 15:23:55 0.0000 0.5288 0.1184 0.6510 0.7333 0.6897 0.5423
3
+ 2 15:25:14 0.0000 0.1156 0.0963 0.7402 0.8218 0.7789 0.6488
4
+ 3 15:26:30 0.0000 0.0693 0.1253 0.7603 0.8027 0.7809 0.6570
5
+ 4 15:27:47 0.0000 0.0490 0.1403 0.7717 0.8095 0.7902 0.6731
6
+ 5 15:29:03 0.0000 0.0356 0.1584 0.7804 0.8122 0.7960 0.6792
7
+ 6 15:30:19 0.0000 0.0269 0.1883 0.7971 0.8177 0.8073 0.6948
8
+ 7 15:31:35 0.0000 0.0200 0.2027 0.8377 0.8218 0.8297 0.7286
9
+ 8 15:32:51 0.0000 0.0145 0.1880 0.8114 0.8313 0.8212 0.7146
10
+ 9 15:34:06 0.0000 0.0101 0.2083 0.8136 0.8313 0.8223 0.7163
11
+ 10 15:35:22 0.0000 0.0064 0.2084 0.8152 0.8340 0.8245 0.7212
runs/events.out.tfevents.1697556160.0468bd9609d6.7281.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ac554fe407f1b50e865f2c1123b77a3a610699540dd5fa569c6be82e2cc1c0a
3
+ size 502461
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,241 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 15:22:40,778 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 15:22:40,779 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 15:22:40,779 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 15:22:40,779 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 15:22:40,779 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 15:22:40,779 Train: 7142 sentences
51
+ 2023-10-17 15:22:40,779 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 15:22:40,779 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 15:22:40,780 Training Params:
54
+ 2023-10-17 15:22:40,780 - learning_rate: "5e-05"
55
+ 2023-10-17 15:22:40,780 - mini_batch_size: "8"
56
+ 2023-10-17 15:22:40,780 - max_epochs: "10"
57
+ 2023-10-17 15:22:40,780 - shuffle: "True"
58
+ 2023-10-17 15:22:40,780 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 15:22:40,780 Plugins:
60
+ 2023-10-17 15:22:40,780 - TensorboardLogger
61
+ 2023-10-17 15:22:40,780 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 15:22:40,780 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 15:22:40,780 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 15:22:40,780 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 15:22:40,780 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 15:22:40,780 Computation:
67
+ 2023-10-17 15:22:40,780 - compute on device: cuda:0
68
+ 2023-10-17 15:22:40,780 - embedding storage: none
69
+ 2023-10-17 15:22:40,780 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 15:22:40,780 Model training base path: "hmbench-newseye/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
71
+ 2023-10-17 15:22:40,780 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 15:22:40,780 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 15:22:40,780 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 15:22:48,008 epoch 1 - iter 89/893 - loss 2.84068290 - time (sec): 7.23 - samples/sec: 3501.73 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 15:22:55,293 epoch 1 - iter 178/893 - loss 1.76508006 - time (sec): 14.51 - samples/sec: 3476.96 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 15:23:02,323 epoch 1 - iter 267/893 - loss 1.32887323 - time (sec): 21.54 - samples/sec: 3444.56 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 15:23:09,344 epoch 1 - iter 356/893 - loss 1.07961683 - time (sec): 28.56 - samples/sec: 3429.95 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 15:23:15,876 epoch 1 - iter 445/893 - loss 0.91537277 - time (sec): 35.09 - samples/sec: 3450.08 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 15:23:22,550 epoch 1 - iter 534/893 - loss 0.79441400 - time (sec): 41.77 - samples/sec: 3488.61 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 15:23:29,582 epoch 1 - iter 623/893 - loss 0.70440578 - time (sec): 48.80 - samples/sec: 3492.34 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 15:23:37,058 epoch 1 - iter 712/893 - loss 0.62842482 - time (sec): 56.28 - samples/sec: 3498.94 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 15:23:44,694 epoch 1 - iter 801/893 - loss 0.57176466 - time (sec): 63.91 - samples/sec: 3491.49 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 15:23:52,068 epoch 1 - iter 890/893 - loss 0.52978902 - time (sec): 71.29 - samples/sec: 3481.64 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 15:23:52,243 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 15:23:52,243 EPOCH 1 done: loss 0.5288 - lr: 0.000050
86
+ 2023-10-17 15:23:55,932 DEV : loss 0.11837812513113022 - f1-score (micro avg) 0.6897
87
+ 2023-10-17 15:23:55,949 saving best model
88
+ 2023-10-17 15:23:56,359 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 15:24:03,910 epoch 2 - iter 89/893 - loss 0.11416371 - time (sec): 7.55 - samples/sec: 3668.50 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 15:24:10,734 epoch 2 - iter 178/893 - loss 0.11054462 - time (sec): 14.37 - samples/sec: 3596.28 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 15:24:17,679 epoch 2 - iter 267/893 - loss 0.10944617 - time (sec): 21.32 - samples/sec: 3587.36 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 15:24:24,969 epoch 2 - iter 356/893 - loss 0.10974003 - time (sec): 28.61 - samples/sec: 3510.45 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 15:24:31,656 epoch 2 - iter 445/893 - loss 0.12542965 - time (sec): 35.29 - samples/sec: 3506.52 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 15:24:38,799 epoch 2 - iter 534/893 - loss 0.12518621 - time (sec): 42.44 - samples/sec: 3480.14 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 15:24:46,264 epoch 2 - iter 623/893 - loss 0.12341348 - time (sec): 49.90 - samples/sec: 3444.96 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 15:24:54,011 epoch 2 - iter 712/893 - loss 0.12016815 - time (sec): 57.65 - samples/sec: 3435.92 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 15:25:01,036 epoch 2 - iter 801/893 - loss 0.11705570 - time (sec): 64.67 - samples/sec: 3438.85 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 15:25:08,460 epoch 2 - iter 890/893 - loss 0.11562128 - time (sec): 72.10 - samples/sec: 3443.42 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 15:25:08,631 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 15:25:08,632 EPOCH 2 done: loss 0.1156 - lr: 0.000044
101
+ 2023-10-17 15:25:14,003 DEV : loss 0.09630837291479111 - f1-score (micro avg) 0.7789
102
+ 2023-10-17 15:25:14,021 saving best model
103
+ 2023-10-17 15:25:14,500 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 15:25:21,435 epoch 3 - iter 89/893 - loss 0.07621002 - time (sec): 6.93 - samples/sec: 3510.78 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 15:25:28,317 epoch 3 - iter 178/893 - loss 0.07028836 - time (sec): 13.81 - samples/sec: 3606.54 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 15:25:35,746 epoch 3 - iter 267/893 - loss 0.06895379 - time (sec): 21.24 - samples/sec: 3639.95 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 15:25:42,631 epoch 3 - iter 356/893 - loss 0.06871513 - time (sec): 28.12 - samples/sec: 3624.74 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 15:25:50,043 epoch 3 - iter 445/893 - loss 0.07020606 - time (sec): 35.54 - samples/sec: 3608.17 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 15:25:56,658 epoch 3 - iter 534/893 - loss 0.07084888 - time (sec): 42.15 - samples/sec: 3570.61 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 15:26:03,774 epoch 3 - iter 623/893 - loss 0.07076245 - time (sec): 49.27 - samples/sec: 3525.50 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 15:26:11,199 epoch 3 - iter 712/893 - loss 0.07034170 - time (sec): 56.69 - samples/sec: 3514.66 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 15:26:19,031 epoch 3 - iter 801/893 - loss 0.06997454 - time (sec): 64.52 - samples/sec: 3487.38 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 15:26:25,774 epoch 3 - iter 890/893 - loss 0.06927984 - time (sec): 71.27 - samples/sec: 3479.19 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 15:26:26,014 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 15:26:26,015 EPOCH 3 done: loss 0.0693 - lr: 0.000039
116
+ 2023-10-17 15:26:30,286 DEV : loss 0.12525002658367157 - f1-score (micro avg) 0.7809
117
+ 2023-10-17 15:26:30,306 saving best model
118
+ 2023-10-17 15:26:30,824 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 15:26:38,462 epoch 4 - iter 89/893 - loss 0.05510630 - time (sec): 7.63 - samples/sec: 3358.06 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 15:26:45,580 epoch 4 - iter 178/893 - loss 0.04948991 - time (sec): 14.75 - samples/sec: 3444.13 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 15:26:52,737 epoch 4 - iter 267/893 - loss 0.04962954 - time (sec): 21.91 - samples/sec: 3459.17 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 15:26:59,532 epoch 4 - iter 356/893 - loss 0.04790656 - time (sec): 28.70 - samples/sec: 3465.08 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 15:27:06,747 epoch 4 - iter 445/893 - loss 0.04939163 - time (sec): 35.92 - samples/sec: 3439.54 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 15:27:13,550 epoch 4 - iter 534/893 - loss 0.04991515 - time (sec): 42.72 - samples/sec: 3455.63 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 15:27:20,682 epoch 4 - iter 623/893 - loss 0.04845630 - time (sec): 49.85 - samples/sec: 3476.52 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 15:27:27,805 epoch 4 - iter 712/893 - loss 0.04875852 - time (sec): 56.98 - samples/sec: 3480.22 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 15:27:35,059 epoch 4 - iter 801/893 - loss 0.04852640 - time (sec): 64.23 - samples/sec: 3481.36 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 15:27:42,111 epoch 4 - iter 890/893 - loss 0.04900835 - time (sec): 71.28 - samples/sec: 3476.67 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 15:27:42,383 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 15:27:42,383 EPOCH 4 done: loss 0.0490 - lr: 0.000033
131
+ 2023-10-17 15:27:47,452 DEV : loss 0.14032277464866638 - f1-score (micro avg) 0.7902
132
+ 2023-10-17 15:27:47,469 saving best model
133
+ 2023-10-17 15:27:48,074 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-17 15:27:55,354 epoch 5 - iter 89/893 - loss 0.03298580 - time (sec): 7.28 - samples/sec: 3427.76 - lr: 0.000033 - momentum: 0.000000
135
+ 2023-10-17 15:28:02,257 epoch 5 - iter 178/893 - loss 0.03246417 - time (sec): 14.18 - samples/sec: 3456.52 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 15:28:09,321 epoch 5 - iter 267/893 - loss 0.03531081 - time (sec): 21.25 - samples/sec: 3460.53 - lr: 0.000032 - momentum: 0.000000
137
+ 2023-10-17 15:28:15,814 epoch 5 - iter 356/893 - loss 0.03662109 - time (sec): 27.74 - samples/sec: 3493.64 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 15:28:22,989 epoch 5 - iter 445/893 - loss 0.03546838 - time (sec): 34.91 - samples/sec: 3475.11 - lr: 0.000031 - momentum: 0.000000
139
+ 2023-10-17 15:28:30,063 epoch 5 - iter 534/893 - loss 0.03683038 - time (sec): 41.99 - samples/sec: 3489.91 - lr: 0.000030 - momentum: 0.000000
140
+ 2023-10-17 15:28:37,101 epoch 5 - iter 623/893 - loss 0.03593909 - time (sec): 49.03 - samples/sec: 3508.58 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 15:28:44,180 epoch 5 - iter 712/893 - loss 0.03641271 - time (sec): 56.10 - samples/sec: 3514.28 - lr: 0.000029 - momentum: 0.000000
142
+ 2023-10-17 15:28:51,506 epoch 5 - iter 801/893 - loss 0.03619958 - time (sec): 63.43 - samples/sec: 3519.41 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 15:28:58,451 epoch 5 - iter 890/893 - loss 0.03553096 - time (sec): 70.38 - samples/sec: 3526.38 - lr: 0.000028 - momentum: 0.000000
144
+ 2023-10-17 15:28:58,615 ----------------------------------------------------------------------------------------------------
145
+ 2023-10-17 15:28:58,615 EPOCH 5 done: loss 0.0356 - lr: 0.000028
146
+ 2023-10-17 15:29:03,077 DEV : loss 0.15836651623249054 - f1-score (micro avg) 0.796
147
+ 2023-10-17 15:29:03,100 saving best model
148
+ 2023-10-17 15:29:04,345 ----------------------------------------------------------------------------------------------------
149
+ 2023-10-17 15:29:11,305 epoch 6 - iter 89/893 - loss 0.01800969 - time (sec): 6.96 - samples/sec: 3567.96 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 15:29:17,844 epoch 6 - iter 178/893 - loss 0.02091387 - time (sec): 13.50 - samples/sec: 3542.18 - lr: 0.000027 - momentum: 0.000000
151
+ 2023-10-17 15:29:25,110 epoch 6 - iter 267/893 - loss 0.02236790 - time (sec): 20.76 - samples/sec: 3520.46 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 15:29:32,572 epoch 6 - iter 356/893 - loss 0.02351990 - time (sec): 28.23 - samples/sec: 3490.62 - lr: 0.000026 - momentum: 0.000000
153
+ 2023-10-17 15:29:39,486 epoch 6 - iter 445/893 - loss 0.02468375 - time (sec): 35.14 - samples/sec: 3507.96 - lr: 0.000025 - momentum: 0.000000
154
+ 2023-10-17 15:29:46,768 epoch 6 - iter 534/893 - loss 0.02606959 - time (sec): 42.42 - samples/sec: 3524.54 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 15:29:54,075 epoch 6 - iter 623/893 - loss 0.02639857 - time (sec): 49.73 - samples/sec: 3513.88 - lr: 0.000024 - momentum: 0.000000
156
+ 2023-10-17 15:30:00,956 epoch 6 - iter 712/893 - loss 0.02599939 - time (sec): 56.61 - samples/sec: 3524.55 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 15:30:07,994 epoch 6 - iter 801/893 - loss 0.02730520 - time (sec): 63.65 - samples/sec: 3523.50 - lr: 0.000023 - momentum: 0.000000
158
+ 2023-10-17 15:30:14,951 epoch 6 - iter 890/893 - loss 0.02699016 - time (sec): 70.60 - samples/sec: 3512.72 - lr: 0.000022 - momentum: 0.000000
159
+ 2023-10-17 15:30:15,147 ----------------------------------------------------------------------------------------------------
160
+ 2023-10-17 15:30:15,147 EPOCH 6 done: loss 0.0269 - lr: 0.000022
161
+ 2023-10-17 15:30:19,463 DEV : loss 0.18827223777770996 - f1-score (micro avg) 0.8073
162
+ 2023-10-17 15:30:19,483 saving best model
163
+ 2023-10-17 15:30:20,021 ----------------------------------------------------------------------------------------------------
164
+ 2023-10-17 15:30:27,186 epoch 7 - iter 89/893 - loss 0.01580982 - time (sec): 7.16 - samples/sec: 3649.38 - lr: 0.000022 - momentum: 0.000000
165
+ 2023-10-17 15:30:34,189 epoch 7 - iter 178/893 - loss 0.01835420 - time (sec): 14.17 - samples/sec: 3574.06 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 15:30:41,197 epoch 7 - iter 267/893 - loss 0.01852637 - time (sec): 21.17 - samples/sec: 3502.01 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-17 15:30:48,198 epoch 7 - iter 356/893 - loss 0.01824809 - time (sec): 28.17 - samples/sec: 3531.46 - lr: 0.000020 - momentum: 0.000000
168
+ 2023-10-17 15:30:55,196 epoch 7 - iter 445/893 - loss 0.01887441 - time (sec): 35.17 - samples/sec: 3536.41 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 15:31:01,894 epoch 7 - iter 534/893 - loss 0.01977477 - time (sec): 41.87 - samples/sec: 3560.21 - lr: 0.000019 - momentum: 0.000000
170
+ 2023-10-17 15:31:08,667 epoch 7 - iter 623/893 - loss 0.01999407 - time (sec): 48.64 - samples/sec: 3563.02 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 15:31:15,718 epoch 7 - iter 712/893 - loss 0.02000396 - time (sec): 55.69 - samples/sec: 3540.87 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-17 15:31:23,232 epoch 7 - iter 801/893 - loss 0.02042434 - time (sec): 63.21 - samples/sec: 3529.38 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 15:31:30,175 epoch 7 - iter 890/893 - loss 0.01995623 - time (sec): 70.15 - samples/sec: 3538.79 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-17 15:31:30,393 ----------------------------------------------------------------------------------------------------
175
+ 2023-10-17 15:31:30,393 EPOCH 7 done: loss 0.0200 - lr: 0.000017
176
+ 2023-10-17 15:31:35,286 DEV : loss 0.20268814265727997 - f1-score (micro avg) 0.8297
177
+ 2023-10-17 15:31:35,303 saving best model
178
+ 2023-10-17 15:31:35,839 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-17 15:31:42,909 epoch 8 - iter 89/893 - loss 0.01596133 - time (sec): 7.07 - samples/sec: 3402.93 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-17 15:31:49,701 epoch 8 - iter 178/893 - loss 0.01480964 - time (sec): 13.86 - samples/sec: 3462.00 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-17 15:31:57,025 epoch 8 - iter 267/893 - loss 0.01675137 - time (sec): 21.18 - samples/sec: 3458.33 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-17 15:32:04,151 epoch 8 - iter 356/893 - loss 0.01522643 - time (sec): 28.31 - samples/sec: 3507.66 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-17 15:32:11,825 epoch 8 - iter 445/893 - loss 0.01508987 - time (sec): 35.98 - samples/sec: 3519.28 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-17 15:32:19,048 epoch 8 - iter 534/893 - loss 0.01436513 - time (sec): 43.21 - samples/sec: 3523.03 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-17 15:32:26,166 epoch 8 - iter 623/893 - loss 0.01425423 - time (sec): 50.32 - samples/sec: 3515.51 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-17 15:32:33,130 epoch 8 - iter 712/893 - loss 0.01422439 - time (sec): 57.29 - samples/sec: 3501.42 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-17 15:32:40,051 epoch 8 - iter 801/893 - loss 0.01401622 - time (sec): 64.21 - samples/sec: 3498.11 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-17 15:32:46,708 epoch 8 - iter 890/893 - loss 0.01447625 - time (sec): 70.87 - samples/sec: 3496.21 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-17 15:32:46,993 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 15:32:46,993 EPOCH 8 done: loss 0.0145 - lr: 0.000011
191
+ 2023-10-17 15:32:51,297 DEV : loss 0.18800464272499084 - f1-score (micro avg) 0.8212
192
+ 2023-10-17 15:32:51,315 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 15:32:58,164 epoch 9 - iter 89/893 - loss 0.01188764 - time (sec): 6.85 - samples/sec: 3518.48 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-17 15:33:04,766 epoch 9 - iter 178/893 - loss 0.01149941 - time (sec): 13.45 - samples/sec: 3575.04 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-17 15:33:11,658 epoch 9 - iter 267/893 - loss 0.01223126 - time (sec): 20.34 - samples/sec: 3572.33 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 15:33:18,377 epoch 9 - iter 356/893 - loss 0.01060371 - time (sec): 27.06 - samples/sec: 3578.76 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-17 15:33:26,375 epoch 9 - iter 445/893 - loss 0.01014695 - time (sec): 35.06 - samples/sec: 3508.51 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 15:33:33,290 epoch 9 - iter 534/893 - loss 0.01151378 - time (sec): 41.97 - samples/sec: 3544.73 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-17 15:33:40,363 epoch 9 - iter 623/893 - loss 0.01164043 - time (sec): 49.05 - samples/sec: 3520.41 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 15:33:47,206 epoch 9 - iter 712/893 - loss 0.01090414 - time (sec): 55.89 - samples/sec: 3536.84 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-17 15:33:54,230 epoch 9 - iter 801/893 - loss 0.01064507 - time (sec): 62.91 - samples/sec: 3534.84 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 15:34:01,797 epoch 9 - iter 890/893 - loss 0.01012024 - time (sec): 70.48 - samples/sec: 3516.33 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-17 15:34:02,023 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 15:34:02,023 EPOCH 9 done: loss 0.0101 - lr: 0.000006
205
+ 2023-10-17 15:34:06,256 DEV : loss 0.20825740694999695 - f1-score (micro avg) 0.8223
206
+ 2023-10-17 15:34:06,274 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 15:34:13,338 epoch 10 - iter 89/893 - loss 0.01106391 - time (sec): 7.06 - samples/sec: 3428.06 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-17 15:34:19,986 epoch 10 - iter 178/893 - loss 0.00869302 - time (sec): 13.71 - samples/sec: 3528.09 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-17 15:34:27,221 epoch 10 - iter 267/893 - loss 0.00786190 - time (sec): 20.95 - samples/sec: 3535.88 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-17 15:34:33,970 epoch 10 - iter 356/893 - loss 0.00840030 - time (sec): 27.69 - samples/sec: 3499.03 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 15:34:40,742 epoch 10 - iter 445/893 - loss 0.00768042 - time (sec): 34.47 - samples/sec: 3487.42 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 15:34:48,133 epoch 10 - iter 534/893 - loss 0.00760238 - time (sec): 41.86 - samples/sec: 3472.82 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 15:34:55,488 epoch 10 - iter 623/893 - loss 0.00744283 - time (sec): 49.21 - samples/sec: 3468.31 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 15:35:02,728 epoch 10 - iter 712/893 - loss 0.00710376 - time (sec): 56.45 - samples/sec: 3457.79 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 15:35:09,784 epoch 10 - iter 801/893 - loss 0.00664551 - time (sec): 63.51 - samples/sec: 3472.68 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 15:35:17,319 epoch 10 - iter 890/893 - loss 0.00642147 - time (sec): 71.04 - samples/sec: 3490.94 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 15:35:17,555 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 15:35:17,555 EPOCH 10 done: loss 0.0064 - lr: 0.000000
219
+ 2023-10-17 15:35:22,442 DEV : loss 0.20835766196250916 - f1-score (micro avg) 0.8245
220
+ 2023-10-17 15:35:22,857 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-17 15:35:22,859 Loading model from best epoch ...
222
+ 2023-10-17 15:35:24,412 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
223
+ 2023-10-17 15:35:34,665
224
+ Results:
225
+ - F-score (micro) 0.721
226
+ - F-score (macro) 0.6426
227
+ - Accuracy 0.5799
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ LOC 0.7364 0.7397 0.7380 1095
233
+ PER 0.7921 0.7717 0.7818 1012
234
+ ORG 0.5012 0.5826 0.5389 357
235
+ HumanProd 0.4151 0.6667 0.5116 33
236
+
237
+ micro avg 0.7130 0.7293 0.7210 2497
238
+ macro avg 0.6112 0.6902 0.6426 2497
239
+ weighted avg 0.7211 0.7293 0.7243 2497
240
+
241
+ 2023-10-17 15:35:34,665 ----------------------------------------------------------------------------------------------------