Hugging Face's logo

stefan-it
/
hmbench-newseye-fr-hmteams-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
9a90149
·
1 Parent(s): 9429622

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.1697549058.0468bd9609d6.7281.5 +3 -0
  5. test.tsv +0 -0
  6. training.log +240 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e23f4f37e8d769e49aa21497d3cd3d918260abffe009019a552f9aa03c7f93e7
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 13:25:30 0.0000 0.4953 0.1379 0.6598 0.7864 0.7176 0.5827
3
+ 2 13:26:44 0.0000 0.1088 0.1115 0.7043 0.8231 0.7591 0.6302
4
+ 3 13:27:59 0.0000 0.0718 0.1155 0.8072 0.7973 0.8022 0.6870
5
+ 4 13:29:14 0.0000 0.0486 0.1423 0.7730 0.8245 0.7979 0.6786
6
+ 5 13:30:28 0.0000 0.0378 0.1556 0.7997 0.7986 0.7992 0.6794
7
+ 6 13:31:42 0.0000 0.0286 0.1966 0.7986 0.8041 0.8014 0.6872
8
+ 7 13:32:55 0.0000 0.0204 0.2123 0.7987 0.8150 0.8067 0.6957
9
+ 8 13:34:10 0.0000 0.0155 0.2218 0.7912 0.8095 0.8003 0.6863
10
+ 9 13:35:23 0.0000 0.0101 0.2231 0.8032 0.8218 0.8124 0.7007
11
+ 10 13:36:39 0.0000 0.0065 0.2328 0.8099 0.8231 0.8165 0.7068
runs/events.out.tfevents.1697549058.0468bd9609d6.7281.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bac2336c976eac282a888c43367fbabcd9a34d6d68457a46dfa56828e37f926
3
+ size 502461
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,240 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-17 13:24:18,291 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 13:24:18,292 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 13:24:18,292 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 13:24:18,292 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 13:24:18,292 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 13:24:18,292 Train: 7142 sentences
51
+ 2023-10-17 13:24:18,292 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 13:24:18,292 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 13:24:18,292 Training Params:
54
+ 2023-10-17 13:24:18,292 - learning_rate: "5e-05"
55
+ 2023-10-17 13:24:18,292 - mini_batch_size: "8"
56
+ 2023-10-17 13:24:18,292 - max_epochs: "10"
57
+ 2023-10-17 13:24:18,292 - shuffle: "True"
58
+ 2023-10-17 13:24:18,292 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 13:24:18,292 Plugins:
60
+ 2023-10-17 13:24:18,292 - TensorboardLogger
61
+ 2023-10-17 13:24:18,292 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 13:24:18,292 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 13:24:18,292 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 13:24:18,292 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 13:24:18,292 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 13:24:18,292 Computation:
67
+ 2023-10-17 13:24:18,292 - compute on device: cuda:0
68
+ 2023-10-17 13:24:18,293 - embedding storage: none
69
+ 2023-10-17 13:24:18,293 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 13:24:18,293 Model training base path: "hmbench-newseye/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
71
+ 2023-10-17 13:24:18,293 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 13:24:18,293 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 13:24:18,293 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 13:24:24,918 epoch 1 - iter 89/893 - loss 2.75866120 - time (sec): 6.62 - samples/sec: 3473.86 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 13:24:32,428 epoch 1 - iter 178/893 - loss 1.58176161 - time (sec): 14.13 - samples/sec: 3513.32 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 13:24:39,299 epoch 1 - iter 267/893 - loss 1.18997196 - time (sec): 21.01 - samples/sec: 3548.14 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 13:24:46,281 epoch 1 - iter 356/893 - loss 0.95916455 - time (sec): 27.99 - samples/sec: 3612.14 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 13:24:52,902 epoch 1 - iter 445/893 - loss 0.81844743 - time (sec): 34.61 - samples/sec: 3606.55 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 13:24:59,404 epoch 1 - iter 534/893 - loss 0.72551967 - time (sec): 41.11 - samples/sec: 3603.88 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 13:25:06,164 epoch 1 - iter 623/893 - loss 0.64807688 - time (sec): 47.87 - samples/sec: 3609.93 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 13:25:13,480 epoch 1 - iter 712/893 - loss 0.58175950 - time (sec): 55.19 - samples/sec: 3610.39 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 13:25:20,051 epoch 1 - iter 801/893 - loss 0.53640711 - time (sec): 61.76 - samples/sec: 3608.51 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 13:25:26,675 epoch 1 - iter 890/893 - loss 0.49591919 - time (sec): 68.38 - samples/sec: 3629.34 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 13:25:26,847 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 13:25:26,847 EPOCH 1 done: loss 0.4953 - lr: 0.000050
86
+ 2023-10-17 13:25:30,025 DEV : loss 0.13788369297981262 - f1-score (micro avg) 0.7176
87
+ 2023-10-17 13:25:30,041 saving best model
88
+ 2023-10-17 13:25:30,417 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 13:25:37,070 epoch 2 - iter 89/893 - loss 0.12012810 - time (sec): 6.65 - samples/sec: 3655.67 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 13:25:43,766 epoch 2 - iter 178/893 - loss 0.11907211 - time (sec): 13.35 - samples/sec: 3598.83 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 13:25:50,441 epoch 2 - iter 267/893 - loss 0.11594867 - time (sec): 20.02 - samples/sec: 3490.94 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 13:25:57,844 epoch 2 - iter 356/893 - loss 0.11429689 - time (sec): 27.43 - samples/sec: 3466.61 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 13:26:04,965 epoch 2 - iter 445/893 - loss 0.11235555 - time (sec): 34.55 - samples/sec: 3515.49 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 13:26:12,139 epoch 2 - iter 534/893 - loss 0.11174439 - time (sec): 41.72 - samples/sec: 3532.14 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 13:26:19,555 epoch 2 - iter 623/893 - loss 0.10874895 - time (sec): 49.14 - samples/sec: 3559.42 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 13:26:26,357 epoch 2 - iter 712/893 - loss 0.11039562 - time (sec): 55.94 - samples/sec: 3574.71 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 13:26:33,252 epoch 2 - iter 801/893 - loss 0.10946145 - time (sec): 62.83 - samples/sec: 3571.72 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 13:26:40,028 epoch 2 - iter 890/893 - loss 0.10884277 - time (sec): 69.61 - samples/sec: 3564.35 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 13:26:40,230 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 13:26:40,230 EPOCH 2 done: loss 0.1088 - lr: 0.000044
101
+ 2023-10-17 13:26:44,981 DEV : loss 0.11145459860563278 - f1-score (micro avg) 0.7591
102
+ 2023-10-17 13:26:44,997 saving best model
103
+ 2023-10-17 13:26:45,466 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 13:26:52,240 epoch 3 - iter 89/893 - loss 0.06579565 - time (sec): 6.77 - samples/sec: 3623.69 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 13:26:59,465 epoch 3 - iter 178/893 - loss 0.06780791 - time (sec): 14.00 - samples/sec: 3529.80 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 13:27:06,519 epoch 3 - iter 267/893 - loss 0.06511173 - time (sec): 21.05 - samples/sec: 3546.04 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 13:27:13,320 epoch 3 - iter 356/893 - loss 0.06708858 - time (sec): 27.85 - samples/sec: 3533.37 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 13:27:20,468 epoch 3 - iter 445/893 - loss 0.06704685 - time (sec): 35.00 - samples/sec: 3543.72 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 13:27:27,155 epoch 3 - iter 534/893 - loss 0.06913881 - time (sec): 41.69 - samples/sec: 3549.64 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 13:27:33,910 epoch 3 - iter 623/893 - loss 0.07009245 - time (sec): 48.44 - samples/sec: 3557.20 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 13:27:41,521 epoch 3 - iter 712/893 - loss 0.07061403 - time (sec): 56.05 - samples/sec: 3538.67 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 13:27:48,514 epoch 3 - iter 801/893 - loss 0.07172932 - time (sec): 63.05 - samples/sec: 3535.47 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 13:27:55,514 epoch 3 - iter 890/893 - loss 0.07158095 - time (sec): 70.05 - samples/sec: 3535.31 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 13:27:55,798 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 13:27:55,798 EPOCH 3 done: loss 0.0718 - lr: 0.000039
116
+ 2023-10-17 13:27:59,930 DEV : loss 0.11546944081783295 - f1-score (micro avg) 0.8022
117
+ 2023-10-17 13:27:59,947 saving best model
118
+ 2023-10-17 13:28:00,357 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-17 13:28:07,372 epoch 4 - iter 89/893 - loss 0.04412197 - time (sec): 7.01 - samples/sec: 3686.05 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 13:28:14,225 epoch 4 - iter 178/893 - loss 0.04610454 - time (sec): 13.87 - samples/sec: 3640.62 - lr: 0.000038 - momentum: 0.000000
121
+ 2023-10-17 13:28:21,074 epoch 4 - iter 267/893 - loss 0.04657536 - time (sec): 20.72 - samples/sec: 3671.19 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 13:28:28,332 epoch 4 - iter 356/893 - loss 0.04801474 - time (sec): 27.97 - samples/sec: 3645.53 - lr: 0.000037 - momentum: 0.000000
123
+ 2023-10-17 13:28:35,026 epoch 4 - iter 445/893 - loss 0.04910268 - time (sec): 34.67 - samples/sec: 3628.37 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 13:28:42,276 epoch 4 - iter 534/893 - loss 0.04764748 - time (sec): 41.92 - samples/sec: 3606.03 - lr: 0.000036 - momentum: 0.000000
125
+ 2023-10-17 13:28:49,159 epoch 4 - iter 623/893 - loss 0.04869073 - time (sec): 48.80 - samples/sec: 3610.17 - lr: 0.000035 - momentum: 0.000000
126
+ 2023-10-17 13:28:55,552 epoch 4 - iter 712/893 - loss 0.04835033 - time (sec): 55.19 - samples/sec: 3619.42 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 13:29:02,534 epoch 4 - iter 801/893 - loss 0.04802865 - time (sec): 62.18 - samples/sec: 3603.83 - lr: 0.000034 - momentum: 0.000000
128
+ 2023-10-17 13:29:09,448 epoch 4 - iter 890/893 - loss 0.04862439 - time (sec): 69.09 - samples/sec: 3586.93 - lr: 0.000033 - momentum: 0.000000
129
+ 2023-10-17 13:29:09,658 ----------------------------------------------------------------------------------------------------
130
+ 2023-10-17 13:29:09,658 EPOCH 4 done: loss 0.0486 - lr: 0.000033
131
+ 2023-10-17 13:29:14,333 DEV : loss 0.14231492578983307 - f1-score (micro avg) 0.7979
132
+ 2023-10-17 13:29:14,349 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 13:29:21,265 epoch 5 - iter 89/893 - loss 0.02919832 - time (sec): 6.92 - samples/sec: 3587.21 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 13:29:28,578 epoch 5 - iter 178/893 - loss 0.03380540 - time (sec): 14.23 - samples/sec: 3596.81 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 13:29:35,749 epoch 5 - iter 267/893 - loss 0.03673622 - time (sec): 21.40 - samples/sec: 3588.93 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 13:29:42,735 epoch 5 - iter 356/893 - loss 0.03585695 - time (sec): 28.39 - samples/sec: 3571.78 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 13:29:49,409 epoch 5 - iter 445/893 - loss 0.03553433 - time (sec): 35.06 - samples/sec: 3555.51 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 13:29:56,393 epoch 5 - iter 534/893 - loss 0.03588921 - time (sec): 42.04 - samples/sec: 3566.40 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 13:30:03,143 epoch 5 - iter 623/893 - loss 0.03598839 - time (sec): 48.79 - samples/sec: 3568.67 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 13:30:09,807 epoch 5 - iter 712/893 - loss 0.03692474 - time (sec): 55.46 - samples/sec: 3586.34 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 13:30:16,339 epoch 5 - iter 801/893 - loss 0.03697731 - time (sec): 61.99 - samples/sec: 3570.11 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 13:30:23,926 epoch 5 - iter 890/893 - loss 0.03792902 - time (sec): 69.58 - samples/sec: 3562.29 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 13:30:24,182 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 13:30:24,182 EPOCH 5 done: loss 0.0378 - lr: 0.000028
145
+ 2023-10-17 13:30:28,303 DEV : loss 0.1556406468153 - f1-score (micro avg) 0.7992
146
+ 2023-10-17 13:30:28,320 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-17 13:30:35,522 epoch 6 - iter 89/893 - loss 0.03244423 - time (sec): 7.20 - samples/sec: 3480.52 - lr: 0.000027 - momentum: 0.000000
148
+ 2023-10-17 13:30:42,825 epoch 6 - iter 178/893 - loss 0.02917985 - time (sec): 14.50 - samples/sec: 3535.82 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 13:30:49,786 epoch 6 - iter 267/893 - loss 0.02840967 - time (sec): 21.47 - samples/sec: 3499.22 - lr: 0.000026 - momentum: 0.000000
150
+ 2023-10-17 13:30:56,763 epoch 6 - iter 356/893 - loss 0.02860021 - time (sec): 28.44 - samples/sec: 3506.93 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 13:31:03,699 epoch 6 - iter 445/893 - loss 0.02825516 - time (sec): 35.38 - samples/sec: 3497.03 - lr: 0.000025 - momentum: 0.000000
152
+ 2023-10-17 13:31:10,471 epoch 6 - iter 534/893 - loss 0.02743104 - time (sec): 42.15 - samples/sec: 3508.88 - lr: 0.000024 - momentum: 0.000000
153
+ 2023-10-17 13:31:17,404 epoch 6 - iter 623/893 - loss 0.02858377 - time (sec): 49.08 - samples/sec: 3519.50 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 13:31:24,472 epoch 6 - iter 712/893 - loss 0.02891426 - time (sec): 56.15 - samples/sec: 3536.30 - lr: 0.000023 - momentum: 0.000000
155
+ 2023-10-17 13:31:31,162 epoch 6 - iter 801/893 - loss 0.02921549 - time (sec): 62.84 - samples/sec: 3545.04 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 13:31:37,875 epoch 6 - iter 890/893 - loss 0.02861389 - time (sec): 69.55 - samples/sec: 3563.39 - lr: 0.000022 - momentum: 0.000000
157
+ 2023-10-17 13:31:38,099 ----------------------------------------------------------------------------------------------------
158
+ 2023-10-17 13:31:38,099 EPOCH 6 done: loss 0.0286 - lr: 0.000022
159
+ 2023-10-17 13:31:42,231 DEV : loss 0.19660857319831848 - f1-score (micro avg) 0.8014
160
+ 2023-10-17 13:31:42,248 ----------------------------------------------------------------------------------------------------
161
+ 2023-10-17 13:31:49,341 epoch 7 - iter 89/893 - loss 0.01678255 - time (sec): 7.09 - samples/sec: 3621.51 - lr: 0.000022 - momentum: 0.000000
162
+ 2023-10-17 13:31:56,211 epoch 7 - iter 178/893 - loss 0.01553467 - time (sec): 13.96 - samples/sec: 3639.54 - lr: 0.000021 - momentum: 0.000000
163
+ 2023-10-17 13:32:02,722 epoch 7 - iter 267/893 - loss 0.01925221 - time (sec): 20.47 - samples/sec: 3658.02 - lr: 0.000021 - momentum: 0.000000
164
+ 2023-10-17 13:32:09,570 epoch 7 - iter 356/893 - loss 0.02042759 - time (sec): 27.32 - samples/sec: 3676.51 - lr: 0.000020 - momentum: 0.000000
165
+ 2023-10-17 13:32:16,679 epoch 7 - iter 445/893 - loss 0.02070852 - time (sec): 34.43 - samples/sec: 3652.01 - lr: 0.000019 - momentum: 0.000000
166
+ 2023-10-17 13:32:23,162 epoch 7 - iter 534/893 - loss 0.02114971 - time (sec): 40.91 - samples/sec: 3654.12 - lr: 0.000019 - momentum: 0.000000
167
+ 2023-10-17 13:32:30,075 epoch 7 - iter 623/893 - loss 0.02086037 - time (sec): 47.83 - samples/sec: 3667.87 - lr: 0.000018 - momentum: 0.000000
168
+ 2023-10-17 13:32:36,985 epoch 7 - iter 712/893 - loss 0.02012071 - time (sec): 54.74 - samples/sec: 3654.83 - lr: 0.000018 - momentum: 0.000000
169
+ 2023-10-17 13:32:43,800 epoch 7 - iter 801/893 - loss 0.02038745 - time (sec): 61.55 - samples/sec: 3617.12 - lr: 0.000017 - momentum: 0.000000
170
+ 2023-10-17 13:32:50,696 epoch 7 - iter 890/893 - loss 0.02046484 - time (sec): 68.45 - samples/sec: 3615.30 - lr: 0.000017 - momentum: 0.000000
171
+ 2023-10-17 13:32:50,929 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-17 13:32:50,930 EPOCH 7 done: loss 0.0204 - lr: 0.000017
173
+ 2023-10-17 13:32:55,592 DEV : loss 0.2123110592365265 - f1-score (micro avg) 0.8067
174
+ 2023-10-17 13:32:55,610 saving best model
175
+ 2023-10-17 13:32:56,074 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-17 13:33:03,283 epoch 8 - iter 89/893 - loss 0.01777584 - time (sec): 7.21 - samples/sec: 3367.87 - lr: 0.000016 - momentum: 0.000000
177
+ 2023-10-17 13:33:10,120 epoch 8 - iter 178/893 - loss 0.01370706 - time (sec): 14.04 - samples/sec: 3476.86 - lr: 0.000016 - momentum: 0.000000
178
+ 2023-10-17 13:33:16,860 epoch 8 - iter 267/893 - loss 0.01393815 - time (sec): 20.78 - samples/sec: 3522.88 - lr: 0.000015 - momentum: 0.000000
179
+ 2023-10-17 13:33:23,827 epoch 8 - iter 356/893 - loss 0.01526503 - time (sec): 27.75 - samples/sec: 3514.42 - lr: 0.000014 - momentum: 0.000000
180
+ 2023-10-17 13:33:30,667 epoch 8 - iter 445/893 - loss 0.01611125 - time (sec): 34.59 - samples/sec: 3537.20 - lr: 0.000014 - momentum: 0.000000
181
+ 2023-10-17 13:33:37,620 epoch 8 - iter 534/893 - loss 0.01582779 - time (sec): 41.54 - samples/sec: 3521.50 - lr: 0.000013 - momentum: 0.000000
182
+ 2023-10-17 13:33:44,461 epoch 8 - iter 623/893 - loss 0.01549864 - time (sec): 48.38 - samples/sec: 3546.15 - lr: 0.000013 - momentum: 0.000000
183
+ 2023-10-17 13:33:52,073 epoch 8 - iter 712/893 - loss 0.01573317 - time (sec): 56.00 - samples/sec: 3543.71 - lr: 0.000012 - momentum: 0.000000
184
+ 2023-10-17 13:33:58,734 epoch 8 - iter 801/893 - loss 0.01601116 - time (sec): 62.66 - samples/sec: 3552.01 - lr: 0.000012 - momentum: 0.000000
185
+ 2023-10-17 13:34:05,638 epoch 8 - iter 890/893 - loss 0.01543464 - time (sec): 69.56 - samples/sec: 3567.03 - lr: 0.000011 - momentum: 0.000000
186
+ 2023-10-17 13:34:05,852 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-17 13:34:05,852 EPOCH 8 done: loss 0.0155 - lr: 0.000011
188
+ 2023-10-17 13:34:10,003 DEV : loss 0.22176583111286163 - f1-score (micro avg) 0.8003
189
+ 2023-10-17 13:34:10,021 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-17 13:34:18,103 epoch 9 - iter 89/893 - loss 0.01083963 - time (sec): 8.08 - samples/sec: 3159.68 - lr: 0.000011 - momentum: 0.000000
191
+ 2023-10-17 13:34:25,070 epoch 9 - iter 178/893 - loss 0.00956570 - time (sec): 15.05 - samples/sec: 3388.71 - lr: 0.000010 - momentum: 0.000000
192
+ 2023-10-17 13:34:31,928 epoch 9 - iter 267/893 - loss 0.01138130 - time (sec): 21.91 - samples/sec: 3434.27 - lr: 0.000009 - momentum: 0.000000
193
+ 2023-10-17 13:34:38,528 epoch 9 - iter 356/893 - loss 0.01058467 - time (sec): 28.51 - samples/sec: 3469.81 - lr: 0.000009 - momentum: 0.000000
194
+ 2023-10-17 13:34:45,321 epoch 9 - iter 445/893 - loss 0.00921370 - time (sec): 35.30 - samples/sec: 3500.48 - lr: 0.000008 - momentum: 0.000000
195
+ 2023-10-17 13:34:51,981 epoch 9 - iter 534/893 - loss 0.00953823 - time (sec): 41.96 - samples/sec: 3527.17 - lr: 0.000008 - momentum: 0.000000
196
+ 2023-10-17 13:34:58,609 epoch 9 - iter 623/893 - loss 0.00962444 - time (sec): 48.59 - samples/sec: 3523.06 - lr: 0.000007 - momentum: 0.000000
197
+ 2023-10-17 13:35:05,539 epoch 9 - iter 712/893 - loss 0.01033271 - time (sec): 55.52 - samples/sec: 3533.02 - lr: 0.000007 - momentum: 0.000000
198
+ 2023-10-17 13:35:12,598 epoch 9 - iter 801/893 - loss 0.01059466 - time (sec): 62.58 - samples/sec: 3540.07 - lr: 0.000006 - momentum: 0.000000
199
+ 2023-10-17 13:35:19,637 epoch 9 - iter 890/893 - loss 0.01016129 - time (sec): 69.61 - samples/sec: 3565.62 - lr: 0.000006 - momentum: 0.000000
200
+ 2023-10-17 13:35:19,813 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-17 13:35:19,813 EPOCH 9 done: loss 0.0101 - lr: 0.000006
202
+ 2023-10-17 13:35:23,967 DEV : loss 0.2231239527463913 - f1-score (micro avg) 0.8124
203
+ 2023-10-17 13:35:23,985 saving best model
204
+ 2023-10-17 13:35:24,449 ----------------------------------------------------------------------------------------------------
205
+ 2023-10-17 13:35:31,551 epoch 10 - iter 89/893 - loss 0.00425626 - time (sec): 7.10 - samples/sec: 3586.43 - lr: 0.000005 - momentum: 0.000000
206
+ 2023-10-17 13:35:38,709 epoch 10 - iter 178/893 - loss 0.00582628 - time (sec): 14.25 - samples/sec: 3585.95 - lr: 0.000004 - momentum: 0.000000
207
+ 2023-10-17 13:35:45,652 epoch 10 - iter 267/893 - loss 0.00793966 - time (sec): 21.20 - samples/sec: 3592.75 - lr: 0.000004 - momentum: 0.000000
208
+ 2023-10-17 13:35:52,247 epoch 10 - iter 356/893 - loss 0.00702058 - time (sec): 27.79 - samples/sec: 3578.58 - lr: 0.000003 - momentum: 0.000000
209
+ 2023-10-17 13:35:59,564 epoch 10 - iter 445/893 - loss 0.00689434 - time (sec): 35.11 - samples/sec: 3565.57 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-17 13:36:06,713 epoch 10 - iter 534/893 - loss 0.00633107 - time (sec): 42.26 - samples/sec: 3543.91 - lr: 0.000002 - momentum: 0.000000
211
+ 2023-10-17 13:36:13,298 epoch 10 - iter 623/893 - loss 0.00613990 - time (sec): 48.84 - samples/sec: 3557.23 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-17 13:36:20,364 epoch 10 - iter 712/893 - loss 0.00603713 - time (sec): 55.91 - samples/sec: 3563.05 - lr: 0.000001 - momentum: 0.000000
213
+ 2023-10-17 13:36:27,000 epoch 10 - iter 801/893 - loss 0.00645980 - time (sec): 62.55 - samples/sec: 3571.76 - lr: 0.000001 - momentum: 0.000000
214
+ 2023-10-17 13:36:34,138 epoch 10 - iter 890/893 - loss 0.00649064 - time (sec): 69.68 - samples/sec: 3557.52 - lr: 0.000000 - momentum: 0.000000
215
+ 2023-10-17 13:36:34,324 ----------------------------------------------------------------------------------------------------
216
+ 2023-10-17 13:36:34,324 EPOCH 10 done: loss 0.0065 - lr: 0.000000
217
+ 2023-10-17 13:36:39,073 DEV : loss 0.23280413448810577 - f1-score (micro avg) 0.8165
218
+ 2023-10-17 13:36:39,090 saving best model
219
+ 2023-10-17 13:36:39,905 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-17 13:36:39,907 Loading model from best epoch ...
221
+ 2023-10-17 13:36:41,238 SequenceTagger predicts: Dictionary with 17 tags: O, S-PER, B-PER, E-PER, I-PER, S-LOC, B-LOC, E-LOC, I-LOC, S-ORG, B-ORG, E-ORG, I-ORG, S-HumanProd, B-HumanProd, E-HumanProd, I-HumanProd
222
+ 2023-10-17 13:36:50,854
223
+ Results:
224
+ - F-score (micro) 0.6959
225
+ - F-score (macro) 0.6247
226
+ - Accuracy 0.5492
227
+
228
+ By class:
229
+ precision recall f1-score support
230
+
231
+ LOC 0.6964 0.6995 0.6979 1095
232
+ PER 0.7849 0.7826 0.7838 1012
233
+ ORG 0.4352 0.5742 0.4952 357
234
+ HumanProd 0.4068 0.7273 0.5217 33
235
+
236
+ micro avg 0.6772 0.7157 0.6959 2497
237
+ macro avg 0.5808 0.6959 0.6247 2497
238
+ weighted avg 0.6911 0.7157 0.7014 2497
239
+
240
+ 2023-10-17 13:36:50,854 ----------------------------------------------------------------------------------------------------