Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2

Token Classification
Flair
PyTorch
TensorBoard
German
sequence-tagger-model
Model card Files Metrics Community
1
stefan-it commited on
Commit
b696a52
•
1 Parent(s): 3e83049

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +245 -0
training.log ADDED
@@ -0,0 +1,245 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 15:09:00,085 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 15:09:00,086 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
6
+ (word_embeddings): Embedding(64001, 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): BertEncoder(
13
+ (layer): ModuleList(
14
+ (0-11): 12 x BertLayer(
15
+ (attention): BertAttention(
16
+ (self): BertSelfAttention(
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): BertSelfOutput(
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): BertIntermediate(
29
+ (dense): Linear(in_features=768, out_features=3072, bias=True)
30
+ (intermediate_act_fn): GELUActivation()
31
+ )
32
+ (output): BertOutput(
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
+ (pooler): BertPooler(
41
+ (dense): Linear(in_features=768, out_features=768, bias=True)
42
+ (activation): Tanh()
43
+ )
44
+ )
45
+ )
46
+ (locked_dropout): LockedDropout(p=0.5)
47
+ (linear): Linear(in_features=768, out_features=25, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-23 15:09:00,086 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 15:09:00,086 MultiCorpus: 1100 train + 206 dev + 240 test sentences
52
+ - NER_HIPE_2022 Corpus: 1100 train + 206 dev + 240 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/ajmc/de/with_doc_seperator
53
+ 2023-10-23 15:09:00,086 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 15:09:00,086 Train: 1100 sentences
55
+ 2023-10-23 15:09:00,086 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 15:09:00,086 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 15:09:00,086 Training Params:
58
+ 2023-10-23 15:09:00,086 - learning_rate: "5e-05"
59
+ 2023-10-23 15:09:00,086 - mini_batch_size: "8"
60
+ 2023-10-23 15:09:00,086 - max_epochs: "10"
61
+ 2023-10-23 15:09:00,086 - shuffle: "True"
62
+ 2023-10-23 15:09:00,087 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 15:09:00,087 Plugins:
64
+ 2023-10-23 15:09:00,087 - TensorboardLogger
65
+ 2023-10-23 15:09:00,087 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 15:09:00,087 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 15:09:00,087 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 15:09:00,087 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 15:09:00,087 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 15:09:00,087 Computation:
71
+ 2023-10-23 15:09:00,087 - compute on device: cuda:0
72
+ 2023-10-23 15:09:00,087 - embedding storage: none
73
+ 2023-10-23 15:09:00,087 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 15:09:00,087 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-23 15:09:00,087 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 15:09:00,087 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 15:09:00,087 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 15:09:00,807 epoch 1 - iter 13/138 - loss 3.30817675 - time (sec): 0.72 - samples/sec: 2987.42 - lr: 0.000004 - momentum: 0.000000
79
+ 2023-10-23 15:09:01,521 epoch 1 - iter 26/138 - loss 2.71086038 - time (sec): 1.43 - samples/sec: 2914.66 - lr: 0.000009 - momentum: 0.000000
80
+ 2023-10-23 15:09:02,222 epoch 1 - iter 39/138 - loss 2.15628855 - time (sec): 2.13 - samples/sec: 2855.54 - lr: 0.000014 - momentum: 0.000000
81
+ 2023-10-23 15:09:02,927 epoch 1 - iter 52/138 - loss 1.82507197 - time (sec): 2.84 - samples/sec: 2838.66 - lr: 0.000018 - momentum: 0.000000
82
+ 2023-10-23 15:09:03,650 epoch 1 - iter 65/138 - loss 1.56174745 - time (sec): 3.56 - samples/sec: 2905.86 - lr: 0.000023 - momentum: 0.000000
83
+ 2023-10-23 15:09:04,366 epoch 1 - iter 78/138 - loss 1.35697247 - time (sec): 4.28 - samples/sec: 2967.13 - lr: 0.000028 - momentum: 0.000000
84
+ 2023-10-23 15:09:05,087 epoch 1 - iter 91/138 - loss 1.21045319 - time (sec): 5.00 - samples/sec: 2982.54 - lr: 0.000033 - momentum: 0.000000
85
+ 2023-10-23 15:09:05,806 epoch 1 - iter 104/138 - loss 1.09402921 - time (sec): 5.72 - samples/sec: 2997.08 - lr: 0.000037 - momentum: 0.000000
86
+ 2023-10-23 15:09:06,524 epoch 1 - iter 117/138 - loss 0.99931724 - time (sec): 6.44 - samples/sec: 2994.86 - lr: 0.000042 - momentum: 0.000000
87
+ 2023-10-23 15:09:07,232 epoch 1 - iter 130/138 - loss 0.91695124 - time (sec): 7.14 - samples/sec: 3022.26 - lr: 0.000047 - momentum: 0.000000
88
+ 2023-10-23 15:09:07,663 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 15:09:07,663 EPOCH 1 done: loss 0.8835 - lr: 0.000047
90
+ 2023-10-23 15:09:08,085 DEV : loss 0.16610857844352722 - f1-score (micro avg) 0.7589
91
+ 2023-10-23 15:09:08,092 saving best model
92
+ 2023-10-23 15:09:08,500 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 15:09:09,217 epoch 2 - iter 13/138 - loss 0.11222475 - time (sec): 0.72 - samples/sec: 2927.76 - lr: 0.000050 - momentum: 0.000000
94
+ 2023-10-23 15:09:09,933 epoch 2 - iter 26/138 - loss 0.13490147 - time (sec): 1.43 - samples/sec: 2920.96 - lr: 0.000049 - momentum: 0.000000
95
+ 2023-10-23 15:09:10,649 epoch 2 - iter 39/138 - loss 0.14882689 - time (sec): 2.15 - samples/sec: 2875.93 - lr: 0.000048 - momentum: 0.000000
96
+ 2023-10-23 15:09:11,364 epoch 2 - iter 52/138 - loss 0.16367161 - time (sec): 2.86 - samples/sec: 2939.80 - lr: 0.000048 - momentum: 0.000000
97
+ 2023-10-23 15:09:12,242 epoch 2 - iter 65/138 - loss 0.17017491 - time (sec): 3.74 - samples/sec: 2808.03 - lr: 0.000047 - momentum: 0.000000
98
+ 2023-10-23 15:09:12,958 epoch 2 - iter 78/138 - loss 0.16368057 - time (sec): 4.46 - samples/sec: 2805.45 - lr: 0.000047 - momentum: 0.000000
99
+ 2023-10-23 15:09:13,671 epoch 2 - iter 91/138 - loss 0.15206442 - time (sec): 5.17 - samples/sec: 2810.79 - lr: 0.000046 - momentum: 0.000000
100
+ 2023-10-23 15:09:14,401 epoch 2 - iter 104/138 - loss 0.15146141 - time (sec): 5.90 - samples/sec: 2873.90 - lr: 0.000046 - momentum: 0.000000
101
+ 2023-10-23 15:09:15,108 epoch 2 - iter 117/138 - loss 0.14489742 - time (sec): 6.61 - samples/sec: 2898.70 - lr: 0.000045 - momentum: 0.000000
102
+ 2023-10-23 15:09:15,825 epoch 2 - iter 130/138 - loss 0.14753327 - time (sec): 7.32 - samples/sec: 2923.39 - lr: 0.000045 - momentum: 0.000000
103
+ 2023-10-23 15:09:16,264 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 15:09:16,264 EPOCH 2 done: loss 0.1500 - lr: 0.000045
105
+ 2023-10-23 15:09:16,800 DEV : loss 0.11995560675859451 - f1-score (micro avg) 0.8565
106
+ 2023-10-23 15:09:16,806 saving best model
107
+ 2023-10-23 15:09:17,358 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 15:09:18,121 epoch 3 - iter 13/138 - loss 0.08208827 - time (sec): 0.76 - samples/sec: 2882.91 - lr: 0.000044 - momentum: 0.000000
109
+ 2023-10-23 15:09:18,861 epoch 3 - iter 26/138 - loss 0.07035186 - time (sec): 1.50 - samples/sec: 2825.43 - lr: 0.000043 - momentum: 0.000000
110
+ 2023-10-23 15:09:19,577 epoch 3 - iter 39/138 - loss 0.06559420 - time (sec): 2.21 - samples/sec: 2741.33 - lr: 0.000043 - momentum: 0.000000
111
+ 2023-10-23 15:09:20,313 epoch 3 - iter 52/138 - loss 0.07919367 - time (sec): 2.95 - samples/sec: 2853.16 - lr: 0.000042 - momentum: 0.000000
112
+ 2023-10-23 15:09:21,082 epoch 3 - iter 65/138 - loss 0.07261362 - time (sec): 3.72 - samples/sec: 2848.48 - lr: 0.000042 - momentum: 0.000000
113
+ 2023-10-23 15:09:21,845 epoch 3 - iter 78/138 - loss 0.08353706 - time (sec): 4.48 - samples/sec: 2897.77 - lr: 0.000041 - momentum: 0.000000
114
+ 2023-10-23 15:09:22,591 epoch 3 - iter 91/138 - loss 0.08212751 - time (sec): 5.23 - samples/sec: 2878.72 - lr: 0.000041 - momentum: 0.000000
115
+ 2023-10-23 15:09:23,357 epoch 3 - iter 104/138 - loss 0.09248064 - time (sec): 5.99 - samples/sec: 2855.22 - lr: 0.000040 - momentum: 0.000000
116
+ 2023-10-23 15:09:24,117 epoch 3 - iter 117/138 - loss 0.08840392 - time (sec): 6.75 - samples/sec: 2827.73 - lr: 0.000040 - momentum: 0.000000
117
+ 2023-10-23 15:09:24,861 epoch 3 - iter 130/138 - loss 0.08729436 - time (sec): 7.50 - samples/sec: 2877.59 - lr: 0.000039 - momentum: 0.000000
118
+ 2023-10-23 15:09:25,304 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 15:09:25,304 EPOCH 3 done: loss 0.0879 - lr: 0.000039
120
+ 2023-10-23 15:09:25,849 DEV : loss 0.12923850119113922 - f1-score (micro avg) 0.8419
121
+ 2023-10-23 15:09:25,854 ----------------------------------------------------------------------------------------------------
122
+ 2023-10-23 15:09:26,585 epoch 4 - iter 13/138 - loss 0.05200905 - time (sec): 0.73 - samples/sec: 2915.79 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-23 15:09:27,337 epoch 4 - iter 26/138 - loss 0.05412447 - time (sec): 1.48 - samples/sec: 2866.05 - lr: 0.000038 - momentum: 0.000000
124
+ 2023-10-23 15:09:28,101 epoch 4 - iter 39/138 - loss 0.07019529 - time (sec): 2.25 - samples/sec: 2997.69 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-23 15:09:28,853 epoch 4 - iter 52/138 - loss 0.07814313 - time (sec): 3.00 - samples/sec: 2964.04 - lr: 0.000037 - momentum: 0.000000
126
+ 2023-10-23 15:09:29,613 epoch 4 - iter 65/138 - loss 0.07463506 - time (sec): 3.76 - samples/sec: 2908.71 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-23 15:09:30,359 epoch 4 - iter 78/138 - loss 0.07111250 - time (sec): 4.50 - samples/sec: 2913.80 - lr: 0.000036 - momentum: 0.000000
128
+ 2023-10-23 15:09:31,089 epoch 4 - iter 91/138 - loss 0.06615343 - time (sec): 5.23 - samples/sec: 2894.17 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-23 15:09:31,812 epoch 4 - iter 104/138 - loss 0.06073453 - time (sec): 5.96 - samples/sec: 2904.56 - lr: 0.000035 - momentum: 0.000000
130
+ 2023-10-23 15:09:32,567 epoch 4 - iter 117/138 - loss 0.05896126 - time (sec): 6.71 - samples/sec: 2914.25 - lr: 0.000034 - momentum: 0.000000
131
+ 2023-10-23 15:09:33,332 epoch 4 - iter 130/138 - loss 0.05591755 - time (sec): 7.48 - samples/sec: 2896.16 - lr: 0.000034 - momentum: 0.000000
132
+ 2023-10-23 15:09:33,792 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-23 15:09:33,792 EPOCH 4 done: loss 0.0535 - lr: 0.000034
134
+ 2023-10-23 15:09:34,333 DEV : loss 0.1422549933195114 - f1-score (micro avg) 0.8493
135
+ 2023-10-23 15:09:34,338 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-23 15:09:35,067 epoch 5 - iter 13/138 - loss 0.08297898 - time (sec): 0.73 - samples/sec: 2802.41 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-23 15:09:35,799 epoch 5 - iter 26/138 - loss 0.04678987 - time (sec): 1.46 - samples/sec: 2966.01 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-23 15:09:36,520 epoch 5 - iter 39/138 - loss 0.04701843 - time (sec): 2.18 - samples/sec: 2955.73 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-23 15:09:37,234 epoch 5 - iter 52/138 - loss 0.04528808 - time (sec): 2.89 - samples/sec: 3000.09 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-23 15:09:37,955 epoch 5 - iter 65/138 - loss 0.05278775 - time (sec): 3.62 - samples/sec: 2919.24 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-23 15:09:38,701 epoch 5 - iter 78/138 - loss 0.04949446 - time (sec): 4.36 - samples/sec: 2975.21 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-23 15:09:39,429 epoch 5 - iter 91/138 - loss 0.04668619 - time (sec): 5.09 - samples/sec: 2995.38 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-23 15:09:40,151 epoch 5 - iter 104/138 - loss 0.04299450 - time (sec): 5.81 - samples/sec: 2975.06 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-23 15:09:40,878 epoch 5 - iter 117/138 - loss 0.04191106 - time (sec): 6.54 - samples/sec: 2967.52 - lr: 0.000029 - momentum: 0.000000
145
+ 2023-10-23 15:09:41,613 epoch 5 - iter 130/138 - loss 0.04395596 - time (sec): 7.27 - samples/sec: 2986.45 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-23 15:09:42,057 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-23 15:09:42,057 EPOCH 5 done: loss 0.0433 - lr: 0.000028
148
+ 2023-10-23 15:09:42,593 DEV : loss 0.13214845955371857 - f1-score (micro avg) 0.8717
149
+ 2023-10-23 15:09:42,599 saving best model
150
+ 2023-10-23 15:09:43,130 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-23 15:09:43,866 epoch 6 - iter 13/138 - loss 0.04858694 - time (sec): 0.73 - samples/sec: 3252.27 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-23 15:09:44,604 epoch 6 - iter 26/138 - loss 0.03040304 - time (sec): 1.47 - samples/sec: 3209.63 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-23 15:09:45,327 epoch 6 - iter 39/138 - loss 0.04288248 - time (sec): 2.19 - samples/sec: 3173.55 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-23 15:09:46,037 epoch 6 - iter 52/138 - loss 0.03874496 - time (sec): 2.90 - samples/sec: 2985.77 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-23 15:09:46,758 epoch 6 - iter 65/138 - loss 0.03459841 - time (sec): 3.63 - samples/sec: 2977.06 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-23 15:09:47,483 epoch 6 - iter 78/138 - loss 0.03051650 - time (sec): 4.35 - samples/sec: 3023.41 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-23 15:09:48,199 epoch 6 - iter 91/138 - loss 0.03324664 - time (sec): 5.07 - samples/sec: 3042.35 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-23 15:09:48,924 epoch 6 - iter 104/138 - loss 0.02975550 - time (sec): 5.79 - samples/sec: 3034.95 - lr: 0.000024 - momentum: 0.000000
159
+ 2023-10-23 15:09:49,650 epoch 6 - iter 117/138 - loss 0.02891134 - time (sec): 6.52 - samples/sec: 3013.07 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-23 15:09:50,388 epoch 6 - iter 130/138 - loss 0.02886668 - time (sec): 7.26 - samples/sec: 3003.23 - lr: 0.000023 - momentum: 0.000000
161
+ 2023-10-23 15:09:50,823 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-23 15:09:50,823 EPOCH 6 done: loss 0.0283 - lr: 0.000023
163
+ 2023-10-23 15:09:51,359 DEV : loss 0.15722046792507172 - f1-score (micro avg) 0.8843
164
+ 2023-10-23 15:09:51,365 saving best model
165
+ 2023-10-23 15:09:51,903 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-23 15:09:52,637 epoch 7 - iter 13/138 - loss 0.02399450 - time (sec): 0.73 - samples/sec: 2634.31 - lr: 0.000022 - momentum: 0.000000
167
+ 2023-10-23 15:09:53,387 epoch 7 - iter 26/138 - loss 0.01265243 - time (sec): 1.48 - samples/sec: 2845.36 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-23 15:09:54,122 epoch 7 - iter 39/138 - loss 0.01612770 - time (sec): 2.22 - samples/sec: 2921.04 - lr: 0.000021 - momentum: 0.000000
169
+ 2023-10-23 15:09:54,837 epoch 7 - iter 52/138 - loss 0.02357778 - time (sec): 2.93 - samples/sec: 2882.53 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-23 15:09:55,565 epoch 7 - iter 65/138 - loss 0.02038982 - time (sec): 3.66 - samples/sec: 2980.57 - lr: 0.000020 - momentum: 0.000000
171
+ 2023-10-23 15:09:56,302 epoch 7 - iter 78/138 - loss 0.02129536 - time (sec): 4.40 - samples/sec: 2976.73 - lr: 0.000019 - momentum: 0.000000
172
+ 2023-10-23 15:09:57,021 epoch 7 - iter 91/138 - loss 0.01919314 - time (sec): 5.11 - samples/sec: 2954.22 - lr: 0.000019 - momentum: 0.000000
173
+ 2023-10-23 15:09:57,758 epoch 7 - iter 104/138 - loss 0.02367637 - time (sec): 5.85 - samples/sec: 2975.61 - lr: 0.000018 - momentum: 0.000000
174
+ 2023-10-23 15:09:58,482 epoch 7 - iter 117/138 - loss 0.02211340 - time (sec): 6.57 - samples/sec: 2993.43 - lr: 0.000018 - momentum: 0.000000
175
+ 2023-10-23 15:09:59,196 epoch 7 - iter 130/138 - loss 0.02251227 - time (sec): 7.29 - samples/sec: 2967.52 - lr: 0.000017 - momentum: 0.000000
176
+ 2023-10-23 15:09:59,625 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-23 15:09:59,625 EPOCH 7 done: loss 0.0223 - lr: 0.000017
178
+ 2023-10-23 15:10:00,164 DEV : loss 0.17066876590251923 - f1-score (micro avg) 0.8961
179
+ 2023-10-23 15:10:00,170 saving best model
180
+ 2023-10-23 15:10:00,706 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-23 15:10:01,456 epoch 8 - iter 13/138 - loss 0.00845146 - time (sec): 0.75 - samples/sec: 2999.37 - lr: 0.000016 - momentum: 0.000000
182
+ 2023-10-23 15:10:02,198 epoch 8 - iter 26/138 - loss 0.01002596 - time (sec): 1.49 - samples/sec: 3004.22 - lr: 0.000016 - momentum: 0.000000
183
+ 2023-10-23 15:10:02,953 epoch 8 - iter 39/138 - loss 0.01643886 - time (sec): 2.24 - samples/sec: 2893.18 - lr: 0.000015 - momentum: 0.000000
184
+ 2023-10-23 15:10:03,725 epoch 8 - iter 52/138 - loss 0.01342550 - time (sec): 3.02 - samples/sec: 2885.82 - lr: 0.000015 - momentum: 0.000000
185
+ 2023-10-23 15:10:04,471 epoch 8 - iter 65/138 - loss 0.01584849 - time (sec): 3.76 - samples/sec: 2906.44 - lr: 0.000014 - momentum: 0.000000
186
+ 2023-10-23 15:10:05,192 epoch 8 - iter 78/138 - loss 0.01788111 - time (sec): 4.48 - samples/sec: 2945.74 - lr: 0.000014 - momentum: 0.000000
187
+ 2023-10-23 15:10:05,918 epoch 8 - iter 91/138 - loss 0.01544449 - time (sec): 5.21 - samples/sec: 2977.28 - lr: 0.000013 - momentum: 0.000000
188
+ 2023-10-23 15:10:06,651 epoch 8 - iter 104/138 - loss 0.01385370 - time (sec): 5.94 - samples/sec: 2938.58 - lr: 0.000013 - momentum: 0.000000
189
+ 2023-10-23 15:10:07,380 epoch 8 - iter 117/138 - loss 0.01384517 - time (sec): 6.67 - samples/sec: 2917.16 - lr: 0.000012 - momentum: 0.000000
190
+ 2023-10-23 15:10:08,133 epoch 8 - iter 130/138 - loss 0.01338048 - time (sec): 7.42 - samples/sec: 2919.81 - lr: 0.000012 - momentum: 0.000000
191
+ 2023-10-23 15:10:08,603 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-23 15:10:08,603 EPOCH 8 done: loss 0.0157 - lr: 0.000012
193
+ 2023-10-23 15:10:09,143 DEV : loss 0.16071170568466187 - f1-score (micro avg) 0.8942
194
+ 2023-10-23 15:10:09,148 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-23 15:10:09,892 epoch 9 - iter 13/138 - loss 0.00315447 - time (sec): 0.74 - samples/sec: 2571.89 - lr: 0.000011 - momentum: 0.000000
196
+ 2023-10-23 15:10:10,619 epoch 9 - iter 26/138 - loss 0.00728140 - time (sec): 1.47 - samples/sec: 2837.31 - lr: 0.000010 - momentum: 0.000000
197
+ 2023-10-23 15:10:11,367 epoch 9 - iter 39/138 - loss 0.00488290 - time (sec): 2.22 - samples/sec: 2920.25 - lr: 0.000010 - momentum: 0.000000
198
+ 2023-10-23 15:10:12,098 epoch 9 - iter 52/138 - loss 0.00382886 - time (sec): 2.95 - samples/sec: 2844.34 - lr: 0.000009 - momentum: 0.000000
199
+ 2023-10-23 15:10:12,813 epoch 9 - iter 65/138 - loss 0.00530259 - time (sec): 3.66 - samples/sec: 2875.94 - lr: 0.000009 - momentum: 0.000000
200
+ 2023-10-23 15:10:13,547 epoch 9 - iter 78/138 - loss 0.00503857 - time (sec): 4.40 - samples/sec: 2891.82 - lr: 0.000008 - momentum: 0.000000
201
+ 2023-10-23 15:10:14,281 epoch 9 - iter 91/138 - loss 0.00434295 - time (sec): 5.13 - samples/sec: 2916.36 - lr: 0.000008 - momentum: 0.000000
202
+ 2023-10-23 15:10:15,018 epoch 9 - iter 104/138 - loss 0.00705956 - time (sec): 5.87 - samples/sec: 2923.38 - lr: 0.000007 - momentum: 0.000000
203
+ 2023-10-23 15:10:15,738 epoch 9 - iter 117/138 - loss 0.00942999 - time (sec): 6.59 - samples/sec: 2921.28 - lr: 0.000007 - momentum: 0.000000
204
+ 2023-10-23 15:10:16,469 epoch 9 - iter 130/138 - loss 0.00981395 - time (sec): 7.32 - samples/sec: 2941.85 - lr: 0.000006 - momentum: 0.000000
205
+ 2023-10-23 15:10:16,929 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-23 15:10:16,929 EPOCH 9 done: loss 0.0108 - lr: 0.000006
207
+ 2023-10-23 15:10:17,469 DEV : loss 0.1666877120733261 - f1-score (micro avg) 0.8972
208
+ 2023-10-23 15:10:17,475 saving best model
209
+ 2023-10-23 15:10:18,012 ----------------------------------------------------------------------------------------------------
210
+ 2023-10-23 15:10:18,766 epoch 10 - iter 13/138 - loss 0.00901088 - time (sec): 0.75 - samples/sec: 2829.11 - lr: 0.000005 - momentum: 0.000000
211
+ 2023-10-23 15:10:19,511 epoch 10 - iter 26/138 - loss 0.00467408 - time (sec): 1.49 - samples/sec: 2764.82 - lr: 0.000005 - momentum: 0.000000
212
+ 2023-10-23 15:10:20,284 epoch 10 - iter 39/138 - loss 0.00779833 - time (sec): 2.26 - samples/sec: 2815.40 - lr: 0.000004 - momentum: 0.000000
213
+ 2023-10-23 15:10:21,075 epoch 10 - iter 52/138 - loss 0.00602233 - time (sec): 3.06 - samples/sec: 2790.53 - lr: 0.000004 - momentum: 0.000000
214
+ 2023-10-23 15:10:21,857 epoch 10 - iter 65/138 - loss 0.00598930 - time (sec): 3.84 - samples/sec: 2759.35 - lr: 0.000003 - momentum: 0.000000
215
+ 2023-10-23 15:10:22,596 epoch 10 - iter 78/138 - loss 0.00629598 - time (sec): 4.58 - samples/sec: 2871.17 - lr: 0.000003 - momentum: 0.000000
216
+ 2023-10-23 15:10:23,361 epoch 10 - iter 91/138 - loss 0.00709990 - time (sec): 5.34 - samples/sec: 2935.94 - lr: 0.000002 - momentum: 0.000000
217
+ 2023-10-23 15:10:24,089 epoch 10 - iter 104/138 - loss 0.00705259 - time (sec): 6.07 - samples/sec: 2940.51 - lr: 0.000002 - momentum: 0.000000
218
+ 2023-10-23 15:10:24,821 epoch 10 - iter 117/138 - loss 0.00652926 - time (sec): 6.80 - samples/sec: 2893.97 - lr: 0.000001 - momentum: 0.000000
219
+ 2023-10-23 15:10:25,588 epoch 10 - iter 130/138 - loss 0.00843776 - time (sec): 7.57 - samples/sec: 2861.39 - lr: 0.000000 - momentum: 0.000000
220
+ 2023-10-23 15:10:26,048 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-23 15:10:26,048 EPOCH 10 done: loss 0.0082 - lr: 0.000000
222
+ 2023-10-23 15:10:26,585 DEV : loss 0.1702803522348404 - f1-score (micro avg) 0.8951
223
+ 2023-10-23 15:10:26,997 ----------------------------------------------------------------------------------------------------
224
+ 2023-10-23 15:10:26,998 Loading model from best epoch ...
225
+ 2023-10-23 15:10:28,749 SequenceTagger predicts: Dictionary with 25 tags: O, S-scope, B-scope, E-scope, I-scope, S-pers, B-pers, E-pers, I-pers, S-work, B-work, E-work, I-work, S-loc, B-loc, E-loc, I-loc, S-object, B-object, E-object, I-object, S-date, B-date, E-date, I-date
226
+ 2023-10-23 15:10:29,406
227
+ Results:
228
+ - F-score (micro) 0.9194
229
+ - F-score (macro) 0.8501
230
+ - Accuracy 0.8593
231
+
232
+ By class:
233
+ precision recall f1-score support
234
+
235
+ scope 0.9023 0.8920 0.8971 176
236
+ pers 0.9921 0.9766 0.9843 128
237
+ work 0.8873 0.8514 0.8690 74
238
+ object 1.0000 1.0000 1.0000 2
239
+ loc 0.5000 0.5000 0.5000 2
240
+
241
+ micro avg 0.9280 0.9110 0.9194 382
242
+ macro avg 0.8563 0.8440 0.8501 382
243
+ weighted avg 0.9279 0.9110 0.9193 382
244
+
245
+ 2023-10-23 15:10:29,407 ----------------------------------------------------------------------------------------------------