Hugging Face's logo

stefan-it
/
hmbench-ajmc-de-hmbert_64k-bs8-wsFalse-e10-lr3e-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
8a2b9e0
•
1 Parent(s): 0e01b0c

Upload ./training.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. training.log +244 -0
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-23 15:07:12,704 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-23 15:07:12,705 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 15:07:12,705 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-23 15:07:12,705 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 15:07:12,705 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-23 15:07:12,705 Train: 1100 sentences
55
+ 2023-10-23 15:07:12,705 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-23 15:07:12,705 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-23 15:07:12,705 Training Params:
58
+ 2023-10-23 15:07:12,705 - learning_rate: "3e-05"
59
+ 2023-10-23 15:07:12,705 - mini_batch_size: "8"
60
+ 2023-10-23 15:07:12,705 - max_epochs: "10"
61
+ 2023-10-23 15:07:12,705 - shuffle: "True"
62
+ 2023-10-23 15:07:12,705 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-23 15:07:12,705 Plugins:
64
+ 2023-10-23 15:07:12,705 - TensorboardLogger
65
+ 2023-10-23 15:07:12,706 - LinearScheduler | warmup_fraction: '0.1'
66
+ 2023-10-23 15:07:12,706 ----------------------------------------------------------------------------------------------------
67
+ 2023-10-23 15:07:12,706 Final evaluation on model from best epoch (best-model.pt)
68
+ 2023-10-23 15:07:12,706 - metric: "('micro avg', 'f1-score')"
69
+ 2023-10-23 15:07:12,706 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-23 15:07:12,706 Computation:
71
+ 2023-10-23 15:07:12,706 - compute on device: cuda:0
72
+ 2023-10-23 15:07:12,706 - embedding storage: none
73
+ 2023-10-23 15:07:12,706 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-23 15:07:12,706 Model training base path: "hmbench-ajmc/de-dbmdz/bert-base-historic-multilingual-64k-td-cased-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2"
75
+ 2023-10-23 15:07:12,706 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-23 15:07:12,706 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-23 15:07:12,706 Logging anything other than scalars to TensorBoard is currently not supported.
78
+ 2023-10-23 15:07:13,429 epoch 1 - iter 13/138 - loss 3.37467106 - time (sec): 0.72 - samples/sec: 2971.73 - lr: 0.000003 - momentum: 0.000000
79
+ 2023-10-23 15:07:14,143 epoch 1 - iter 26/138 - loss 2.96938082 - time (sec): 1.44 - samples/sec: 2907.62 - lr: 0.000005 - momentum: 0.000000
80
+ 2023-10-23 15:07:14,848 epoch 1 - iter 39/138 - loss 2.44657037 - time (sec): 2.14 - samples/sec: 2846.49 - lr: 0.000008 - momentum: 0.000000
81
+ 2023-10-23 15:07:15,559 epoch 1 - iter 52/138 - loss 2.06681506 - time (sec): 2.85 - samples/sec: 2825.81 - lr: 0.000011 - momentum: 0.000000
82
+ 2023-10-23 15:07:16,303 epoch 1 - iter 65/138 - loss 1.78927097 - time (sec): 3.60 - samples/sec: 2878.28 - lr: 0.000014 - momentum: 0.000000
83
+ 2023-10-23 15:07:17,052 epoch 1 - iter 78/138 - loss 1.56584748 - time (sec): 4.34 - samples/sec: 2921.38 - lr: 0.000017 - momentum: 0.000000
84
+ 2023-10-23 15:07:17,771 epoch 1 - iter 91/138 - loss 1.40260405 - time (sec): 5.06 - samples/sec: 2943.91 - lr: 0.000020 - momentum: 0.000000
85
+ 2023-10-23 15:07:18,483 epoch 1 - iter 104/138 - loss 1.27483414 - time (sec): 5.78 - samples/sec: 2966.95 - lr: 0.000022 - momentum: 0.000000
86
+ 2023-10-23 15:07:19,221 epoch 1 - iter 117/138 - loss 1.16935322 - time (sec): 6.51 - samples/sec: 2958.64 - lr: 0.000025 - momentum: 0.000000
87
+ 2023-10-23 15:07:19,945 epoch 1 - iter 130/138 - loss 1.07390114 - time (sec): 7.24 - samples/sec: 2982.84 - lr: 0.000028 - momentum: 0.000000
88
+ 2023-10-23 15:07:20,374 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-23 15:07:20,374 EPOCH 1 done: loss 1.0347 - lr: 0.000028
90
+ 2023-10-23 15:07:20,968 DEV : loss 0.19735337793827057 - f1-score (micro avg) 0.6963
91
+ 2023-10-23 15:07:20,974 saving best model
92
+ 2023-10-23 15:07:21,373 ----------------------------------------------------------------------------------------------------
93
+ 2023-10-23 15:07:22,079 epoch 2 - iter 13/138 - loss 0.15888997 - time (sec): 0.70 - samples/sec: 2975.19 - lr: 0.000030 - momentum: 0.000000
94
+ 2023-10-23 15:07:22,792 epoch 2 - iter 26/138 - loss 0.17882334 - time (sec): 1.42 - samples/sec: 2950.17 - lr: 0.000029 - momentum: 0.000000
95
+ 2023-10-23 15:07:23,500 epoch 2 - iter 39/138 - loss 0.18258217 - time (sec): 2.13 - samples/sec: 2905.83 - lr: 0.000029 - momentum: 0.000000
96
+ 2023-10-23 15:07:24,220 epoch 2 - iter 52/138 - loss 0.19444341 - time (sec): 2.85 - samples/sec: 2957.20 - lr: 0.000029 - momentum: 0.000000
97
+ 2023-10-23 15:07:24,929 epoch 2 - iter 65/138 - loss 0.19897156 - time (sec): 3.55 - samples/sec: 2954.44 - lr: 0.000028 - momentum: 0.000000
98
+ 2023-10-23 15:07:25,646 epoch 2 - iter 78/138 - loss 0.19171456 - time (sec): 4.27 - samples/sec: 2927.05 - lr: 0.000028 - momentum: 0.000000
99
+ 2023-10-23 15:07:26,357 epoch 2 - iter 91/138 - loss 0.17941956 - time (sec): 4.98 - samples/sec: 2916.55 - lr: 0.000028 - momentum: 0.000000
100
+ 2023-10-23 15:07:27,083 epoch 2 - iter 104/138 - loss 0.17639339 - time (sec): 5.71 - samples/sec: 2970.36 - lr: 0.000028 - momentum: 0.000000
101
+ 2023-10-23 15:07:27,812 epoch 2 - iter 117/138 - loss 0.16912778 - time (sec): 6.44 - samples/sec: 2974.91 - lr: 0.000027 - momentum: 0.000000
102
+ 2023-10-23 15:07:28,534 epoch 2 - iter 130/138 - loss 0.17110248 - time (sec): 7.16 - samples/sec: 2990.69 - lr: 0.000027 - momentum: 0.000000
103
+ 2023-10-23 15:07:28,976 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-23 15:07:28,976 EPOCH 2 done: loss 0.1705 - lr: 0.000027
105
+ 2023-10-23 15:07:29,512 DEV : loss 0.122329480946064 - f1-score (micro avg) 0.8271
106
+ 2023-10-23 15:07:29,518 saving best model
107
+ 2023-10-23 15:07:30,073 ----------------------------------------------------------------------------------------------------
108
+ 2023-10-23 15:07:30,808 epoch 3 - iter 13/138 - loss 0.08335533 - time (sec): 0.73 - samples/sec: 2991.57 - lr: 0.000026 - momentum: 0.000000
109
+ 2023-10-23 15:07:31,532 epoch 3 - iter 26/138 - loss 0.08264747 - time (sec): 1.45 - samples/sec: 2908.96 - lr: 0.000026 - momentum: 0.000000
110
+ 2023-10-23 15:07:32,255 epoch 3 - iter 39/138 - loss 0.07886078 - time (sec): 2.18 - samples/sec: 2788.01 - lr: 0.000026 - momentum: 0.000000
111
+ 2023-10-23 15:07:32,965 epoch 3 - iter 52/138 - loss 0.08829144 - time (sec): 2.89 - samples/sec: 2915.05 - lr: 0.000025 - momentum: 0.000000
112
+ 2023-10-23 15:07:33,706 epoch 3 - iter 65/138 - loss 0.08097315 - time (sec): 3.63 - samples/sec: 2919.45 - lr: 0.000025 - momentum: 0.000000
113
+ 2023-10-23 15:07:34,428 epoch 3 - iter 78/138 - loss 0.09177425 - time (sec): 4.35 - samples/sec: 2985.50 - lr: 0.000025 - momentum: 0.000000
114
+ 2023-10-23 15:07:35,146 epoch 3 - iter 91/138 - loss 0.09142755 - time (sec): 5.07 - samples/sec: 2969.81 - lr: 0.000025 - momentum: 0.000000
115
+ 2023-10-23 15:07:35,861 epoch 3 - iter 104/138 - loss 0.09832228 - time (sec): 5.78 - samples/sec: 2959.21 - lr: 0.000024 - momentum: 0.000000
116
+ 2023-10-23 15:07:36,586 epoch 3 - iter 117/138 - loss 0.09428056 - time (sec): 6.51 - samples/sec: 2934.42 - lr: 0.000024 - momentum: 0.000000
117
+ 2023-10-23 15:07:37,315 epoch 3 - iter 130/138 - loss 0.09309894 - time (sec): 7.24 - samples/sec: 2981.29 - lr: 0.000024 - momentum: 0.000000
118
+ 2023-10-23 15:07:37,749 ----------------------------------------------------------------------------------------------------
119
+ 2023-10-23 15:07:37,749 EPOCH 3 done: loss 0.0929 - lr: 0.000024
120
+ 2023-10-23 15:07:38,296 DEV : loss 0.11146871745586395 - f1-score (micro avg) 0.844
121
+ 2023-10-23 15:07:38,302 saving best model
122
+ 2023-10-23 15:07:38,852 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-23 15:07:39,565 epoch 4 - iter 13/138 - loss 0.07417365 - time (sec): 0.71 - samples/sec: 2998.80 - lr: 0.000023 - momentum: 0.000000
124
+ 2023-10-23 15:07:40,286 epoch 4 - iter 26/138 - loss 0.06986805 - time (sec): 1.43 - samples/sec: 2968.61 - lr: 0.000023 - momentum: 0.000000
125
+ 2023-10-23 15:07:41,007 epoch 4 - iter 39/138 - loss 0.08114707 - time (sec): 2.15 - samples/sec: 3128.61 - lr: 0.000022 - momentum: 0.000000
126
+ 2023-10-23 15:07:41,736 epoch 4 - iter 52/138 - loss 0.08438909 - time (sec): 2.88 - samples/sec: 3084.25 - lr: 0.000022 - momentum: 0.000000
127
+ 2023-10-23 15:07:42,461 epoch 4 - iter 65/138 - loss 0.08351933 - time (sec): 3.61 - samples/sec: 3031.35 - lr: 0.000022 - momentum: 0.000000
128
+ 2023-10-23 15:07:43,184 epoch 4 - iter 78/138 - loss 0.08021593 - time (sec): 4.33 - samples/sec: 3031.07 - lr: 0.000021 - momentum: 0.000000
129
+ 2023-10-23 15:07:43,906 epoch 4 - iter 91/138 - loss 0.07395782 - time (sec): 5.05 - samples/sec: 2999.11 - lr: 0.000021 - momentum: 0.000000
130
+ 2023-10-23 15:07:44,620 epoch 4 - iter 104/138 - loss 0.06842096 - time (sec): 5.76 - samples/sec: 3001.16 - lr: 0.000021 - momentum: 0.000000
131
+ 2023-10-23 15:07:45,339 epoch 4 - iter 117/138 - loss 0.06532291 - time (sec): 6.48 - samples/sec: 3016.64 - lr: 0.000021 - momentum: 0.000000
132
+ 2023-10-23 15:07:46,062 epoch 4 - iter 130/138 - loss 0.06170555 - time (sec): 7.21 - samples/sec: 3004.71 - lr: 0.000020 - momentum: 0.000000
133
+ 2023-10-23 15:07:46,496 ----------------------------------------------------------------------------------------------------
134
+ 2023-10-23 15:07:46,497 EPOCH 4 done: loss 0.0591 - lr: 0.000020
135
+ 2023-10-23 15:07:47,039 DEV : loss 0.14198631048202515 - f1-score (micro avg) 0.8429
136
+ 2023-10-23 15:07:47,045 ----------------------------------------------------------------------------------------------------
137
+ 2023-10-23 15:07:47,788 epoch 5 - iter 13/138 - loss 0.06644428 - time (sec): 0.74 - samples/sec: 2745.04 - lr: 0.000020 - momentum: 0.000000
138
+ 2023-10-23 15:07:48,512 epoch 5 - iter 26/138 - loss 0.04553320 - time (sec): 1.47 - samples/sec: 2952.14 - lr: 0.000019 - momentum: 0.000000
139
+ 2023-10-23 15:07:49,230 epoch 5 - iter 39/138 - loss 0.04521235 - time (sec): 2.18 - samples/sec: 2950.05 - lr: 0.000019 - momentum: 0.000000
140
+ 2023-10-23 15:07:49,949 epoch 5 - iter 52/138 - loss 0.04484997 - time (sec): 2.90 - samples/sec: 2990.83 - lr: 0.000019 - momentum: 0.000000
141
+ 2023-10-23 15:07:50,661 epoch 5 - iter 65/138 - loss 0.04792661 - time (sec): 3.61 - samples/sec: 2919.57 - lr: 0.000018 - momentum: 0.000000
142
+ 2023-10-23 15:07:51,387 epoch 5 - iter 78/138 - loss 0.04659725 - time (sec): 4.34 - samples/sec: 2989.06 - lr: 0.000018 - momentum: 0.000000
143
+ 2023-10-23 15:07:52,103 epoch 5 - iter 91/138 - loss 0.04544001 - time (sec): 5.06 - samples/sec: 3014.62 - lr: 0.000018 - momentum: 0.000000
144
+ 2023-10-23 15:07:52,819 epoch 5 - iter 104/138 - loss 0.04228585 - time (sec): 5.77 - samples/sec: 2995.04 - lr: 0.000018 - momentum: 0.000000
145
+ 2023-10-23 15:07:53,539 epoch 5 - iter 117/138 - loss 0.04306651 - time (sec): 6.49 - samples/sec: 2988.26 - lr: 0.000017 - momentum: 0.000000
146
+ 2023-10-23 15:07:54,265 epoch 5 - iter 130/138 - loss 0.04583492 - time (sec): 7.22 - samples/sec: 3009.23 - lr: 0.000017 - momentum: 0.000000
147
+ 2023-10-23 15:07:54,703 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-23 15:07:54,704 EPOCH 5 done: loss 0.0454 - lr: 0.000017
149
+ 2023-10-23 15:07:55,244 DEV : loss 0.1429574191570282 - f1-score (micro avg) 0.8729
150
+ 2023-10-23 15:07:55,250 saving best model
151
+ 2023-10-23 15:07:55,797 ----------------------------------------------------------------------------------------------------
152
+ 2023-10-23 15:07:56,548 epoch 6 - iter 13/138 - loss 0.05313669 - time (sec): 0.74 - samples/sec: 3211.35 - lr: 0.000016 - momentum: 0.000000
153
+ 2023-10-23 15:07:57,283 epoch 6 - iter 26/138 - loss 0.03327101 - time (sec): 1.48 - samples/sec: 3195.35 - lr: 0.000016 - momentum: 0.000000
154
+ 2023-10-23 15:07:58,021 epoch 6 - iter 39/138 - loss 0.04254490 - time (sec): 2.22 - samples/sec: 3140.84 - lr: 0.000016 - momentum: 0.000000
155
+ 2023-10-23 15:07:58,758 epoch 6 - iter 52/138 - loss 0.03923725 - time (sec): 2.95 - samples/sec: 2936.13 - lr: 0.000015 - momentum: 0.000000
156
+ 2023-10-23 15:07:59,478 epoch 6 - iter 65/138 - loss 0.03746846 - time (sec): 3.67 - samples/sec: 2937.94 - lr: 0.000015 - momentum: 0.000000
157
+ 2023-10-23 15:08:00,197 epoch 6 - iter 78/138 - loss 0.03435769 - time (sec): 4.39 - samples/sec: 2994.45 - lr: 0.000015 - momentum: 0.000000
158
+ 2023-10-23 15:08:00,945 epoch 6 - iter 91/138 - loss 0.03640010 - time (sec): 5.14 - samples/sec: 2998.68 - lr: 0.000015 - momentum: 0.000000
159
+ 2023-10-23 15:08:01,694 epoch 6 - iter 104/138 - loss 0.03377304 - time (sec): 5.89 - samples/sec: 2984.79 - lr: 0.000014 - momentum: 0.000000
160
+ 2023-10-23 15:08:02,446 epoch 6 - iter 117/138 - loss 0.03257520 - time (sec): 6.64 - samples/sec: 2957.25 - lr: 0.000014 - momentum: 0.000000
161
+ 2023-10-23 15:08:03,180 epoch 6 - iter 130/138 - loss 0.03234360 - time (sec): 7.38 - samples/sec: 2954.25 - lr: 0.000014 - momentum: 0.000000
162
+ 2023-10-23 15:08:03,655 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-23 15:08:03,656 EPOCH 6 done: loss 0.0321 - lr: 0.000014
164
+ 2023-10-23 15:08:04,195 DEV : loss 0.1479213535785675 - f1-score (micro avg) 0.8709
165
+ 2023-10-23 15:08:04,200 ----------------------------------------------------------------------------------------------------
166
+ 2023-10-23 15:08:04,966 epoch 7 - iter 13/138 - loss 0.02597140 - time (sec): 0.76 - samples/sec: 2514.83 - lr: 0.000013 - momentum: 0.000000
167
+ 2023-10-23 15:08:05,726 epoch 7 - iter 26/138 - loss 0.01437665 - time (sec): 1.52 - samples/sec: 2761.37 - lr: 0.000013 - momentum: 0.000000
168
+ 2023-10-23 15:08:06,471 epoch 7 - iter 39/138 - loss 0.01851670 - time (sec): 2.27 - samples/sec: 2850.88 - lr: 0.000012 - momentum: 0.000000
169
+ 2023-10-23 15:08:07,196 epoch 7 - iter 52/138 - loss 0.02480619 - time (sec): 2.99 - samples/sec: 2820.13 - lr: 0.000012 - momentum: 0.000000
170
+ 2023-10-23 15:08:07,948 epoch 7 - iter 65/138 - loss 0.02149033 - time (sec): 3.75 - samples/sec: 2910.10 - lr: 0.000012 - momentum: 0.000000
171
+ 2023-10-23 15:08:08,703 epoch 7 - iter 78/138 - loss 0.02322504 - time (sec): 4.50 - samples/sec: 2906.22 - lr: 0.000012 - momentum: 0.000000
172
+ 2023-10-23 15:08:09,465 epoch 7 - iter 91/138 - loss 0.02397668 - time (sec): 5.26 - samples/sec: 2870.09 - lr: 0.000011 - momentum: 0.000000
173
+ 2023-10-23 15:08:10,222 epoch 7 - iter 104/138 - loss 0.02779713 - time (sec): 6.02 - samples/sec: 2892.16 - lr: 0.000011 - momentum: 0.000000
174
+ 2023-10-23 15:08:10,971 epoch 7 - iter 117/138 - loss 0.02625708 - time (sec): 6.77 - samples/sec: 2907.51 - lr: 0.000011 - momentum: 0.000000
175
+ 2023-10-23 15:08:11,719 epoch 7 - iter 130/138 - loss 0.02663558 - time (sec): 7.52 - samples/sec: 2877.48 - lr: 0.000010 - momentum: 0.000000
176
+ 2023-10-23 15:08:12,167 ----------------------------------------------------------------------------------------------------
177
+ 2023-10-23 15:08:12,168 EPOCH 7 done: loss 0.0262 - lr: 0.000010
178
+ 2023-10-23 15:08:12,700 DEV : loss 0.1471543312072754 - f1-score (micro avg) 0.8889
179
+ 2023-10-23 15:08:12,706 saving best model
180
+ 2023-10-23 15:08:13,258 ----------------------------------------------------------------------------------------------------
181
+ 2023-10-23 15:08:13,992 epoch 8 - iter 13/138 - loss 0.00685940 - time (sec): 0.73 - samples/sec: 3052.76 - lr: 0.000010 - momentum: 0.000000
182
+ 2023-10-23 15:08:14,719 epoch 8 - iter 26/138 - loss 0.00837478 - time (sec): 1.46 - samples/sec: 3063.30 - lr: 0.000009 - momentum: 0.000000
183
+ 2023-10-23 15:08:15,449 epoch 8 - iter 39/138 - loss 0.01552073 - time (sec): 2.19 - samples/sec: 2964.82 - lr: 0.000009 - momentum: 0.000000
184
+ 2023-10-23 15:08:16,191 epoch 8 - iter 52/138 - loss 0.01548429 - time (sec): 2.93 - samples/sec: 2968.22 - lr: 0.000009 - momentum: 0.000000
185
+ 2023-10-23 15:08:16,913 epoch 8 - iter 65/138 - loss 0.01707087 - time (sec): 3.65 - samples/sec: 2992.16 - lr: 0.000009 - momentum: 0.000000
186
+ 2023-10-23 15:08:17,643 epoch 8 - iter 78/138 - loss 0.01863647 - time (sec): 4.38 - samples/sec: 3012.24 - lr: 0.000008 - momentum: 0.000000
187
+ 2023-10-23 15:08:18,388 epoch 8 - iter 91/138 - loss 0.01654718 - time (sec): 5.13 - samples/sec: 3023.60 - lr: 0.000008 - momentum: 0.000000
188
+ 2023-10-23 15:08:19,120 epoch 8 - iter 104/138 - loss 0.01502671 - time (sec): 5.86 - samples/sec: 2978.80 - lr: 0.000008 - momentum: 0.000000
189
+ 2023-10-23 15:08:19,834 epoch 8 - iter 117/138 - loss 0.01598256 - time (sec): 6.57 - samples/sec: 2959.46 - lr: 0.000007 - momentum: 0.000000
190
+ 2023-10-23 15:08:20,554 epoch 8 - iter 130/138 - loss 0.01714523 - time (sec): 7.29 - samples/sec: 2971.22 - lr: 0.000007 - momentum: 0.000000
191
+ 2023-10-23 15:08:21,007 ----------------------------------------------------------------------------------------------------
192
+ 2023-10-23 15:08:21,007 EPOCH 8 done: loss 0.0202 - lr: 0.000007
193
+ 2023-10-23 15:08:21,548 DEV : loss 0.16060495376586914 - f1-score (micro avg) 0.8709
194
+ 2023-10-23 15:08:21,554 ----------------------------------------------------------------------------------------------------
195
+ 2023-10-23 15:08:22,282 epoch 9 - iter 13/138 - loss 0.01332285 - time (sec): 0.73 - samples/sec: 2626.51 - lr: 0.000006 - momentum: 0.000000
196
+ 2023-10-23 15:08:23,018 epoch 9 - iter 26/138 - loss 0.01710958 - time (sec): 1.46 - samples/sec: 2850.06 - lr: 0.000006 - momentum: 0.000000
197
+ 2023-10-23 15:08:23,760 epoch 9 - iter 39/138 - loss 0.01294442 - time (sec): 2.20 - samples/sec: 2937.72 - lr: 0.000006 - momentum: 0.000000
198
+ 2023-10-23 15:08:24,471 epoch 9 - iter 52/138 - loss 0.01105454 - time (sec): 2.92 - samples/sec: 2875.90 - lr: 0.000005 - momentum: 0.000000
199
+ 2023-10-23 15:08:25,187 epoch 9 - iter 65/138 - loss 0.01446311 - time (sec): 3.63 - samples/sec: 2900.29 - lr: 0.000005 - momentum: 0.000000
200
+ 2023-10-23 15:08:25,912 epoch 9 - iter 78/138 - loss 0.01373708 - time (sec): 4.36 - samples/sec: 2918.40 - lr: 0.000005 - momentum: 0.000000
201
+ 2023-10-23 15:08:26,634 epoch 9 - iter 91/138 - loss 0.01216404 - time (sec): 5.08 - samples/sec: 2946.47 - lr: 0.000005 - momentum: 0.000000
202
+ 2023-10-23 15:08:27,354 epoch 9 - iter 104/138 - loss 0.01273020 - time (sec): 5.80 - samples/sec: 2957.94 - lr: 0.000004 - momentum: 0.000000
203
+ 2023-10-23 15:08:28,075 epoch 9 - iter 117/138 - loss 0.01627844 - time (sec): 6.52 - samples/sec: 2952.13 - lr: 0.000004 - momentum: 0.000000
204
+ 2023-10-23 15:08:28,814 epoch 9 - iter 130/138 - loss 0.01638689 - time (sec): 7.26 - samples/sec: 2966.35 - lr: 0.000004 - momentum: 0.000000
205
+ 2023-10-23 15:08:29,252 ----------------------------------------------------------------------------------------------------
206
+ 2023-10-23 15:08:29,252 EPOCH 9 done: loss 0.0177 - lr: 0.000004
207
+ 2023-10-23 15:08:29,788 DEV : loss 0.16575126349925995 - f1-score (micro avg) 0.873
208
+ 2023-10-23 15:08:29,794 ----------------------------------------------------------------------------------------------------
209
+ 2023-10-23 15:08:30,511 epoch 10 - iter 13/138 - loss 0.02224445 - time (sec): 0.72 - samples/sec: 2949.26 - lr: 0.000003 - momentum: 0.000000
210
+ 2023-10-23 15:08:31,229 epoch 10 - iter 26/138 - loss 0.01329094 - time (sec): 1.43 - samples/sec: 2876.82 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-23 15:08:31,953 epoch 10 - iter 39/138 - loss 0.01583951 - time (sec): 2.16 - samples/sec: 2954.08 - lr: 0.000002 - momentum: 0.000000
212
+ 2023-10-23 15:08:32,674 epoch 10 - iter 52/138 - loss 0.01334604 - time (sec): 2.88 - samples/sec: 2962.65 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-23 15:08:33,393 epoch 10 - iter 65/138 - loss 0.01096514 - time (sec): 3.60 - samples/sec: 2943.65 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-23 15:08:34,127 epoch 10 - iter 78/138 - loss 0.01231639 - time (sec): 4.33 - samples/sec: 3033.22 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-23 15:08:34,865 epoch 10 - iter 91/138 - loss 0.01196000 - time (sec): 5.07 - samples/sec: 3093.54 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-23 15:08:35,600 epoch 10 - iter 104/138 - loss 0.01316873 - time (sec): 5.81 - samples/sec: 3074.63 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-23 15:08:36,309 epoch 10 - iter 117/138 - loss 0.01240979 - time (sec): 6.51 - samples/sec: 3021.99 - lr: 0.000001 - momentum: 0.000000
218
+ 2023-10-23 15:08:37,035 epoch 10 - iter 130/138 - loss 0.01491721 - time (sec): 7.24 - samples/sec: 2991.14 - lr: 0.000000 - momentum: 0.000000
219
+ 2023-10-23 15:08:37,473 ----------------------------------------------------------------------------------------------------
220
+ 2023-10-23 15:08:37,473 EPOCH 10 done: loss 0.0146 - lr: 0.000000
221
+ 2023-10-23 15:08:38,012 DEV : loss 0.1697995662689209 - f1-score (micro avg) 0.8779
222
+ 2023-10-23 15:08:38,413 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-23 15:08:38,414 Loading model from best epoch ...
224
+ 2023-10-23 15:08:40,173 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
225
+ 2023-10-23 15:08:40,847
226
+ Results:
227
+ - F-score (micro) 0.9089
228
+ - F-score (macro) 0.7794
229
+ - Accuracy 0.8411
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ scope 0.8814 0.8864 0.8839 176
235
+ pers 0.9615 0.9766 0.9690 128
236
+ work 0.9385 0.8243 0.8777 74
237
+ object 0.5000 0.5000 0.5000 2
238
+ loc 1.0000 0.5000 0.6667 2
239
+
240
+ micro avg 0.9173 0.9005 0.9089 382
241
+ macro avg 0.8563 0.7375 0.7794 382
242
+ weighted avg 0.9179 0.9005 0.9080 382
243
+
244
+ 2023-10-23 15:08:40,847 ----------------------------------------------------------------------------------------------------