Hugging Face's logo

stefan-it
/
hmbench-icdar-nl-hmbyt5-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1

Token Classification
Flair
PyTorch
TensorBoard
Dutch
sequence-tagger-model
Model card Files
xet
Metrics Community
2
stefan-it commited on
Commit
6f9b4a8
·
1 Parent(s): d81d94e

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. final-model.pt +3 -0
  4. loss.tsv +11 -0
  5. runs/events.out.tfevents.1697037532.c8b2203b18a8.1914.1 +3 -0
  6. test.tsv +0 -0
  7. training.log +262 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc27b63e798005eca77116e5897e73c51421d24a34dd99116f0603150fab60f
3
+ size 870793839
dev.tsv ADDED
The diff for this file is too large to render. See raw diff
 
final-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d51ea279dcdebcc07cdbf7c5de267da63b6d3a4bae8ca2c82c69e897b63f90
3
+ size 870793956
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 15:26:04 0.0002 1.1462 0.2301 0.0000 0.0000 0.0000 0.0000
3
+ 2 15:33:11 0.0001 0.1361 0.1178 0.7028 0.7376 0.7198 0.5805
4
+ 3 15:40:23 0.0001 0.0826 0.0953 0.8369 0.7211 0.7747 0.6439
5
+ 4 15:48:19 0.0001 0.0528 0.0786 0.8614 0.8151 0.8376 0.7367
6
+ 5 15:55:23 0.0001 0.0363 0.0809 0.8510 0.8440 0.8475 0.7502
7
+ 6 16:02:46 0.0001 0.0281 0.0903 0.8772 0.8337 0.8549 0.7606
8
+ 7 16:10:14 0.0001 0.0218 0.1077 0.8772 0.8264 0.8511 0.7540
9
+ 8 16:18:18 0.0000 0.0176 0.1181 0.8662 0.8295 0.8475 0.7484
10
+ 9 16:25:52 0.0000 0.0141 0.1251 0.8625 0.8357 0.8489 0.7505
11
+ 10 16:33:16 0.0000 0.0123 0.1305 0.8601 0.8192 0.8392 0.7356
runs/events.out.tfevents.1697037532.c8b2203b18a8.1914.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4674d8f872727f7b9942284b23c60b16172550880ddbefe9e2e825f8e70b7e23
3
+ size 407048
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-11 15:18:52,762 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-11 15:18:52,764 Model: "SequenceTagger(
3
+ (embeddings): ByT5Embeddings(
4
+ (model): T5EncoderModel(
5
+ (shared): Embedding(384, 1472)
6
+ (encoder): T5Stack(
7
+ (embed_tokens): Embedding(384, 1472)
8
+ (block): ModuleList(
9
+ (0): T5Block(
10
+ (layer): ModuleList(
11
+ (0): T5LayerSelfAttention(
12
+ (SelfAttention): T5Attention(
13
+ (q): Linear(in_features=1472, out_features=384, bias=False)
14
+ (k): Linear(in_features=1472, out_features=384, bias=False)
15
+ (v): Linear(in_features=1472, out_features=384, bias=False)
16
+ (o): Linear(in_features=384, out_features=1472, bias=False)
17
+ (relative_attention_bias): Embedding(32, 6)
18
+ )
19
+ (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
20
+ (dropout): Dropout(p=0.1, inplace=False)
21
+ )
22
+ (1): T5LayerFF(
23
+ (DenseReluDense): T5DenseGatedActDense(
24
+ (wi_0): Linear(in_features=1472, out_features=3584, bias=False)
25
+ (wi_1): Linear(in_features=1472, out_features=3584, bias=False)
26
+ (wo): Linear(in_features=3584, out_features=1472, bias=False)
27
+ (dropout): Dropout(p=0.1, inplace=False)
28
+ (act): NewGELUActivation()
29
+ )
30
+ (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
31
+ (dropout): Dropout(p=0.1, inplace=False)
32
+ )
33
+ )
34
+ )
35
+ (1-11): 11 x T5Block(
36
+ (layer): ModuleList(
37
+ (0): T5LayerSelfAttention(
38
+ (SelfAttention): T5Attention(
39
+ (q): Linear(in_features=1472, out_features=384, bias=False)
40
+ (k): Linear(in_features=1472, out_features=384, bias=False)
41
+ (v): Linear(in_features=1472, out_features=384, bias=False)
42
+ (o): Linear(in_features=384, out_features=1472, bias=False)
43
+ )
44
+ (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
45
+ (dropout): Dropout(p=0.1, inplace=False)
46
+ )
47
+ (1): T5LayerFF(
48
+ (DenseReluDense): T5DenseGatedActDense(
49
+ (wi_0): Linear(in_features=1472, out_features=3584, bias=False)
50
+ (wi_1): Linear(in_features=1472, out_features=3584, bias=False)
51
+ (wo): Linear(in_features=3584, out_features=1472, bias=False)
52
+ (dropout): Dropout(p=0.1, inplace=False)
53
+ (act): NewGELUActivation()
54
+ )
55
+ (layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
56
+ (dropout): Dropout(p=0.1, inplace=False)
57
+ )
58
+ )
59
+ )
60
+ )
61
+ (final_layer_norm): FusedRMSNorm(torch.Size([1472]), eps=1e-06, elementwise_affine=True)
62
+ (dropout): Dropout(p=0.1, inplace=False)
63
+ )
64
+ )
65
+ )
66
+ (locked_dropout): LockedDropout(p=0.5)
67
+ (linear): Linear(in_features=1472, out_features=13, bias=True)
68
+ (loss_function): CrossEntropyLoss()
69
+ )"
70
+ 2023-10-11 15:18:52,764 ----------------------------------------------------------------------------------------------------
71
+ 2023-10-11 15:18:52,764 MultiCorpus: 5777 train + 722 dev + 723 test sentences
72
+ - NER_ICDAR_EUROPEANA Corpus: 5777 train + 722 dev + 723 test sentences - /root/.flair/datasets/ner_icdar_europeana/nl
73
+ 2023-10-11 15:18:52,764 ----------------------------------------------------------------------------------------------------
74
+ 2023-10-11 15:18:52,764 Train: 5777 sentences
75
+ 2023-10-11 15:18:52,765 (train_with_dev=False, train_with_test=False)
76
+ 2023-10-11 15:18:52,765 ----------------------------------------------------------------------------------------------------
77
+ 2023-10-11 15:18:52,765 Training Params:
78
+ 2023-10-11 15:18:52,765 - learning_rate: "0.00016"
79
+ 2023-10-11 15:18:52,765 - mini_batch_size: "8"
80
+ 2023-10-11 15:18:52,765 - max_epochs: "10"
81
+ 2023-10-11 15:18:52,765 - shuffle: "True"
82
+ 2023-10-11 15:18:52,765 ----------------------------------------------------------------------------------------------------
83
+ 2023-10-11 15:18:52,765 Plugins:
84
+ 2023-10-11 15:18:52,765 - TensorboardLogger
85
+ 2023-10-11 15:18:52,765 - LinearScheduler | warmup_fraction: '0.1'
86
+ 2023-10-11 15:18:52,765 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-11 15:18:52,765 Final evaluation on model from best epoch (best-model.pt)
88
+ 2023-10-11 15:18:52,765 - metric: "('micro avg', 'f1-score')"
89
+ 2023-10-11 15:18:52,765 ----------------------------------------------------------------------------------------------------
90
+ 2023-10-11 15:18:52,766 Computation:
91
+ 2023-10-11 15:18:52,766 - compute on device: cuda:0
92
+ 2023-10-11 15:18:52,766 - embedding storage: none
93
+ 2023-10-11 15:18:52,766 ----------------------------------------------------------------------------------------------------
94
+ 2023-10-11 15:18:52,766 Model training base path: "hmbench-icdar/nl-hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1"
95
+ 2023-10-11 15:18:52,766 ----------------------------------------------------------------------------------------------------
96
+ 2023-10-11 15:18:52,766 ----------------------------------------------------------------------------------------------------
97
+ 2023-10-11 15:18:52,766 Logging anything other than scalars to TensorBoard is currently not supported.
98
+ 2023-10-11 15:19:33,021 epoch 1 - iter 72/723 - loss 2.58640498 - time (sec): 40.25 - samples/sec: 437.63 - lr: 0.000016 - momentum: 0.000000
99
+ 2023-10-11 15:20:15,240 epoch 1 - iter 144/723 - loss 2.54575181 - time (sec): 82.47 - samples/sec: 450.66 - lr: 0.000032 - momentum: 0.000000
100
+ 2023-10-11 15:20:55,763 epoch 1 - iter 216/723 - loss 2.39945434 - time (sec): 122.99 - samples/sec: 435.33 - lr: 0.000048 - momentum: 0.000000
101
+ 2023-10-11 15:21:37,028 epoch 1 - iter 288/723 - loss 2.17892498 - time (sec): 164.26 - samples/sec: 435.94 - lr: 0.000064 - momentum: 0.000000
102
+ 2023-10-11 15:22:20,557 epoch 1 - iter 360/723 - loss 1.92804078 - time (sec): 207.79 - samples/sec: 438.73 - lr: 0.000079 - momentum: 0.000000
103
+ 2023-10-11 15:23:02,576 epoch 1 - iter 432/723 - loss 1.71210703 - time (sec): 249.81 - samples/sec: 432.91 - lr: 0.000095 - momentum: 0.000000
104
+ 2023-10-11 15:23:45,206 epoch 1 - iter 504/723 - loss 1.52388016 - time (sec): 292.44 - samples/sec: 429.48 - lr: 0.000111 - momentum: 0.000000
105
+ 2023-10-11 15:24:25,404 epoch 1 - iter 576/723 - loss 1.37250291 - time (sec): 332.64 - samples/sec: 428.17 - lr: 0.000127 - momentum: 0.000000
106
+ 2023-10-11 15:25:04,451 epoch 1 - iter 648/723 - loss 1.25612134 - time (sec): 371.68 - samples/sec: 425.47 - lr: 0.000143 - momentum: 0.000000
107
+ 2023-10-11 15:25:44,336 epoch 1 - iter 720/723 - loss 1.14790086 - time (sec): 411.57 - samples/sec: 427.20 - lr: 0.000159 - momentum: 0.000000
108
+ 2023-10-11 15:25:45,493 ----------------------------------------------------------------------------------------------------
109
+ 2023-10-11 15:25:45,494 EPOCH 1 done: loss 1.1462 - lr: 0.000159
110
+ 2023-10-11 15:26:04,954 DEV : loss 0.23013751208782196 - f1-score (micro avg) 0.0
111
+ 2023-10-11 15:26:04,983 ----------------------------------------------------------------------------------------------------
112
+ 2023-10-11 15:26:44,924 epoch 2 - iter 72/723 - loss 0.18779348 - time (sec): 39.94 - samples/sec: 451.51 - lr: 0.000158 - momentum: 0.000000
113
+ 2023-10-11 15:27:25,506 epoch 2 - iter 144/723 - loss 0.16703311 - time (sec): 80.52 - samples/sec: 441.10 - lr: 0.000156 - momentum: 0.000000
114
+ 2023-10-11 15:28:05,904 epoch 2 - iter 216/723 - loss 0.16733631 - time (sec): 120.92 - samples/sec: 427.45 - lr: 0.000155 - momentum: 0.000000
115
+ 2023-10-11 15:28:47,010 epoch 2 - iter 288/723 - loss 0.16076280 - time (sec): 162.02 - samples/sec: 428.06 - lr: 0.000153 - momentum: 0.000000
116
+ 2023-10-11 15:29:27,132 epoch 2 - iter 360/723 - loss 0.15822813 - time (sec): 202.15 - samples/sec: 432.35 - lr: 0.000151 - momentum: 0.000000
117
+ 2023-10-11 15:30:06,139 epoch 2 - iter 432/723 - loss 0.15494629 - time (sec): 241.15 - samples/sec: 434.81 - lr: 0.000149 - momentum: 0.000000
118
+ 2023-10-11 15:30:46,534 epoch 2 - iter 504/723 - loss 0.14781553 - time (sec): 281.55 - samples/sec: 437.97 - lr: 0.000148 - momentum: 0.000000
119
+ 2023-10-11 15:31:28,218 epoch 2 - iter 576/723 - loss 0.14089350 - time (sec): 323.23 - samples/sec: 442.36 - lr: 0.000146 - momentum: 0.000000
120
+ 2023-10-11 15:32:07,820 epoch 2 - iter 648/723 - loss 0.13806927 - time (sec): 362.83 - samples/sec: 438.46 - lr: 0.000144 - momentum: 0.000000
121
+ 2023-10-11 15:32:47,840 epoch 2 - iter 720/723 - loss 0.13620972 - time (sec): 402.86 - samples/sec: 435.58 - lr: 0.000142 - momentum: 0.000000
122
+ 2023-10-11 15:32:49,348 ----------------------------------------------------------------------------------------------------
123
+ 2023-10-11 15:32:49,349 EPOCH 2 done: loss 0.1361 - lr: 0.000142
124
+ 2023-10-11 15:33:11,468 DEV : loss 0.11784520745277405 - f1-score (micro avg) 0.7198
125
+ 2023-10-11 15:33:11,498 saving best model
126
+ 2023-10-11 15:33:12,500 ----------------------------------------------------------------------------------------------------
127
+ 2023-10-11 15:33:56,445 epoch 3 - iter 72/723 - loss 0.08434424 - time (sec): 43.94 - samples/sec: 393.04 - lr: 0.000140 - momentum: 0.000000
128
+ 2023-10-11 15:34:38,669 epoch 3 - iter 144/723 - loss 0.09138352 - time (sec): 86.17 - samples/sec: 399.52 - lr: 0.000139 - momentum: 0.000000
129
+ 2023-10-11 15:35:17,265 epoch 3 - iter 216/723 - loss 0.08550606 - time (sec): 124.76 - samples/sec: 416.98 - lr: 0.000137 - momentum: 0.000000
130
+ 2023-10-11 15:35:57,111 epoch 3 - iter 288/723 - loss 0.09254066 - time (sec): 164.61 - samples/sec: 417.05 - lr: 0.000135 - momentum: 0.000000
131
+ 2023-10-11 15:36:38,099 epoch 3 - iter 360/723 - loss 0.09054215 - time (sec): 205.60 - samples/sec: 424.30 - lr: 0.000133 - momentum: 0.000000
132
+ 2023-10-11 15:37:16,378 epoch 3 - iter 432/723 - loss 0.09029129 - time (sec): 243.88 - samples/sec: 426.52 - lr: 0.000132 - momentum: 0.000000
133
+ 2023-10-11 15:37:56,089 epoch 3 - iter 504/723 - loss 0.08953230 - time (sec): 283.59 - samples/sec: 428.48 - lr: 0.000130 - momentum: 0.000000
134
+ 2023-10-11 15:38:36,917 epoch 3 - iter 576/723 - loss 0.08628376 - time (sec): 324.42 - samples/sec: 430.75 - lr: 0.000128 - momentum: 0.000000
135
+ 2023-10-11 15:39:16,306 epoch 3 - iter 648/723 - loss 0.08375845 - time (sec): 363.80 - samples/sec: 434.46 - lr: 0.000126 - momentum: 0.000000
136
+ 2023-10-11 15:39:58,736 epoch 3 - iter 720/723 - loss 0.08263566 - time (sec): 406.23 - samples/sec: 432.38 - lr: 0.000125 - momentum: 0.000000
137
+ 2023-10-11 15:40:00,098 ----------------------------------------------------------------------------------------------------
138
+ 2023-10-11 15:40:00,099 EPOCH 3 done: loss 0.0826 - lr: 0.000125
139
+ 2023-10-11 15:40:23,121 DEV : loss 0.09526825696229935 - f1-score (micro avg) 0.7747
140
+ 2023-10-11 15:40:23,153 saving best model
141
+ 2023-10-11 15:40:25,742 ----------------------------------------------------------------------------------------------------
142
+ 2023-10-11 15:41:11,486 epoch 4 - iter 72/723 - loss 0.07098217 - time (sec): 45.74 - samples/sec: 395.35 - lr: 0.000123 - momentum: 0.000000
143
+ 2023-10-11 15:41:56,161 epoch 4 - iter 144/723 - loss 0.06244011 - time (sec): 90.41 - samples/sec: 387.90 - lr: 0.000121 - momentum: 0.000000
144
+ 2023-10-11 15:42:41,898 epoch 4 - iter 216/723 - loss 0.05892834 - time (sec): 136.15 - samples/sec: 388.41 - lr: 0.000119 - momentum: 0.000000
145
+ 2023-10-11 15:43:27,740 epoch 4 - iter 288/723 - loss 0.05706105 - time (sec): 181.99 - samples/sec: 386.02 - lr: 0.000117 - momentum: 0.000000
146
+ 2023-10-11 15:44:13,629 epoch 4 - iter 360/723 - loss 0.05540965 - time (sec): 227.88 - samples/sec: 382.82 - lr: 0.000116 - momentum: 0.000000
147
+ 2023-10-11 15:44:57,779 epoch 4 - iter 432/723 - loss 0.05519746 - time (sec): 272.03 - samples/sec: 381.49 - lr: 0.000114 - momentum: 0.000000
148
+ 2023-10-11 15:45:42,220 epoch 4 - iter 504/723 - loss 0.05511683 - time (sec): 316.47 - samples/sec: 382.27 - lr: 0.000112 - momentum: 0.000000
149
+ 2023-10-11 15:46:28,521 epoch 4 - iter 576/723 - loss 0.05612426 - time (sec): 362.77 - samples/sec: 384.07 - lr: 0.000110 - momentum: 0.000000
150
+ 2023-10-11 15:47:13,618 epoch 4 - iter 648/723 - loss 0.05489093 - time (sec): 407.87 - samples/sec: 385.40 - lr: 0.000109 - momentum: 0.000000
151
+ 2023-10-11 15:47:57,365 epoch 4 - iter 720/723 - loss 0.05280893 - time (sec): 451.62 - samples/sec: 389.22 - lr: 0.000107 - momentum: 0.000000
152
+ 2023-10-11 15:47:58,594 ----------------------------------------------------------------------------------------------------
153
+ 2023-10-11 15:47:58,594 EPOCH 4 done: loss 0.0528 - lr: 0.000107
154
+ 2023-10-11 15:48:19,766 DEV : loss 0.07857168465852737 - f1-score (micro avg) 0.8376
155
+ 2023-10-11 15:48:19,797 saving best model
156
+ 2023-10-11 15:48:22,416 ----------------------------------------------------------------------------------------------------
157
+ 2023-10-11 15:49:02,536 epoch 5 - iter 72/723 - loss 0.02925552 - time (sec): 40.12 - samples/sec: 445.20 - lr: 0.000105 - momentum: 0.000000
158
+ 2023-10-11 15:49:40,160 epoch 5 - iter 144/723 - loss 0.03139574 - time (sec): 77.74 - samples/sec: 444.68 - lr: 0.000103 - momentum: 0.000000
159
+ 2023-10-11 15:50:18,818 epoch 5 - iter 216/723 - loss 0.03596320 - time (sec): 116.40 - samples/sec: 441.32 - lr: 0.000101 - momentum: 0.000000
160
+ 2023-10-11 15:50:58,827 epoch 5 - iter 288/723 - loss 0.03461253 - time (sec): 156.41 - samples/sec: 442.52 - lr: 0.000100 - momentum: 0.000000
161
+ 2023-10-11 15:51:39,726 epoch 5 - iter 360/723 - loss 0.03830367 - time (sec): 197.31 - samples/sec: 445.19 - lr: 0.000098 - momentum: 0.000000
162
+ 2023-10-11 15:52:18,234 epoch 5 - iter 432/723 - loss 0.03612181 - time (sec): 235.81 - samples/sec: 442.09 - lr: 0.000096 - momentum: 0.000000
163
+ 2023-10-11 15:52:57,653 epoch 5 - iter 504/723 - loss 0.03611999 - time (sec): 275.23 - samples/sec: 442.66 - lr: 0.000094 - momentum: 0.000000
164
+ 2023-10-11 15:53:39,398 epoch 5 - iter 576/723 - loss 0.03635599 - time (sec): 316.98 - samples/sec: 443.94 - lr: 0.000093 - momentum: 0.000000
165
+ 2023-10-11 15:54:18,572 epoch 5 - iter 648/723 - loss 0.03657235 - time (sec): 356.15 - samples/sec: 442.26 - lr: 0.000091 - momentum: 0.000000
166
+ 2023-10-11 15:54:59,785 epoch 5 - iter 720/723 - loss 0.03624887 - time (sec): 397.36 - samples/sec: 442.18 - lr: 0.000089 - momentum: 0.000000
167
+ 2023-10-11 15:55:01,035 ----------------------------------------------------------------------------------------------------
168
+ 2023-10-11 15:55:01,036 EPOCH 5 done: loss 0.0363 - lr: 0.000089
169
+ 2023-10-11 15:55:23,163 DEV : loss 0.08089756220579147 - f1-score (micro avg) 0.8475
170
+ 2023-10-11 15:55:23,201 saving best model
171
+ 2023-10-11 15:55:25,804 ----------------------------------------------------------------------------------------------------
172
+ 2023-10-11 15:56:06,123 epoch 6 - iter 72/723 - loss 0.02940130 - time (sec): 40.31 - samples/sec: 417.22 - lr: 0.000087 - momentum: 0.000000
173
+ 2023-10-11 15:56:47,163 epoch 6 - iter 144/723 - loss 0.03149005 - time (sec): 81.35 - samples/sec: 418.21 - lr: 0.000085 - momentum: 0.000000
174
+ 2023-10-11 15:57:29,010 epoch 6 - iter 216/723 - loss 0.03196977 - time (sec): 123.20 - samples/sec: 421.16 - lr: 0.000084 - momentum: 0.000000
175
+ 2023-10-11 15:58:11,799 epoch 6 - iter 288/723 - loss 0.02911791 - time (sec): 165.99 - samples/sec: 421.81 - lr: 0.000082 - momentum: 0.000000
176
+ 2023-10-11 15:58:56,449 epoch 6 - iter 360/723 - loss 0.02913213 - time (sec): 210.64 - samples/sec: 419.65 - lr: 0.000080 - momentum: 0.000000
177
+ 2023-10-11 15:59:41,504 epoch 6 - iter 432/723 - loss 0.02849520 - time (sec): 255.70 - samples/sec: 412.23 - lr: 0.000078 - momentum: 0.000000
178
+ 2023-10-11 16:00:22,165 epoch 6 - iter 504/723 - loss 0.02767609 - time (sec): 296.36 - samples/sec: 412.30 - lr: 0.000077 - momentum: 0.000000
179
+ 2023-10-11 16:01:04,601 epoch 6 - iter 576/723 - loss 0.02699882 - time (sec): 338.79 - samples/sec: 412.62 - lr: 0.000075 - momentum: 0.000000
180
+ 2023-10-11 16:01:45,681 epoch 6 - iter 648/723 - loss 0.02774246 - time (sec): 379.87 - samples/sec: 419.60 - lr: 0.000073 - momentum: 0.000000
181
+ 2023-10-11 16:02:24,287 epoch 6 - iter 720/723 - loss 0.02783453 - time (sec): 418.48 - samples/sec: 420.01 - lr: 0.000071 - momentum: 0.000000
182
+ 2023-10-11 16:02:25,435 ----------------------------------------------------------------------------------------------------
183
+ 2023-10-11 16:02:25,436 EPOCH 6 done: loss 0.0281 - lr: 0.000071
184
+ 2023-10-11 16:02:46,632 DEV : loss 0.09028322994709015 - f1-score (micro avg) 0.8549
185
+ 2023-10-11 16:02:46,667 saving best model
186
+ 2023-10-11 16:02:49,267 ----------------------------------------------------------------------------------------------------
187
+ 2023-10-11 16:03:30,122 epoch 7 - iter 72/723 - loss 0.02328474 - time (sec): 40.85 - samples/sec: 438.26 - lr: 0.000069 - momentum: 0.000000
188
+ 2023-10-11 16:04:09,577 epoch 7 - iter 144/723 - loss 0.01939381 - time (sec): 80.31 - samples/sec: 434.55 - lr: 0.000068 - momentum: 0.000000
189
+ 2023-10-11 16:04:49,205 epoch 7 - iter 216/723 - loss 0.01823087 - time (sec): 119.93 - samples/sec: 432.07 - lr: 0.000066 - momentum: 0.000000
190
+ 2023-10-11 16:05:30,859 epoch 7 - iter 288/723 - loss 0.01970687 - time (sec): 161.59 - samples/sec: 426.14 - lr: 0.000064 - momentum: 0.000000
191
+ 2023-10-11 16:06:11,413 epoch 7 - iter 360/723 - loss 0.02102339 - time (sec): 202.14 - samples/sec: 427.93 - lr: 0.000062 - momentum: 0.000000
192
+ 2023-10-11 16:06:56,523 epoch 7 - iter 432/723 - loss 0.02184920 - time (sec): 247.25 - samples/sec: 422.29 - lr: 0.000061 - momentum: 0.000000
193
+ 2023-10-11 16:07:39,113 epoch 7 - iter 504/723 - loss 0.02240161 - time (sec): 289.84 - samples/sec: 422.63 - lr: 0.000059 - momentum: 0.000000
194
+ 2023-10-11 16:08:19,982 epoch 7 - iter 576/723 - loss 0.02113173 - time (sec): 330.71 - samples/sec: 422.97 - lr: 0.000057 - momentum: 0.000000
195
+ 2023-10-11 16:09:02,449 epoch 7 - iter 648/723 - loss 0.02209098 - time (sec): 373.18 - samples/sec: 421.17 - lr: 0.000055 - momentum: 0.000000
196
+ 2023-10-11 16:09:48,752 epoch 7 - iter 720/723 - loss 0.02183950 - time (sec): 419.48 - samples/sec: 418.39 - lr: 0.000053 - momentum: 0.000000
197
+ 2023-10-11 16:09:50,406 ----------------------------------------------------------------------------------------------------
198
+ 2023-10-11 16:09:50,406 EPOCH 7 done: loss 0.0218 - lr: 0.000053
199
+ 2023-10-11 16:10:14,848 DEV : loss 0.1077359989285469 - f1-score (micro avg) 0.8511
200
+ 2023-10-11 16:10:14,891 ----------------------------------------------------------------------------------------------------
201
+ 2023-10-11 16:11:04,173 epoch 8 - iter 72/723 - loss 0.01776157 - time (sec): 49.28 - samples/sec: 380.87 - lr: 0.000052 - momentum: 0.000000
202
+ 2023-10-11 16:11:49,030 epoch 8 - iter 144/723 - loss 0.01607038 - time (sec): 94.14 - samples/sec: 382.08 - lr: 0.000050 - momentum: 0.000000
203
+ 2023-10-11 16:12:35,654 epoch 8 - iter 216/723 - loss 0.01527344 - time (sec): 140.76 - samples/sec: 376.84 - lr: 0.000048 - momentum: 0.000000
204
+ 2023-10-11 16:13:21,937 epoch 8 - iter 288/723 - loss 0.01465974 - time (sec): 187.04 - samples/sec: 373.55 - lr: 0.000046 - momentum: 0.000000
205
+ 2023-10-11 16:14:08,463 epoch 8 - iter 360/723 - loss 0.01544379 - time (sec): 233.57 - samples/sec: 376.05 - lr: 0.000045 - momentum: 0.000000
206
+ 2023-10-11 16:14:53,901 epoch 8 - iter 432/723 - loss 0.01555183 - time (sec): 279.01 - samples/sec: 380.63 - lr: 0.000043 - momentum: 0.000000
207
+ 2023-10-11 16:15:38,074 epoch 8 - iter 504/723 - loss 0.01639593 - time (sec): 323.18 - samples/sec: 384.22 - lr: 0.000041 - momentum: 0.000000
208
+ 2023-10-11 16:16:23,453 epoch 8 - iter 576/723 - loss 0.01765329 - time (sec): 368.56 - samples/sec: 386.50 - lr: 0.000039 - momentum: 0.000000
209
+ 2023-10-11 16:17:07,576 epoch 8 - iter 648/723 - loss 0.01757496 - time (sec): 412.68 - samples/sec: 383.80 - lr: 0.000037 - momentum: 0.000000
210
+ 2023-10-11 16:17:52,827 epoch 8 - iter 720/723 - loss 0.01756128 - time (sec): 457.93 - samples/sec: 383.62 - lr: 0.000036 - momentum: 0.000000
211
+ 2023-10-11 16:17:54,262 ----------------------------------------------------------------------------------------------------
212
+ 2023-10-11 16:17:54,262 EPOCH 8 done: loss 0.0176 - lr: 0.000036
213
+ 2023-10-11 16:18:18,043 DEV : loss 0.11811362206935883 - f1-score (micro avg) 0.8475
214
+ 2023-10-11 16:18:18,077 ----------------------------------------------------------------------------------------------------
215
+ 2023-10-11 16:19:02,582 epoch 9 - iter 72/723 - loss 0.02085559 - time (sec): 44.50 - samples/sec: 421.75 - lr: 0.000034 - momentum: 0.000000
216
+ 2023-10-11 16:19:44,728 epoch 9 - iter 144/723 - loss 0.01556397 - time (sec): 86.65 - samples/sec: 407.11 - lr: 0.000032 - momentum: 0.000000
217
+ 2023-10-11 16:20:29,081 epoch 9 - iter 216/723 - loss 0.01455073 - time (sec): 131.00 - samples/sec: 411.44 - lr: 0.000030 - momentum: 0.000000
218
+ 2023-10-11 16:21:15,015 epoch 9 - iter 288/723 - loss 0.01377233 - time (sec): 176.94 - samples/sec: 403.57 - lr: 0.000028 - momentum: 0.000000
219
+ 2023-10-11 16:21:59,624 epoch 9 - iter 360/723 - loss 0.01410060 - time (sec): 221.54 - samples/sec: 400.43 - lr: 0.000027 - momentum: 0.000000
220
+ 2023-10-11 16:22:39,825 epoch 9 - iter 432/723 - loss 0.01447392 - time (sec): 261.75 - samples/sec: 406.36 - lr: 0.000025 - momentum: 0.000000
221
+ 2023-10-11 16:23:22,295 epoch 9 - iter 504/723 - loss 0.01453168 - time (sec): 304.22 - samples/sec: 410.26 - lr: 0.000023 - momentum: 0.000000
222
+ 2023-10-11 16:24:03,364 epoch 9 - iter 576/723 - loss 0.01468837 - time (sec): 345.29 - samples/sec: 409.78 - lr: 0.000021 - momentum: 0.000000
223
+ 2023-10-11 16:24:47,724 epoch 9 - iter 648/723 - loss 0.01396882 - time (sec): 389.65 - samples/sec: 406.74 - lr: 0.000020 - momentum: 0.000000
224
+ 2023-10-11 16:25:30,313 epoch 9 - iter 720/723 - loss 0.01410103 - time (sec): 432.23 - samples/sec: 406.78 - lr: 0.000018 - momentum: 0.000000
225
+ 2023-10-11 16:25:31,403 ----------------------------------------------------------------------------------------------------
226
+ 2023-10-11 16:25:31,403 EPOCH 9 done: loss 0.0141 - lr: 0.000018
227
+ 2023-10-11 16:25:52,109 DEV : loss 0.12514764070510864 - f1-score (micro avg) 0.8489
228
+ 2023-10-11 16:25:52,145 ----------------------------------------------------------------------------------------------------
229
+ 2023-10-11 16:26:32,572 epoch 10 - iter 72/723 - loss 0.00691167 - time (sec): 40.43 - samples/sec: 414.99 - lr: 0.000016 - momentum: 0.000000
230
+ 2023-10-11 16:27:18,626 epoch 10 - iter 144/723 - loss 0.01193292 - time (sec): 86.48 - samples/sec: 407.69 - lr: 0.000014 - momentum: 0.000000
231
+ 2023-10-11 16:28:03,587 epoch 10 - iter 216/723 - loss 0.01238731 - time (sec): 131.44 - samples/sec: 398.85 - lr: 0.000012 - momentum: 0.000000
232
+ 2023-10-11 16:28:47,658 epoch 10 - iter 288/723 - loss 0.01210096 - time (sec): 175.51 - samples/sec: 394.39 - lr: 0.000011 - momentum: 0.000000
233
+ 2023-10-11 16:29:30,706 epoch 10 - iter 360/723 - loss 0.01176008 - time (sec): 218.56 - samples/sec: 401.34 - lr: 0.000009 - momentum: 0.000000
234
+ 2023-10-11 16:30:14,701 epoch 10 - iter 432/723 - loss 0.01133392 - time (sec): 262.55 - samples/sec: 403.84 - lr: 0.000007 - momentum: 0.000000
235
+ 2023-10-11 16:30:53,960 epoch 10 - iter 504/723 - loss 0.01234490 - time (sec): 301.81 - samples/sec: 411.19 - lr: 0.000005 - momentum: 0.000000
236
+ 2023-10-11 16:31:35,278 epoch 10 - iter 576/723 - loss 0.01209169 - time (sec): 343.13 - samples/sec: 410.10 - lr: 0.000004 - momentum: 0.000000
237
+ 2023-10-11 16:32:15,815 epoch 10 - iter 648/723 - loss 0.01228765 - time (sec): 383.67 - samples/sec: 412.84 - lr: 0.000002 - momentum: 0.000000
238
+ 2023-10-11 16:32:54,288 epoch 10 - iter 720/723 - loss 0.01234272 - time (sec): 422.14 - samples/sec: 415.95 - lr: 0.000000 - momentum: 0.000000
239
+ 2023-10-11 16:32:55,551 ----------------------------------------------------------------------------------------------------
240
+ 2023-10-11 16:32:55,552 EPOCH 10 done: loss 0.0123 - lr: 0.000000
241
+ 2023-10-11 16:33:16,205 DEV : loss 0.13051000237464905 - f1-score (micro avg) 0.8392
242
+ 2023-10-11 16:33:17,164 ----------------------------------------------------------------------------------------------------
243
+ 2023-10-11 16:33:17,166 Loading model from best epoch ...
244
+ 2023-10-11 16:33:21,267 SequenceTagger predicts: Dictionary with 13 tags: O, S-LOC, B-LOC, E-LOC, I-LOC, S-PER, B-PER, E-PER, I-PER, S-ORG, B-ORG, E-ORG, I-ORG
245
+ 2023-10-11 16:33:42,968
246
+ Results:
247
+ - F-score (micro) 0.8506
248
+ - F-score (macro) 0.7523
249
+ - Accuracy 0.7511
250
+
251
+ By class:
252
+ precision recall f1-score support
253
+
254
+ PER 0.8497 0.8444 0.8470 482
255
+ LOC 0.9109 0.8930 0.9019 458
256
+ ORG 0.5614 0.4638 0.5079 69
257
+
258
+ micro avg 0.8609 0.8404 0.8506 1009
259
+ macro avg 0.7740 0.7337 0.7523 1009
260
+ weighted avg 0.8578 0.8404 0.8487 1009
261
+
262
+ 2023-10-11 16:33:42,969 ----------------------------------------------------------------------------------------------------