Hugging Face's logo

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

Token Classification
Flair
PyTorch
TensorBoard
French
sequence-tagger-model
Model card Files Metrics Community
stefan-it commited on
Commit
9730304
·
1 Parent(s): 71bd4b4

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.1697562692.4aef72135bc5.1113.15 +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:f1d85beb6b5b9e047ebfb92de1f660f87dfe83a7d12df74ad5bd3dacd6b24541
3
+ size 440941957
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 17:13:46 0.0000 0.3063 0.1094 0.5177 0.7849 0.6239 0.4645
3
+ 2 17:16:05 0.0000 0.0907 0.1161 0.5221 0.7849 0.6271 0.4635
4
+ 3 17:18:09 0.0000 0.0658 0.1407 0.5564 0.7059 0.6223 0.4584
5
+ 4 17:20:13 0.0000 0.0479 0.1930 0.5470 0.7849 0.6447 0.4821
6
+ 5 17:22:18 0.0000 0.0365 0.2711 0.5481 0.7952 0.6489 0.4881
7
+ 6 17:24:29 0.0000 0.0257 0.2926 0.5684 0.7746 0.6557 0.4971
8
+ 7 17:26:43 0.0000 0.0157 0.3530 0.5532 0.8089 0.6571 0.4965
9
+ 8 17:29:01 0.0000 0.0119 0.3651 0.5619 0.7941 0.6581 0.4975
10
+ 9 17:31:20 0.0000 0.0075 0.3908 0.5672 0.7723 0.6541 0.4931
11
+ 10 17:33:44 0.0000 0.0050 0.3981 0.5682 0.7769 0.6564 0.4956
runs/events.out.tfevents.1697562692.4aef72135bc5.1113.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d376b57f5324b0fb0d711e52bc42b57d9bc46f7a277954f857c08bac63f8aa7b
3
+ size 1018100
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 17:11:32,078 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-17 17:11:32,079 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=13, bias=True)
44
+ (loss_function): CrossEntropyLoss()
45
+ )"
46
+ 2023-10-17 17:11:32,079 ----------------------------------------------------------------------------------------------------
47
+ 2023-10-17 17:11:32,079 MultiCorpus: 14465 train + 1392 dev + 2432 test sentences
48
+ - NER_HIPE_2022 Corpus: 14465 train + 1392 dev + 2432 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/letemps/fr/with_doc_seperator
49
+ 2023-10-17 17:11:32,079 ----------------------------------------------------------------------------------------------------
50
+ 2023-10-17 17:11:32,079 Train: 14465 sentences
51
+ 2023-10-17 17:11:32,079 (train_with_dev=False, train_with_test=False)
52
+ 2023-10-17 17:11:32,079 ----------------------------------------------------------------------------------------------------
53
+ 2023-10-17 17:11:32,080 Training Params:
54
+ 2023-10-17 17:11:32,080 - learning_rate: "5e-05"
55
+ 2023-10-17 17:11:32,080 - mini_batch_size: "8"
56
+ 2023-10-17 17:11:32,080 - max_epochs: "10"
57
+ 2023-10-17 17:11:32,080 - shuffle: "True"
58
+ 2023-10-17 17:11:32,080 ----------------------------------------------------------------------------------------------------
59
+ 2023-10-17 17:11:32,080 Plugins:
60
+ 2023-10-17 17:11:32,080 - TensorboardLogger
61
+ 2023-10-17 17:11:32,080 - LinearScheduler | warmup_fraction: '0.1'
62
+ 2023-10-17 17:11:32,080 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-17 17:11:32,080 Final evaluation on model from best epoch (best-model.pt)
64
+ 2023-10-17 17:11:32,080 - metric: "('micro avg', 'f1-score')"
65
+ 2023-10-17 17:11:32,080 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-17 17:11:32,080 Computation:
67
+ 2023-10-17 17:11:32,080 - compute on device: cuda:0
68
+ 2023-10-17 17:11:32,080 - embedding storage: none
69
+ 2023-10-17 17:11:32,080 ----------------------------------------------------------------------------------------------------
70
+ 2023-10-17 17:11:32,080 Model training base path: "hmbench-letemps/fr-hmteams/teams-base-historic-multilingual-discriminator-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4"
71
+ 2023-10-17 17:11:32,080 ----------------------------------------------------------------------------------------------------
72
+ 2023-10-17 17:11:32,080 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-17 17:11:32,080 Logging anything other than scalars to TensorBoard is currently not supported.
74
+ 2023-10-17 17:11:44,801 epoch 1 - iter 180/1809 - loss 1.93561623 - time (sec): 12.72 - samples/sec: 2872.61 - lr: 0.000005 - momentum: 0.000000
75
+ 2023-10-17 17:11:57,763 epoch 1 - iter 360/1809 - loss 1.05326650 - time (sec): 25.68 - samples/sec: 2943.24 - lr: 0.000010 - momentum: 0.000000
76
+ 2023-10-17 17:12:10,514 epoch 1 - iter 540/1809 - loss 0.75155809 - time (sec): 38.43 - samples/sec: 2953.08 - lr: 0.000015 - momentum: 0.000000
77
+ 2023-10-17 17:12:23,512 epoch 1 - iter 720/1809 - loss 0.59410555 - time (sec): 51.43 - samples/sec: 2963.13 - lr: 0.000020 - momentum: 0.000000
78
+ 2023-10-17 17:12:36,258 epoch 1 - iter 900/1809 - loss 0.50080498 - time (sec): 64.18 - samples/sec: 2948.84 - lr: 0.000025 - momentum: 0.000000
79
+ 2023-10-17 17:12:48,969 epoch 1 - iter 1080/1809 - loss 0.43858981 - time (sec): 76.89 - samples/sec: 2957.34 - lr: 0.000030 - momentum: 0.000000
80
+ 2023-10-17 17:13:01,864 epoch 1 - iter 1260/1809 - loss 0.39099624 - time (sec): 89.78 - samples/sec: 2959.58 - lr: 0.000035 - momentum: 0.000000
81
+ 2023-10-17 17:13:14,940 epoch 1 - iter 1440/1809 - loss 0.35498992 - time (sec): 102.86 - samples/sec: 2964.88 - lr: 0.000040 - momentum: 0.000000
82
+ 2023-10-17 17:13:27,651 epoch 1 - iter 1620/1809 - loss 0.32835651 - time (sec): 115.57 - samples/sec: 2959.52 - lr: 0.000045 - momentum: 0.000000
83
+ 2023-10-17 17:13:40,504 epoch 1 - iter 1800/1809 - loss 0.30714743 - time (sec): 128.42 - samples/sec: 2947.39 - lr: 0.000050 - momentum: 0.000000
84
+ 2023-10-17 17:13:41,091 ----------------------------------------------------------------------------------------------------
85
+ 2023-10-17 17:13:41,092 EPOCH 1 done: loss 0.3063 - lr: 0.000050
86
+ 2023-10-17 17:13:46,484 DEV : loss 0.10938248783349991 - f1-score (micro avg) 0.6239
87
+ 2023-10-17 17:13:46,524 saving best model
88
+ 2023-10-17 17:13:47,036 ----------------------------------------------------------------------------------------------------
89
+ 2023-10-17 17:14:00,035 epoch 2 - iter 180/1809 - loss 0.10079900 - time (sec): 13.00 - samples/sec: 2981.06 - lr: 0.000049 - momentum: 0.000000
90
+ 2023-10-17 17:14:12,944 epoch 2 - iter 360/1809 - loss 0.09271722 - time (sec): 25.91 - samples/sec: 2951.93 - lr: 0.000049 - momentum: 0.000000
91
+ 2023-10-17 17:14:25,719 epoch 2 - iter 540/1809 - loss 0.08663485 - time (sec): 38.68 - samples/sec: 2966.04 - lr: 0.000048 - momentum: 0.000000
92
+ 2023-10-17 17:14:38,078 epoch 2 - iter 720/1809 - loss 0.08679926 - time (sec): 51.04 - samples/sec: 2962.84 - lr: 0.000048 - momentum: 0.000000
93
+ 2023-10-17 17:14:50,907 epoch 2 - iter 900/1809 - loss 0.09124566 - time (sec): 63.87 - samples/sec: 2948.30 - lr: 0.000047 - momentum: 0.000000
94
+ 2023-10-17 17:15:03,593 epoch 2 - iter 1080/1809 - loss 0.09266770 - time (sec): 76.56 - samples/sec: 2932.10 - lr: 0.000047 - momentum: 0.000000
95
+ 2023-10-17 17:15:16,588 epoch 2 - iter 1260/1809 - loss 0.09325153 - time (sec): 89.55 - samples/sec: 2929.00 - lr: 0.000046 - momentum: 0.000000
96
+ 2023-10-17 17:15:29,899 epoch 2 - iter 1440/1809 - loss 0.09224137 - time (sec): 102.86 - samples/sec: 2929.07 - lr: 0.000046 - momentum: 0.000000
97
+ 2023-10-17 17:15:43,216 epoch 2 - iter 1620/1809 - loss 0.09170900 - time (sec): 116.18 - samples/sec: 2913.77 - lr: 0.000045 - momentum: 0.000000
98
+ 2023-10-17 17:15:57,487 epoch 2 - iter 1800/1809 - loss 0.09078426 - time (sec): 130.45 - samples/sec: 2897.12 - lr: 0.000044 - momentum: 0.000000
99
+ 2023-10-17 17:15:58,247 ----------------------------------------------------------------------------------------------------
100
+ 2023-10-17 17:15:58,248 EPOCH 2 done: loss 0.0907 - lr: 0.000044
101
+ 2023-10-17 17:16:05,410 DEV : loss 0.1160627156496048 - f1-score (micro avg) 0.6271
102
+ 2023-10-17 17:16:05,450 saving best model
103
+ 2023-10-17 17:16:06,018 ----------------------------------------------------------------------------------------------------
104
+ 2023-10-17 17:16:17,628 epoch 3 - iter 180/1809 - loss 0.06093404 - time (sec): 11.61 - samples/sec: 3292.81 - lr: 0.000044 - momentum: 0.000000
105
+ 2023-10-17 17:16:29,276 epoch 3 - iter 360/1809 - loss 0.06003849 - time (sec): 23.26 - samples/sec: 3289.97 - lr: 0.000043 - momentum: 0.000000
106
+ 2023-10-17 17:16:40,839 epoch 3 - iter 540/1809 - loss 0.05954656 - time (sec): 34.82 - samples/sec: 3268.21 - lr: 0.000043 - momentum: 0.000000
107
+ 2023-10-17 17:16:52,586 epoch 3 - iter 720/1809 - loss 0.06117659 - time (sec): 46.57 - samples/sec: 3255.69 - lr: 0.000042 - momentum: 0.000000
108
+ 2023-10-17 17:17:04,060 epoch 3 - iter 900/1809 - loss 0.06253581 - time (sec): 58.04 - samples/sec: 3255.61 - lr: 0.000042 - momentum: 0.000000
109
+ 2023-10-17 17:17:15,528 epoch 3 - iter 1080/1809 - loss 0.06281026 - time (sec): 69.51 - samples/sec: 3261.44 - lr: 0.000041 - momentum: 0.000000
110
+ 2023-10-17 17:17:27,332 epoch 3 - iter 1260/1809 - loss 0.06335577 - time (sec): 81.31 - samples/sec: 3259.87 - lr: 0.000041 - momentum: 0.000000
111
+ 2023-10-17 17:17:38,880 epoch 3 - iter 1440/1809 - loss 0.06437289 - time (sec): 92.86 - samples/sec: 3252.54 - lr: 0.000040 - momentum: 0.000000
112
+ 2023-10-17 17:17:50,414 epoch 3 - iter 1620/1809 - loss 0.06571986 - time (sec): 104.39 - samples/sec: 3248.91 - lr: 0.000039 - momentum: 0.000000
113
+ 2023-10-17 17:18:02,437 epoch 3 - iter 1800/1809 - loss 0.06565150 - time (sec): 116.42 - samples/sec: 3250.23 - lr: 0.000039 - momentum: 0.000000
114
+ 2023-10-17 17:18:02,972 ----------------------------------------------------------------------------------------------------
115
+ 2023-10-17 17:18:02,972 EPOCH 3 done: loss 0.0658 - lr: 0.000039
116
+ 2023-10-17 17:18:09,303 DEV : loss 0.14074555039405823 - f1-score (micro avg) 0.6223
117
+ 2023-10-17 17:18:09,344 ----------------------------------------------------------------------------------------------------
118
+ 2023-10-17 17:18:20,880 epoch 4 - iter 180/1809 - loss 0.03667366 - time (sec): 11.53 - samples/sec: 3245.02 - lr: 0.000038 - momentum: 0.000000
119
+ 2023-10-17 17:18:32,507 epoch 4 - iter 360/1809 - loss 0.04218888 - time (sec): 23.16 - samples/sec: 3262.25 - lr: 0.000038 - momentum: 0.000000
120
+ 2023-10-17 17:18:44,274 epoch 4 - iter 540/1809 - loss 0.04768593 - time (sec): 34.93 - samples/sec: 3279.30 - lr: 0.000037 - momentum: 0.000000
121
+ 2023-10-17 17:18:56,716 epoch 4 - iter 720/1809 - loss 0.04825907 - time (sec): 47.37 - samples/sec: 3197.49 - lr: 0.000037 - momentum: 0.000000
122
+ 2023-10-17 17:19:07,914 epoch 4 - iter 900/1809 - loss 0.04754011 - time (sec): 58.57 - samples/sec: 3203.52 - lr: 0.000036 - momentum: 0.000000
123
+ 2023-10-17 17:19:19,903 epoch 4 - iter 1080/1809 - loss 0.04777440 - time (sec): 70.56 - samples/sec: 3221.03 - lr: 0.000036 - momentum: 0.000000
124
+ 2023-10-17 17:19:31,289 epoch 4 - iter 1260/1809 - loss 0.04719754 - time (sec): 81.94 - samples/sec: 3228.10 - lr: 0.000035 - momentum: 0.000000
125
+ 2023-10-17 17:19:42,794 epoch 4 - iter 1440/1809 - loss 0.04734516 - time (sec): 93.45 - samples/sec: 3227.79 - lr: 0.000034 - momentum: 0.000000
126
+ 2023-10-17 17:19:54,449 epoch 4 - iter 1620/1809 - loss 0.04770838 - time (sec): 105.10 - samples/sec: 3240.33 - lr: 0.000034 - momentum: 0.000000
127
+ 2023-10-17 17:20:06,242 epoch 4 - iter 1800/1809 - loss 0.04788521 - time (sec): 116.90 - samples/sec: 3235.87 - lr: 0.000033 - momentum: 0.000000
128
+ 2023-10-17 17:20:06,788 ----------------------------------------------------------------------------------------------------
129
+ 2023-10-17 17:20:06,789 EPOCH 4 done: loss 0.0479 - lr: 0.000033
130
+ 2023-10-17 17:20:13,082 DEV : loss 0.19297103583812714 - f1-score (micro avg) 0.6447
131
+ 2023-10-17 17:20:13,123 saving best model
132
+ 2023-10-17 17:20:13,730 ----------------------------------------------------------------------------------------------------
133
+ 2023-10-17 17:20:25,234 epoch 5 - iter 180/1809 - loss 0.03277920 - time (sec): 11.50 - samples/sec: 3302.89 - lr: 0.000033 - momentum: 0.000000
134
+ 2023-10-17 17:20:36,730 epoch 5 - iter 360/1809 - loss 0.03524838 - time (sec): 23.00 - samples/sec: 3286.71 - lr: 0.000032 - momentum: 0.000000
135
+ 2023-10-17 17:20:48,176 epoch 5 - iter 540/1809 - loss 0.03536296 - time (sec): 34.44 - samples/sec: 3271.30 - lr: 0.000032 - momentum: 0.000000
136
+ 2023-10-17 17:20:59,738 epoch 5 - iter 720/1809 - loss 0.03462499 - time (sec): 46.01 - samples/sec: 3270.53 - lr: 0.000031 - momentum: 0.000000
137
+ 2023-10-17 17:21:11,201 epoch 5 - iter 900/1809 - loss 0.03564067 - time (sec): 57.47 - samples/sec: 3261.46 - lr: 0.000031 - momentum: 0.000000
138
+ 2023-10-17 17:21:22,490 epoch 5 - iter 1080/1809 - loss 0.03492180 - time (sec): 68.76 - samples/sec: 3259.96 - lr: 0.000030 - momentum: 0.000000
139
+ 2023-10-17 17:21:34,269 epoch 5 - iter 1260/1809 - loss 0.03567128 - time (sec): 80.54 - samples/sec: 3266.60 - lr: 0.000029 - momentum: 0.000000
140
+ 2023-10-17 17:21:45,765 epoch 5 - iter 1440/1809 - loss 0.03640100 - time (sec): 92.03 - samples/sec: 3271.15 - lr: 0.000029 - momentum: 0.000000
141
+ 2023-10-17 17:21:57,633 epoch 5 - iter 1620/1809 - loss 0.03683705 - time (sec): 103.90 - samples/sec: 3266.95 - lr: 0.000028 - momentum: 0.000000
142
+ 2023-10-17 17:22:10,494 epoch 5 - iter 1800/1809 - loss 0.03664054 - time (sec): 116.76 - samples/sec: 3240.02 - lr: 0.000028 - momentum: 0.000000
143
+ 2023-10-17 17:22:11,124 ----------------------------------------------------------------------------------------------------
144
+ 2023-10-17 17:22:11,124 EPOCH 5 done: loss 0.0365 - lr: 0.000028
145
+ 2023-10-17 17:22:18,401 DEV : loss 0.27114248275756836 - f1-score (micro avg) 0.6489
146
+ 2023-10-17 17:22:18,442 saving best model
147
+ 2023-10-17 17:22:19,012 ----------------------------------------------------------------------------------------------------
148
+ 2023-10-17 17:22:30,865 epoch 6 - iter 180/1809 - loss 0.02380828 - time (sec): 11.85 - samples/sec: 3203.90 - lr: 0.000027 - momentum: 0.000000
149
+ 2023-10-17 17:22:42,265 epoch 6 - iter 360/1809 - loss 0.02336456 - time (sec): 23.25 - samples/sec: 3201.60 - lr: 0.000027 - momentum: 0.000000
150
+ 2023-10-17 17:22:53,931 epoch 6 - iter 540/1809 - loss 0.02458402 - time (sec): 34.92 - samples/sec: 3210.75 - lr: 0.000026 - momentum: 0.000000
151
+ 2023-10-17 17:23:06,012 epoch 6 - iter 720/1809 - loss 0.02370887 - time (sec): 47.00 - samples/sec: 3231.32 - lr: 0.000026 - momentum: 0.000000
152
+ 2023-10-17 17:23:17,769 epoch 6 - iter 900/1809 - loss 0.02321931 - time (sec): 58.76 - samples/sec: 3223.85 - lr: 0.000025 - momentum: 0.000000
153
+ 2023-10-17 17:23:30,920 epoch 6 - iter 1080/1809 - loss 0.02428414 - time (sec): 71.91 - samples/sec: 3165.19 - lr: 0.000024 - momentum: 0.000000
154
+ 2023-10-17 17:23:43,365 epoch 6 - iter 1260/1809 - loss 0.02576350 - time (sec): 84.35 - samples/sec: 3117.42 - lr: 0.000024 - momentum: 0.000000
155
+ 2023-10-17 17:23:56,563 epoch 6 - iter 1440/1809 - loss 0.02577017 - time (sec): 97.55 - samples/sec: 3086.57 - lr: 0.000023 - momentum: 0.000000
156
+ 2023-10-17 17:24:09,657 epoch 6 - iter 1620/1809 - loss 0.02611217 - time (sec): 110.64 - samples/sec: 3067.46 - lr: 0.000023 - momentum: 0.000000
157
+ 2023-10-17 17:24:22,953 epoch 6 - iter 1800/1809 - loss 0.02567029 - time (sec): 123.94 - samples/sec: 3052.44 - lr: 0.000022 - momentum: 0.000000
158
+ 2023-10-17 17:24:23,520 ----------------------------------------------------------------------------------------------------
159
+ 2023-10-17 17:24:23,521 EPOCH 6 done: loss 0.0257 - lr: 0.000022
160
+ 2023-10-17 17:24:29,799 DEV : loss 0.2926296889781952 - f1-score (micro avg) 0.6557
161
+ 2023-10-17 17:24:29,840 saving best model
162
+ 2023-10-17 17:24:30,418 ----------------------------------------------------------------------------------------------------
163
+ 2023-10-17 17:24:41,928 epoch 7 - iter 180/1809 - loss 0.01540372 - time (sec): 11.51 - samples/sec: 3142.49 - lr: 0.000022 - momentum: 0.000000
164
+ 2023-10-17 17:24:53,530 epoch 7 - iter 360/1809 - loss 0.01373858 - time (sec): 23.11 - samples/sec: 3149.87 - lr: 0.000021 - momentum: 0.000000
165
+ 2023-10-17 17:25:04,891 epoch 7 - iter 540/1809 - loss 0.01476080 - time (sec): 34.47 - samples/sec: 3169.89 - lr: 0.000021 - momentum: 0.000000
166
+ 2023-10-17 17:25:17,063 epoch 7 - iter 720/1809 - loss 0.01553034 - time (sec): 46.64 - samples/sec: 3178.69 - lr: 0.000020 - momentum: 0.000000
167
+ 2023-10-17 17:25:31,212 epoch 7 - iter 900/1809 - loss 0.01608482 - time (sec): 60.79 - samples/sec: 3092.52 - lr: 0.000019 - momentum: 0.000000
168
+ 2023-10-17 17:25:44,555 epoch 7 - iter 1080/1809 - loss 0.01625864 - time (sec): 74.14 - samples/sec: 3065.32 - lr: 0.000019 - momentum: 0.000000
169
+ 2023-10-17 17:25:57,185 epoch 7 - iter 1260/1809 - loss 0.01598109 - time (sec): 86.77 - samples/sec: 3046.68 - lr: 0.000018 - momentum: 0.000000
170
+ 2023-10-17 17:26:10,352 epoch 7 - iter 1440/1809 - loss 0.01620623 - time (sec): 99.93 - samples/sec: 3018.29 - lr: 0.000018 - momentum: 0.000000
171
+ 2023-10-17 17:26:23,271 epoch 7 - iter 1620/1809 - loss 0.01562169 - time (sec): 112.85 - samples/sec: 3008.43 - lr: 0.000017 - momentum: 0.000000
172
+ 2023-10-17 17:26:35,991 epoch 7 - iter 1800/1809 - loss 0.01568355 - time (sec): 125.57 - samples/sec: 3009.51 - lr: 0.000017 - momentum: 0.000000
173
+ 2023-10-17 17:26:36,606 ----------------------------------------------------------------------------------------------------
174
+ 2023-10-17 17:26:36,607 EPOCH 7 done: loss 0.0157 - lr: 0.000017
175
+ 2023-10-17 17:26:43,029 DEV : loss 0.3529641330242157 - f1-score (micro avg) 0.6571
176
+ 2023-10-17 17:26:43,073 saving best model
177
+ 2023-10-17 17:26:43,674 ----------------------------------------------------------------------------------------------------
178
+ 2023-10-17 17:26:56,220 epoch 8 - iter 180/1809 - loss 0.01695089 - time (sec): 12.54 - samples/sec: 2962.85 - lr: 0.000016 - momentum: 0.000000
179
+ 2023-10-17 17:27:08,773 epoch 8 - iter 360/1809 - loss 0.01377195 - time (sec): 25.10 - samples/sec: 2935.92 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-17 17:27:21,487 epoch 8 - iter 540/1809 - loss 0.01220865 - time (sec): 37.81 - samples/sec: 2935.57 - lr: 0.000015 - momentum: 0.000000
181
+ 2023-10-17 17:27:35,132 epoch 8 - iter 720/1809 - loss 0.01373650 - time (sec): 51.46 - samples/sec: 2917.35 - lr: 0.000014 - momentum: 0.000000
182
+ 2023-10-17 17:27:48,191 epoch 8 - iter 900/1809 - loss 0.01422431 - time (sec): 64.52 - samples/sec: 2914.87 - lr: 0.000014 - momentum: 0.000000
183
+ 2023-10-17 17:28:01,243 epoch 8 - iter 1080/1809 - loss 0.01318920 - time (sec): 77.57 - samples/sec: 2904.54 - lr: 0.000013 - momentum: 0.000000
184
+ 2023-10-17 17:28:14,364 epoch 8 - iter 1260/1809 - loss 0.01262812 - time (sec): 90.69 - samples/sec: 2907.44 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-17 17:28:27,356 epoch 8 - iter 1440/1809 - loss 0.01230139 - time (sec): 103.68 - samples/sec: 2915.00 - lr: 0.000012 - momentum: 0.000000
186
+ 2023-10-17 17:28:40,048 epoch 8 - iter 1620/1809 - loss 0.01216736 - time (sec): 116.37 - samples/sec: 2911.57 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-17 17:28:53,484 epoch 8 - iter 1800/1809 - loss 0.01174195 - time (sec): 129.81 - samples/sec: 2910.13 - lr: 0.000011 - momentum: 0.000000
188
+ 2023-10-17 17:28:54,159 ----------------------------------------------------------------------------------------------------
189
+ 2023-10-17 17:28:54,160 EPOCH 8 done: loss 0.0119 - lr: 0.000011
190
+ 2023-10-17 17:29:01,334 DEV : loss 0.36510923504829407 - f1-score (micro avg) 0.6581
191
+ 2023-10-17 17:29:01,379 saving best model
192
+ 2023-10-17 17:29:01,990 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-17 17:29:14,799 epoch 9 - iter 180/1809 - loss 0.00676309 - time (sec): 12.81 - samples/sec: 2836.96 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-17 17:29:27,626 epoch 9 - iter 360/1809 - loss 0.00654625 - time (sec): 25.63 - samples/sec: 2881.92 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-17 17:29:40,593 epoch 9 - iter 540/1809 - loss 0.00662540 - time (sec): 38.60 - samples/sec: 2901.39 - lr: 0.000009 - momentum: 0.000000
196
+ 2023-10-17 17:29:54,034 epoch 9 - iter 720/1809 - loss 0.00713313 - time (sec): 52.04 - samples/sec: 2892.66 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-17 17:30:07,467 epoch 9 - iter 900/1809 - loss 0.00725837 - time (sec): 65.48 - samples/sec: 2877.00 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-17 17:30:20,535 epoch 9 - iter 1080/1809 - loss 0.00748436 - time (sec): 78.54 - samples/sec: 2881.75 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-17 17:30:34,143 epoch 9 - iter 1260/1809 - loss 0.00775191 - time (sec): 92.15 - samples/sec: 2889.46 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-17 17:30:46,967 epoch 9 - iter 1440/1809 - loss 0.00761670 - time (sec): 104.97 - samples/sec: 2900.62 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-17 17:30:59,707 epoch 9 - iter 1620/1809 - loss 0.00766050 - time (sec): 117.71 - samples/sec: 2901.81 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-17 17:31:13,080 epoch 9 - iter 1800/1809 - loss 0.00746642 - time (sec): 131.09 - samples/sec: 2886.97 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-17 17:31:13,704 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-17 17:31:13,704 EPOCH 9 done: loss 0.0075 - lr: 0.000006
205
+ 2023-10-17 17:31:20,092 DEV : loss 0.39079737663269043 - f1-score (micro avg) 0.6541
206
+ 2023-10-17 17:31:20,133 ----------------------------------------------------------------------------------------------------
207
+ 2023-10-17 17:31:34,992 epoch 10 - iter 180/1809 - loss 0.00435699 - time (sec): 14.86 - samples/sec: 2533.83 - lr: 0.000005 - momentum: 0.000000
208
+ 2023-10-17 17:31:49,379 epoch 10 - iter 360/1809 - loss 0.00449193 - time (sec): 29.24 - samples/sec: 2657.93 - lr: 0.000004 - momentum: 0.000000
209
+ 2023-10-17 17:32:03,565 epoch 10 - iter 540/1809 - loss 0.00402430 - time (sec): 43.43 - samples/sec: 2649.88 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-17 17:32:17,158 epoch 10 - iter 720/1809 - loss 0.00509725 - time (sec): 57.02 - samples/sec: 2683.43 - lr: 0.000003 - momentum: 0.000000
211
+ 2023-10-17 17:32:30,887 epoch 10 - iter 900/1809 - loss 0.00529774 - time (sec): 70.75 - samples/sec: 2670.34 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-17 17:32:44,665 epoch 10 - iter 1080/1809 - loss 0.00507294 - time (sec): 84.53 - samples/sec: 2692.78 - lr: 0.000002 - momentum: 0.000000
213
+ 2023-10-17 17:32:57,604 epoch 10 - iter 1260/1809 - loss 0.00509465 - time (sec): 97.47 - samples/sec: 2728.72 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-17 17:33:10,510 epoch 10 - iter 1440/1809 - loss 0.00507500 - time (sec): 110.38 - samples/sec: 2749.44 - lr: 0.000001 - momentum: 0.000000
215
+ 2023-10-17 17:33:23,583 epoch 10 - iter 1620/1809 - loss 0.00502796 - time (sec): 123.45 - samples/sec: 2774.09 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-17 17:33:37,029 epoch 10 - iter 1800/1809 - loss 0.00499215 - time (sec): 136.89 - samples/sec: 2765.41 - lr: 0.000000 - momentum: 0.000000
217
+ 2023-10-17 17:33:37,688 ----------------------------------------------------------------------------------------------------
218
+ 2023-10-17 17:33:37,688 EPOCH 10 done: loss 0.0050 - lr: 0.000000
219
+ 2023-10-17 17:33:43,978 DEV : loss 0.39810895919799805 - f1-score (micro avg) 0.6564
220
+ 2023-10-17 17:33:44,542 ----------------------------------------------------------------------------------------------------
221
+ 2023-10-17 17:33:44,544 Loading model from best epoch ...
222
+ 2023-10-17 17:33:46,262 SequenceTagger predicts: Dictionary with 13 tags: O, S-loc, B-loc, E-loc, I-loc, S-pers, B-pers, E-pers, I-pers, S-org, B-org, E-org, I-org
223
+ 2023-10-17 17:33:55,163
224
+ Results:
225
+ - F-score (micro) 0.6707
226
+ - F-score (macro) 0.5415
227
+ - Accuracy 0.5185
228
+
229
+ By class:
230
+ precision recall f1-score support
231
+
232
+ loc 0.6425 0.8088 0.7161 591
233
+ pers 0.5864 0.7703 0.6659 357
234
+ org 0.3019 0.2025 0.2424 79
235
+
236
+ micro avg 0.6074 0.7488 0.6707 1027
237
+ macro avg 0.5102 0.5939 0.5415 1027
238
+ weighted avg 0.5968 0.7488 0.6622 1027
239
+
240
+ 2023-10-17 17:33:55,163 ----------------------------------------------------------------------------------------------------