Hugging Face's logo

stefan-it
/
hmbench-hipe2020-fr-hmbert-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5

Token Classification
Flair
PyTorch
French
sequence-tagger-model
Model card Files Community
1
stefan-it commited on
Commit
1b8deea
·
1 Parent(s): aa1cff8

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. best-model.pt +3 -0
  2. dev.tsv +0 -0
  3. loss.tsv +11 -0
  4. test.tsv +0 -0
  5. training.log +244 -0
best-model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953dffe6226fddce0fa1c3582ec7cd06b02927802c86a66d3743a16acbd26677
3
+ size 443335879
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 18:37:36 0.0000 0.5197 0.1232 0.6903 0.7635 0.7250 0.5994
3
+ 2 18:38:38 0.0000 0.1208 0.1271 0.7516 0.8076 0.7786 0.6629
4
+ 3 18:39:39 0.0000 0.0743 0.1227 0.8065 0.8162 0.8113 0.7041
5
+ 4 18:40:41 0.0000 0.0520 0.1609 0.7982 0.8316 0.8146 0.7139
6
+ 5 18:41:42 0.0000 0.0353 0.1759 0.8199 0.8368 0.8282 0.7287
7
+ 6 18:42:45 0.0000 0.0264 0.1890 0.8218 0.8265 0.8241 0.7306
8
+ 7 18:43:46 0.0000 0.0178 0.2096 0.8197 0.8179 0.8188 0.7223
9
+ 8 18:44:47 0.0000 0.0125 0.2140 0.8185 0.8345 0.8264 0.7344
10
+ 9 18:45:47 0.0000 0.0092 0.2165 0.8208 0.8368 0.8287 0.7345
11
+ 10 18:46:49 0.0000 0.0058 0.2265 0.8210 0.8408 0.8308 0.7388
test.tsv ADDED
The diff for this file is too large to render. See raw diff
 
training.log ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-10-13 18:36:40,767 ----------------------------------------------------------------------------------------------------
2
+ 2023-10-13 18:36:40,768 Model: "SequenceTagger(
3
+ (embeddings): TransformerWordEmbeddings(
4
+ (model): BertModel(
5
+ (embeddings): BertEmbeddings(
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): 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=21, bias=True)
48
+ (loss_function): CrossEntropyLoss()
49
+ )"
50
+ 2023-10-13 18:36:40,768 ----------------------------------------------------------------------------------------------------
51
+ 2023-10-13 18:36:40,768 MultiCorpus: 5901 train + 1287 dev + 1505 test sentences
52
+ - NER_HIPE_2022 Corpus: 5901 train + 1287 dev + 1505 test sentences - /root/.flair/datasets/ner_hipe_2022/v2.1/hipe2020/fr/with_doc_seperator
53
+ 2023-10-13 18:36:40,768 ----------------------------------------------------------------------------------------------------
54
+ 2023-10-13 18:36:40,768 Train: 5901 sentences
55
+ 2023-10-13 18:36:40,768 (train_with_dev=False, train_with_test=False)
56
+ 2023-10-13 18:36:40,768 ----------------------------------------------------------------------------------------------------
57
+ 2023-10-13 18:36:40,768 Training Params:
58
+ 2023-10-13 18:36:40,768 - learning_rate: "5e-05"
59
+ 2023-10-13 18:36:40,768 - mini_batch_size: "8"
60
+ 2023-10-13 18:36:40,768 - max_epochs: "10"
61
+ 2023-10-13 18:36:40,768 - shuffle: "True"
62
+ 2023-10-13 18:36:40,768 ----------------------------------------------------------------------------------------------------
63
+ 2023-10-13 18:36:40,768 Plugins:
64
+ 2023-10-13 18:36:40,768 - LinearScheduler | warmup_fraction: '0.1'
65
+ 2023-10-13 18:36:40,768 ----------------------------------------------------------------------------------------------------
66
+ 2023-10-13 18:36:40,768 Final evaluation on model from best epoch (best-model.pt)
67
+ 2023-10-13 18:36:40,768 - metric: "('micro avg', 'f1-score')"
68
+ 2023-10-13 18:36:40,768 ----------------------------------------------------------------------------------------------------
69
+ 2023-10-13 18:36:40,768 Computation:
70
+ 2023-10-13 18:36:40,768 - compute on device: cuda:0
71
+ 2023-10-13 18:36:40,768 - embedding storage: none
72
+ 2023-10-13 18:36:40,768 ----------------------------------------------------------------------------------------------------
73
+ 2023-10-13 18:36:40,768 Model training base path: "hmbench-hipe2020/fr-dbmdz/bert-base-historic-multilingual-cased-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5"
74
+ 2023-10-13 18:36:40,769 ----------------------------------------------------------------------------------------------------
75
+ 2023-10-13 18:36:40,769 ----------------------------------------------------------------------------------------------------
76
+ 2023-10-13 18:36:45,338 epoch 1 - iter 73/738 - loss 2.54931084 - time (sec): 4.57 - samples/sec: 3537.61 - lr: 0.000005 - momentum: 0.000000
77
+ 2023-10-13 18:36:50,041 epoch 1 - iter 146/738 - loss 1.59605592 - time (sec): 9.27 - samples/sec: 3504.76 - lr: 0.000010 - momentum: 0.000000
78
+ 2023-10-13 18:36:54,788 epoch 1 - iter 219/738 - loss 1.19783690 - time (sec): 14.02 - samples/sec: 3467.00 - lr: 0.000015 - momentum: 0.000000
79
+ 2023-10-13 18:36:59,439 epoch 1 - iter 292/738 - loss 0.98169682 - time (sec): 18.67 - samples/sec: 3456.39 - lr: 0.000020 - momentum: 0.000000
80
+ 2023-10-13 18:37:04,570 epoch 1 - iter 365/738 - loss 0.84572983 - time (sec): 23.80 - samples/sec: 3410.98 - lr: 0.000025 - momentum: 0.000000
81
+ 2023-10-13 18:37:09,103 epoch 1 - iter 438/738 - loss 0.75132701 - time (sec): 28.33 - samples/sec: 3402.43 - lr: 0.000030 - momentum: 0.000000
82
+ 2023-10-13 18:37:14,016 epoch 1 - iter 511/738 - loss 0.67059184 - time (sec): 33.25 - samples/sec: 3422.44 - lr: 0.000035 - momentum: 0.000000
83
+ 2023-10-13 18:37:19,055 epoch 1 - iter 584/738 - loss 0.60768668 - time (sec): 38.29 - samples/sec: 3429.10 - lr: 0.000039 - momentum: 0.000000
84
+ 2023-10-13 18:37:23,839 epoch 1 - iter 657/738 - loss 0.56205620 - time (sec): 43.07 - samples/sec: 3426.96 - lr: 0.000044 - momentum: 0.000000
85
+ 2023-10-13 18:37:29,004 epoch 1 - iter 730/738 - loss 0.52323394 - time (sec): 48.23 - samples/sec: 3413.91 - lr: 0.000049 - momentum: 0.000000
86
+ 2023-10-13 18:37:29,580 ----------------------------------------------------------------------------------------------------
87
+ 2023-10-13 18:37:29,580 EPOCH 1 done: loss 0.5197 - lr: 0.000049
88
+ 2023-10-13 18:37:35,971 DEV : loss 0.12315742671489716 - f1-score (micro avg) 0.725
89
+ 2023-10-13 18:37:36,008 saving best model
90
+ 2023-10-13 18:37:36,393 ----------------------------------------------------------------------------------------------------
91
+ 2023-10-13 18:37:42,332 epoch 2 - iter 73/738 - loss 0.12545050 - time (sec): 5.94 - samples/sec: 2810.64 - lr: 0.000049 - momentum: 0.000000
92
+ 2023-10-13 18:37:47,119 epoch 2 - iter 146/738 - loss 0.13016972 - time (sec): 10.72 - samples/sec: 3078.41 - lr: 0.000049 - momentum: 0.000000
93
+ 2023-10-13 18:37:52,148 epoch 2 - iter 219/738 - loss 0.12926236 - time (sec): 15.75 - samples/sec: 3155.66 - lr: 0.000048 - momentum: 0.000000
94
+ 2023-10-13 18:37:56,732 epoch 2 - iter 292/738 - loss 0.12658168 - time (sec): 20.34 - samples/sec: 3203.09 - lr: 0.000048 - momentum: 0.000000
95
+ 2023-10-13 18:38:01,818 epoch 2 - iter 365/738 - loss 0.12194424 - time (sec): 25.42 - samples/sec: 3270.82 - lr: 0.000047 - momentum: 0.000000
96
+ 2023-10-13 18:38:08,055 epoch 2 - iter 438/738 - loss 0.12424182 - time (sec): 31.66 - samples/sec: 3280.65 - lr: 0.000047 - momentum: 0.000000
97
+ 2023-10-13 18:38:12,544 epoch 2 - iter 511/738 - loss 0.12292217 - time (sec): 36.15 - samples/sec: 3293.17 - lr: 0.000046 - momentum: 0.000000
98
+ 2023-10-13 18:38:17,596 epoch 2 - iter 584/738 - loss 0.12227691 - time (sec): 41.20 - samples/sec: 3299.69 - lr: 0.000046 - momentum: 0.000000
99
+ 2023-10-13 18:38:21,808 epoch 2 - iter 657/738 - loss 0.12156959 - time (sec): 45.41 - samples/sec: 3310.25 - lr: 0.000045 - momentum: 0.000000
100
+ 2023-10-13 18:38:26,383 epoch 2 - iter 730/738 - loss 0.12154467 - time (sec): 49.99 - samples/sec: 3300.38 - lr: 0.000045 - momentum: 0.000000
101
+ 2023-10-13 18:38:26,800 ----------------------------------------------------------------------------------------------------
102
+ 2023-10-13 18:38:26,800 EPOCH 2 done: loss 0.1208 - lr: 0.000045
103
+ 2023-10-13 18:38:38,300 DEV : loss 0.12709642946720123 - f1-score (micro avg) 0.7786
104
+ 2023-10-13 18:38:38,335 saving best model
105
+ 2023-10-13 18:38:38,922 ----------------------------------------------------------------------------------------------------
106
+ 2023-10-13 18:38:44,137 epoch 3 - iter 73/738 - loss 0.07100891 - time (sec): 5.21 - samples/sec: 3549.04 - lr: 0.000044 - momentum: 0.000000
107
+ 2023-10-13 18:38:49,196 epoch 3 - iter 146/738 - loss 0.06897740 - time (sec): 10.27 - samples/sec: 3413.40 - lr: 0.000043 - momentum: 0.000000
108
+ 2023-10-13 18:38:53,971 epoch 3 - iter 219/738 - loss 0.07112884 - time (sec): 15.04 - samples/sec: 3440.71 - lr: 0.000043 - momentum: 0.000000
109
+ 2023-10-13 18:38:59,474 epoch 3 - iter 292/738 - loss 0.07710969 - time (sec): 20.55 - samples/sec: 3404.61 - lr: 0.000042 - momentum: 0.000000
110
+ 2023-10-13 18:39:04,037 epoch 3 - iter 365/738 - loss 0.07954551 - time (sec): 25.11 - samples/sec: 3390.98 - lr: 0.000042 - momentum: 0.000000
111
+ 2023-10-13 18:39:08,941 epoch 3 - iter 438/738 - loss 0.07609338 - time (sec): 30.01 - samples/sec: 3374.51 - lr: 0.000041 - momentum: 0.000000
112
+ 2023-10-13 18:39:13,532 epoch 3 - iter 511/738 - loss 0.07547912 - time (sec): 34.60 - samples/sec: 3375.82 - lr: 0.000041 - momentum: 0.000000
113
+ 2023-10-13 18:39:18,257 epoch 3 - iter 584/738 - loss 0.07423094 - time (sec): 39.33 - samples/sec: 3375.57 - lr: 0.000040 - momentum: 0.000000
114
+ 2023-10-13 18:39:23,065 epoch 3 - iter 657/738 - loss 0.07474968 - time (sec): 44.14 - samples/sec: 3370.05 - lr: 0.000040 - momentum: 0.000000
115
+ 2023-10-13 18:39:27,700 epoch 3 - iter 730/738 - loss 0.07410272 - time (sec): 48.77 - samples/sec: 3381.11 - lr: 0.000039 - momentum: 0.000000
116
+ 2023-10-13 18:39:28,155 ----------------------------------------------------------------------------------------------------
117
+ 2023-10-13 18:39:28,156 EPOCH 3 done: loss 0.0743 - lr: 0.000039
118
+ 2023-10-13 18:39:39,626 DEV : loss 0.12267415970563889 - f1-score (micro avg) 0.8113
119
+ 2023-10-13 18:39:39,657 saving best model
120
+ 2023-10-13 18:39:40,149 ----------------------------------------------------------------------------------------------------
121
+ 2023-10-13 18:39:45,061 epoch 4 - iter 73/738 - loss 0.04639953 - time (sec): 4.91 - samples/sec: 3252.59 - lr: 0.000038 - momentum: 0.000000
122
+ 2023-10-13 18:39:50,759 epoch 4 - iter 146/738 - loss 0.05317424 - time (sec): 10.61 - samples/sec: 3345.90 - lr: 0.000038 - momentum: 0.000000
123
+ 2023-10-13 18:39:55,789 epoch 4 - iter 219/738 - loss 0.05357739 - time (sec): 15.64 - samples/sec: 3291.31 - lr: 0.000037 - momentum: 0.000000
124
+ 2023-10-13 18:40:00,304 epoch 4 - iter 292/738 - loss 0.05278044 - time (sec): 20.15 - samples/sec: 3277.58 - lr: 0.000037 - momentum: 0.000000
125
+ 2023-10-13 18:40:05,274 epoch 4 - iter 365/738 - loss 0.05181301 - time (sec): 25.12 - samples/sec: 3295.30 - lr: 0.000036 - momentum: 0.000000
126
+ 2023-10-13 18:40:09,947 epoch 4 - iter 438/738 - loss 0.05305014 - time (sec): 29.79 - samples/sec: 3318.60 - lr: 0.000036 - momentum: 0.000000
127
+ 2023-10-13 18:40:14,570 epoch 4 - iter 511/738 - loss 0.05296526 - time (sec): 34.42 - samples/sec: 3310.78 - lr: 0.000035 - momentum: 0.000000
128
+ 2023-10-13 18:40:19,155 epoch 4 - iter 584/738 - loss 0.05307194 - time (sec): 39.00 - samples/sec: 3325.60 - lr: 0.000035 - momentum: 0.000000
129
+ 2023-10-13 18:40:24,038 epoch 4 - iter 657/738 - loss 0.05280718 - time (sec): 43.89 - samples/sec: 3317.54 - lr: 0.000034 - momentum: 0.000000
130
+ 2023-10-13 18:40:29,545 epoch 4 - iter 730/738 - loss 0.05136550 - time (sec): 49.39 - samples/sec: 3335.13 - lr: 0.000033 - momentum: 0.000000
131
+ 2023-10-13 18:40:30,006 ----------------------------------------------------------------------------------------------------
132
+ 2023-10-13 18:40:30,006 EPOCH 4 done: loss 0.0520 - lr: 0.000033
133
+ 2023-10-13 18:40:41,252 DEV : loss 0.16094207763671875 - f1-score (micro avg) 0.8146
134
+ 2023-10-13 18:40:41,284 saving best model
135
+ 2023-10-13 18:40:41,778 ----------------------------------------------------------------------------------------------------
136
+ 2023-10-13 18:40:46,604 epoch 5 - iter 73/738 - loss 0.04101661 - time (sec): 4.82 - samples/sec: 3467.75 - lr: 0.000033 - momentum: 0.000000
137
+ 2023-10-13 18:40:51,195 epoch 5 - iter 146/738 - loss 0.03612267 - time (sec): 9.42 - samples/sec: 3326.71 - lr: 0.000032 - momentum: 0.000000
138
+ 2023-10-13 18:40:56,254 epoch 5 - iter 219/738 - loss 0.03677011 - time (sec): 14.47 - samples/sec: 3313.52 - lr: 0.000032 - momentum: 0.000000
139
+ 2023-10-13 18:41:01,176 epoch 5 - iter 292/738 - loss 0.03501988 - time (sec): 19.40 - samples/sec: 3322.02 - lr: 0.000031 - momentum: 0.000000
140
+ 2023-10-13 18:41:06,266 epoch 5 - iter 365/738 - loss 0.03519205 - time (sec): 24.49 - samples/sec: 3328.85 - lr: 0.000031 - momentum: 0.000000
141
+ 2023-10-13 18:41:11,315 epoch 5 - iter 438/738 - loss 0.03597672 - time (sec): 29.54 - samples/sec: 3327.20 - lr: 0.000030 - momentum: 0.000000
142
+ 2023-10-13 18:41:16,308 epoch 5 - iter 511/738 - loss 0.03576352 - time (sec): 34.53 - samples/sec: 3326.40 - lr: 0.000030 - momentum: 0.000000
143
+ 2023-10-13 18:41:21,531 epoch 5 - iter 584/738 - loss 0.03576562 - time (sec): 39.75 - samples/sec: 3317.15 - lr: 0.000029 - momentum: 0.000000
144
+ 2023-10-13 18:41:26,525 epoch 5 - iter 657/738 - loss 0.03587166 - time (sec): 44.75 - samples/sec: 3323.91 - lr: 0.000028 - momentum: 0.000000
145
+ 2023-10-13 18:41:31,082 epoch 5 - iter 730/738 - loss 0.03565094 - time (sec): 49.30 - samples/sec: 3338.67 - lr: 0.000028 - momentum: 0.000000
146
+ 2023-10-13 18:41:31,690 ----------------------------------------------------------------------------------------------------
147
+ 2023-10-13 18:41:31,690 EPOCH 5 done: loss 0.0353 - lr: 0.000028
148
+ 2023-10-13 18:41:42,876 DEV : loss 0.1758503019809723 - f1-score (micro avg) 0.8282
149
+ 2023-10-13 18:41:42,905 saving best model
150
+ 2023-10-13 18:41:43,492 ----------------------------------------------------------------------------------------------------
151
+ 2023-10-13 18:41:48,507 epoch 6 - iter 73/738 - loss 0.02903248 - time (sec): 5.01 - samples/sec: 3384.93 - lr: 0.000027 - momentum: 0.000000
152
+ 2023-10-13 18:41:53,294 epoch 6 - iter 146/738 - loss 0.02622059 - time (sec): 9.80 - samples/sec: 3291.20 - lr: 0.000027 - momentum: 0.000000
153
+ 2023-10-13 18:41:58,719 epoch 6 - iter 219/738 - loss 0.02646847 - time (sec): 15.22 - samples/sec: 3178.14 - lr: 0.000026 - momentum: 0.000000
154
+ 2023-10-13 18:42:03,631 epoch 6 - iter 292/738 - loss 0.02958010 - time (sec): 20.14 - samples/sec: 3207.56 - lr: 0.000026 - momentum: 0.000000
155
+ 2023-10-13 18:42:08,390 epoch 6 - iter 365/738 - loss 0.02718745 - time (sec): 24.89 - samples/sec: 3219.83 - lr: 0.000025 - momentum: 0.000000
156
+ 2023-10-13 18:42:12,874 epoch 6 - iter 438/738 - loss 0.02700128 - time (sec): 29.38 - samples/sec: 3244.77 - lr: 0.000025 - momentum: 0.000000
157
+ 2023-10-13 18:42:18,097 epoch 6 - iter 511/738 - loss 0.02627538 - time (sec): 34.60 - samples/sec: 3267.81 - lr: 0.000024 - momentum: 0.000000
158
+ 2023-10-13 18:42:22,935 epoch 6 - iter 584/738 - loss 0.02629923 - time (sec): 39.44 - samples/sec: 3279.67 - lr: 0.000023 - momentum: 0.000000
159
+ 2023-10-13 18:42:27,917 epoch 6 - iter 657/738 - loss 0.02668968 - time (sec): 44.42 - samples/sec: 3282.99 - lr: 0.000023 - momentum: 0.000000
160
+ 2023-10-13 18:42:32,910 epoch 6 - iter 730/738 - loss 0.02662988 - time (sec): 49.42 - samples/sec: 3320.82 - lr: 0.000022 - momentum: 0.000000
161
+ 2023-10-13 18:42:33,632 ----------------------------------------------------------------------------------------------------
162
+ 2023-10-13 18:42:33,633 EPOCH 6 done: loss 0.0264 - lr: 0.000022
163
+ 2023-10-13 18:42:45,145 DEV : loss 0.18904562294483185 - f1-score (micro avg) 0.8241
164
+ 2023-10-13 18:42:45,175 ----------------------------------------------------------------------------------------------------
165
+ 2023-10-13 18:42:50,275 epoch 7 - iter 73/738 - loss 0.01959069 - time (sec): 5.10 - samples/sec: 3400.94 - lr: 0.000022 - momentum: 0.000000
166
+ 2023-10-13 18:42:56,300 epoch 7 - iter 146/738 - loss 0.02030636 - time (sec): 11.12 - samples/sec: 3214.64 - lr: 0.000021 - momentum: 0.000000
167
+ 2023-10-13 18:43:01,614 epoch 7 - iter 219/738 - loss 0.01749591 - time (sec): 16.44 - samples/sec: 3222.85 - lr: 0.000021 - momentum: 0.000000
168
+ 2023-10-13 18:43:06,937 epoch 7 - iter 292/738 - loss 0.01940326 - time (sec): 21.76 - samples/sec: 3263.51 - lr: 0.000020 - momentum: 0.000000
169
+ 2023-10-13 18:43:11,149 epoch 7 - iter 365/738 - loss 0.01847137 - time (sec): 25.97 - samples/sec: 3307.19 - lr: 0.000020 - momentum: 0.000000
170
+ 2023-10-13 18:43:16,079 epoch 7 - iter 438/738 - loss 0.01934351 - time (sec): 30.90 - samples/sec: 3314.03 - lr: 0.000019 - momentum: 0.000000
171
+ 2023-10-13 18:43:20,783 epoch 7 - iter 511/738 - loss 0.01938525 - time (sec): 35.61 - samples/sec: 3317.37 - lr: 0.000018 - momentum: 0.000000
172
+ 2023-10-13 18:43:25,364 epoch 7 - iter 584/738 - loss 0.01849506 - time (sec): 40.19 - samples/sec: 3323.78 - lr: 0.000018 - momentum: 0.000000
173
+ 2023-10-13 18:43:30,037 epoch 7 - iter 657/738 - loss 0.01814382 - time (sec): 44.86 - samples/sec: 3329.67 - lr: 0.000017 - momentum: 0.000000
174
+ 2023-10-13 18:43:34,614 epoch 7 - iter 730/738 - loss 0.01783909 - time (sec): 49.44 - samples/sec: 3329.33 - lr: 0.000017 - momentum: 0.000000
175
+ 2023-10-13 18:43:35,103 ----------------------------------------------------------------------------------------------------
176
+ 2023-10-13 18:43:35,103 EPOCH 7 done: loss 0.0178 - lr: 0.000017
177
+ 2023-10-13 18:43:46,346 DEV : loss 0.2096458524465561 - f1-score (micro avg) 0.8188
178
+ 2023-10-13 18:43:46,376 ----------------------------------------------------------------------------------------------------
179
+ 2023-10-13 18:43:51,287 epoch 8 - iter 73/738 - loss 0.01043596 - time (sec): 4.91 - samples/sec: 3589.86 - lr: 0.000016 - momentum: 0.000000
180
+ 2023-10-13 18:43:55,837 epoch 8 - iter 146/738 - loss 0.00825281 - time (sec): 9.46 - samples/sec: 3471.96 - lr: 0.000016 - momentum: 0.000000
181
+ 2023-10-13 18:44:01,171 epoch 8 - iter 219/738 - loss 0.01181636 - time (sec): 14.79 - samples/sec: 3487.90 - lr: 0.000015 - momentum: 0.000000
182
+ 2023-10-13 18:44:06,152 epoch 8 - iter 292/738 - loss 0.01070298 - time (sec): 19.77 - samples/sec: 3387.84 - lr: 0.000015 - momentum: 0.000000
183
+ 2023-10-13 18:44:10,412 epoch 8 - iter 365/738 - loss 0.01219064 - time (sec): 24.03 - samples/sec: 3387.86 - lr: 0.000014 - momentum: 0.000000
184
+ 2023-10-13 18:44:15,244 epoch 8 - iter 438/738 - loss 0.01311692 - time (sec): 28.87 - samples/sec: 3369.74 - lr: 0.000013 - momentum: 0.000000
185
+ 2023-10-13 18:44:20,242 epoch 8 - iter 511/738 - loss 0.01306631 - time (sec): 33.87 - samples/sec: 3387.73 - lr: 0.000013 - momentum: 0.000000
186
+ 2023-10-13 18:44:25,159 epoch 8 - iter 584/738 - loss 0.01229285 - time (sec): 38.78 - samples/sec: 3375.92 - lr: 0.000012 - momentum: 0.000000
187
+ 2023-10-13 18:44:30,088 epoch 8 - iter 657/738 - loss 0.01286131 - time (sec): 43.71 - samples/sec: 3366.15 - lr: 0.000012 - momentum: 0.000000
188
+ 2023-10-13 18:44:35,102 epoch 8 - iter 730/738 - loss 0.01254249 - time (sec): 48.72 - samples/sec: 3367.31 - lr: 0.000011 - momentum: 0.000000
189
+ 2023-10-13 18:44:35,798 ----------------------------------------------------------------------------------------------------
190
+ 2023-10-13 18:44:35,798 EPOCH 8 done: loss 0.0125 - lr: 0.000011
191
+ 2023-10-13 18:44:47,081 DEV : loss 0.2140151411294937 - f1-score (micro avg) 0.8264
192
+ 2023-10-13 18:44:47,113 ----------------------------------------------------------------------------------------------------
193
+ 2023-10-13 18:44:51,980 epoch 9 - iter 73/738 - loss 0.00976824 - time (sec): 4.87 - samples/sec: 3281.97 - lr: 0.000011 - momentum: 0.000000
194
+ 2023-10-13 18:44:56,729 epoch 9 - iter 146/738 - loss 0.01142894 - time (sec): 9.61 - samples/sec: 3343.88 - lr: 0.000010 - momentum: 0.000000
195
+ 2023-10-13 18:45:01,104 epoch 9 - iter 219/738 - loss 0.00946193 - time (sec): 13.99 - samples/sec: 3350.40 - lr: 0.000010 - momentum: 0.000000
196
+ 2023-10-13 18:45:06,392 epoch 9 - iter 292/738 - loss 0.01046465 - time (sec): 19.28 - samples/sec: 3308.53 - lr: 0.000009 - momentum: 0.000000
197
+ 2023-10-13 18:45:11,073 epoch 9 - iter 365/738 - loss 0.00966350 - time (sec): 23.96 - samples/sec: 3309.18 - lr: 0.000008 - momentum: 0.000000
198
+ 2023-10-13 18:45:16,024 epoch 9 - iter 438/738 - loss 0.00924954 - time (sec): 28.91 - samples/sec: 3301.58 - lr: 0.000008 - momentum: 0.000000
199
+ 2023-10-13 18:45:21,095 epoch 9 - iter 511/738 - loss 0.00925664 - time (sec): 33.98 - samples/sec: 3327.92 - lr: 0.000007 - momentum: 0.000000
200
+ 2023-10-13 18:45:26,558 epoch 9 - iter 584/738 - loss 0.00935297 - time (sec): 39.44 - samples/sec: 3333.00 - lr: 0.000007 - momentum: 0.000000
201
+ 2023-10-13 18:45:31,135 epoch 9 - iter 657/738 - loss 0.00875783 - time (sec): 44.02 - samples/sec: 3334.98 - lr: 0.000006 - momentum: 0.000000
202
+ 2023-10-13 18:45:35,898 epoch 9 - iter 730/738 - loss 0.00930370 - time (sec): 48.78 - samples/sec: 3354.77 - lr: 0.000006 - momentum: 0.000000
203
+ 2023-10-13 18:45:36,765 ----------------------------------------------------------------------------------------------------
204
+ 2023-10-13 18:45:36,765 EPOCH 9 done: loss 0.0092 - lr: 0.000006
205
+ 2023-10-13 18:45:47,968 DEV : loss 0.216547891497612 - f1-score (micro avg) 0.8287
206
+ 2023-10-13 18:45:47,999 saving best model
207
+ 2023-10-13 18:45:48,546 ----------------------------------------------------------------------------------------------------
208
+ 2023-10-13 18:45:53,055 epoch 10 - iter 73/738 - loss 0.00309356 - time (sec): 4.50 - samples/sec: 3370.27 - lr: 0.000005 - momentum: 0.000000
209
+ 2023-10-13 18:45:58,249 epoch 10 - iter 146/738 - loss 0.00338579 - time (sec): 9.70 - samples/sec: 3347.86 - lr: 0.000004 - momentum: 0.000000
210
+ 2023-10-13 18:46:03,400 epoch 10 - iter 219/738 - loss 0.00387549 - time (sec): 14.85 - samples/sec: 3316.93 - lr: 0.000004 - momentum: 0.000000
211
+ 2023-10-13 18:46:08,537 epoch 10 - iter 292/738 - loss 0.00458478 - time (sec): 19.99 - samples/sec: 3320.98 - lr: 0.000003 - momentum: 0.000000
212
+ 2023-10-13 18:46:13,808 epoch 10 - iter 365/738 - loss 0.00487712 - time (sec): 25.26 - samples/sec: 3335.23 - lr: 0.000003 - momentum: 0.000000
213
+ 2023-10-13 18:46:18,296 epoch 10 - iter 438/738 - loss 0.00479942 - time (sec): 29.75 - samples/sec: 3354.93 - lr: 0.000002 - momentum: 0.000000
214
+ 2023-10-13 18:46:22,698 epoch 10 - iter 511/738 - loss 0.00567514 - time (sec): 34.15 - samples/sec: 3371.44 - lr: 0.000002 - momentum: 0.000000
215
+ 2023-10-13 18:46:27,738 epoch 10 - iter 584/738 - loss 0.00588151 - time (sec): 39.19 - samples/sec: 3356.15 - lr: 0.000001 - momentum: 0.000000
216
+ 2023-10-13 18:46:32,799 epoch 10 - iter 657/738 - loss 0.00591418 - time (sec): 44.25 - samples/sec: 3374.15 - lr: 0.000001 - momentum: 0.000000
217
+ 2023-10-13 18:46:37,320 epoch 10 - iter 730/738 - loss 0.00582670 - time (sec): 48.77 - samples/sec: 3379.83 - lr: 0.000000 - momentum: 0.000000
218
+ 2023-10-13 18:46:37,769 ----------------------------------------------------------------------------------------------------
219
+ 2023-10-13 18:46:37,769 EPOCH 10 done: loss 0.0058 - lr: 0.000000
220
+ 2023-10-13 18:46:49,686 DEV : loss 0.22645464539527893 - f1-score (micro avg) 0.8308
221
+ 2023-10-13 18:46:49,715 saving best model
222
+ 2023-10-13 18:46:50,693 ----------------------------------------------------------------------------------------------------
223
+ 2023-10-13 18:46:50,695 Loading model from best epoch ...
224
+ 2023-10-13 18:46:52,055 SequenceTagger predicts: Dictionary with 21 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, S-time, B-time, E-time, I-time, S-prod, B-prod, E-prod, I-prod
225
+ 2023-10-13 18:46:58,097
226
+ Results:
227
+ - F-score (micro) 0.7976
228
+ - F-score (macro) 0.7
229
+ - Accuracy 0.6875
230
+
231
+ By class:
232
+ precision recall f1-score support
233
+
234
+ loc 0.8567 0.8776 0.8670 858
235
+ pers 0.7557 0.8063 0.7802 537
236
+ org 0.5423 0.5833 0.5620 132
237
+ prod 0.6923 0.7377 0.7143 61
238
+ time 0.5312 0.6296 0.5763 54
239
+
240
+ micro avg 0.7789 0.8173 0.7976 1642
241
+ macro avg 0.6756 0.7269 0.7000 1642
242
+ weighted avg 0.7815 0.8173 0.7989 1642
243
+
244
+ 2023-10-13 18:46:58,097 ----------------------------------------------------------------------------------------------------