initial model commit
Browse files- README.md +166 -0
- en-pos-ontonotes-v0.4.pt +3 -0
- loss.tsv +143 -0
- training.log +0 -0
README.md
ADDED
@@ -0,0 +1,166 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- flair
|
4 |
+
- token-classification
|
5 |
+
- sequence-tagger-model
|
6 |
+
language: en
|
7 |
+
datasets:
|
8 |
+
- ontonotes
|
9 |
+
inference: false
|
10 |
+
---
|
11 |
+
|
12 |
+
## English Universal Part-of-Speech Tagging in Flair (default model)
|
13 |
+
|
14 |
+
This is the standard universal part-of-speech tagging model for English that ships with [Flair](https://github.com/flairNLP/flair/).
|
15 |
+
|
16 |
+
F1-Score: **98,19** (Ontonotes)
|
17 |
+
|
18 |
+
Predicts universal POS tags:
|
19 |
+
|
20 |
+
| **tag** | **meaning** |
|
21 |
+
|---------------------------------|-----------|
|
22 |
+
|ADD | Email |
|
23 |
+
|AFX | Affix |
|
24 |
+
|CC | Coordinating conjunction |
|
25 |
+
|CD | Cardinal number |
|
26 |
+
|DT | Determiner |
|
27 |
+
|EX | Existential there |
|
28 |
+
|FW | Foreign word |
|
29 |
+
|HYPH | Hyphen |
|
30 |
+
|IN | Preposition or subordinating conjunction |
|
31 |
+
|JJ | Adjective |
|
32 |
+
|JJR |Adjective, comparative |
|
33 |
+
|JJS | Adjective, superlative |
|
34 |
+
|LS | List item marker |
|
35 |
+
|MD | Modal |
|
36 |
+
|NFP | Superfluous punctuation |
|
37 |
+
|NN | Noun, singular or mass |
|
38 |
+
|NNP |Proper noun, singular |
|
39 |
+
|NNPS | Proper noun, plural |
|
40 |
+
|NNS |Noun, plural |
|
41 |
+
|
42 |
+
|
43 |
+
|
44 |
+
Based on [Flair embeddings](https://www.aclweb.org/anthology/C18-1139/) and LSTM-CRF.
|
45 |
+
|
46 |
+
---
|
47 |
+
|
48 |
+
### Demo: How to use in Flair
|
49 |
+
|
50 |
+
Requires: **[Flair](https://github.com/flairNLP/flair/)** (`pip install flair`)
|
51 |
+
|
52 |
+
```python
|
53 |
+
from flair.data import Sentence
|
54 |
+
from flair.models import SequenceTagger
|
55 |
+
|
56 |
+
# load tagger
|
57 |
+
tagger = SequenceTagger.load("flair/upos-english")
|
58 |
+
|
59 |
+
# make example sentence
|
60 |
+
sentence = Sentence("I love Berlin.")
|
61 |
+
|
62 |
+
# predict NER tags
|
63 |
+
tagger.predict(sentence)
|
64 |
+
|
65 |
+
# print sentence
|
66 |
+
print(sentence)
|
67 |
+
|
68 |
+
# print predicted NER spans
|
69 |
+
print('The following NER tags are found:')
|
70 |
+
# iterate over entities and print
|
71 |
+
for entity in sentence.get_spans('upos'):
|
72 |
+
print(entity)
|
73 |
+
|
74 |
+
```
|
75 |
+
|
76 |
+
This yields the following output:
|
77 |
+
```
|
78 |
+
Span [1]: "I" [− Labels: PRP (1.0)]
|
79 |
+
Span [2]: "love" [− Labels: VBP (1.0)]
|
80 |
+
Span [3]: "Berlin" [− Labels: NNP (0.9999)]
|
81 |
+
Span [4]: "." [− Labels: . (1.0)]
|
82 |
+
|
83 |
+
```
|
84 |
+
|
85 |
+
So, the word "*I*" is labeled as a **pronoun** (PRP), "*love*" is labeled as a **verb** (VBP) and "*Berlin*" is labeled as a **proper noun** (NNP) in the sentence "*TheI love Berlin*".
|
86 |
+
|
87 |
+
|
88 |
+
---
|
89 |
+
|
90 |
+
### Training: Script to train this model
|
91 |
+
|
92 |
+
The following Flair script was used to train this model:
|
93 |
+
|
94 |
+
```python
|
95 |
+
from flair.data import Corpus
|
96 |
+
from flair.datasets import ColumnCorpus
|
97 |
+
from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings
|
98 |
+
|
99 |
+
# 1. load the corpus (Ontonotes does not ship with Flair, you need to download and reformat into a column format yourself)
|
100 |
+
corpus: Corpus = ColumnCorpus(
|
101 |
+
"resources/tasks/onto-ner",
|
102 |
+
column_format={0: "text", 1: "pos", 2: "upos", 3: "ner"},
|
103 |
+
tag_to_bioes="ner",
|
104 |
+
)
|
105 |
+
|
106 |
+
# 2. what tag do we want to predict?
|
107 |
+
tag_type = 'upos'
|
108 |
+
|
109 |
+
# 3. make the tag dictionary from the corpus
|
110 |
+
tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)
|
111 |
+
|
112 |
+
# 4. initialize each embedding we use
|
113 |
+
embedding_types = [
|
114 |
+
|
115 |
+
# contextual string embeddings, forward
|
116 |
+
FlairEmbeddings('news-forward'),
|
117 |
+
|
118 |
+
# contextual string embeddings, backward
|
119 |
+
FlairEmbeddings('news-backward'),
|
120 |
+
]
|
121 |
+
|
122 |
+
# embedding stack consists of Flair and GloVe embeddings
|
123 |
+
embeddings = StackedEmbeddings(embeddings=embedding_types)
|
124 |
+
|
125 |
+
# 5. initialize sequence tagger
|
126 |
+
from flair.models import SequenceTagger
|
127 |
+
|
128 |
+
tagger = SequenceTagger(hidden_size=256,
|
129 |
+
embeddings=embeddings,
|
130 |
+
tag_dictionary=tag_dictionary,
|
131 |
+
tag_type=tag_type)
|
132 |
+
|
133 |
+
# 6. initialize trainer
|
134 |
+
from flair.trainers import ModelTrainer
|
135 |
+
|
136 |
+
trainer = ModelTrainer(tagger, corpus)
|
137 |
+
|
138 |
+
# 7. run training
|
139 |
+
trainer.train('resources/taggers/upos-english',
|
140 |
+
train_with_dev=True,
|
141 |
+
max_epochs=150)
|
142 |
+
```
|
143 |
+
|
144 |
+
|
145 |
+
|
146 |
+
---
|
147 |
+
|
148 |
+
### Cite
|
149 |
+
|
150 |
+
Please cite the following paper when using this model.
|
151 |
+
|
152 |
+
```
|
153 |
+
@inproceedings{akbik2018coling,
|
154 |
+
title={Contextual String Embeddings for Sequence Labeling},
|
155 |
+
author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
|
156 |
+
booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
|
157 |
+
pages = {1638--1649},
|
158 |
+
year = {2018}
|
159 |
+
}
|
160 |
+
```
|
161 |
+
|
162 |
+
---
|
163 |
+
|
164 |
+
### Issues?
|
165 |
+
|
166 |
+
The Flair issue tracker is available [here](https://github.com/flairNLP/flair/issues/).
|
en-pos-ontonotes-v0.4.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:930d325f23403a084096d5f32e374f82bcb9096df0260f8fc9ed0c50d2480633
|
3 |
+
size 432218302
|
loss.tsv
ADDED
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
EPOCH TIMESTAMP BAD_EPOCHS LEARNING_RATE TRAIN_LOSS TEST_LOSS TEST_PRECISION TEST_RECALL TEST_F1
|
2 |
+
0 14:36:34 0 0.1000 4.008367513935521 1.2577271461486816 0.9789 0.9789 0.9789
|
3 |
+
1 14:44:29 0 0.1000 2.163354017959451 1.0980191230773926 0.9811 0.9811 0.9811
|
4 |
+
2 14:53:01 0 0.1000 1.9004344679949419 1.0910283327102661 0.9812 0.9812 0.9812
|
5 |
+
3 15:01:14 0 0.1000 1.751520331726884 1.0109158754348755 0.983 0.983 0.983
|
6 |
+
4 15:10:10 0 0.1000 1.6782221034112967 0.9781177639961243 0.9827 0.9827 0.9827
|
7 |
+
5 15:18:30 0 0.1000 1.5933319744523966 0.9855104088783264 0.9832 0.9832 0.9832
|
8 |
+
6 15:26:42 0 0.1000 1.5720505905488753 0.9396699070930481 0.9839 0.9839 0.9839
|
9 |
+
7 15:34:34 0 0.1000 1.4993335689463705 0.9325671195983887 0.9843 0.9843 0.9843
|
10 |
+
8 15:42:32 0 0.1000 1.4683161432225749 0.9401538968086243 0.9838 0.9838 0.9838
|
11 |
+
9 15:50:56 0 0.1000 1.4346334695366194 0.9269382357597351 0.9841 0.9841 0.9841
|
12 |
+
10 15:59:54 0 0.1000 1.4206131338061028 0.9161098003387451 0.984 0.984 0.984
|
13 |
+
11 16:07:57 0 0.1000 1.4055630077730934 0.897429347038269 0.9846 0.9846 0.9846
|
14 |
+
12 16:16:06 0 0.1000 1.373073951512013 0.9149079322814941 0.9845 0.9845 0.9845
|
15 |
+
13 16:24:46 0 0.1000 1.3466703206075812 0.8978148698806763 0.9848 0.9848 0.9848
|
16 |
+
14 16:33:08 0 0.1000 1.3374556048298782 0.8893901109695435 0.9845 0.9845 0.9845
|
17 |
+
15 16:41:06 0 0.1000 1.3307637055864874 0.9063434600830078 0.9847 0.9847 0.9847
|
18 |
+
16 16:49:37 0 0.1000 1.3076906337490621 0.8879907131195068 0.9844 0.9844 0.9844
|
19 |
+
17 16:58:02 0 0.1000 1.2761721186817816 0.8983049392700195 0.9845 0.9845 0.9845
|
20 |
+
18 17:05:53 0 0.1000 1.271227304136978 0.8802424073219299 0.9851 0.9851 0.9851
|
21 |
+
19 17:14:16 0 0.1000 1.2710339361316754 0.8875988125801086 0.9848 0.9848 0.9848
|
22 |
+
20 17:22:23 0 0.1000 1.2573032806729372 0.868634045124054 0.9851 0.9851 0.9851
|
23 |
+
21 17:30:41 0 0.1000 1.245996435796315 0.8761005401611328 0.985 0.985 0.985
|
24 |
+
22 17:38:59 0 0.1000 1.222834424320257 0.9007474780082703 0.9848 0.9848 0.9848
|
25 |
+
23 17:47:06 0 0.1000 1.2212693688667045 0.8793701529502869 0.9846 0.9846 0.9846
|
26 |
+
24 17:55:32 0 0.1000 1.2166621732037022 0.8733012676239014 0.9852 0.9852 0.9852
|
27 |
+
25 18:03:46 0 0.1000 1.2115359597610977 0.8737635612487793 0.9849 0.9849 0.9849
|
28 |
+
26 18:11:54 0 0.1000 1.1791622321898083 0.8651444315910339 0.9853 0.9853 0.9853
|
29 |
+
27 18:20:28 1 0.1000 1.189784155330568 0.8619667887687683 0.9852 0.9852 0.9852
|
30 |
+
28 18:28:24 2 0.1000 1.1796241974605703 0.8816197514533997 0.985 0.985 0.985
|
31 |
+
29 18:37:07 3 0.1000 1.1875165427687033 0.874102771282196 0.9855 0.9855 0.9855
|
32 |
+
30 18:45:33 0 0.1000 1.1682702933842282 0.8671573996543884 0.9854 0.9854 0.9854
|
33 |
+
31 18:53:49 0 0.1000 1.1570520079360818 0.8725769519805908 0.9852 0.9852 0.9852
|
34 |
+
32 19:02:17 1 0.1000 1.1585131167240863 0.8707659244537354 0.9853 0.9853 0.9853
|
35 |
+
33 19:10:39 0 0.1000 1.1393565388445583 0.8681735992431641 0.9853 0.9853 0.9853
|
36 |
+
34 19:19:04 1 0.1000 1.1428494264494697 0.8624382615089417 0.9854 0.9854 0.9854
|
37 |
+
35 19:27:45 2 0.1000 1.1424201743557767 0.8647207021713257 0.9854 0.9854 0.9854
|
38 |
+
36 19:36:05 0 0.1000 1.1202877420299457 0.8638347387313843 0.9854 0.9854 0.9854
|
39 |
+
37 19:44:21 1 0.1000 1.1311183402673253 0.8702887892723083 0.9851 0.9851 0.9851
|
40 |
+
38 19:52:55 2 0.1000 1.12726934715262 0.8800793290138245 0.9852 0.9852 0.9852
|
41 |
+
39 20:00:54 3 0.1000 1.1242271356650118 0.8791370391845703 0.9854 0.9854 0.9854
|
42 |
+
40 20:09:18 0 0.1000 1.0961355772220864 0.8757585287094116 0.9854 0.9854 0.9854
|
43 |
+
41 20:17:09 1 0.1000 1.1003335604127849 0.8738007545471191 0.9851 0.9851 0.9851
|
44 |
+
42 20:25:02 0 0.1000 1.0918549644384743 0.8711261749267578 0.9857 0.9857 0.9857
|
45 |
+
43 20:32:56 1 0.1000 1.095643256216679 0.8664193153381348 0.9854 0.9854 0.9854
|
46 |
+
44 20:41:10 2 0.1000 1.0931422947487741 0.8765290379524231 0.9853 0.9853 0.9853
|
47 |
+
45 20:49:32 3 0.1000 1.095532551767691 0.8595676422119141 0.9857 0.9857 0.9857
|
48 |
+
46 20:57:48 0 0.1000 1.0823876487983848 0.8736404776573181 0.9855 0.9855 0.9855
|
49 |
+
47 21:06:08 0 0.1000 1.0658918488925357 0.8816397786140442 0.9856 0.9856 0.9856
|
50 |
+
48 21:15:03 1 0.1000 1.066866978406906 0.8638147115707397 0.9854 0.9854 0.9854
|
51 |
+
49 21:22:56 2 0.1000 1.0886192945714266 0.8806375861167908 0.9853 0.9853 0.9853
|
52 |
+
50 21:31:47 0 0.1000 1.0568831916237778 0.8815222978591919 0.9853 0.9853 0.9853
|
53 |
+
51 21:40:17 1 0.1000 1.059176179834132 0.8800312876701355 0.9854 0.9854 0.9854
|
54 |
+
52 21:48:19 0 0.1000 1.0550847964691665 0.8634426593780518 0.9857 0.9857 0.9857
|
55 |
+
53 21:56:32 0 0.1000 1.0347917758518794 0.8902379274368286 0.9858 0.9858 0.9858
|
56 |
+
54 22:04:53 1 0.1000 1.0553579241712139 0.8602169156074524 0.9855 0.9855 0.9855
|
57 |
+
55 22:12:49 2 0.1000 1.0556637697849633 0.8598523139953613 0.9858 0.9858 0.9858
|
58 |
+
56 22:21:14 3 0.1000 1.0436716236933223 0.8705869317054749 0.9856 0.9856 0.9856
|
59 |
+
57 22:29:57 0 0.1000 1.0228789444914403 0.870323896408081 0.9858 0.9858 0.9858
|
60 |
+
58 22:38:26 1 0.1000 1.0271192405808647 0.888481855392456 0.9854 0.9854 0.9854
|
61 |
+
59 22:47:07 2 0.1000 1.0378682003043733 0.8799546360969543 0.9855 0.9855 0.9855
|
62 |
+
60 22:54:55 0 0.1000 1.0227146919268482 0.8756501078605652 0.9858 0.9858 0.9858
|
63 |
+
61 23:03:59 0 0.1000 1.0122003238830926 0.8810533285140991 0.9855 0.9855 0.9855
|
64 |
+
62 23:12:52 1 0.1000 1.0485500928815805 0.8817822933197021 0.9854 0.9854 0.9854
|
65 |
+
63 23:21:33 2 0.1000 1.0170415557667893 0.8638274669647217 0.9855 0.9855 0.9855
|
66 |
+
64 23:29:55 3 0.1000 1.014521924718371 0.8873447775840759 0.9854 0.9854 0.9854
|
67 |
+
65 23:37:57 4 0.1000 1.014803165444788 0.8913549184799194 0.9855 0.9855 0.9855
|
68 |
+
66 23:46:39 0 0.0500 0.9479580966650315 0.8857957124710083 0.9859 0.9859 0.9859
|
69 |
+
67 23:55:04 0 0.0500 0.9425211805217671 0.8628813028335571 0.9857 0.9857 0.9857
|
70 |
+
68 00:03:54 0 0.0500 0.9135979884862899 0.8728424906730652 0.9858 0.9858 0.9858
|
71 |
+
69 00:12:33 1 0.0500 0.9247301808674381 0.872383177280426 0.9858 0.9858 0.9858
|
72 |
+
70 00:21:15 0 0.0500 0.9128732096361664 0.8710495233535767 0.9859 0.9859 0.9859
|
73 |
+
71 00:29:40 0 0.0500 0.9042936521093801 0.8692572116851807 0.9857 0.9857 0.9857
|
74 |
+
72 00:37:44 0 0.0500 0.9033016588159327 0.878852903842926 0.986 0.986 0.986
|
75 |
+
73 00:45:57 0 0.0500 0.8773919828714065 0.865746259689331 0.9857 0.9857 0.9857
|
76 |
+
74 00:54:34 0 0.0500 0.8679883146735857 0.8742089867591858 0.9859 0.9859 0.9859
|
77 |
+
75 01:03:03 1 0.0500 0.891358519876903 0.87213134765625 0.9858 0.9858 0.9858
|
78 |
+
76 01:11:20 2 0.0500 0.872176597422024 0.8654622435569763 0.9859 0.9859 0.9859
|
79 |
+
77 01:19:45 3 0.0500 0.872468108962167 0.8700181245803833 0.9859 0.9859 0.9859
|
80 |
+
78 01:28:01 4 0.0500 0.8821615111827851 0.8670461773872375 0.986 0.986 0.986
|
81 |
+
79 01:36:12 0 0.0250 0.8530965350202795 0.8679666519165039 0.9859 0.9859 0.9859
|
82 |
+
80 01:44:54 0 0.0250 0.8332193144424906 0.8621937036514282 0.9859 0.9859 0.9859
|
83 |
+
81 01:53:07 0 0.0250 0.8315853100621475 0.8638757467269897 0.986 0.986 0.986
|
84 |
+
82 02:01:49 0 0.0250 0.8290982493477047 0.8625437617301941 0.986 0.986 0.986
|
85 |
+
83 02:10:17 1 0.0250 0.8297435836353392 0.8690134882926941 0.986 0.986 0.986
|
86 |
+
84 02:18:32 0 0.0250 0.8172947089289719 0.8628909587860107 0.986 0.986 0.986
|
87 |
+
85 02:26:43 0 0.0250 0.812517744538919 0.8665143251419067 0.986 0.986 0.986
|
88 |
+
86 02:35:36 0 0.0250 0.8107178360504924 0.8698837161064148 0.986 0.986 0.986
|
89 |
+
87 02:44:17 0 0.0250 0.8075715616851483 0.8780113458633423 0.986 0.986 0.986
|
90 |
+
88 02:53:06 0 0.0250 0.8073269930144525 0.8748922944068909 0.9861 0.9861 0.9861
|
91 |
+
89 03:02:06 0 0.0250 0.7929732948091794 0.8709448575973511 0.9861 0.9861 0.9861
|
92 |
+
90 03:10:44 1 0.0250 0.8116432329393782 0.8663097620010376 0.986 0.986 0.986
|
93 |
+
91 03:19:48 2 0.0250 0.805180228661816 0.8722399473190308 0.9859 0.9859 0.9859
|
94 |
+
92 03:27:59 3 0.0250 0.7929308533949672 0.8725450038909912 0.9861 0.9861 0.9861
|
95 |
+
93 03:36:29 4 0.0250 0.8075241990584248 0.8720933198928833 0.9861 0.9861 0.9861
|
96 |
+
94 03:44:53 0 0.0125 0.7846327245966443 0.8689613938331604 0.986 0.986 0.986
|
97 |
+
95 03:53:13 1 0.0125 0.7975563114937746 0.864532470703125 0.9861 0.9861 0.9861
|
98 |
+
96 04:01:28 0 0.0125 0.7842649862788759 0.8675511479377747 0.986 0.986 0.986
|
99 |
+
97 04:10:05 0 0.0125 0.7774382631171425 0.8691446185112 0.986 0.986 0.986
|
100 |
+
98 04:18:02 1 0.0125 0.7893856516874062 0.8716655373573303 0.9859 0.9859 0.9859
|
101 |
+
99 04:26:19 2 0.0125 0.7788836819776949 0.8742871880531311 0.9862 0.9862 0.9862
|
102 |
+
100 04:34:37 0 0.0125 0.7732159744905975 0.8769155740737915 0.9859 0.9859 0.9859
|
103 |
+
101 04:43:07 1 0.0125 0.7743589581633514 0.8772578835487366 0.986 0.986 0.986
|
104 |
+
102 04:51:52 0 0.0125 0.7597070909783525 0.8754911422729492 0.986 0.986 0.986
|
105 |
+
103 05:00:07 1 0.0125 0.7657219985127449 0.8714533448219299 0.9862 0.9862 0.9862
|
106 |
+
104 05:08:09 2 0.0125 0.7751772561613118 0.8732997179031372 0.986 0.986 0.986
|
107 |
+
105 05:15:57 3 0.0125 0.7704332929456009 0.8731410503387451 0.986 0.986 0.986
|
108 |
+
106 05:24:43 4 0.0125 0.7656213049731164 0.8733732104301453 0.9861 0.9861 0.9861
|
109 |
+
107 05:33:14 0 0.0063 0.7456300285346104 0.8719821572303772 0.986 0.986 0.986
|
110 |
+
108 05:41:43 1 0.0063 0.767869704764969 0.8725889921188354 0.9861 0.9861 0.9861
|
111 |
+
109 05:50:10 2 0.0063 0.7621631826207322 0.874808669090271 0.9861 0.9861 0.9861
|
112 |
+
110 05:59:14 3 0.0063 0.7490265315433718 0.8728870749473572 0.986 0.986 0.986
|
113 |
+
111 06:07:41 4 0.0063 0.7540235197431636 0.8721423149108887 0.9861 0.9861 0.9861
|
114 |
+
112 06:15:40 0 0.0031 0.7366209726176172 0.8710729479789734 0.9861 0.9861 0.9861
|
115 |
+
113 06:24:11 1 0.0031 0.7613341029747477 0.8746064305305481 0.986 0.986 0.986
|
116 |
+
114 06:31:59 2 0.0031 0.759065353459907 0.8729156255722046 0.9859 0.9859 0.9859
|
117 |
+
115 06:40:34 3 0.0031 0.7491356465332913 0.8742703199386597 0.986 0.986 0.986
|
118 |
+
116 06:49:10 4 0.0031 0.7422314731411214 0.8741567730903625 0.986 0.986 0.986
|
119 |
+
117 06:57:33 1 0.0016 0.7465769196400103 0.8745524883270264 0.986 0.986 0.986
|
120 |
+
118 07:05:30 0 0.0016 0.7297081322040198 0.8748660683631897 0.9861 0.9861 0.9861
|
121 |
+
119 07:13:44 1 0.0016 0.7487920585724542 0.8736621141433716 0.986 0.986 0.986
|
122 |
+
120 07:22:37 2 0.0016 0.7521174660549974 0.8738390803337097 0.986 0.986 0.986
|
123 |
+
121 07:31:14 3 0.0016 0.7467978782361409 0.8738065958023071 0.9861 0.9861 0.9861
|
124 |
+
122 07:39:58 4 0.0016 0.7361560741404317 0.8747486472129822 0.9861 0.9861 0.9861
|
125 |
+
123 07:48:40 1 0.0008 0.7401143690831257 0.8742570877075195 0.986 0.986 0.986
|
126 |
+
124 07:57:08 2 0.0008 0.7347634346192737 0.8744410872459412 0.986 0.986 0.986
|
127 |
+
125 08:05:23 3 0.0008 0.7467471407044609 0.8747740387916565 0.986 0.986 0.986
|
128 |
+
126 08:13:42 0 0.0008 0.726040545162165 0.8744993805885315 0.986 0.986 0.986
|
129 |
+
127 08:22:38 1 0.0008 0.7422327684737602 0.8742579221725464 0.9861 0.9861 0.9861
|
130 |
+
128 08:31:00 2 0.0008 0.753200509531318 0.8744280338287354 0.9861 0.9861 0.9861
|
131 |
+
129 08:38:48 3 0.0008 0.7488863416044217 0.8747811913490295 0.986 0.986 0.986
|
132 |
+
130 08:47:02 4 0.0008 0.7427260273020222 0.8745757937431335 0.986 0.986 0.986
|
133 |
+
131 08:55:32 1 0.0004 0.7283043986109068 0.8750640153884888 0.9861 0.9861 0.9861
|
134 |
+
132 09:04:08 2 0.0004 0.7460261738469016 0.874792218208313 0.986 0.986 0.986
|
135 |
+
133 09:12:12 3 0.0004 0.7422142098984629 0.8739121556282043 0.986 0.986 0.986
|
136 |
+
134 09:20:21 4 0.0004 0.7333195368017791 0.8739151954650879 0.986 0.986 0.986
|
137 |
+
135 09:28:48 1 0.0002 0.7446140764906721 0.8738541007041931 0.986 0.986 0.986
|
138 |
+
136 09:36:52 2 0.0002 0.7396735451300189 0.8738033175468445 0.986 0.986 0.986
|
139 |
+
137 09:45:28 0 0.0002 0.722099937464831 0.8742627501487732 0.986 0.986 0.986
|
140 |
+
138 09:53:49 1 0.0002 0.7288362916966654 0.8744918704032898 0.986 0.986 0.986
|
141 |
+
139 10:02:27 2 0.0002 0.7390751829687154 0.8747418522834778 0.986 0.986 0.986
|
142 |
+
140 10:10:36 3 0.0002 0.7397080369602959 0.8742198944091797 0.986 0.986 0.986
|
143 |
+
141 10:18:53 4 0.0002 0.7296309486368917 0.8745017051696777 0.986 0.986 0.986
|
training.log
ADDED
The diff for this file is too large to render.
See raw diff
|
|