Skip to content

Commit

Permalink
Update custom_ner_model26-2git including iteration_data.json
Browse files Browse the repository at this point in the history
  • Loading branch information
actions-user committed Sep 4, 2024
1 parent feffb39 commit e69836e
Show file tree
Hide file tree
Showing 12 changed files with 737 additions and 0 deletions.
130 changes: 130 additions & 0 deletions machine-learn/custom_ner_model26-2git/config.cfg
Original file line number Diff line number Diff line change
@@ -0,0 +1,130 @@
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null

[system]
seed = 0
gpu_allocator = null

[nlp]
lang = "he"
pipeline = ["ner"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 1000
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
vectors = {"@vectors":"spacy.Vectors.v1"}

[components]

[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100

[components.ner.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "ner"
extra_state_tokens = false
hidden_width = 64
maxout_pieces = 2
use_upper = true
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy.HashEmbedCNN.v2"
pretrained_vectors = null
width = 96
depth = 4
embed_size = 2000
window_size = 1
maxout_pieces = 3
subword_features = true

[corpora]

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
gold_preproc = false
max_length = 0
limit = 0
augmenter = null

[training]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
before_update = null

[training.batcher]
@batchers = "spacy.batch_by_words.v1"
discard_oversize = false
tolerance = 0.2
get_length = null

[training.batcher.size]
@schedules = "compounding.v1"
start = 100
stop = 1000
compound = 1.001
t = 0.0

[training.logger]
@loggers = "spacy.ConsoleLogger.v1"
progress_bar = false

[training.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = false
eps = 0.00000001
learn_rate = 0.001

[training.score_weights]
ents_f = 1.0
ents_p = 0.0
ents_r = 0.0
ents_per_type = null

[pretraining]

[initialize]
vectors = ${paths.vectors}
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.tokenizer]
191 changes: 191 additions & 0 deletions machine-learn/custom_ner_model26-2git/iteration_data.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,191 @@
{
"0": {
"ner": 12829.268936021599
},
"1": {
"ner": 5288.61154107945
},
"2": {
"ner": 4010.279001060649
},
"3": {
"ner": 3342.6077484852967
},
"4": {
"ner": 2779.44430093708
},
"5": {
"ner": 2417.017281319538
},
"6": {
"ner": 2145.370857243011
},
"7": {
"ner": 1945.3069024951578
},
"8": {
"ner": 1786.6124535732579
},
"9": {
"ner": 1592.722500299328
},
"10": {
"ner": 1458.6055029937122
},
"11": {
"ner": 1412.628290276284
},
"12": {
"ner": 1270.1784596940765
},
"13": {
"ner": 1233.4871364434712
},
"14": {
"ner": 1170.6039487503945
},
"15": {
"ner": 1085.6399518454257
},
"16": {
"ner": 981.9086165212015
},
"17": {
"ner": 1006.103503299482
},
"18": {
"ner": 922.6093019341196
},
"19": {
"ner": 831.9595955031491
},
"20": {
"ner": 874.0157920350324
},
"21": {
"ner": 793.1060643759754
},
"22": {
"ner": 767.9707171256962
},
"23": {
"ner": 726.3477556222558
},
"24": {
"ner": 732.0792036476424
},
"25": {
"ner": 753.0026134637139
},
"26": {
"ner": 743.6070205710976
},
"27": {
"ner": 692.0272432851326
},
"28": {
"ner": 599.5374451201415
},
"29": {
"ner": 656.8815858371446
},
"30": {
"ner": 619.6258139519923
},
"31": {
"ner": 584.9650389681061
},
"32": {
"ner": 611.4069361581223
},
"33": {
"ner": 601.0637330348058
},
"34": {
"ner": 579.2538403866164
},
"35": {
"ner": 542.7123493300741
},
"36": {
"ner": 530.2375180049286
},
"37": {
"ner": 502.59026285137475
},
"38": {
"ner": 489.6553235067264
},
"39": {
"ner": 522.4335603848879
},
"40": {
"ner": 464.4122316053967
},
"41": {
"ner": 495.7066176457358
},
"42": {
"ner": 415.38148953345876
},
"43": {
"ner": 454.17124849658285
},
"44": {
"ner": 471.62500761005685
},
"45": {
"ner": 461.8187350828204
},
"46": {
"ner": 403.8885279210463
},
"47": {
"ner": 448.94709746042054
},
"48": {
"ner": 437.70217616621176
},
"49": {
"ner": 445.5640186682623
},
"50": {
"ner": 381.22090856852344
},
"51": {
"ner": 441.0620033268054
},
"52": {
"ner": 371.07393265048785
},
"53": {
"ner": 372.9061112657521
},
"54": {
"ner": 335.365082073529
},
"55": {
"ner": 407.3718583103276
},
"56": {
"ner": 397.1070403724761
},
"57": {
"ner": 328.1406121531826
},
"58": {
"ner": 400.6574210714674
},
"59": {
"ner": 330.8792310809734
},
"60": {
"ner": 338.7823423585593
},
"61": {
"ner": 362.6620669327486
},
"62": {
"ner": 347.2972889202144
}
}
40 changes: 40 additions & 0 deletions machine-learn/custom_ner_model26-2git/meta.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
{
"lang":"he",
"name":"singer_ner_he",
"version":"0.0.0",
"spacy_version":">=3.7.5,<3.8.0",
"description":"Model for recognizing singer names in Hebrew song titles",
"author":"nhlocal",
"email":"[email protected]",
"url":"",
"license":"MIT",
"spacy_git_version":"a6d0fc360",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null,
"mode":"default"
},
"labels":{
"ner":[
"SINGER"
]
},
"pipeline":[
"ner"
],
"components":[
"ner"
],
"disabled":[

],
"tags":[
"NER",
"Hebrew",
"Singer",
"Named Entity Recognition",
"Text Classification"
]
}
13 changes: 13 additions & 0 deletions machine-learn/custom_ner_model26-2git/ner/cfg
Original file line number Diff line number Diff line change
@@ -0,0 +1,13 @@
{
"moves":null,
"update_with_oracle_cut_size":100,
"multitasks":[

],
"min_action_freq":1,
"learn_tokens":false,
"beam_width":1,
"beam_density":0.0,
"beam_update_prob":0.0,
"incorrect_spans_key":null
}
Binary file added machine-learn/custom_ner_model26-2git/ner/model
Binary file not shown.
1 change: 1 addition & 0 deletions machine-learn/custom_ner_model26-2git/ner/moves
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
��moves�`{"0":{},"1":{"SINGER":-1},"2":{"SINGER":-1},"3":{"SINGER":-1},"4":{"":1,"SINGER":-1},"5":{"":1}}�cfg��neg_key�
3 changes: 3 additions & 0 deletions machine-learn/custom_ner_model26-2git/tokenizer

Large diffs are not rendered by default.

1 change: 1 addition & 0 deletions machine-learn/custom_ner_model26-2git/vocab/key2row
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
1 change: 1 addition & 0 deletions machine-learn/custom_ner_model26-2git/vocab/lookups.bin
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Loading

0 comments on commit e69836e

Please sign in to comment.