Update custom_ner_model29+23git including iteration_data.json

machine-learn/custom_ner_model29+23git/config.cfg

@@ -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]

machine-learn/custom_ner_model29+23git/iteration_data.json

@@ -0,0 +1,137 @@
+{
+  "0": {
+    "ner": 5484.815419910544
+  },
+  "1": {
+    "ner": 4061.5594986048127
+  },
+  "2": {
+    "ner": 3520.311618876494
+  },
+  "3": {
+    "ner": 3066.540119213855
+  },
+  "4": {
+    "ner": 2816.9802054431316
+  },
+  "5": {
+    "ner": 2577.5899541594054
+  },
+  "6": {
+    "ner": 2394.6483108831953
+  },
+  "7": {
+    "ner": 2183.958616338036
+  },
+  "8": {
+    "ner": 2095.5018199014057
+  },
+  "9": {
+    "ner": 2030.003688368699
+  },
+  "10": {
+    "ner": 1831.3214491433941
+  },
+  "11": {
+    "ner": 1824.4250713130543
+  },
+  "12": {
+    "ner": 1639.6365791448866
+  },
+  "13": {
+    "ner": 1687.973438248313
+  },
+  "14": {
+    "ner": 1544.036731916184
+  },
+  "15": {
+    "ner": 1465.4052241359173
+  },
+  "16": {
+    "ner": 1429.866118074566
+  },
+  "17": {
+    "ner": 1479.5187474263882
+  },
+  "18": {
+    "ner": 1393.2753708683979
+  },
+  "19": {
+    "ner": 1324.5225238006356
+  },
+  "20": {
+    "ner": 1282.0719241405684
+  },
+  "21": {
+    "ner": 1251.7200750361592
+  },
+  "22": {
+    "ner": 1199.7855886442971
+  },
+  "23": {
+    "ner": 1230.131443838447
+  },
+  "24": {
+    "ner": 1170.898725174042
+  },
+  "25": {
+    "ner": 1138.5827790192063
+  },
+  "26": {
+    "ner": 1140.2765419732962
+  },
+  "27": {
+    "ner": 1117.605643857973
+  },
+  "28": {
+    "ner": 1101.5327979249448
+  },
+  "29": {
+    "ner": 1072.423757627589
+  },
+  "30": {
+    "ner": 1052.236232151256
+  },
+  "31": {
+    "ner": 1007.7708340441367
+  },
+  "32": {
+    "ner": 1042.7775605390434
+  },
+  "33": {
+    "ner": 1018.2000822361591
+  },
+  "34": {
+    "ner": 978.4730503899373
+  },
+  "35": {
+    "ner": 970.7060047189916
+  },
+  "36": {
+    "ner": 978.1619547070326
+  },
+  "37": {
+    "ner": 931.3444447387258
+  },
+  "38": {
+    "ner": 891.2886472328244
+  },
+  "39": {
+    "ner": 843.175660477352
+  },
+  "40": {
+    "ner": 891.6552256734897
+  },
+  "41": {
+    "ner": 870.9881989732969
+  },
+  "42": {
+    "ner": 907.5495785041613
+  },
+  "43": {
+    "ner": 907.2868393560917
+  },
+  "44": {
+    "ner": 889.2378362529386
+  }
+}

machine-learn/custom_ner_model29+23git/meta.json

@@ -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"
+  ]
+}

machine-learn/custom_ner_model29+23git/ner/cfg

@@ -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
+}

machine-learn/custom_ner_model29+23git/ner/moves

@@ -0,0 +1 @@
+��moves�`{"0":{},"1":{"SINGER":-1},"2":{"SINGER":-1},"3":{"SINGER":-1},"4":{"":1,"SINGER":-1},"5":{"":1}}�cfg��neg_key�

machine-learn/custom_ner_model29+23git/vocab/key2row

@@ -0,0 +1 @@
+�

machine-learn/custom_ner_model29+23git/vocab/lookups.bin

@@ -0,0 +1 @@
+�