# fa_ent_news_sm — Persian NER, CPU size (sm).
#
# Standalone package, built by `spacy project run ner`, sitting alongside (not inside)
# fa_dep_news_sm. Trained on the PerDT treebank's own NER layer (CC BY-SA 4.0, edited
# prose), transferred onto this project's tokenization by scripts/transfer_perdt_ner.py.
# Scores ENTS_F 71.87 on the PerDT test split; see docs/MODELS.md §3.2 for the corpus
# survey (ParsTwiNER, ARMAN, PEYMA and others were considered and rejected on licence or
# genre grounds).
#
# Deliberate deviation from `spacy init config --pipeline ner`: the tok2vec is
# EMBEDDED inside components.ner.model instead of being a separate `tok2vec`
# component with a Tok2VecListener. A listener can only resolve inside the pipeline
# it was trained in; embedding makes the component self-contained and therefore
# sourceable into another pipeline via `nlp.add_pipe("ner", source=...)`. This is the same
# design as en_core_web_sm, whose `ner` "has its own independent internal tok2vec"
# (https://spacy.io/models#design). `assemble-core` in project.yml uses exactly that to
# source this component into fa_core_news_sm alongside the dep pipeline.

[paths]
train = null
dev = null
vectors = null
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "fa"
pipeline = ["ner"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null

[nlp.tokenizer]
@tokenizers = "spacy.Tokenizer.v1"

[nlp.vectors]
@vectors = "spacy.Vectors.v1"

[components]

[components.ner]
factory = "ner"
moves = null
update_with_oracle_cut_size = 100
incorrect_spans_key = null

[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.Tok2Vec.v2"

[components.ner.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = ${components.ner.model.tok2vec.encode.width}
attrs = ["NORM", "PREFIX", "SUFFIX", "SHAPE"]
rows = [5000, 1000, 2500, 2500]
include_static_vectors = false

[components.ner.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3

[components.ner.scorer]
@scorers = "spacy.ner_scorer.v1"

[corpora]

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

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

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600
max_epochs = 0
max_steps = 20000
eval_frequency = 400
frozen_components = []
annotating_components = []
before_to_disk = null
before_update = null

[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 = 1e-08
learn_rate = 0.001

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

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

[initialize.tokenizer]

[initialize.components]

[pretraining]