# fa_core_news_trf: the whole pipeline on one fine-tuned ParsBERT encoder.
#
# Differences from the sm/md/lg tiers, all forced by the transformer:
#
#   * One corpus, not two. sm/md/lg train `ner` separately (own embedded tok2vec) and source
#     it into the dep model. Fine-tuning a 162M-parameter encoder twice would double GPU cost
#     and ship two encoders in one wheel, and the second would collide on the `transformer`
#     component name. So every component listens to a single shared transformer and trains
#     against corpus/joint/, built by scripts/merge_joint_corpus.py (UD layer + the
#     difflib-transferred NER layer on identical tokenization).
#   * `use_upper = false` on both transition-based parsers: with a transformer upstream the
#     extra maxout layer is redundant, and this matches the upstream *_trf configs.
#   * Adam + warmup_linear and accumulate_gradient=3, not the flat 0.001 the CPU tiers use.
#     Fine-tuning a pretrained encoder at 1e-3 diverges.
#   * gpu_allocator = "pytorch" so thinc and torch share one CUDA memory pool.
#
# Encoder: HooshvareLab/bert-base-parsbert-uncased. NOTE the licence caveat in
# docs/MODELS.md §3.4 - ParsBERT's model card carries no licence statement, so this wheel is
# NOT redistributable on those grounds; HooshvareLab/roberta-fa-zwnj-base (Apache-2.0) is the
# publishable alternative and drops in by changing `name` below.

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

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "fa"
pipeline = ["transformer","tagger","morphologizer","trainable_lemmatizer","parser","ner"]
batch_size = 128
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.transformer]
factory = "transformer"
max_batch_items = 4096

[components.transformer.set_extra_annotations]
@annotation_setters = "spacy-transformers.null_annotation_setter.v1"

[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "HooshvareLab/bert-base-parsbert-uncased"
mixed_precision = false

[components.transformer.model.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96

[components.transformer.model.tokenizer_config]
use_fast = true

[components.transformer.model.transformer_config]

[components.transformer.model.grad_scaler_config]

[components.tagger]
factory = "tagger"
label_smoothing = 0.05
overwrite = false
neg_prefix = "!"

[components.tagger.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false

[components.tagger.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
upstream = "*"

[components.tagger.model.tok2vec.pooling]
@layers = "reduce_mean.v1"

[components.tagger.scorer]
@scorers = "spacy.tagger_scorer.v1"

[components.morphologizer]
factory = "morphologizer"
label_smoothing = 0.05
overwrite = true
extend = false

[components.morphologizer.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false

[components.morphologizer.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
upstream = "*"

[components.morphologizer.model.tok2vec.pooling]
@layers = "reduce_mean.v1"

[components.morphologizer.scorer]
@scorers = "spacy.morphologizer_scorer.v1"

[components.trainable_lemmatizer]
factory = "trainable_lemmatizer"
backoff = "orth"
min_tree_freq = 3
overwrite = false
top_k = 1

[components.trainable_lemmatizer.model]
@architectures = "spacy.Tagger.v2"
nO = null
normalize = false

[components.trainable_lemmatizer.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
upstream = "*"

[components.trainable_lemmatizer.model.tok2vec.pooling]
@layers = "reduce_mean.v1"

[components.trainable_lemmatizer.scorer]
@scorers = "spacy.lemmatizer_scorer.v1"

[components.parser]
factory = "parser"
moves = null
update_with_oracle_cut_size = 100
learn_tokens = false
min_action_freq = 30

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

[components.parser.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
upstream = "*"

[components.parser.model.tok2vec.pooling]
@layers = "reduce_mean.v1"

[components.parser.scorer]
@scorers = "spacy.parser_scorer.v1"

[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 = false
nO = null

[components.ner.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
upstream = "*"

[components.ner.model.tok2vec.pooling]
@layers = "reduce_mean.v1"

[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 = 3
# 3000 steps is ~40 epochs over this 445k-token corpus, measured at ~29 steps/min on a T4
# (~1.8h). The CPU tiers' 20000/1600 would be ~270 epochs and ~12h here, and worse than
# wasteful: warmup_linear anneals against `total_steps`, so a run stopped early by patience
# never leaves the peak learning rate. Budget and schedule are kept equal on purpose:
# training.optimizer.learn_rate.total_steps must track any change to max_steps.
patience = 600
max_epochs = 0
max_steps = 3000
eval_frequency = 100
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

[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 3000
initial_rate = 5e-5

[training.batcher]
@batchers = "spacy.batch_by_padded.v1"
discard_oversize = true
size = 2000
buffer = 256
get_length = null

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

[training.score_weights]
tag_acc = 0.16
pos_acc = 0.08
tag_micro_p = null
tag_micro_r = null
tag_micro_f = null
morph_acc = 0.08
morph_per_feat = null
lemma_acc = 0.16
dep_uas = 0.08
dep_las = 0.16
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = 0.0
ents_f = 0.28
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]