config.cfg

[paths]
train = "/Users/jamartin/matilda-oe-2026/data/combined/gold_plus_silver_balanced.spacy"
dev = "corpus_unified/spacy/dev.spacy"
vectors = "assets/vectors/doec_fold_synth"
raw_text = "assets/corpora/doec_fold_synth/pretrain.jsonl"
init_tok2vec = "runs/pretrain_doec_fold_synth/model19.bin"

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "en"
pipeline = ["tok2vec", "tagger", "morphologizer", "trainable_lemmatizer", "parser"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null

[corpora]

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 3200
max_epochs = 0
max_steps = 40000
eval_frequency = 200
frozen_components = []
annotating_components = []
before_to_disk = null
before_update = null

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

[components]

[pretraining]
max_epochs = 20
dropout = 0.2
n_save_every = null
n_save_epoch = null
component = "tok2vec"
layer = ""
corpus = "corpora.pretrain"

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

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

[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

[corpora.pretrain]
@readers = "spacy.JsonlCorpus.v1"
path = ${paths.raw_text}
min_length = 5
max_length = 500
limit = 0

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

[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 = 1e-08
learn_rate = 0.001

[training.score_weights]
tag_acc = 0.15
pos_acc = 0.15
tag_micro_p = null
tag_micro_r = null
tag_micro_f = null
morph_acc = 0.15
morph_per_feat = null
lemma_acc = 0.15
dep_uas = 0.1
dep_las = 0.2
dep_las_per_type = null
sents_p = null
sents_r = null
sents_f = 0.1

[initialize.components]

[initialize.tokenizer]

[components.tok2vec]
factory = "tok2vec"

[components.tagger]
factory = "tagger"
neg_prefix = "!"
overwrite = false
label_smoothing = 0.0

[components.morphologizer]
factory = "morphologizer"
extend = false
overwrite = true
label_smoothing = 0.0

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

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

[pretraining.batcher]
@batchers = "spacy.batch_by_words.v1"
size = 3000
discard_oversize = false
tolerance = 0.2
get_length = null

[pretraining.objective]
@architectures = "spacy.PretrainCharacters.v1"
maxout_pieces = 3
hidden_size = 300
n_characters = 4

[pretraining.optimizer]
@optimizers = "Adam.v1"
beta1 = 0.9
beta2 = 0.999
L2_is_weight_decay = true
L2 = 0.01
grad_clip = 1.0
use_averages = true
eps = 1e-08
learn_rate = 0.001

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

[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"

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

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

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

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

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

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

[components.parser.model]
@architectures = "spacy.TransitionBasedParser.v2"
state_type = "parser"
extra_state_tokens = false
hidden_width = 128
maxout_pieces = 3
use_upper = true
nO = null

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

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

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
depth = 8
window_size = 1
maxout_pieces = 3

[components.tagger.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"

[components.morphologizer.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"

[components.trainable_lemmatizer.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"

[components.parser.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"