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

[system]
seed = 342
gpu_allocator = null

[nlp]
lang = "en"
pipeline = ["tok2vec", "relation_extractor"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
#tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
batch_size = 64

[components]

[components.tok2vec]
source = "./chemrelmodels/rel/tok2vec"
component = "tok2vec"


[components.relation_extractor]
source = "./chemrelmodels/rel/tok2vec"
component = "relation_extractor"
[initialize]

[initialize.components]

[corpora]

[corpora.dev]
@readers = "Gold_ents_Corpus.v1"
file = ${paths.dev}

[corpora.train]
@readers = "Gold_ents_Corpus.v1"
file = ${paths.train}

[training]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.3
accumulate_gradient = 1
patience = 160000000
max_epochs = 0
max_steps = 10000000
eval_frequency = 10
frozen_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
logger = {"@loggers":"spacy.ConsoleLogger.v1"}

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

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

[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 = 0.0005

[training.score_weights]
rel_micro_p = 0.0
rel_micro_r = 0.0
rel_micro_f = 1.0