Hello, I would just like a confirmation.
When training my spancat in GPU mode, it crashes and I get an error message "cupy.cuda.Memory.OutOfMemoryError
I've been browsing the forums and the problem often comes from the size of the batch-size. So I set a batch_size to 1. And after that I get the error :
Is it because my training game contains long conversations (sometimes more than 20 minutes) and that I have to cut each conversation or it has nothing to do with that at all?
This is my command :
python3 -m prodigy train ./training_gpu --my_train_datas --eval-split 0.10 --lang "fr" --gpu-id 0 --label-stats --config ./training/conf.cfg
Here is my conf file:
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
gpu_allocator = null
seed = 0
[nlp]
lang = "fr"
pipeline = ["tok2vec","spancat"]
batch_size = 1
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
[components]
[components.spancat]
factory = "spancat"
max_positive = null
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
spans_key = "sc"
threshold = 0.5
[components.spancat.model]
@architectures = "spacy.SpanCategorizer.v1"
[components.spancat.model.reducer]
@layers = "spacy.mean_max_reducer.v1"
hidden_size = 128
[components.spancat.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = null
nI = null
[components.spancat.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"
[components.spancat.suggester]
@misc = "spacy.ngram_range_suggester.v1"
min_size = 1
max_size = 65
[components.tok2vec]
factory = "tok2vec"
[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"
[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 = false
[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 96
depth = 4
window_size = 1
maxout_pieces = 3
[corpora]
@readers = "prodigy.MergedCorpus.v1"
eval_split = 0.03
sample_size = 1.0
ner = null
textcat = null
textcat_multilabel = null
parser = null
tagger = null
senter = null
[corpora.spancat]
@readers = "prodigy.SpanCatCorpus.v1"
datasets = ["lettria_annotation_initiale"]
eval_datasets = []
spans_key = "sc"
[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 = 100
frozen_components = []
annotating_components = []
before_to_disk = 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]
spans_sc_f = 1.0
spans_sc_p = 0.0
spans_sc_r = 0.0
[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]