Issue Training Spancat with Transformers Component #10152
Description
Hi,
I generated a config for spancat data on prodigy. I tried to adapt the config to accommodate a transformers component using the guidance at https://spacy.io/usage/embeddings-transformers#transformers. When I run the debug data command, I receive "ValueError: Cannot get dimension 'nO' for model 'transformer-listener': value unset." Obviously the nO value is null by default, but I wasn't able to find a resource for how to adapt the spancat training pipeline to work with transformers, so I'd appreciate knowing any other modifications to the config that should make the transformers component compatible.
- spaCy version: 3.2.1
- Platform: Linux-4.14.252-131.483.amzn1.x86_64-x86_64-with-glibc2.9
- Python version: 3.6.13
My config and error messages are reproduced below.
[paths]
train = "./medical_span_classifier_binary/train.spacy"
dev = "./medical_span_classifier_binary/dev.spacy"
vectors = null
init_tok2vec = null
[system]
gpu_allocator = "pytorch"
seed = 0
[nlp]
lang = "en"
pipeline = ["spancat"]
batch_size = 64
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-transformers.TransformerListener.v1"
grad_factor = 1.0
pooling = {"@layers":"reduce_mean.v1"}
upstream = "*"
[components.spancat.suggester]
@misc = "spacy.ngram_range_suggester.v1"
min_size = 1
max_size = 13
[corpora]
[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null
[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
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 = 200
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.components.spancat]
[initialize.components.spancat.labels]
@readers = "spacy.read_labels.v1"
path = "medical_span_classifier_binary/labels/spancat.json"
require = false
[initialize.tokenizer]
Traceback (most recent call last):
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/spacy/__main__.py", line 4, in <module>
setup_cli()
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/spacy/cli/_util.py", line 71, in setup_cli
command(prog_name=COMMAND)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/click/core.py", line 829, in __call__
return self.main(*args, **kwargs)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/click/core.py", line 782, in main
rv = self.invoke(ctx)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/click/core.py", line 1066, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/click/core.py", line 610, in invoke
return callback(*args, **kwargs)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/typer/main.py", line 497, in wrapper
return callback(**use_params) # type: ignore
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/spacy/cli/debug_data.py", line 73, in debug_data_cli
silent=False,
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/spacy/cli/debug_data.py", line 107, in debug_data
nlp.initialize(lambda: train_corpus(nlp))
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/spacy/language.py", line 1305, in initialize
proc.initialize(get_examples, nlp=self, **p_settings)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/spacy/pipeline/spancat.py", line 417, in initialize
self.model.initialize(X=(docs, spans), Y=Y)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/model.py", line 299, in initialize
self.init(self, X=X, Y=Y)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/layers/chain.py", line 88, in init
layer.initialize(X=curr_input)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/model.py", line 299, in initialize
self.init(self, X=X, Y=Y)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/layers/with_getitem.py", line 44, in init
model.layers[0].initialize(X=X_i, Y=Y_i)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/model.py", line 299, in initialize
self.init(self, X=X, Y=Y)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/layers/chain.py", line 86, in init
layer.initialize(X=curr_input, Y=Y)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/model.py", line 299, in initialize
self.init(self, X=X, Y=Y)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/layers/chain.py", line 90, in init
curr_input = layer.predict(curr_input)
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/model.py", line 315, in predict
return self._func(self, X, is_train=False)[0]
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/spacy_transformers/layers/listener.py", line 61, in forward
width = model.get_dim("nO")
File "/home/ec2-user/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/thinc/model.py", line 175, in get_dim
raise ValueError(err)
ValueError: Cannot get dimension 'nO' for model 'transformer-listener': value unset