Error while training ner and re simultaneously: (ValueError: operands could not be broadcast together with shapes)

[TarkanKaracay]

Hello,
I'm trying to train named entity recognition and relation extractor same time with transformers.

This is my config file. Is there anything wrong or missing?

[paths]
train = "/content/drive/MyDrive/sil/trouCY_relations_training.spacy"
dev = "/content/drive/MyDrive/sil/trouCY_relations_dev.spacy"
vectors = null
init_tok2vec = null

[system]
gpu_allocator = "pytorch"
seed = 0

[nlp]
lang = "en"
pipeline = ["transformer","ner", "relation_extractor"]
tokenizer = {"@Tokenizers":"spacy.Tokenizer.v1"}
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 128

[components]

[components.ner]
factory = "ner"
incorrect_spans_key = null
moves = null
scorer = {"@scorers":"spacy.ner_scorer.v1"}
update_with_oracle_cut_size = 100

[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.Tok2VecTransformer.v3"
name = "dmis-lab/biobert-base-cased-v1.2"
mixed_precision = false
pooling = {"@layers":"reduce_mean.v1"}
grad_factor = 1.0

[components.ner.model.tok2vec.get_spans]
@span_getters = "spacy-transformers.strided_spans.v1"
window = 128
stride = 96

[components.ner.model.tok2vec.grad_scaler_config]

[components.ner.model.tok2vec.tokenizer_config]
use_fast = true

[components.ner.model.tok2vec.transformer_config]

[components.transformer]
factory = "transformer"
max_batch_items = 4096
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}

[components.transformer.model]
@architectures = "spacy-transformers.TransformerModel.v3"
name = "dmis-lab/biobert-base-cased-v1.2"
mixed_precision = false

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

[components.transformer.model.grad_scaler_config]

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

[components.transformer.model.transformer_config]

[components.relation_extractor]
factory = "relation_extractor"
threshold = 0.5

[components.relation_extractor.model]
@architectures = "rel_model.v1"

[components.relation_extractor.model.create_instance_tensor]
@architectures = "rel_instance_tensor.v1"

[components.relation_extractor.model.create_instance_tensor.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0

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

[components.relation_extractor.model.create_instance_tensor.pooling]
@layers = "reduce_mean.v1"

[components.relation_extractor.model.create_instance_tensor.get_instances]
@misc = "rel_instance_generator.v1"
max_length = 10

[components.relation_extractor.model.classification_layer]
@architectures = "rel_classification_layer.v1"
nI = null
nO = null

[corpora]

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 0

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0

[training]
seed = ${system.seed}
gpu_allocator = ${system.gpu_allocator}
dropout = 0.1
accumulate_gradient = 1
patience = 1600000
max_epochs = 0
max_steps = 1000
eval_frequency = 10
frozen_components = []
annotating_components = ["ner"]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
logger = {"@Loggers":"spacy.ConsoleLogger.v1"}

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

[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

[training.optimizer.learn_rate]
@schedules = "warmup_linear.v1"
warmup_steps = 250
total_steps = 20000
initial_rate = 5e-5

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

[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]

My custom_functions.py file is simply a copy-paste of the contents of rel_pipe.py and rel_model.py.
When I use this code I get an error:

!python -m spacy train -g 0 /content/drive/MyDrive/sil/config_spacy.cfg --output /content/drive/MyDrive/sil/ -c /content/drive/MyDrive/sil/custom_functions.py

ERROR

2023-11-21 11:53:00.118526: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2023-11-21 11:53:00.118582: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2023-11-21 11:53:00.118612: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2023-11-21 11:53:01.244493: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
ℹ Saving to output directory: /content/drive/MyDrive/sil
ℹ Using GPU: 0

=========================== Initializing pipeline ===========================
✔ Initialized pipeline

============================= Training pipeline =============================
ℹ Pipeline: ['transformer', 'ner', 'relation_extractor']
ℹ Set annotations on update for: ['ner']
ℹ Initial learn rate: 0.0
E # LOSS TRANS... LOSS NER LOSS RELAT... ENTS_F ENTS_P ENTS_R REL_MICRO_P REL_MICRO_R REL_MICRO_F SCORE

---

⚠ Aborting and saving the final best model. Encountered exception:
ValueError('operands could not be broadcast together with shapes (25750, 5)
(498, 5)')
Traceback (most recent call last):
File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/usr/lib/python3.10/runpy.py", line 86, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.10/dist-packages/spacy/main.py", line 4, in
setup_cli()
File "/usr/local/lib/python3.10/dist-packages/spacy/cli/_util.py", line 87, in setup_cli
command(prog_name=COMMAND)
File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1157, in call
return self.main(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/typer/core.py", line 778, in main
return _main(
File "/usr/local/lib/python3.10/dist-packages/typer/core.py", line 216, in _main
rv = self.invoke(ctx)
File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1688, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1434, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 783, in invoke
return __callback(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/typer/main.py", line 683, in wrapper
return callback(**use_params) # type: ignore
File "/usr/local/lib/python3.10/dist-packages/spacy/cli/train.py", line 54, in train_cli
train(config_path, output_path, use_gpu=use_gpu, overrides=overrides)
File "/usr/local/lib/python3.10/dist-packages/spacy/cli/train.py", line 84, in train
train_nlp(nlp, output_path, use_gpu=use_gpu, stdout=sys.stdout, stderr=sys.stderr)
File "/usr/local/lib/python3.10/dist-packages/spacy/training/loop.py", line 135, in train
raise e
File "/usr/local/lib/python3.10/dist-packages/spacy/training/loop.py", line 118, in train
for batch, info, is_best_checkpoint in training_step_iterator:
File "/usr/local/lib/python3.10/dist-packages/spacy/training/loop.py", line 220, in train_while_improving
nlp.update(
File "/usr/local/lib/python3.10/dist-packages/spacy/language.py", line 1193, in update
proc.update(examples, sgd=None, losses=losses, **component_cfg[name]) # type: ignore
File "/content/drive/MyDrive/sil/custom_functions.py", line 133, in update
loss, gradient = self.get_loss(examples, predictions)
File "/content/drive/MyDrive/sil/custom_functions.py", line 146, in get_loss
gradient = scores - truths
File "cupy/_core/core.pyx", line 1271, in cupy._core.core._ndarray_base.sub
File "cupy/_core/_kernel.pyx", line 1251, in cupy._core._kernel.ufunc.call
File "cupy/_core/internal.pyx", line 382, in cupy._core.internal._broadcast_core
ValueError: operands could not be broadcast together with shapes (25750, 5) (498, 5)

Do you have any ideas to solve the problem?

[rmitsch]

Hi @TarkanKaracay, does training only NER without REL work?

[TarkanKaracay]

Yes. I trained NER without REL. It perfectly worked.