Apple M2 RuntimeError: Placeholder storage has not been allocated on MPS device

Question

I am running this basic training example on an Apple M2 Pro. I am using Python 3.11, sentence-transformers 3.0.1, accelerate 0.32.1 and torch 2.3.1.

from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, SentenceTransformerTrainingArguments, losses
from datasets import Dataset

path = "/Users/austin/Documents/Career/huggingface"
model_directory = path + "/hub/all-mpnet-base-v2"

model = SentenceTransformer(model_directory)
train_dataset = Dataset.from_dict({
    "anchor": ["It's nice weather outside today.", "He drove to work."],
    "positive": ["It's so sunny.", "He took the car to the office."],
    "negative": ["It's quite rainy, sadly.", "She walked to the store."],
})

loss = losses.TripletLoss(model=model)

args = SentenceTransformerTrainingArguments(
    output_dir="test_trainer",
    use_mps_device=True,
)

trainer = SentenceTransformerTrainer(
    model=model,
    args=args,
    train_dataset=train_dataset,
    loss=loss,
)
trainer.train()

error: Traceback (most recent call last): File "/Users/austin/Documents/Career/github/sentence-transformers/examples/training/sts/training_test.py", line 27, in trainer.train() File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/transformers/trainer.py", line 1932, in train return inner_training_loop( ^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/transformers/trainer.py", line 2268, in _inner_training_loop tr_loss_step = self.training_step(model, inputs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/transformers/trainer.py", line 3307, in training_step loss = self.compute_loss(model, inputs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/austin/Documents/Career/github/sentence-transformers/sentence_transformers/trainer.py", line 329, in compute_loss loss = loss_fn(features, labels) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/austin/Documents/Career/github/sentence-transformers/sentence_transformers/losses/TripletLoss.py", line 79, in forward reps = [self.model(sentence_feature)["sentence_embedding"] for sentence_feature in sentence_features] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/austin/Documents/Career/github/sentence-transformers/sentence_transformers/losses/TripletLoss.py", line 79, in reps = [self.model(sentence_feature)["sentence_embedding"] for sentence_feature in sentence_features] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/container.py", line 217, in forward input = module(input) ^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/austin/Documents/Career/github/sentence-transformers/sentence_transformers/models/Transformer.py", line 118, in forward output_states = self.auto_model(**trans_features, return_dict=False) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/transformers/models/mpnet/modeling_mpnet.py", line 543, in forward embedding_output = self.embeddings(input_ids=input_ids, position_ids=position_ids, inputs_embeds=inputs_embeds) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/transformers/models/mpnet/modeling_mpnet.py", line 101, in forward inputs_embeds = self.word_embeddings(input_ids) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/modules/sparse.py", line 163, in forward return F.embedding( ^^^^^^^^^^^^ File "/opt/anaconda3/envs/py311/lib/python3.11/site-packages/torch/nn/functional.py", line 2264, in embedding return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Placeholder storage has not been allocated on MPS device!

---

And I try print my device info :

import torch
if torch.backends.mps.is_available():
    mps_device = torch.device("mps")
    x = torch.ones(1, device=mps_device)
    print (x)
else:
    print ("MPS device not found.")

tensor([1.], device='mps:0')

Answer 1

training_args = TrainingArguments(
    no_cuda=True,  # 
)

adding this works for me, this indicates Use CPU since MPS may have compatibility issues.