Resuming training fails with CUDA out of memory error

Hi There,

I am using my university’s HPC cluster and there is a time limit per job. So I ran the train method of the Trainer class with resume_from_checkpoint=MODEL and resumed the training. The following is the code for resuming. To prevent CUDA out of memory errors, we set param.requires_grad = False in the model as before resuming.

training_args = TrainingArguments(
    logging_steps=500,
    save_steps=500,
    eval_steps=500,
    output_dir='/home/groups/group_a/yuspqr/result/'+NAME+'.global',
    num_train_epochs=3,              # total # of training epochs
    adam_epsilon=1e-6,
    per_device_train_batch_size=REAL_BS,  # batch size per device during training
    per_device_eval_batch_size=REAL_BS,   # batch size for evaluation
    warmup_steps=500,                # number of warmup steps for learning rate scheduler
    weight_decay=0.01,               # strength of weight decay
    gradient_accumulation_steps=ACCUM_NUM, # directory for storing logs
    #gradient_checkpointing=True,
    dataloader_num_workers=4,
    fp16=True,
    learning_rate=RL,
    do_train=True,
    do_eval=True,
    logging_dir='/home/users/yuspqr/runs/'+NAME+'/',
    report_to='tensorboard',
    evaluation_strategy='steps',
    logging_strategy='steps',
    save_strategy='steps',
)

import glob
def latest_checkpoint(path):
    cl=glob.glob(path)
    max_digit=max([len(i) for i in cl])
    return max([i for i in cl if len(i)==max_digit])

MODEL=latest_checkpoint('/home/groups/group_a/yuspqr/result/'+NAME+'.global/*')
model = RobertaLongForSequenceClassification.from_pretrained(MODEL)

for param in model.roberta.embeddings.parameters():
    param.requires_grad = False
for layer in model.roberta.encoder.layer[:8]:
    for param in layer.parameters():
        param.requires_grad = False 

trainer = Trainer(
    model=model,                         # the instantiated 🤗 Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_dataset,         # training dataset
    eval_dataset=val_dataset,            # evaluation dataset
)
trainer.train(resume_from_checkpoint=MODEL)

Here I got the following error. This happened after skipping the first batches.

Traceback (most recent call last):
  File "longformer_processing_final2.py", line 209, in <module>
    trainer.train(resume_from_checkpoint=MODEL)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/trainer.py", line 1332, in train
    tr_loss_step = self.training_step(model, inputs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/trainer.py", line 1891, in training_step
    loss = self.compute_loss(model, inputs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/trainer.py", line 1923, in compute_loss
    outputs = model(**inputs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/models/roberta/modeling_roberta.py", line 1212, in forward
    return_dict=return_dict,
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/models/roberta/modeling_roberta.py", line 861, in forward
    return_dict=return_dict,
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/models/roberta/modeling_roberta.py", line 533, in forward
    output_attentions,
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/models/roberta/modeling_roberta.py", line 417, in forward
    past_key_value=self_attn_past_key_value,
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/models/roberta/modeling_roberta.py", line 346, in forward
    output_attentions,
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "longformer_processing_final2.py", line 132, in forward
    output_attentions=output_attentions)
  File "/home/users/yuspqr/.local/lib/python3.6/site-packages/transformers/models/longformer/modeling_longformer.py", line 632, in forward
    attn_probs = torch.masked_fill(attn_probs, is_index_masked[:, :, None, None], 0.0)
RuntimeError: CUDA out of memory. Tried to allocate 1.84 GiB (GPU 0; 31.75 GiB total capacity; 29.37 GiB already allocated; 616.19 MiB free; 29.95 GiB reserved in total by PyTorch)
  0%|          | 0/21072 [01:04<?, ?it/s]

Considering that the training before the resumption was run with the same Tesla V100 32G single GPU for the full time limit, it seems strange that the CUDA out of memory would occur upon resumption.
I am very troubled that I cannot continue my research at this point. Your help would be greatly appreciated.