RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn #17
Description
After running the script for finetuning on cmu mosei sentiment analysis dataset, the following error pops out
88.6 M Trainable params
0 Non-trainable params
88.6 M Total params
354.447 Total estimated model params size (MB)
ERROR - TVLT - Failed after 0:00:59!
Traceback (most recent calls WITHOUT sacred internals):
File "/home/ankan-pg/TVLT/run.py", line 68, in main
trainer.fit(model, datamodule=dm)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 770, in fit
self._call_and_handle_interrupt(
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 721, in _call_and_handle_interrupt
return self.strategy.launcher.launch(trainer_fn, *args, trainer=self, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/strategies/launchers/subprocess_script.py", line 93, in launch
return function(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 811, in _fit_impl
results = self._run(model, ckpt_path=self.ckpt_path)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1236, in _run
results = self._run_stage()
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1323, in _run_stage
return self._run_train()
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1353, in _run_train
self.fit_loop.run()
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/base.py", line 204, in run
self.advance(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/fit_loop.py", line 266, in advance
self._outputs = self.epoch_loop.run(self._data_fetcher)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/base.py", line 204, in run
self.advance(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/epoch/training_epoch_loop.py", line 208, in advance
batch_output = self.batch_loop.run(batch, batch_idx)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/base.py", line 204, in run
self.advance(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/batch/training_batch_loop.py", line 88, in advance
outputs = self.optimizer_loop.run(split_batch, optimizers, batch_idx)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/base.py", line 204, in run
self.advance(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 203, in advance
result = self._run_optimization(
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 256, in _run_optimization
self._optimizer_step(optimizer, opt_idx, batch_idx, closure)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 369, in _optimizer_step
self.trainer._call_lightning_module_hook(
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1595, in _call_lightning_module_hook
output = fn(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/core/lightning.py", line 1646, in optimizer_step
optimizer.step(closure=optimizer_closure)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/core/optimizer.py", line 168, in step
step_output = self._strategy.optimizer_step(self._optimizer, self._optimizer_idx, closure, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/strategies/ddp.py", line 286, in optimizer_step
optimizer_output = super().optimizer_step(optimizer, opt_idx, closure, model, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/strategies/strategy.py", line 193, in optimizer_step
return self.precision_plugin.optimizer_step(model, optimizer, opt_idx, closure, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 155, in optimizer_step
return optimizer.step(closure=closure, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/torch/optim/lr_scheduler.py", line 68, in wrapper
return wrapped(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/torch/optim/optimizer.py", line 373, in wrapper
out = func(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/transformers/optimization.py", line 439, in step
loss = closure()
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 140, in _wrap_closure
closure_result = closure()
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 148, in call
self._result = self.closure(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 143, in closure
self._backward_fn(step_output.closure_loss)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/loops/optimization/optimizer_loop.py", line 311, in backward_fn
self.trainer._call_strategy_hook("backward", loss, optimizer, opt_idx)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/trainer/trainer.py", line 1765, in _call_strategy_hook
output = fn(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/strategies/strategy.py", line 168, in backward
self.precision_plugin.backward(self.lightning_module, closure_loss, *args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/plugins/precision/precision_plugin.py", line 80, in backward
model.backward(closure_loss, optimizer, *args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/pytorch_lightning/core/lightning.py", line 1391, in backward
loss.backward(*args, **kwargs)
File "/home/ankan-pg/.local/lib/python3.10/site-packages/torch/_tensor.py", line 492, in backward
torch.autograd.backward(
File "/home/ankan-pg/.local/lib/python3.10/site-packages/torch/autograd/init.py", line 251, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
Ru
ntimeError: element 0 of tensors does not require grad and does not have a grad_fn
any suggestions to resolve the same? @zinengtang