But now I get the index error
11 data_collator=default_data_collator,
12 )
—> 13 trainer.train()
/opt/conda/lib/python3.7/site-packages/transformers/trainer.py in train(self, resume_from_checkpoint, trial, ignore_keys_for_eval, **kwargs)
1315 tr_loss_step = self.training_step(model, inputs)
1316 else:
→ 1317 tr_loss_step = self.training_step(model, inputs)
1318
1319 if (
/opt/conda/lib/python3.7/site-packages/transformers/trainer.py in training_step(self, model, inputs)
1855 loss = self.compute_loss(model, inputs)
1856 else:
→ 1857 loss = self.compute_loss(model, inputs)
1858
1859 if self.args.n_gpu > 1:
/opt/conda/lib/python3.7/site-packages/transformers/trainer.py in compute_loss(self, model, inputs, return_outputs)
1887 else:
1888 labels = None
→ 1889 outputs = model(**inputs)
1890 # Save past state if it exists
1891 # TODO: this needs to be fixed and made cleaner later.
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1050 or _global_forward_hooks or _global_forward_pre_hooks):
→ 1051 return forward_call(*input, **kwargs)
1052 # Do not call functions when jit is used
1053 full_backward_hooks, non_full_backward_hooks = ,
/opt/conda/lib/python3.7/site-
packages/transformers/models/vision_encoder_decoder/modeling_vision_encoder_decoder.py in forward(self, pixel_values, decoder_input_ids, decoder_attention_mask, encoder_outputs, past_key_values, decoder_inputs_embeds, labels, use_cache, output_attentions, output_hidden_states, return_dict, **kwargs)
491 past_key_values=past_key_values,
492 return_dict=return_dict,
--> 493 **kwargs_decoder,
494 )
495
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1050 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1051 return forward_call(*input, **kwargs)
1052 # Do not call functions when jit is used
1053 full_backward_hooks, non_full_backward_hooks = [], []
/opt/conda/lib/python3.7/site-packages/transformers/models/gpt2/modeling_gpt2.py in forward(self, input_ids, past_key_values, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, encoder_hidden_states, encoder_attention_mask, labels, use_cache, output_attentions, output_hidden_states, return_dict)
1055 output_attentions=output_attentions,
1056 output_hidden_states=output_hidden_states,
-> 1057 return_dict=return_dict,
1058 )
1059 hidden_states = transformer_outputs[0]
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1050 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1051 return forward_call(*input, **kwargs)
1052 # Do not call functions when jit is used
1053 full_backward_hooks, non_full_backward_hooks = [], []
/opt/conda/lib/python3.7/site-packages/transformers/models/gpt2/modeling_gpt2.py in forward(self, input_ids, past_key_values, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, encoder_hidden_states, encoder_attention_mask, use_cache, output_attentions, output_hidden_states, return_dict)
828
829 if inputs_embeds is None:
--> 830 inputs_embeds = self.wte(input_ids)
831 position_embeds = self.wpe(position_ids)
832 hidden_states = inputs_embeds + position_embeds
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1049 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1050 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1051 return forward_call(*input, **kwargs)
1052 # Do not call functions when jit is used
1053 full_backward_hooks, non_full_backward_hooks = [], []
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/sparse.py in forward(self, input)
158 return F.embedding(
159 input, self.weight, self.padding_idx, self.max_norm,
--> 160 self.norm_type, self.scale_grad_by_freq, self.sparse)
161
162 def extra_repr(self) -> str:
/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
2041 # remove once script supports set_grad_enabled
2042 _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
-> 2043 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
2044
2045
IndexError: index out of range in self