day 100 of reporting, still getting this error 
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-38-dda642f3d8b6> in <module>()
47 )
48
---> 49 train_results = trainer.train()
11 frames
/usr/local/lib/python3.7/dist-packages/transformers/trainer.py in train(self, resume_from_checkpoint, trial, **kwargs)
1118 tr_loss += self.training_step(model, inputs)
1119 else:
-> 1120 tr_loss += self.training_step(model, inputs)
1121 self._total_flos += float(self.floating_point_ops(inputs))
1122
/usr/local/lib/python3.7/dist-packages/transformers/trainer.py in training_step(self, model, inputs)
1522 loss = self.compute_loss(model, inputs)
1523 else:
-> 1524 loss = self.compute_loss(model, inputs)
1525
1526 if self.args.n_gpu > 1:
/usr/local/lib/python3.7/dist-packages/transformers/trainer.py in compute_loss(self, model, inputs, return_outputs)
1554 else:
1555 labels = None
-> 1556 outputs = model(**inputs)
1557 # Save past state if it exists
1558 # TODO: this needs to be fixed and made cleaner later.
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/usr/local/lib/python3.7/dist-packages/transformers/models/longformer/modeling_longformer.py in forward(self, input_ids, attention_mask, global_attention_mask, head_mask, token_type_ids, position_ids, inputs_embeds, labels, output_attentions, output_hidden_states, return_dict)
1855 output_attentions=output_attentions,
1856 output_hidden_states=output_hidden_states,
-> 1857 return_dict=return_dict,
1858 )
1859 sequence_output = outputs[0]
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/usr/local/lib/python3.7/dist-packages/transformers/models/longformer/modeling_longformer.py in forward(self, input_ids, attention_mask, global_attention_mask, head_mask, token_type_ids, position_ids, inputs_embeds, output_attentions, output_hidden_states, return_dict)
1662
1663 embedding_output = self.embeddings(
-> 1664 input_ids=input_ids, position_ids=position_ids, token_type_ids=token_type_ids, inputs_embeds=inputs_embeds
1665 )
1666
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/usr/local/lib/python3.7/dist-packages/transformers/models/longformer/modeling_longformer.py in forward(self, input_ids, token_type_ids, position_ids, inputs_embeds)
491 if inputs_embeds is None:
492 inputs_embeds = self.word_embeddings(input_ids)
--> 493 position_embeddings = self.position_embeddings(position_ids)
494 token_type_embeddings = self.token_type_embeddings(token_type_ids)
495
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/usr/local/lib/python3.7/dist-packages/torch/nn/modules/sparse.py in forward(self, input)
156 return F.embedding(
157 input, self.weight, self.padding_idx, self.max_norm,
--> 158 self.norm_type, self.scale_grad_by_freq, self.sparse)
159
160 def extra_repr(self) -> str:
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
1914 # remove once script supports set_grad_enabled
1915 _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
-> 1916 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
1917
1918
IndexError: index out of range in self
Still trying to get out of this…