studio-ousia / luke Goto Github PK

Traceback (most recent call last):
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/dl/mughil/luke/examples/cli.py", line 132, in <module>
    cli()
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "/home/dl/mughil/luke/examples/utils/trainer.py", line 32, in wrapper
    return func(*args, **kwargs)
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context().obj, *args, **kwargs)
  File "/home/dl/mughil/luke/examples/reading_comprehension/main.py", line 123, in run
    model.load_state_dict(torch.load(args.checkpoint_file, map_location="cpu"))
  File "/home/dl/mughil/luke/luke/model.py", line 234, in load_state_dict
    super(LukeEntityAwareAttentionModel, self).load_state_dict(new_state_dict, *args, **kwargs)
  File "/usr/local/finra/anaconda/anaconda3/envs/LUKE_p36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 845, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for LukeForReadingComprehension:
        size mismatch for encoder.layer.0.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.0.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.0.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.0.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.0.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.0.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.0.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.0.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.0.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.0.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.0.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.0.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.1.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.1.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.1.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.1.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.1.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.1.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.1.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.1.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.1.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.1.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.1.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.2.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.2.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.2.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.2.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.2.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.2.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.2.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.2.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.2.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.2.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.2.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.3.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.3.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.3.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.3.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.3.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.3.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.3.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.3.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.3.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.3.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.3.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.4.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.4.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.4.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.4.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.4.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.4.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.4.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.4.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.4.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.4.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.4.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.5.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.5.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.5.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.5.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.5.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.5.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.5.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.5.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.5.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.5.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.5.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.6.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.6.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.6.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.6.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.6.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.6.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.6.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.6.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.6.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.6.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.6.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.7.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.7.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.7.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.7.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.7.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.7.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.7.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.7.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.7.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.7.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.7.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.8.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.8.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.8.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.8.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.8.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.8.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.8.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.8.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.8.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.8.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.8.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.9.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.9.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.9.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.9.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.9.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.9.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.9.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.9.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.9.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.9.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.9.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.10.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.10.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.10.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.10.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.10.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.10.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.10.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.10.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.10.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.10.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.10.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.self.query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.11.attention.self.query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.self.key.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.11.attention.self.key.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.self.value.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.11.attention.self.value.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.self.w2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.11.attention.self.w2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.self.e2w_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.11.attention.self.e2w_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.self.e2e_query.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.11.attention.self.e2e_query.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.output.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for encoder.layer.11.attention.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.attention.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.intermediate.dense.weight: copying a param with shape torch.Size([4096, 1024]) from checkpoint, the shape in current model is torch.Size([3072, 768]).
        size mismatch for encoder.layer.11.intermediate.dense.bias: copying a param with shape torch.Size([4096]) from checkpoint, the shape in current model is torch.Size([3072]).
        size mismatch for encoder.layer.11.output.dense.weight: copying a param with shape torch.Size([1024, 4096]) from checkpoint, the shape in current model is torch.Size([768, 3072]).
        size mismatch for encoder.layer.11.output.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.output.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for encoder.layer.11.output.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for pooler.dense.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([768, 768]).
        size mismatch for pooler.dense.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for embeddings.word_embeddings.weight: copying a param with shape torch.Size([50265, 1024]) from checkpoint, the shape in current model is torch.Size([50265, 768]).
        size mismatch for embeddings.position_embeddings.weight: copying a param with shape torch.Size([514, 1024]) from checkpoint, the shape in current model is torch.Size([514, 768]).
        size mismatch for embeddings.token_type_embeddings.weight: copying a param with shape torch.Size([1, 1024]) from checkpoint, the shape in current model is torch.Size([1, 768]).
        size mismatch for embeddings.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for embeddings.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for entity_embeddings.entity_embedding_dense.weight: copying a param with shape torch.Size([1024, 256]) from checkpoint, the shape in current model is torch.Size([768, 256]).
        size mismatch for entity_embeddings.position_embeddings.weight: copying a param with shape torch.Size([514, 1024]) from checkpoint, the shape in current model is torch.Size([514, 768]).
        size mismatch for entity_embeddings.token_type_embeddings.weight: copying a param with shape torch.Size([1, 1024]) from checkpoint, the shape in current model is torch.Size([1, 768]).
        size mismatch for entity_embeddings.LayerNorm.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for entity_embeddings.LayerNorm.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([768]).
        size mismatch for qa_outputs.weight: copying a param with shape torch.Size([2, 1024]) from checkpoint, the shape in current model is torch.Size([2, 768]).

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/apex/__init__.py", line 13, in <module>
    from pyramid.session import UnencryptedCookieSessionFactoryConfig
ImportError: cannot import name 'UnencryptedCookieSessionFactoryConfig' from 'pyramid.session' (unknown location)

guid=train-945
words=['SOCCER', '-', 'ENGLISH', 'SOCCER', 'RESULTS', '.', 'LONDON', '1996-08-30', 'Results', 'of', 'English', 'league', 'matches', 'on', 'Friday', ':', 'Division', 'two', 'Plymouth', '2', 'Preston', '1', 'Division', 'three', 'Swansea', '1', 'Lincoln', '2']
labels=['O', 'O', 'B-MISC', 'O', 'O', 'O', 'B-LOC', 'O', 'O', 'O', 'B-MISC', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'B-ORG', 'O', 'B-ORG', 'O', 'O', 'O', 'B-ORG', 'O', 'B-ORG', 'O']

       precision    recall  f1-score   support

  PER     0.9639    0.4338    0.5984      1602
 MISC     0.8680    0.5720    0.6896       701
  LOC     0.9596    0.7407    0.8360      1666
  ORG     0.9418    0.5792    0.7173      1647

python -m examples.cli --model-file=luke_large_500k.tar.gz --output-dir=<OUTPUT_DIR> ner run --data-dir=<DATA_DIR> --fp16 --train-batch-size=2 --gradient-accumulation-steps=2 --learning-rate=1e-5 --num-train-epochs=5

Eval: 100%|##########| 181/181 [04:43<00:00,  1.56s/it]
Traceback (most recent call last):
  File "/data1/zekangli/anaconda3/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/data1/zekangli/anaconda3/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/apdcephfs/share_47076/zekangli/multilingual/luke/examples/cli.py", line 135, in <module>
    cli()
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/click/core.py", line 764, in __call__
    return self.main(*args, **kwargs)
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/click/core.py", line 717, in main
    rv = self.invoke(ctx)
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/click/core.py", line 1137, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/click/core.py", line 1137, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/click/core.py", line 956, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/click/core.py", line 555, in invoke
    return callback(*args, **kwargs)
  File "/apdcephfs/share_47076/zekangli/multilingual/luke/examples/utils/trainer.py", line 32, in wrapper
    return func(*args, **kwargs)
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/click/decorators.py", line 27, in new_func
    return f(get_current_context().obj, *args, **kwargs)
  File "/apdcephfs/share_47076/zekangli/multilingual/luke/examples/ner/main.py", line 90, in run
    results.update({f"dev_{k}": v for k, v in evaluate(args, model, "dev", dev_output_file).items()})
  File "/apdcephfs/share_47076/zekangli/multilingual/luke/examples/ner/main.py", line 155, in evaluate
    print(seqeval.metrics.classification_report(final_labels, final_predictions, digits=4))
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/seqeval/metrics/sequence_labeling.py", line 697, in classification_report
    suffix=suffix
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/seqeval/metrics/sequence_labeling.py", line 139, in precision_recall_fscore_support
    extract_tp_actual_correct=extract_tp_actual_correct
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/seqeval/metrics/v1.py", line 122, in _precision_recall_fscore_support
    check_consistent_length(y_true, y_pred)
  File "/data1/zekangli/anaconda3/lib/python3.7/site-packages/seqeval/metrics/v1.py", line 97, in check_consistent_length
    raise TypeError('Found input variables without list of list.')
TypeError: Found input variables without list of list.
The number of labels: 51362

The number of labels: 51362
Traceback (most recent call last):
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/ha1/czuk/nlp/eclipse/workspace_deepner/luke/luke/examples/cli.py", line 135, in <module>
    cli()
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "/ha1/czuk/nlp/eclipse/workspace_deepner/luke/luke/examples/utils/trainer.py", line 32, in wrapper
    return func(*args, **kwargs)
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context().obj, *args, **kwargs)
  File "/ha1/czuk/nlp/eclipse/workspace_deepner/luke/luke/examples/ner/main.py", line 90, in run
    results.update({f"dev_{k}": v for k, v in evaluate(args, model, "dev", dev_output_file).items()})
  File "/ha1/czuk/nlp/eclipse/workspace_deepner/luke/luke/examples/ner/main.py", line 155, in evaluate
    print(seqeval.metrics.classification_report(final_labels, final_predictions, digits=4))
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/seqeval/metrics/sequence_labeling.py", line 697, in classification_report
    suffix=suffix
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/seqeval/metrics/sequence_labeling.py", line 139, in precision_recall_fscore_support
    extract_tp_actual_correct=extract_tp_actual_correct
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/seqeval/metrics/v1.py", line 122, in _precision_recall_fscore_support
    check_consistent_length(y_true, y_pred)
  File "/home/czuk/anaconda3/envs/luke/lib/python3.6/site-packages/seqeval/metrics/v1.py", line 97, in check_consistent_length
    raise TypeError('Found input variables without list of list.')
TypeError: Found input variables without list of list.

python -m examples.cli --model-file=luke_large_500k.tar.gz --output-dir=<OUTPUT_DIR> ner run --data-dir=<DATA_DIR> --fp16 --train-batch-size=2 --gradient-accumulation-steps=2 --learning-rate=1e-5 --num-train-epochs=5

valid_titles = None
if wikipedia_titles_file:
    with open(wikipedia_titles_file) as f:
        valid_titles = frozenset([t.rstrip() for t in f])

redirects = {}
if wikipedia_redirects_file:
    with open(wikipedia_redirects_file) as f:
        for line in f:
            (src, dest) = line.rstrip().split("\t")
            redirects[src] = dest

python -m examples.cli --model-file=luke_large_500k.tar.gz --output-dir=RelationClassification relation-classification run --data-dir=data/tacred --fp16 --train-batch-size=4 --gradient-accumulation-steps=8 --learning-rate=1e-5 --num-train-epochs=5 

python -m examples.cli \
--model-file=/hdd1/user/research/luke/luke_large_500k.tar.gz \
--output-dir=/hdd1/user/research/luke \
relation-classification run \
--data-dir=/hdd1/user/data/TACRED/data/json \
 --checkpoint-file=/hdd1/user/research/luke/pytorch_model.bin \
--no-train

Traceback (most recent call last):
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 187, in nti
    n = int(s.strip() or "0", 8)
ValueError: invalid literal for int() with base 8: 'r_v2\nq\x02('

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 2289, in next
    tarinfo = self.tarinfo.fromtarfile(self)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 1095, in fromtarfile
    obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 1037, in frombuf
    chksum = nti(buf[148:156])
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 189, in nti
    raise InvalidHeaderError("invalid header")
tarfile.InvalidHeaderError: invalid header

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/torch/serialization.py", line 555, in _load
    return legacy_load(f)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/torch/serialization.py", line 466, in legacy_load
    with closing(tarfile.open(fileobj=f, mode='r:', format=tarfile.PAX_FORMAT)) as tar, \
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 1593, in open
    return func(name, filemode, fileobj, **kwargs)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 1623, in taropen
    return cls(name, mode, fileobj, **kwargs)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 1486, in __init__
    self.firstmember = self.next()
  File "/home/user/anaconda3/envs/luke/lib/python3.7/tarfile.py", line 2301, in next
    raise ReadError(str(e))
tarfile.ReadError: invalid header

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/user/anaconda3/envs/luke/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/user/github/luke/examples/cli.py", line 132, in <module>
    cli()
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "/home/user/github/luke/examples/utils/trainer.py", line 32, in wrapper
    return func(*args, **kwargs)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context().obj, *args, **kwargs)
  File "/home/user/github/luke/examples/relation_classification/main.py", line 110, in run
    model.load_state_dict(torch.load(args.checkpoint_file, map_location="cpu"))
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/torch/serialization.py", line 386, in load
    return _load(f, map_location, pickle_module, **pickle_load_args)
  File "/home/user/anaconda3/envs/luke/lib/python3.7/site-packages/torch/serialization.py", line 559, in _load
    raise RuntimeError("{} is a zip archive (did you mean to use torch.jit.load()?)".format(f.name))
RuntimeError: /hdd1/user/research/luke/pytorch_model.bin is a zip archive (did you mean to use torch.jit.load()?)

[2020-12-09 15:33:29,940] [INFO] Loading features from cached file data/tacred/cached_roberta_30_train.pkl ([email protected]:188)
epoch: 0 loss: 1.7077439:   1%|▉                                                                                        | 1703/170310 [11:36<19:09:14,  2.45it/s]
Traceback (most recent call last):
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/llq/homework/luke/examples/cli.py", line 135, in <module>
    cli()
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "/home/llq/homework/luke/examples/utils/trainer.py", line 32, in wrapper
    return func(*args, **kwargs)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context().obj, *args, **kwargs)
  File "/home/llq/homework/luke/examples/relation_classification/main.py", line 94, in run
    trainer.train()
  File "/home/llq/homework/luke/examples/utils/trainer.py", line 93, in train
    outputs = model(**inputs)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/llq/homework/luke/examples/relation_classification/model.py", line 38, in forward
    entity_attention_mask,
  File "/home/llq/homework/luke/luke/model.py", line 213, in forward
    return self.encoder(word_embeddings, entity_embeddings, attention_mask)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/llq/homework/luke/luke/model.py", line 342, in forward
    word_hidden_states, entity_hidden_states, attention_mask
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/llq/homework/luke/luke/model.py", line 325, in forward
    word_hidden_states, entity_hidden_states, attention_mask
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/llq/homework/luke/luke/model.py", line 308, in forward
    word_self_output, entity_self_output = self.self(word_hidden_states, entity_hidden_states, attention_mask)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/llq/homework/luke/luke/model.py", line 287, in forward
    attention_probs = self.dropout(attention_probs)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/modules/dropout.py", line 54, in forward
    return F.dropout(input, self.p, self.training, self.inplace)
  File "/home/llq/anaconda3/envs/py36/lib/python3.6/site-packages/torch/nn/functional.py", line 807, in dropout
    else _VF.dropout(input, p, training))
RuntimeError: CUDA out of memory. Tried to allocate 12.00 MiB (GPU 0; 10.91 GiB total capacity; 8.55 GiB already allocated; 8.50 MiB free; 8.75 GiB reserved in total by PyTorch)

Traceback (most recent call last):
  File "/usr/playground/luke/luke/pretraining/train.py", line 353, in run_pretraining
    result = model(**batch)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
    result = self.forward(*input, **kwargs)
  File "/usr/playground/luke/luke/pretraining/model.py", line 81, in forward
    entity_attention_mask,
  File "/usr/playground/luke/luke/model.py", line 109, in forward
    entity_embedding_output = self.entity_embeddings(entity_ids, entity_position_ids, entity_segment_ids)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
    result = self.forward(*input, **kwargs)
  File "/usr/playground/luke/luke/model.py", line 60, in forward
    entity_embeddings = self.entity_embedding_dense(entity_embeddings)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
    result = self.forward(*input, **kwargs)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 87, in forward
    return F.linear(input, self.weight, self.bias)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/torch/nn/functional.py", line 1612, in linear
    output = input.matmul(weight.t())
RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)`
[2020-12-09 00:43:15,490] [ERROR] Consecutive errors have been observed. Exiting... ([email protected]:379)
Traceback (most recent call last):
  File "/usr/playground/luke/luke/pretraining/train.py", line 352, in run_pretraining
    batch = {k: torch.from_numpy(v).to(device) for k, v in batch.items()}
  File "/usr/playground/luke/luke/pretraining/train.py", line 352, in <dictcomp>
    batch = {k: torch.from_numpy(v).to(device) for k, v in batch.items()}
RuntimeError: CUDA error: an illegal memory access was encountered
Traceback (most recent call last):
  File "./luke/cli.py", line 67, in <module>
    cli()
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/usr/.pyenv/versions/luke/lib/python3.7/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "/usr/playground/luke/luke/pretraining/train.py", line 82, in pretrain
    run_pretraining(Namespace(**kwargs))
  File "/usr/playground/luke/luke/pretraining/train.py", line 352, in run_pretraining
    batch = {k: torch.from_numpy(v).to(device) for k, v in batch.items()}
  File "/usr/playground/luke/luke/pretraining/train.py", line 352, in <dictcomp>
    batch = {k: torch.from_numpy(v).to(device) for k, v in batch.items()}
RuntimeError: CUDA error: an illegal memory access was encountered

Traceback (most recent call last):


  File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)

  File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)

  File "/home/akshay/re_rc/luke/examples/cli.py", line 132, in <module>
    cli()

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/click/core.py", line 1259, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)

  File "/home/akshay/re_rc/luke/examples/utils/trainer.py", line 32, in wrapper
    return func(*args, **kwargs)

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context().obj, *args, **kwargs)

  File "/home/akshay/re_rc/luke/examples/relation_classification/main.py", line 110, in run
    model.load_state_dict(torch.load(args.checkpoint_file, map_location="cpu"))

  File "/home/akshay/re_rc/luke/luke/model.py", line 236, in load_state_dict
    super(LukeEntityAwareAttentionModel, self).load_state_dict(new_state_dict, *args, **kwargs)

  File "/home/akshay/pyTorch-env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 769, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))

RuntimeError: Error(s) in loading state_dict for LukeForRelationClassification:
	size mismatch for embeddings.word_embeddings.weight: copying a param with shape torch.Size([50266, 1024]) from checkpoint, the shape in current model is torch.Size([50267, 1024]).

	size mismatch for entity_embeddings.entity_embeddings.weight: copying a param with shape torch.Size([2, 256]) from checkpoint, the shape in current model is torch.Size([3, 256]).