fix: liger fails to run loss with new param

[anhuong]

In newer versions of transformers past 4.46, num_items_in_batch is passed to the loss function as seen here which lead to error TypeError: lce_forward() got an unexpected keyword argument 'num_items_in_batch' (full error below). To fix this I pass in the additional parameter to lce_forward which allowed tuning to run through successfully.

ERROR:sft_trainer.py:Traceback (most recent call last):
  File "/home/tuning/.local/lib/python3.12/site-packages/tuning/sft_trainer.py", line 675, in main
    trainer, additional_train_info = train(
                                     ^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/tuning/sft_trainer.py", line 419, in train
    trainer.train(resume_from_checkpoint)
  File "/home/tuning/.local/lib/python3.12/site-packages/transformers/trainer.py", line 2171, in train
    return inner_training_loop(
           ^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/transformers/trainer.py", line 2531, in _inner_training_loop
    tr_loss_step = self.training_step(model, inputs, num_items_in_batch)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/transformers/trainer.py", line 3675, in training_step
    loss = self.compute_loss(model, inputs, num_items_in_batch=num_items_in_batch)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/transformers/trainer.py", line 3731, in compute_loss
    outputs = model(**inputs)
              ^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/torch/distributed/fsdp/fully_sharded_data_parallel.py", line 863, in forward
    output = self._fsdp_wrapped_module(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/peft/peft_model.py", line 1644, in forward
    return self.base_model(
           ^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/tuning/.local/lib/python3.12/site-packages/peft/tuners/tuners_utils.py", line 197, in forward
    return self.model.forward(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: lce_forward() got an unexpected keyword argument 'num_items_in_batch'

Successful run of tuning:

***************** Module Forwards Patching *************
INFO:framework.py:***************** Module Forwards Patching *************
Rule: llama-fused-lce Module:                           Class: LlamaForCausalLM Num:  1
INFO:framework.py:Rule: llama-fused-lce Module:                           Class: LlamaForCausalLM Num:  1
Rule: llama-rms       Module: input_layernorm           Class: LlamaRMSNorm    Num: 32
INFO:framework.py:Rule: llama-rms       Module: input_layernorm           Class: LlamaRMSNorm    Num: 32
Rule: llama-rms       Module: model                     Class: LlamaRMSNorm    Num:  1
INFO:framework.py:Rule: llama-rms       Module: model                     Class: LlamaRMSNorm    Num:  1
Rule: llama-rms       Module: post_attention_layernorm  Class: LlamaRMSNorm    Num: 32
INFO:framework.py:Rule: llama-rms       Module: post_attention_layernorm  Class: LlamaRMSNorm    Num: 32
Rule: llama-rope      Module:                           Class: LlamaForCausalLM Num:  1
INFO:framework.py:Rule: llama-rope      Module:                           Class: LlamaForCausalLM Num:  1

[willmj]

Nice, LGTM! Thanks Anh

[fabianlim]

LGTM