423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 20:52:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #1316

Browse Source 
Former-commit-id: f4e4a04529a60b4c4ccc66cbf67f6e951fbc68d3
This commit is contained in:
hiyouga 2023-10-31 11:32:08 +08:00
parent 8fb1c94632
commit 6493f6d2e9
3 changed files with 11 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
src/llmtuner/tuner/sft/trainer.py
View File

@ -35,26 +35,18 @@ class CustomSeq2SeqTrainer(Seq2SeqTrainer):
"""
if self.args.predict_with_generate:
assert self.tokenizer.padding_side == "left", "This method only accepts left-padded tensor."
assert self.tokenizer.pad_token_id is not None, "Pad token is required."
prompt_len, label_len = inputs["input_ids"].size(-1), inputs["labels"].size(-1)
labels = inputs["labels"].clone()
if prompt_len > label_len:
inputs["labels"] = self._pad_tensors_to_target_len(inputs["labels"], inputs["input_ids"])
if label_len > prompt_len:
inputs["input_ids"] = self._pad_tensors_to_target_len(inputs["input_ids"], inputs["labels"])
if "attention_mask" in inputs:
inputs["attention_mask"] = self._pad_tensors_to_target_len(
inputs["attention_mask"], inputs["labels"], pad_token_id=0
)
if "position_ids" in inputs:
inputs["position_ids"] = self._pad_tensors_to_target_len(
inputs["position_ids"], inputs["labels"], pad_token_id=0
)
inputs["labels"] = inputs["labels"][:, :prompt_len] # truncate the labels instead of padding the inputs
loss, generated_tokens, labels = super().prediction_step(
loss, generated_tokens, _ = super().prediction_step(
model, inputs, prediction_loss_only=prediction_loss_only, ignore_keys=ignore_keys
)
if generated_tokens is not None and self.args.predict_with_generate:
generated_tokens[:, :max(prompt_len, label_len)] = self.tokenizer.pad_token_id
generated_tokens[:, :prompt_len] = self.tokenizer.pad_token_id
generated_tokens = generated_tokens.contiguous()
return loss, generated_tokens, labels
@ -62,14 +54,13 @@ class CustomSeq2SeqTrainer(Seq2SeqTrainer):
def _pad_tensors_to_target_len(
self,
src_tensor: torch.Tensor,
tgt_tensor: torch.Tensor,
pad_token_id: Optional[int] = None
tgt_tensor: torch.Tensor
) -> torch.Tensor:
r"""
Pads the tensor to the same length as the target tensor.
"""
pad_token_id = pad_token_id if pad_token_id is not None else self.tokenizer.pad_token_id
padded_tensor = pad_token_id * torch.ones_like(tgt_tensor)
assert self.tokenizer.pad_token_id is not None, "Pad token is required."
padded_tensor = self.tokenizer.pad_token_id * torch.ones_like(tgt_tensor)
padded_tensor[:, -src_tensor.shape[-1]:] = src_tensor # adopt left-padding
return padded_tensor.contiguous() # in contiguous memory

2
src/llmtuner/tuner/sft/workflow.py
View File

@ -33,7 +33,7 @@ def run_sft(
data_collator = DataCollatorForSeq2Seq(
tokenizer=tokenizer,
pad_to_multiple_of=4, # for shift short attention
pad_to_multiple_of=4 if tokenizer.padding_side == "right" else None, # for shift short attention
label_pad_token_id=IGNORE_INDEX if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
)