423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 22:32:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update cal_lr.py

Browse Source 
Former-commit-id: 829e879e040cae3b49ace981b3d4a8eaf1e0c4ae
This commit is contained in:
hiyouga 2023-11-14 21:14:42 +08:00
parent 426c2fc340
commit 2ba88c6b08
1 changed files with 2 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
tests/cal_lr.py
View File

@ -32,19 +32,14 @@ def calculate_lr(
dataset=dataset,
template="default",
cutoff_len=cutoff_len,
output_dir="dummy_dir",
fp16=True
output_dir="dummy_dir"
))
trainset = get_dataset(model_args, data_args)
_, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, is_trainable=False, stage="sft")
trainset = preprocess_dataset(trainset, tokenizer, data_args, training_args, stage="sft")
data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, label_pad_token_id=IGNORE_INDEX)
dataloader = DataLoader(
dataset=trainset,
batch_size=batch_size,
shuffle=True,
collate_fn=data_collator,
pin_memory=True
dataset=trainset, batch_size=batch_size, shuffle=True, collate_fn=data_collator, pin_memory=True
)
valid_tokens, total_tokens = 0, 0
for batch in tqdm(dataloader):