423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 10:56:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

1. add custom eval dataset support

Browse Source 
2. merge load dataset and split dataset function


Former-commit-id: 76f3bbcfc0
This commit is contained in:
codingma
2024-07-05 15:52:10 +08:00
parent 8379a39776
commit 74f0d02eb8
16 changed files with 104 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
scripts/cal_lr.py
View File

@@ -65,7 +65,7 @@ def calculate_lr(
)
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
trainset = get_dataset(model_args, data_args, training_args, stage, **tokenizer_module)
dataset_module = get_dataset(model_args, data_args, training_args, stage, **tokenizer_module)
if stage == "pt":
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
elif stage == "sft":
@@ -73,7 +73,7 @@ def calculate_lr(
else:
raise NotImplementedError("Stage does not supported: {}.".format(stage))
dataloader = DataLoader(trainset, batch_size, shuffle=False, collate_fn=data_collator, pin_memory=True)
dataloader = DataLoader(dataset_module["eval_dataset"], batch_size, shuffle=False, collate_fn=data_collator, pin_memory=True)
valid_tokens, total_tokens = 0, 0
for batch in tqdm(dataloader):
valid_tokens += torch.sum(batch["labels"] != IGNORE_INDEX).item()

4
scripts/cal_ppl.py
View File

@@ -87,7 +87,7 @@ def cal_ppl(
)
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
trainset = get_dataset(model_args, data_args, training_args, stage, **tokenizer_module)
dataset_module = get_dataset(model_args, data_args, training_args, stage, **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, is_trainable=False)
if stage == "pt":
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
@@ -100,7 +100,7 @@ def cal_ppl(
else:
raise NotImplementedError("Stage does not supported: {}.".format(stage))
dataloader = DataLoader(trainset, batch_size, shuffle=False, collate_fn=data_collator, pin_memory=True)
dataloader = DataLoader(dataset_module["eval_dataset"], batch_size, shuffle=False, collate_fn=data_collator, pin_memory=True)
criterion = torch.nn.CrossEntropyLoss(reduction="none")
total_ppl = 0
perplexities = []

6
scripts/length_cdf.py
View File

@@ -47,10 +47,10 @@ def length_cdf(
)
)
tokenizer_module = load_tokenizer(model_args)
trainset = get_dataset(model_args, data_args, training_args, stage="sft", **tokenizer_module)
total_num = len(trainset)
dataset_module = get_dataset(model_args, data_args, training_args, stage="sft", **tokenizer_module)
total_num = len(dataset_module["eval_dataset"])
length_dict = defaultdict(int)
for sample in tqdm(trainset["input_ids"]):
for sample in tqdm(dataset_module["eval_dataset"]["input_ids"]):
length_dict[len(sample) // interval * interval] += 1
length_tuples = list(length_dict.items())