Spaces:
Runtime error
Runtime error
File size: 1,472 Bytes
9e6d02d 7e76760 9e6d02d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments, DataCollatorForLanguageModeling
from datasets import load_dataset
tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2")
model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2")
tokenizer.pad_token = tokenizer.eos_token
dataset = load_dataset("HuggingFaceH4/ultrachat_200k")
dataset = dataset['train_sft'].select(range(5))
def tokenize_function(examples):
return tokenizer(examples["prompt"], padding="max_length", truncation=True)
td = dataset.map(tokenize_function, batched=True)
training_args = TrainingArguments(
output_dir="./output",
per_device_train_batch_size=4,
num_train_epochs=3,
logging_dir="./logs",
)
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
"""
dataloader_config = DataLoaderConfiguration(
dispatch_batches=None,
split_batches=False,
even_batches=True,
use_seedable_sampler=True
)
accelerator = Accelerator(dataloader_config=dataloader_config)
with accelerator.prepare():
trainer = Trainer(
model=model,
args=training_args,
data_collator=data_collator,
train_dataset=td,
)
trainer.train()
trainer.save_model("fine_tuned_gpt2")
"""
trainer = Trainer(
model=model,
args=training_args,
data_collator=data_collator,
train_dataset=td,
)
trainer.train()
trainer.save_model("fine_tuned_gpt2") |