File size: 1,454 Bytes
bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 e669806 bdf2090 |
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 |
from datasets import load_dataset
from transformers import T5Tokenizer, T5ForConditionalGeneration, Trainer, TrainingArguments
# Step 1: Load dataset
dataset = load_dataset("DetectiveShadow/MVPQuestion")["train"]
# Optional: Rename columns if needed
# dataset = dataset.rename_columns({"your_input_column": "input", "your_output_column": "output"})
# Step 2: Load tokenizer and model
model_name = "t5-small"
tokenizer = T5Tokenizer.from_pretrained(model_name)
model = T5ForConditionalGeneration.from_pretrained(model_name)
# Step 3: Tokenization function
def tokenize(example):
input_enc = tokenizer(example["input"], truncation=True, padding="max_length", max_length=64)
target_enc = tokenizer(example["output"], truncation=True, padding="max_length", max_length=64)
input_enc["labels"] = target_enc["input_ids"]
return input_enc
tokenized = dataset.map(tokenize)
# Step 4: Training configuration
training_args = TrainingArguments(
output_dir="./MVPTrivia",
per_device_train_batch_size=8,
num_train_epochs=3,
logging_steps=10,
save_strategy="epoch",
push_to_hub=True,
hub_model_id="DetectiveShadow/MVPTrivia", # This is where your model will go
hub_strategy="every_save"
)
# Step 5: Trainer
trainer = Trainer(
model=model,
args=training_args,
train_dataset=tokenized
)
# Step 6: Train and push
trainer.train()
trainer.push_to_hub()
tokenizer.push_to_hub("DetectiveShadow/MVPTrivia")
|