Trainer

This is the model trainer

train_model.py

@@ -0,0 +1,42 @@
+from datasets import load_dataset
+from transformers import T5Tokenizer, T5ForConditionalGeneration, Trainer, TrainingArguments
+
+# Load your dataset
+dataset = load_dataset("json", data_files="dataset.jsonl")["train"]
+
+# Load tokenizer and model
+model_name = "t5-small"
+tokenizer = T5Tokenizer.from_pretrained(model_name)
+model = T5ForConditionalGeneration.from_pretrained(model_name)
+
+# Preprocessing
+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_data = dataset.map(tokenize)
+
+# Training arguments
+training_args = TrainingArguments(
+    output_dir="./trivia-genie-t5",
+    per_device_train_batch_size=8,
+    num_train_epochs=3,
+    logging_steps=10,
+    save_total_limit=2,
+    save_strategy="epoch"
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_data,
+)
+
+# Train
+trainer.train()
+
+# Optional: Push to Hugging Face Hub
+# model.push_to_hub("your-username/trivia-genie-t5")
+# tokenizer.push_to_hub("your-username/trivia-genie-t5")