Delete train.py

train.py

@@ -1,44 +0,0 @@
-from datasets import load_dataset
-from transformers import GPT2Tokenizer, GPT2LMHeadModel, Trainer, TrainingArguments, DataCollatorForLanguageModeling
-
-# Load small dataset
-dataset = load_dataset("wikitext", "wikitext-2-raw-v1")
-
-# Load pretrained GPT2 tiny
-tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
-tokenizer.pad_token = tokenizer.eos_token
-model = GPT2LMHeadModel.from_pretrained("gpt2")
-
-# Tokenize
-def tokenize(examples):
-    return tokenizer(examples['text'], truncation=True, max_length=128, padding="max_length")
-
-tokenized = dataset.map(tokenize, batched=True)
-tokenized.set_format(type="torch", columns=["input_ids"])
-
-# Data collator
-data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
-
-# Training arguments
-training_args = TrainingArguments(
-    output_dir="./tiny-gpt",
-    per_device_train_batch_size=2,
-    num_train_epochs=1,  # keep it 1 for speed
-    logging_steps=50,
-    save_steps=200,
-    save_total_limit=1,
-    learning_rate=5e-4
-)
-
-trainer = Trainer(
-    model=model,
-    args=training_args,
-    train_dataset=tokenized['train'],
-    tokenizer=tokenizer,
-    data_collator=data_collator
-)
-
-trainer.train()
-model.save_pretrained("./tiny-gpt")
-tokenizer.save_pretrained("./tiny-gpt")
-print("Training complete!")