finnetunning

Finetunning/finetunning.py

@@ -0,0 +1,152 @@
+import torch
+from datasets import load_dataset
+from transformers import (
+    AutoTokenizer,
+    AutoModelForCausalLM,
+    TrainingArguments,
+)
+from peft import (
+    LoraConfig,
+    get_peft_model,
+    prepare_model_for_kbit_training,
+)
+from trl import SFTTrainer
+import os
+os.environ["TORCHDYNAMO_DISABLE"] = "1"
+
+# ----------------------------
+# Model configuration
+# ----------------------------
+MODEL_NAME = "Qwen/Qwen2.5-14B-Instruct"
+
+print("=== Starting fine-tuning script ===")
+
+print(f"{80 * '_'}\n[1/7] Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(
+    MODEL_NAME,
+    trust_remote_code=True
+)
+
+# Ensure padding token is defined
+tokenizer.pad_token = tokenizer.eos_token
+tokenizer.model_max_length = 1024
+
+print("Tokenizer loaded and configured.")
+
+print(f"{80 * '_'}\n[2/7] Loading model in 4-bit mode (QLoRA)...")
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    load_in_4bit=True,
+    device_map="auto",
+    torch_dtype=torch.float16,  # OK for weights
+    trust_remote_code=True,
+)
+print("Model loaded.")
+
+print(f"{80 * '_'}\n[3/7] Preparing model for k-bit training...")
+model = prepare_model_for_kbit_training(model)
+print("Model prepared for k-bit training.")
+
+# ----------------------------
+# LoRA configuration
+# ----------------------------
+print(f"{80 * '_'}\n[4/7] Configuring LoRA adapters...")
+lora_config = LoraConfig(
+    r=16,
+    lora_alpha=32,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=[
+        "q_proj",
+        "k_proj",
+        "v_proj",
+        "o_proj",
+        "gate_proj",
+        "up_proj",
+        "down_proj",
+    ],
+)
+
+model = get_peft_model(model, lora_config)
+model.print_trainable_parameters()
+print("LoRA adapters attached to the model.")
+
+# ----------------------------
+# Dataset loading
+# ----------------------------
+print(f"{80 * '_'}\n[5/7] Loading dataset from JSON file...")
+dataset = load_dataset(
+    "json",
+    data_files="traductions.json"
+)
+print(f"Dataset loaded with {len(dataset['train'])} samples.")
+
+print("Formatting dataset for Ukrainian → French translation...")
+
+def format_prompt(example):
+    prompt = (
+        "Translate the following Ukrainian text into French.\n\n"
+        f"Ukrainian: {example['text']}\n"
+        f"French: {example['translation']}"
+    )
+    return {"text": prompt}
+
+dataset = dataset.map(format_prompt, remove_columns=dataset["train"].column_names)
+print("Dataset formatting completed.")
+
+# ----------------------------
+# Training arguments
+# ----------------------------
+print(f"{80 * '_'}\n[6/7] Initializing training arguments...")
+training_args = TrainingArguments(
+    output_dir="./qwen-uk-fr-lora",
+    per_device_train_batch_size=1,
+    gradient_accumulation_steps=8,
+    learning_rate=2e-4,
+    num_train_epochs=3,
+
+    fp16=False,
+    bf16=False,
+
+    logging_steps=10,
+    save_steps=500,
+    save_total_limit=2,
+
+    # Use 32-bit optimizer
+    optim="paged_adamw_32bit",
+
+    report_to="none",
+)
+
+
+print("Training arguments ready.")
+
+# ----------------------------
+# Trainer
+# ----------------------------
+print("Initializing SFTTrainer...")
+trainer = SFTTrainer(
+    model=model,
+    train_dataset=dataset["train"],
+    processing_class=tokenizer,
+    args=training_args,
+)
+print("Trainer initialized.")
+
+# ----------------------------
+# Train
+# ----------------------------
+print(f"{80 * '_'}\n[7/7] Starting training...")
+trainer.train()
+print("Training completed successfully.")
+
+# ----------------------------
+# Save LoRA adapter
+# ----------------------------
+print("Saving LoRA adapter and tokenizer...")
+trainer.model.save_pretrained("./qwen-uk-fr-lora")
+tokenizer.save_pretrained("./qwen-uk-fr-lora")
+
+print("=== Fine-tuning finished ===")
+print("LoRA adapter saved in ./qwen-uk-fr-lora")