fine_tunning_llama2_bode_alpaca.py

fine_tunning_llama2_bode_alpaca.py

from datasets import load_dataset, Dataset
from trl import SFTTrainer
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TrainingArguments
from peft import LoraConfig
import torch, sys

dataset = load_dataset("celsowm/auryn", split="train"
                       #, download_mode="force_redownload"
                       )

# Specify the model
model_name = 'recogna-nlp/bode-7b-alpaca-pt-br-no-peft'

# Load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)

# BitsAndBytesConfig int-4 config
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16,
)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    quantization_config=bnb_config,
    use_cache=False,
    device_map="auto",
    torch_dtype=torch.float16
)

peft_config = LoraConfig(
    lora_alpha=64,
    lora_dropout=0.05,
    r=128,
    bias="none",
    target_modules="all-linear",
    task_type="CAUSAL_LM",
)

training_args = TrainingArguments(
    output_dir='outputs/auryn',
    num_train_epochs=3,                     # number of training epochs
    per_device_train_batch_size=3,          # batch size per device during training
    gradient_accumulation_steps=2,          # number of steps before performing a backward/update pass
    gradient_checkpointing=True,            # use gradient checkpointing to save memory
    optim="adamw_torch_fused",              # use fused adamw optimizer
    logging_steps=10,                       # log every 10 steps
    save_strategy="epoch",                  # save checkpoint every epoch
    learning_rate=2e-4,                     # learning rate, based on QLoRA paper
    bf16=True,                              # use fploat16 precision
    tf32=True,                              # use tf32 precision
    max_grad_norm=0.3,                      # max gradient norm based on QLoRA paper
    warmup_ratio=0.03,                      # warmup ratio based on QLoRA paper
    lr_scheduler_type="constant"
)

trainer = SFTTrainer(
    model=model,
    peft_config=peft_config,
    args=training_args,
    train_dataset=dataset,
    packing=True
)

# Train the model
trainer.train()

# Save the trained model and tokenizer
trainer.model.save_pretrained(training_args.output_dir)
tokenizer.save_pretrained(training_args.output_dir)