Integrate with unsloth¶

import comet_ml
import torch
from transformers import TrainingArguments
from trl import SFTTrainer
from unsloth import FastLanguageModel, is_bfloat16_supported

comet_ml.login()
exp = comet_ml.Experiment(project_name = <YOUR-PROJECT-NAME>)

# 1. Enable logging of model checkpoints
os.environ["COMET_LOG_ASSETS"] = "True"

# 2. Define your model and tokeniker
model, tokenizer = FastLanguageModel.from_pretrained(
    ...
)

# 3. Add LoRA adapters
model = FastLanguageModel.get_peft_model(
    ...
)

# 4. Train your model

trainer = SFTTTrainer(
...
)

trainer.train()

pip install comet_ml pip install "unsloth[cu121-torch240] @ git+https://github.com/unslothai/unsloth.git" "torch>=2.4.0" xformers trl peft accelerate bitsandbytes triton

import os

import comet_ml

# Enable logging of model checkpoints
os.environ["COMET_LOG_ASSETS"] = "True"

comet_ml.login(project_name="comet-example-unsloth")

import torch
from datasets import load_dataset
from trl import SFTTrainer
from transformers import TrainingArguments
from unsloth import FastLanguageModel, is_bfloat16_supported

max_seq_length = 2048
dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
load_in_4bit = True

# Download model and tokenizer
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/Meta-Llama-3.1-8B",
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    token = HF_TOKEN
)

# Add LoRA adapters
model = FastLanguageModel.get_peft_model(
    model,
    r = 16, # Suggested 8, 16, 32, 64, 128
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj",],
    lora_alpha = 16,
    lora_dropout = 0, # Supports any, but = 0 is optimized
    bias = "none",    # Supports any, but = "none" is optimized
    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
    random_state = 3407,
    use_rslora = False,  # rank stabilized LoRA
    loftq_config = None, # LoftQ
)

# Data download and preparation
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN
def formatting_prompts_func(examples):
    instructions = examples["instruction"]
    inputs       = examples["input"]
    outputs      = examples["output"]
    texts = []
    for instruction, input, output in zip(instructions, inputs, outputs):
        # Must add EOS_TOKEN, otherwise your generation will go on forever!
        text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN
        texts.append(text)
    return { "text" : texts, }
pass

dataset = load_dataset("yahma/alpaca-cleaned", split = "train")
dataset = dataset.map(formatting_prompts_func, batched = True,)

# Train the model
trainer = SFTTrainer(
    model = model,
    tokenizer = tokenizer,
    train_dataset = dataset,
    dataset_text_field = "text",
    max_seq_length = max_seq_length,
    dataset_num_proc = 2,
    packing = False, # Can make training 5x faster for short sequences.
    args = TrainingArguments(
        per_device_train_batch_size = 2,
        gradient_accumulation_steps = 4,
        warmup_steps = 5,
        # num_train_epochs = 1, # Set this for 1 full training run.
        max_steps = 60,
        learning_rate = 2e-4,
        fp16 = not is_bfloat16_supported(),
        bf16 = is_bfloat16_supported(),
        logging_steps = 1,
        optim = "adamw_8bit",
        weight_decay = 0.01,
        lr_scheduler_type = "linear",
        seed = 3407,
        output_dir = "outputs",
    ),
)

trainer_stats = trainer.train()