alnrg2arg/

test3_sft_16bit_dpo

from transformers import TrainingArguments, AutoModelForCausalLM
from trl import DPOTrainer

dpo_trainer = DPOTrainer(
    model = model,
   
    ref_model = None,
    args = TrainingArguments(
        per_device_train_batch_size = 8,
        gradient_accumulation_steps = 8,
        warmup_ratio = 0.1,
        num_train_epochs = 3,
        learning_rate = 5e-6,
        fp16 = not torch.cuda.is_bf16_supported(),
        bf16 = torch.cuda.is_bf16_supported(),
        logging_steps = 1,
        optim = "adamw_8bit",
        weight_decay = 0.0,
        lr_scheduler_type = "linear",
        seed = 42,
        output_dir = "output_DPO",
    ),
    beta = 0.1,
    train_dataset = dataset,
    # eval_dataset = raw_datasets["test"],
    tokenizer = tokenizer,
    max_length = 1024,
    max_prompt_length = 512,
)