JoanneJegou/

GRPO_post_trained_v1

lora_config = LoraConfig(
    r = 16, 
    lora_alpha = 32,
    lora_dropout = 0.0,
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    bias="none",
    task_type="CAUSAL_LM",
)

training_args = GRPOConfig(
    output_dir = OUTPUT_DIR,
    learning_rate = 1e-6,
    num_generations = N_GROUP,
    max_steps = 1500,
    per_device_train_batch_size = 1,
    gradient_accumulation_steps = 8,
    max_completion_length = 3090,
    use_vllm = True,
    vllm_gpu_memory_utilization = 0.55,
    #vllm_max_model_len = 4096,
)

merged_model.generation_config = GenerationConfig(
    bos_token_id=tokenizer.bos_token_id if tokenizer.bos_token_id is not None else tokenizer.eos_token_id,
    do_sample=True,
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.pad_token_id,
    temperature=0.6,
    top_k=20,
    top_p=0.95,
)