RDson/

Phi-3-mini-code-finetune-128k-instruct-v1

    learning_rate=5e-5,
    lr_scheduler_type="cosine",
    max_length=1024,
    max_prompt_length=512,
    overwrite_output_dir=True,
    beta=0.1,
    gradient_accumulation_steps=8,
    optim="adamw_torch",
    num_train_epochs=1,
    evaluation_strategy="steps",
    eval_steps=0.2,
    logging_steps=1,
    warmup_steps=50,
    fp16=True,
    save_steps=50