How to load fine-tuned model?

[BaamPark]

I fine-tuned Efficient-Large-Model/NVILA-Lite-8B enabling LoRA and got the model checkpoint as below. I want to 1) load the saved model and 2) finetune the model from the saved model checkpoint. I tried setting STAGE_PATH to runs/mymodel/model, which is where the model was saved but I got an error, 'runs/mymodel/model/checkpoint-12150/llm'. Please provide either the path to a local folder or the repo_id of a model on the Hub.

Could you please help?

#saved model
runs/mymodel
└── model
    ├── adapter_config.json
    ├── adapter_model.safetensors
    ├── checkpoint-12150
    │   ├── adapter_config.json
    │   ├── adapter_model.safetensors
    │   ├── config.json
    │   ├── global_step12150
    │   │   ├── bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
    │   │   ├── bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
    │   │   ├── zero_pp_rank_0_mp_rank_00_model_states.pt
    │   │   └── zero_pp_rank_1_mp_rank_00_model_states.pt
    │   ├── latest
    │   ├── non_lora_trainables.bin
    │   ├── README.md
    │   ├── rng_state_0.pth
    │   ├── rng_state_1.pth
    │   ├── scheduler.pt
    │   ├── trainer_state.json
    │   └── zero_to_fp32.py
    ├── config.json
    ├── non_lora_trainables.bin
    ├── README.md
    └── trainer_state.json