Kermt Finetune
Finetune a pretrained KERMT encoder on a labeled CSV.
Install
npx skills add NVIDIA-BioNeMo/bionemo-agent-toolkit --skill kermt-finetune -g -a claude-code -y- Repository
- NVIDIA-BioNeMo/bionemo-agent-toolkit503
- Category
- AI and agents
- Updated
- 8d ago
- License
- Apache-2.0
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Finetune a pretrained KERMT encoder on a labeled CSV. The skill validates the input checkpoint (must be a pretrain ckpt, grover_base / cmim / hybrid), validates the labeled CSV, prepares the data (clean + features + optional split), then launches main.py finetune inside the kermt container (detached for hours-scale runs). Hyperparameters come from agent/config/defaults_finetune.json with per-flag CLI override.
kermt-finetune
Finetune a pretrained KERMT encoder on a user-supplied labeled CSV. The skill is the workflow orchestrator: validate ckpt, validate data, prepare data, launch the runner detached, return a run directory + container name.
Hardware requirements
- GPUs: 1 by default (single-GPU); pass
--gpus 0(or whichever id) to select one. For faster training on a multi-GPU host, pass--num-gpus N(N>1) to run data-parallel DDP across N GPUs,--batch-sizeis then per-GPU (effective global batch = batch_size × N). - VRAM: ≥ 8 GB for the default
batch_size 32configuration. Lower VRAM works at smaller batch sizes, pass--batch-size Nto override. - Disk: a few GB per run (checkpoint + features + logs).
- Driver / CUDA: any host supporting CUDA 12.6 (the kermt image base).
kermt-setupvalidates this up-front.
Inputs
Required:
--csv <path>, labeled CSV. First column issmiles; every other column is a target.
Checkpoint (optional, defaults to the released model if omitted):
--ckpt <path>, input pretrain checkpoint (grover_base / cmim / hybrid). The validator refuses already-finetuned ckpts with a redirect tokermt-infer. If omitted, the skill offers to download the released pretrained hybrid model nvidia/NV-KERMT-70M-v2 and finetune from it, see "Resolve & validate the checkpoint" (workflow step 3).--pretrained-release, explicit opt-in to use the released model without the interactive prompt (for non-interactive / agent runs). Mutually exclusive with--ckpt.--model-dir <dir>, where to save the downloaded bundle (default$KERMT_REPO/models/NV-KERMT-70M-v2/). An already-complete bundle there is reused, not re-downloaded.
Optional:
