> ## Documentation Index > Fetch the complete documentation index at: https://docs.nscale.com/llms.txt > Use this file to discover all available pages before exploring further. # Fine-tuning PubMedQA > Convert a sub-set of [PubMedQA](https://huggingface.co/datasets/qiaojin/PubMedQA) dataset to the required CSV format, upload as a dataset, then create and monitor a fine-tuning job on Nscale. **Fine-tuning service going offline** As of May 20, 2026, the existing fine-tuning service is offline while we prepare the next version. If you still need to export models or datasets, [contact support](mailto:support@nscale.com). [Learn more ](/docs/faqs/deprecations) ## Introduction This cookbook walks you through creating a fine-tuning dataset from the PubMedQA corpus and running an end-to-end job on Nscale. * Dataset: [PubMedQA](https://huggingface.co/datasets/qiaojin/PubMedQA/viewer/pqa_labeled) The goal is to demonstrate how to create a pair of CSV files in the required format (with columns `question` and `answer`) that you can upload to Nscale and use to fine-tune a base model. ## Requirements * Python 3.9+ * Packages: datasets, pandas * Nscale service token and organization ID Install dependencies: ```bash theme={null} pip install datasets pandas ``` ## Generate the dataset CSVs To use Nscale to fine-tune a model, you need a dataset in the [required CSV format](/docs/ai-services/datasets). The script below converts a small subset of PubMedQA dataset (\~2k samples) to a simple Q/A CSV format. You can adapt the same approach for other datasets. * Input prompt: question * Output target: long\_answer when present, otherwise the categorical final\_decision (e.g., yes/no/maybe) It creates two CSVs: train and validation. ```python theme={null} from typing import Dict, Iterable, Optional import pandas as pd from datasets import Dataset, DatasetDict, load_dataset def example_to_qa_row(ex: Dict) -> Optional[Dict[str, str]]: """Convert one PubMedQA pqa_artificial example to a question/answer row. - question: use the provided question string (omit context entirely). - answer: prefer `long_answer` if non-empty; otherwise use `final_decision`. """ question = str(ex.get("question", "")).strip() long_answer = ex.get("long_answer") final_decision = ex.get("final_decision") la = (str(long_answer).strip() if long_answer is not None else "") fd = (str(final_decision).strip() if final_decision is not None else "") answer = la if la else fd return {"question": question, "answer": answer} def dataset_to_csv(ds_split: Iterable[Dict], out_path: str) -> None: rows = [] for ex in ds_split: row = example_to_qa_row(ex) if row: rows.append(row) pd.DataFrame(rows).to_csv(out_path, index=False) def main() -> None: """Build train/validation Q/A split from sub-set of PubMedQA (pqa_artificial). - Loads `qiaojin/PubMedQA` with config `pqa_artificial` (train split). - Randomly splits into train and validation (seed=42), and select a subset of them. - Select 2048 examples for training, and 128 for validation. - Writes two CSVs with columns: `question`, `answer`. - `answer` is `long_answer` if present, else `final_decision`. """ ds_all: DatasetDict = load_dataset("qiaojin/PubMedQA", "pqa_artificial") if "train" not in ds_all: raise RuntimeError("Expected a 'train' split in PubMedQA pqa_artificial") base: Dataset = ds_all["train"] split = base.train_test_split(test_size=0.2, seed=42, shuffle=True) train_ds: Dataset = split["train"] val_ds: Dataset = split["test"] train_limit = min(len(train_ds), 2048) val_limit = min(len(val_ds), 128) train_head = train_ds.select(range(train_limit)) val_head = val_ds.select(range(val_limit)) dataset_to_csv(train_head, "pubmedqa_pqa_artificial_train_qa.csv") dataset_to_csv(val_head, "pubmedqa_pqa_artificial_validation_qa.csv") print( "Wrote pubmedqa_pqa_artificial_train_qa.csv ({} examples) and " "pubmedqa_pqa_artificial_validation_qa.csv ({} examples)".format( train_limit, val_limit ) ) if __name__ == "__main__": main() ``` Save the script as `convert.py`, then run it: ```bash theme={null} python convert.py ``` The script produces two files: * `pubmedqa_pqa_artificial_train_qa.csv` * `pubmedqa_pqa_artificial_validation_qa.csv` Each CSV has headers `question,answer`. ## Create a fine-tuning job You can create the fine-tuning job in the Nscale Console or via API. The steps below show how to do it with the Nscale Fine-tuning API. ### 1. Upload files Export your Nscale token and organization ID, then upload both CSVs. Save the returned file ids for the next step. ```bash theme={null} export NSCALE_API_TOKEN="" export ORGANIZATION_ID="" curl -X POST "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/files" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Content-Type: multipart/form-data' \ -H 'Accept: application/json' \ -F 'file=@pubmedqa_pqa_artificial_train_qa.csv' curl -X POST "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/files" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Content-Type: multipart/form-data' \ -H 'Accept: application/json' \ -F 'file=@pubmedqa_pqa_artificial_validation_qa.csv' ``` ### 2. Create the dataset Use the two file ids returned above. Save returned dataset id to create a fine-tuning job: ```bash theme={null} curl -X POST "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/datasets" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Content-Type: application/json' \ -H 'Accept: application/json' \ -d '{ "name": "pubmedqa-pqa-labeled-qa", "training_file_id": "", "validation_file_id": "" }' ``` ### 3. Create and monitor a fine-tuning job Ensure you have enough credits in your account. First, list available base models and pick one. You can also find a list of available models in the [Fine-tuning guide](/docs/ai-services/fine-tuning). ```bash theme={null} curl -X GET "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/base-models" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Accept: application/json' ``` Create a job that maps our CSV columns to the job's expected inputs. Here, `question` is the prompt and `answer` is the target output. The example below uses `meta-llama/Meta-Llama-3.1-8B-Instruct` as the base model (ID: `5b912da4-4a68-43eb-9224-38239535d934`). Replace `base_model_id` with the ID of your chosen model from the list above. ```bash theme={null} curl -X POST "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/jobs" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Content-Type: application/json' \ -H 'Accept: application/json' \ -d '{ "name": "pubmedqa-finetune", "base_model_id": "5b912da4-4a68-43eb-9224-38239535d934", "dataset": { "id": "", "prompt_column": "question", "answer_column": "answer" }, "hyperparameters": { "batch_size": 32, "best_checkpoints": false, "learning_rate": 0.00001, "lora": { "alpha": 16, "dropout": 0, "enabled": true, "r": 8, "trainable_modules": [] }, "n_epochs": 3, "n_evals": 6, "warmup_ratio": 0, "weight_decay": 0.03, "mask_prompt_labels": false } }' ``` List jobs and poll a specific job for status: ```bash theme={null} curl -X GET "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/jobs" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Accept: application/json' curl -X GET "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/jobs/" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Accept: application/json' ``` Retrieve training metrics (e.g., train\_loss, eval\_loss, perplexity): ```bash theme={null} curl -X GET "https://fine-tuning.api.nscale.com/api/v1/organizations/$ORGANIZATION_ID/jobs//metrics" \ -H "Authorization: Bearer $NSCALE_API_TOKEN" \ -H 'Accept: application/json' ``` When the job completes, export to Hugging Face or download the model as needed. See the [Fine-tuning guide](/docs/ai-services/fine-tuning) for details. Alternatively, you can monitor your fine-tuning job progress from [Nscale UI console](https://console.nscale.com/) live, as shown below. fine-tuning-cookbook.png