{"query":"Weights Training","corpusVersion":"local","generatedAt":"2026-11-02T06:32:32.014Z","results":[{"blockId":"assets.weights#weights-training","pageId":"assets.weights","title":"Weights Training","pageTitle":"Weights Training","url":"https://teammately.ai/docs/weights-training.md","humanUrl":"https://teammately.ai/docs/weights-training#weights-training","markdownUrl":"https://teammately.ai/docs/weights-training.md","sectionId":"weights-training","kind":"reference","productArea":"weights_training","score":1249.6674829378978,"reasons":["search_match","title_match","display_title_match","term_match"],"markdown":"# Weights Training\n\nWeights training turns selected Benchmark criteria into inspectable training material and connects that material to model training. Open it from the Benchmark workspace."},{"blockId":"assets.weights#fields-states-or-lifecycle-rules","pageId":"assets.weights","title":"Fields, states, or lifecycle rules","pageTitle":"Weights Training","url":"https://teammately.ai/docs/weights-training.md","humanUrl":"https://teammately.ai/docs/weights-training#fields-states-or-lifecycle-rules","markdownUrl":"https://teammately.ai/docs/weights-training.md","sectionId":"fields-states-or-lifecycle-rules","kind":"reference","productArea":"weights_training","score":726.3780226942589,"reasons":["search_match","display_title_match","page_title_match","term_match"],"markdown":"## Fields, states, or lifecycle rules\n\n- Demonstration and preference datasets have different learner targets.\n- Examples retain their governing criteria and source context.\n- Training, validation and test splits remain distinguishable.\n- A download package captures an exact dataset state and export profile.\n- A training run records the connection, base model, configuration, provider job and resulting model identity.\n- Training completion does not establish benchmark improvement."},{"blockId":"assets.weights#definition","pageId":"assets.weights","title":"Definition","pageTitle":"Weights Training","url":"https://teammately.ai/docs/weights-training.md","humanUrl":"https://teammately.ai/docs/weights-training#definition","markdownUrl":"https://teammately.ai/docs/weights-training.md","sectionId":"definition","kind":"reference","productArea":"weights_training","score":725.7367024379805,"reasons":["search_match","display_title_match","page_title_match","term_match"],"markdown":"## Definition\n\nA preparation records the Benchmark Version, training method, selected scope and generation settings. The workspace has **Overview**, **Dataset**, **Coverage** and **Results**.\n\nOverview summarizes the preparation and prepares the exact dataset download. Dataset exposes examples and splits. Coverage shows representation. Results configures and follows connected training and separately authorized evaluation."},{"blockId":"assets.weights#keep-training-and-evaluation-separate","pageId":"assets.weights","title":"Keep training and evaluation separate","pageTitle":"Weights Training","url":"https://teammately.ai/docs/weights-training.md","humanUrl":"https://teammately.ai/docs/weights-training#keep-training-and-evaluation-separate","markdownUrl":"https://teammately.ai/docs/weights-training.md","sectionId":"keep-training-and-evaluation-separate","kind":"reference","productArea":"weights_training","score":654.4227089595936,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Keep training and evaluation separate\n\nGeneration checks describe prepared material. Coverage describes its representation. A provider completion identifies a training output. Held-out evaluation measures that output through its supported inference path. None substitutes for the others.\n\nKeep test records out of training and provider validation uploads. Preserve exact package and model identities when comparing results with an ordinary Harness evaluation."},{"blockId":"assets.weights#related-task-pages","pageId":"assets.weights","title":"Related task pages","pageTitle":"Weights Training","url":"https://teammately.ai/docs/weights-training.md","humanUrl":"https://teammately.ai/docs/weights-training#related-task-pages","markdownUrl":"https://teammately.ai/docs/weights-training.md","sectionId":"related-task-pages","kind":"reference","productArea":"weights_training","score":528.6158869563592,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Related task pages\n\n{% related-card-grid title=\"Related task pages\" %}\n- [Training Datasets and Coverage](/docs/weights-training/datasets)\n- [Export, Train, and Evaluate](/docs/weights-training/exports-and-training)\n- [Workspace Integrations](/docs/admin-console/integrations)\n- [Evaluation Results](/docs/benchmark-evaluations/results)\n{% /related-card-grid %}"},{"blockId":"weights-training.datasets#training-datasets-and-coverage","pageId":"weights-training.datasets","title":"Training Datasets and Coverage","pageTitle":"Training Datasets and Coverage","url":"https://teammately.ai/docs/weights-training/datasets.md","humanUrl":"https://teammately.ai/docs/weights-training/datasets#training-datasets-and-coverage","markdownUrl":"https://teammately.ai/docs/weights-training/datasets.md","sectionId":"training-datasets-and-coverage","kind":"task","productArea":"weights_training","score":472.3516730510036,"reasons":["search_match","term_match"],"markdown":"# Training Datasets and Coverage\n\nInspect the dataset before exporting or training. Generation completion does not establish realistic examples, balanced coverage or useful learned behavior."},{"blockId":"assets.weights#use-the-workspace","pageId":"assets.weights","title":"Use the workspace","pageTitle":"Weights Training","url":"https://teammately.ai/docs/weights-training.md","humanUrl":"https://teammately.ai/docs/weights-training#use-the-workspace","markdownUrl":"https://teammately.ai/docs/weights-training.md","sectionId":"use-the-workspace","kind":"reference","productArea":"weights_training","score":454.4103160067146,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Use the workspace\n\n1. Create a preparation for the intended Benchmark Version and method.\n2. Inspect generated examples in Dataset.\n3. Check splits and meaningful representation in Coverage.\n4. Use **Prepare download** in Overview and inspect the package settings.\n5. Download the exact ready package or use Results to configure a connected training service.\n6. Launch training deliberately and follow the recorded job.\n7. Authorize evaluation separately and inspect the actual resulting responses and judgments.\n\nA provider connection is not required to download a canonical dataset. Connected training services accept only the methods, model families and material types supported by their selected profile."},{"blockId":"admin-console.integrations#training-and-inference","pageId":"admin-console.integrations","title":"Training and inference","pageTitle":"Workspace Integrations","url":"https://teammately.ai/docs/admin-console/integrations.md","humanUrl":"https://teammately.ai/docs/admin-console/integrations#training-and-inference","markdownUrl":"https://teammately.ai/docs/admin-console/integrations.md","sectionId":"training-and-inference","kind":"reference","productArea":"admin_console","score":404.37387182866206,"reasons":["search_match","term_match"],"markdown":"## Training and inference\n\nWeights training selects an active service connection, supported model and compatible method. Connection checks do not certify quota, create-job permission, storage access or training quality.\n\nSome evaluation paths require an existing callable inference deployment. A training job does not automatically allocate serving resources for every service. The deployment-to-output association can be user-reported where the adapter identifies it that way."}]}