Kanha Qwen3 experiment

Run identity

• Run ID: incidentio-incidents-1.7b-full-v1
• Base model: Qwen/Qwen3-1.7B
• Base model revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
• Tokenizer revision: 70d244cc86ccca08cf5af4e1e306ecf908b1ad5e
• Training method: full
• Final merged dtype: bfloat16
• Source site: https://docs.incident.io
• Dataset hash: 60d31b62ef843cac4863ffbed1c16127dcc53899c11f137bd802df4191804a94
• Train split: 276 records (c9f3c08e10208c56db651f2df9341c18c6e87f8c89fbfe1675f3eee9ec044659)
• Validation split: 33 records (eb14d70e7e0b965785778acea21669327bb0d7a13c8367356876afc0e8a714c4)
• Holdout split: 0 records (e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855)

Hyperparameters

• Maximum sequence length: 2048
• Seed: 42
• Epochs: 4.0
• Learning rate: 1e-05
• Per-device batch size: 4
• Gradient accumulation steps: 2
• Warmup ratio: 0.1
• Assistant-only loss: true

Evaluation

• dates_recall: 1.0
• deterministic_pass_rate: 0.0
• list_recall: 1.0
• numbers_recall: 1.0
• refusal_rate: 0.0
• requires_review_rate: 1.0
• total: 3
• unsupported_value_rate: 0.0
• urls_recall: 1.0

Deterministic scoring and the server-side Transformers benchmark are not browser qualification. Validate the exact converted model in the target browser and device environments.

MLC availability

No validated MLC artifact is included in this publication.

Intended use

This checkpoint is intended for research comparing training methods on the same Kanha website-derived dataset and for controlled evaluation of website question answering.

Limitations

The checkpoint can produce incorrect, incomplete, or stale answers. It may memorize training content. Review outputs, test representative failure cases, and qualify the exact runtime before any user-facing use.

Provenance artifacts

• research/run-manifest.json
• research/training-config.yaml
• research/publication-inventory.json
• research/evaluation/metrics.json
• research/evaluation/evaluation-manifest.json