Rowan Walshe cca2da835c Merge branch 'topic/Add-ability-to-unpack-generated-and-evaluated-datasets' into 'main' ...

Make it possible to unpack generated and evaluated datasets

See merge request eng/ai/ada-eval!20

2026-01-29 13:54:45 +00:00

..

data

Remove the proof_steps metric

2026-01-28 10:32:37 +00:00

conftest.py

Add tests

2025-11-17 18:44:24 +00:00

helpers.py

Use conftest.py for fixtures

2025-11-04 14:18:21 +00:00

test_check_datasets.py

Migrate dataset file contents to base64 encoding

2026-01-26 17:17:13 +00:00

test_cli.py

Restore signature of report_evaluation_results()

2025-11-19 10:08:23 +00:00

test_datasets.py

Use conftest.py for fixtures

2025-11-04 14:18:21 +00:00

test_directory_contents.py

Migrate dataset file contents to base64 encoding

2026-01-26 17:17:13 +00:00

test_evals.py

Remove the proof_steps metric

2026-01-28 10:32:37 +00:00

test_loader.py

Remove the proof_steps metric

2026-01-28 10:32:37 +00:00

test_metrics.py

Simplify Metric constructors

2025-11-18 16:16:27 +00:00

test_pack_unpack_datasets.py

Use conftest.py for fixtures

2025-11-04 14:18:21 +00:00

test_report.py

Remove the proof_steps metric

2026-01-28 10:32:37 +00:00

test_samples.py

Self-review

2025-09-03 17:09:08 +01:00

test_tools.py

Migrate dataset file contents to base64 encoding

2026-01-26 17:17:13 +00:00

test_unpack_generated_evaluated.py

Apply 1 suggestion(s) to 1 file(s)

2026-01-29 13:47:27 +00:00

test_utils.py

Self-review

2025-10-30 11:12:18 +00:00