Skip to content

Actions: mattpocock/evalite

Actions

CI Checks

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
277 workflow runs
277 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Tweak
CI Checks #27: Commit 4873e8a pushed by mattpocock
December 2, 2024 19:58 42s main
December 2, 2024 19:58 42s
Added a cacheLanguageModel function
CI Checks #26: Commit 505bfe3 pushed by mattpocock
December 2, 2024 14:48 52s main
December 2, 2024 14:48 52s
Fixed TS errors
CI Checks #25: Commit f736353 pushed by mattpocock
December 2, 2024 12:53 50s main
December 2, 2024 12:53 50s
Added readme to evalite
CI Checks #24: Commit a821a51 pushed by mattpocock
December 2, 2024 12:49 16s main
December 2, 2024 12:49 16s
Initial changeset
CI Checks #23: Commit 4ca6a7d pushed by mattpocock
December 2, 2024 12:46 16s main
December 2, 2024 12:46 16s
Moved evalite dir
CI Checks #22: Commit 5eb120a pushed by mattpocock
December 2, 2024 12:45 18s main
December 2, 2024 12:45 18s
Changed banner temporarily
CI Checks #21: Commit f50773e pushed by mattpocock
December 2, 2024 12:15 40s main
December 2, 2024 12:15 40s
Removed evalite-report.jsonl
CI Checks #20: Commit 9f37dd1 pushed by mattpocock
December 2, 2024 12:05 46s main
December 2, 2024 12:05 46s
Showed a table when there's only one eval running
CI Checks #19: Commit a85f7ee pushed by mattpocock
December 2, 2024 12:04 38s main
December 2, 2024 12:04 38s
Experiments with tuple task
CI Checks #18: Commit 4664a9f pushed by mattpocock
December 2, 2024 07:48 34s experiments-with-tuple-task
December 2, 2024 07:48 34s
Tweak
CI Checks #17: Commit a5263dc pushed by mattpocock
November 30, 2024 19:55 35s main
November 30, 2024 19:55 35s
Added a hash of the source code to the evals db
CI Checks #16: Commit f3a067f pushed by mattpocock
November 30, 2024 18:54 34s main
November 30, 2024 18:54 34s
Removed globals
CI Checks #15: Commit bef1956 pushed by mattpocock
November 30, 2024 13:59 38s main
November 30, 2024 13:59 38s
Tweak
CI Checks #14: Commit c293e77 pushed by mattpocock
November 30, 2024 13:39 37s main
November 30, 2024 13:39 37s
Added tests and improved core code
CI Checks #13: Commit 8012fe9 pushed by mattpocock
November 30, 2024 13:38 41s main
November 30, 2024 13:38 41s
Changed the DB structure so that it saves evals, not files in the jsonl
CI Checks #12: Commit fc0cdcc pushed by mattpocock
November 30, 2024 10:02 42s main
November 30, 2024 10:02 42s
Made the evalite-report.jsonl local to the output of the command
CI Checks #11: Commit 86c773e pushed by mattpocock
November 30, 2024 09:46 32s main
November 30, 2024 09:46 32s
Created a test harness and used vitest/node
CI Checks #10: Commit c8252a8 pushed by mattpocock
November 30, 2024 08:53 33s main
November 30, 2024 08:53 33s
More checks
CI Checks #9: Commit e37e4fd pushed by mattpocock
November 15, 2024 19:15 26s main
November 15, 2024 19:15 26s
Upgraded turbo
CI Checks #8: Commit 71d8cfb pushed by mattpocock
November 15, 2024 16:04 28s main
November 15, 2024 16:04 28s
Added task view page
CI Checks #7: Commit a3747e3 pushed by mattpocock
November 15, 2024 16:01 27s main
November 15, 2024 16:01 27s
More improvement to file viewing in the UI
CI Checks #6: Commit 92e3d95 pushed by mattpocock
November 15, 2024 14:35 30s main
November 15, 2024 14:35 30s
Began work on the evalite ui
CI Checks #5: Commit 4d3d44a pushed by mattpocock
November 15, 2024 12:18 28s main
November 15, 2024 12:18 28s
Improved outputs by adding the expected text
CI Checks #4: Commit e510833 pushed by mattpocock
November 14, 2024 16:30 23s main
November 14, 2024 16:30 23s
Parallelized test runner
CI Checks #3: Commit 42191e4 pushed by mattpocock
November 14, 2024 15:30 24s main
November 14, 2024 15:30 24s
ProTip! You can narrow down the results and go further in time using created:<2024-11-14 or the other filters available.