mirror of
https://github.com/amazon-science/chronos-forecasting
synced 2026-05-23 17:48:23 +00:00
72ab64166c
*Issue #, if available:* N/A *Description of changes:* This PR adds support for Chronos-Bolt models. TODOs: - [x] Update evaluation script - [x] Fix and add tests for Bolt - [x] Update docstrings - [x] Update README example and mention Chronos-Bolt - [x] Update results bar plot in README - [x] Add versions for libraries in `pyproject.toml` - [x] Check that the training and eval scripts work - [x] Change `autogluon` -> `amazon` in model names Post Merge: - [ ] Update Citation style in README, both Github and HuggingFace repos - [ ] Remove note about AutoGluon - [ ] Update READMEs of original Chronos models to refer to Chronos-Bolt NOTE: To be merged after Chronos-Bolt models are available under the `amazon` namespace on HF. By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice. --------- Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de> Co-authored-by: Caner Turkmen <turkmen.ac@gmail.com> Co-authored-by: Lorenzo Stella <stellalo@amazon.com>
2.1 KiB
2.1 KiB
| 1 | dataset | model | MASE | WQL |
|---|---|---|---|---|
| 2 | ETTh | amazon/chronos-t5-base | 0.7653491494991778 | 0.08087267701042929 |
| 3 | ETTm | amazon/chronos-t5-base | 0.7737006634032871 | 0.07008650633028274 |
| 4 | dominick | amazon/chronos-t5-base | 0.8194044957573132 | 0.33201307438298133 |
| 5 | ercot | amazon/chronos-t5-base | 0.5014399265038706 | 0.013589435745554596 |
| 6 | exchange_rate | amazon/chronos-t5-base | 2.055616906406159 | 0.011066070028466317 |
| 7 | m4_quarterly | amazon/chronos-t5-base | 1.2253036947743137 | 0.08327936201395683 |
| 8 | m4_yearly | amazon/chronos-t5-base | 3.639991540990927 | 0.13539258375263963 |
| 9 | m5 | amazon/chronos-t5-base | 0.9391874615167101 | 0.5867234116216755 |
| 10 | monash_australian_electricity | amazon/chronos-t5-base | 1.2944069383163321 | 0.07070604202031877 |
| 11 | monash_car_parts | amazon/chronos-t5-base | 0.9071940271035218 | 1.077797124337994 |
| 12 | monash_cif_2016 | amazon/chronos-t5-base | 0.9840747802099565 | 0.011825556826558836 |
| 13 | monash_covid_deaths | amazon/chronos-t5-base | 42.68503365359237 | 0.042229910495746356 |
| 14 | monash_fred_md | amazon/chronos-t5-base | 0.4857773806790164 | 0.021204829049512715 |
| 15 | monash_hospital | amazon/chronos-t5-base | 0.7053005021431749 | 0.05630687524507516 |
| 16 | monash_m1_monthly | amazon/chronos-t5-base | 1.1153039466137842 | 0.12724419775326076 |
| 17 | monash_m1_quarterly | amazon/chronos-t5-base | 1.746093728928804 | 0.1123583549291933 |
| 18 | monash_m1_yearly | amazon/chronos-t5-base | 4.401291522370069 | 0.18541586641719554 |
| 19 | monash_m3_monthly | amazon/chronos-t5-base | 0.8627172231908679 | 0.09640536232169555 |
| 20 | monash_m3_quarterly | amazon/chronos-t5-base | 1.1696030904401578 | 0.07392876900131434 |
| 21 | monash_m3_yearly | amazon/chronos-t5-base | 3.1298600218573775 | 0.1486674447940158 |
| 22 | monash_nn5_weekly | amazon/chronos-t5-base | 0.9334860602210187 | 0.08972736821598823 |
| 23 | monash_tourism_monthly | amazon/chronos-t5-base | 1.7937702435879332 | 0.10260220444264027 |
| 24 | monash_tourism_quarterly | amazon/chronos-t5-base | 1.7791494997972261 | 0.06852507950474919 |
| 25 | monash_tourism_yearly | amazon/chronos-t5-base | 3.8359926053603197 | 0.20722699382964643 |
| 26 | monash_traffic | amazon/chronos-t5-base | 0.8015262383138622 | 0.25565153982140926 |
| 27 | monash_weather | amazon/chronos-t5-base | 0.8159511190589147 | 0.13802320967454584 |
| 28 | nn5 | amazon/chronos-t5-base | 0.5927076179914024 | 0.1630476065585159 |