mirror of
https://github.com/amazon-science/chronos-forecasting
synced 2026-05-23 01:29:48 +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 KiB
2 KiB
| 1 | dataset | model | MASE | WQL |
|---|---|---|---|---|
| 2 | ETTh | amazon/chronos-t5-tiny | 0.8184074113571701 | 0.08578203438707048 |
| 3 | ETTm | amazon/chronos-t5-tiny | 0.9103621000781905 | 0.07975361086322658 |
| 4 | dominick | amazon/chronos-t5-tiny | 0.8538295532466194 | 0.3597090770361857 |
| 5 | ercot | amazon/chronos-t5-tiny | 0.7273437589773705 | 0.020843170924006626 |
| 6 | exchange_rate | amazon/chronos-t5-tiny | 1.6621128608546154 | 0.01085145980896454 |
| 7 | m4_quarterly | amazon/chronos-t5-tiny | 1.2696259955861924 | 0.0861404188925996 |
| 8 | m4_yearly | amazon/chronos-t5-tiny | 3.5293881164900527 | 0.13281575565500411 |
| 9 | m5 | amazon/chronos-t5-tiny | 0.9394059505709506 | 0.5981531758388589 |
| 10 | monash_australian_electricity | amazon/chronos-t5-tiny | 1.4558820561269024 | 0.07673567331332948 |
| 11 | monash_car_parts | amazon/chronos-t5-tiny | 0.9058206654011024 | 1.0236307963149358 |
| 12 | monash_cif_2016 | amazon/chronos-t5-tiny | 1.09349564130852 | 0.014066593076202984 |
| 13 | monash_covid_deaths | amazon/chronos-t5-tiny | 46.53079664940016 | 0.09201919385053775 |
| 14 | monash_fred_md | amazon/chronos-t5-tiny | 0.48008374212956456 | 0.03219550761153211 |
| 15 | monash_hospital | amazon/chronos-t5-tiny | 0.7062562198194838 | 0.05790409320432609 |
| 16 | monash_m1_monthly | amazon/chronos-t5-tiny | 1.214892145549996 | 0.14723095246308077 |
| 17 | monash_m1_quarterly | amazon/chronos-t5-tiny | 1.8968576926613199 | 0.11026972972622998 |
| 18 | monash_m1_yearly | amazon/chronos-t5-tiny | 4.829453202075546 | 0.17286063726000958 |
| 19 | monash_m3_monthly | amazon/chronos-t5-tiny | 0.9095746605884618 | 0.10117875324490073 |
| 20 | monash_m3_quarterly | amazon/chronos-t5-tiny | 1.3234957548639883 | 0.08209032993637215 |
| 21 | monash_m3_yearly | amazon/chronos-t5-tiny | 3.1489371074890093 | 0.1492445630072877 |
| 22 | monash_nn5_weekly | amazon/chronos-t5-tiny | 0.9637480731663901 | 0.09205994784693056 |
| 23 | monash_tourism_monthly | amazon/chronos-t5-tiny | 2.151677532807024 | 0.11356761694754255 |
| 24 | monash_tourism_quarterly | amazon/chronos-t5-tiny | 1.9116538900950555 | 0.07191734222366106 |
| 25 | monash_tourism_yearly | amazon/chronos-t5-tiny | 3.820615532600914 | 0.19709256337364625 |
| 26 | monash_traffic | amazon/chronos-t5-tiny | 0.878709088458116 | 0.2632101606272236 |
| 27 | monash_weather | amazon/chronos-t5-tiny | 0.8504899606521996 | 0.14787595319625085 |
| 28 | nn5 | amazon/chronos-t5-tiny | 0.7021735456568664 | 0.19071330483289695 |