[chore] Revert environment: secrets changes & cleanup finetuned models

[gee-senbong]

This PR

• reverts changes in chore(deps): bump werkzeug from 3.1.5 to 3.1.6 #768 in an attempt to fix bot created PR permission issue
• adds a cleanup step before each tests to make sure finetuned models created more than 1 hours ago are removed
• adds pip cache clearing before the Snowflake packaging step

[elessar-for-github]

Changes made by this pull request:

.github/workflows/ci.yaml
[Error processing diff]

.github/workflows/pytest.yml
[Error processing diff]

[github-actions]

Experiment Results

Experiment 1: air-passengers

Description:

variable	experiment
h	12
season_length	12
freq	MS
level	None
n_windows	1

Results:

metric	timegpt-1	timegpt-1-long-horizon	SeasonalNaive	Naive
mae	12.6793	11.0623	47.8333	76
mape	0.027	0.0232	0.0999	0.1425
mse	213.936	199.132	2571.33	10604.2
total_time	14.0609	1.2824	0.0045	0.0035

Plot:

Experiment 2: air-passengers

Description:

variable	experiment
h	24
season_length	12
freq	MS
level	None
n_windows	1

Results:

metric	timegpt-1	timegpt-1-long-horizon	SeasonalNaive	Naive
mae	58.1031	58.4587	71.25	115.25
mape	0.1257	0.1267	0.1552	0.2358
mse	4040.21	4110.79	5928.17	18859.2
total_time	1.7462	0.7312	0.004	0.0035

Plot:

Experiment 3: electricity-multiple-series

Description:

variable	experiment
h	24
season_length	24
freq	H
level	None
n_windows	1

Results:

metric	timegpt-1	timegpt-1-long-horizon	SeasonalNaive	Naive
mae	178.293	268.13	269.23	1331.02
mape	0.0234	0.0311	0.0304	0.1692
mse	121589	219485	213677	4.68961e+06
total_time	1.1601	1.3062	0.005	0.0044

Plot:

Experiment 4: electricity-multiple-series

Description:

variable	experiment
h	168
season_length	24
freq	H
level	None
n_windows	1

Results:

metric	timegpt-1	timegpt-1-long-horizon	SeasonalNaive	Naive
mae	465.497	346.972	398.956	1119.26
mape	0.062	0.0436	0.0512	0.1583
mse	835021	403760	656723	3.17316e+06
total_time	0.8054	1.3598	0.0052	0.0045

Plot:

Experiment 5: electricity-multiple-series

Description:

variable	experiment
h	336
season_length	24
freq	H
level	None
n_windows	1

Results:

metric	timegpt-1	timegpt-1-long-horizon	SeasonalNaive	Naive
mae	558.673	459.757	602.926	1340.95
mape	0.0697	0.0565	0.0787	0.17
mse	1.22723e+06	739114	1.61572e+06	6.04619e+06
total_time	1.0088	0.8961	0.0052	0.0046

Plot:

[JQGoh]

thanks for this fix, better than my suggestion

[JQGoh]

Test run on windows https://github.com/Nixtla/nixtla/actions/runs/23035439135/job/66902312995?pr=774

returns error like
UnicodeEncodeError: 'charmap' codec can't encode character '\u2713' in position 0: character maps to <undefined>

This is minor but could improve the printing of information.