autogluon.timeseries 1.1.2b20241120__tar.gz → 1.1.2b20241122__tar.gz

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.2b20241120
+Version: 1.1.2b20241122
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/setup.py

@@ -30,7 +30,7 @@ install_requires = [
     "pytorch_lightning",  # version range defined in `core/_setup_utils.py`
     "transformers[sentencepiece]",  # version range defined in `core/_setup_utils.py`
     "accelerate",  # version range defined in `core/_setup_utils.py`
-    "gluonts==0.16.0",
+    "gluonts>=0.15.0,<0.17",
     "networkx",  # version range defined in `core/_setup_utils.py`
     "statsforecast>=1.7.0,<1.8",
     "mlforecast==0.13.4",

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/src/autogluon/timeseries/configs/presets_configs.py

@@ -12,19 +12,19 @@ TIMESERIES_PRESETS_CONFIGS = dict(
     fast_training={"hyperparameters": "very_light"},
     # Chronos-Bolt models
     bolt_tiny={
-        "hyperparameters": {"Chronos": {"model_path": "bolt-tiny"}},
+        "hyperparameters": {"Chronos": {"model_path": "bolt_tiny"}},
         "skip_model_selection": True,
     },
     bolt_mini={
-        "hyperparameters": {"Chronos": {"model_path": "bolt-mini"}},
+        "hyperparameters": {"Chronos": {"model_path": "bolt_mini"}},
         "skip_model_selection": True,
     },
     bolt_small={
-        "hyperparameters": {"Chronos": {"model_path": "bolt-small"}},
+        "hyperparameters": {"Chronos": {"model_path": "bolt_small"}},
         "skip_model_selection": True,
     },
     bolt_base={
-        "hyperparameters": {"Chronos": {"model_path": "bolt-base"}},
+        "hyperparameters": {"Chronos": {"model_path": "bolt_base"}},
         "skip_model_selection": True,
     },
     # Original Chronos models

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/src/autogluon/timeseries/models/chronos/model.py

@@ -67,10 +67,10 @@ MODEL_ALIASES = {
     "small": "autogluon/chronos-t5-small",
     "base": "autogluon/chronos-t5-base",
     "large": "autogluon/chronos-t5-large",
-    "bolt-tiny": "autogluon/chronos-bolt-tiny",
-    "bolt-mini": "autogluon/chronos-bolt-mini",
-    "bolt-small": "autogluon/chronos-bolt-small",
-    "bolt-base": "autogluon/chronos-bolt-base",
+    "bolt_tiny": "autogluon/chronos-bolt-tiny",
+    "bolt_mini": "autogluon/chronos-bolt-mini",
+    "bolt_small": "autogluon/chronos-bolt-small",
+    "bolt_base": "autogluon/chronos-bolt-base",
 }
 
 
@@ -109,7 +109,7 @@ class ChronosModel(AbstractTimeSeriesModel):
         compatible model name on HuggingFace Hub or a local path to a model directory. Original
         Chronos models (i.e., ``autogluon/chronos-t5-{model_size}``) can be specified with aliases
         ``tiny``, ``mini`` , ``small``, ``base``, and ``large``. Chronos-Bolt models can be specified
-        with ``bolt-mini``, ``bolt-small``, and ``bolt-base``.
+        with ``bolt_tiny``, ``bolt_mini``, ``bolt_small``, and ``bolt_base``.
     batch_size : int, default = 16
         Size of batches used during inference
     num_samples : int, default = 20
@@ -140,8 +140,9 @@ class ChronosModel(AbstractTimeSeriesModel):
         for more information.
     fine_tune : bool, default = False
         If True, the pretrained model will be fine-tuned
-    fine_tune_lr: float, default = 0.0001
-        The learning rate used for fine-tuning
+    fine_tune_lr: float, default = 1e-5
+        The learning rate used for fine-tuning. This default is suitable for Chronos-Bolt models; for the original
+        Chronos models, we recommend using a higher learning rate such as ``1e-4``
     fine_tune_steps : int, default = 1000
         The number of gradient update steps to fine-tune for
     fine_tune_batch_size : int, default = 32
@@ -321,7 +322,7 @@ class ChronosModel(AbstractTimeSeriesModel):
 
         init_args.setdefault("fine_tune", False)
         init_args.setdefault("keep_transformers_logs", False)
-        init_args.setdefault("fine_tune_lr", 1e-4)
+        init_args.setdefault("fine_tune_lr", 1e-5)
         init_args.setdefault("fine_tune_steps", 1000)
         init_args.setdefault("fine_tune_batch_size", 32)
         init_args.setdefault("eval_during_fine_tune", False)

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/src/autogluon/timeseries/models/presets.py

@@ -134,7 +134,7 @@ def get_default_hps(key):
             "RecursiveTabular": {},
             "DirectTabular": {},
             "TemporalFusionTransformer": {},
-            "Chronos": {"model_path": "bolt-small"},
+            "Chronos": {"model_path": "bolt_small"},
         },
         "light_inference": {
             "SeasonalNaive": {},
@@ -157,11 +157,11 @@ def get_default_hps(key):
             "Chronos": [
                 {
                     "ag_args": {"name_suffix": "ZeroShot"},
-                    "model_path": "bolt-base",
+                    "model_path": "bolt_base",
                 },
                 {
                     "ag_args": {"name_suffix": "FineTuned"},
-                    "model_path": "bolt-small",
+                    "model_path": "bolt_small",
                     "fine_tune": True,
                     "target_scaler": "standard",
                     "covariate_regressor": {"model_name": "CAT", "model_hyperparameters": {"iterations": 1_000}},

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/src/autogluon/timeseries/version.py

@@ -1,3 +1,3 @@
 """This is the autogluon version file."""
-__version__ = '1.1.2b20241120'
+__version__ = '1.1.2b20241122'
 __lite__ = False

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/src/autogluon.timeseries.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: autogluon.timeseries
-Version: 1.1.2b20241120
+Version: 1.1.2b20241122
 Summary: Fast and Accurate ML in 3 Lines of Code
 Home-page: https://github.com/autogluon/autogluon
 Author: AutoGluon Community

{autogluon.timeseries-1.1.2b20241120 → autogluon.timeseries-1.1.2b20241122}/src/autogluon.timeseries.egg-info/requires.txt

@@ -1,13 +1,13 @@
 joblib<2,>=1.1
-numpy<1.29,>=1.21
-scipy<1.13,>=1.5.4
+numpy<2.1.4,>=1.25.0
+scipy<1.16,>=1.5.4
 pandas<2.3.0,>=2.0.0
 torch<2.6,>=2.2
 lightning<2.6,>=2.2
 pytorch_lightning
 transformers[sentencepiece]<5,>=4.38.0
 accelerate<1.0,>=0.32.0
-gluonts==0.16.0
+gluonts<0.17,>=0.15.0
 networkx<4,>=3.0
 statsforecast<1.8,>=1.7.0
 mlforecast==0.13.4
@@ -17,9 +17,9 @@ fugue>=0.9.0
 tqdm<5,>=4.38
 orjson~=3.9
 tensorboard<3,>=2.9
-autogluon.core[raytune]==1.1.2b20241120
-autogluon.common==1.1.2b20241120
-autogluon.tabular[catboost,lightgbm,xgboost]==1.1.2b20241120
+autogluon.core[raytune]==1.1.2b20241122
+autogluon.common==1.1.2b20241122
+autogluon.tabular[catboost,lightgbm,xgboost]==1.1.2b20241122
 
 [all]
 optimum[onnxruntime]<1.20,>=1.17