diff --git a/Project.toml b/Project.toml
index 08a6e6de6..a034496aa 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,7 +1,7 @@
 name = "Lux"
 uuid = "b2108857-7c20-44ae-9111-449ecde12c47"
 authors = ["Avik Pal <avikpal@mit.edu> and contributors"]
-version = "1.2.2"
+version = "1.2.3"
 
 [deps]
 ADTypes = "47edcb42-4c32-4615-8424-f2b9edc5f35b"
@@ -95,7 +95,7 @@ MacroTools = "0.5.13"
 Markdown = "1.10"
 NCCL = "0.1.1"
 NNlib = "0.9.24"
-Optimisers = "0.3.3"
+Optimisers = "0.3.3, 4"
 Preferences = "1.4.3"
 Random = "1.10"
 Reactant = "0.2.4"
diff --git a/docs/Project.toml b/docs/Project.toml
index a48d7c818..2de8220ce 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -50,7 +50,7 @@ LuxCore = "1"
 LuxLib = "1.3.4"
 LuxTestUtils = "1.5"
 MLDataDevices = "1.4"
-Optimisers = "0.3.3"
+Optimisers = "0.3.3, 4"
 Pkg = "1.10"
 Printf = "1.10"
 Random = "1.10"
diff --git a/examples/Basics/Project.toml b/examples/Basics/Project.toml
index f24bb08ca..94d8344d2 100644
--- a/examples/Basics/Project.toml
+++ b/examples/Basics/Project.toml
@@ -13,5 +13,5 @@ ComponentArrays = "0.15"
 ForwardDiff = "0.10"
 Lux = "1"
 LuxCUDA = "0.3"
-Optimisers = "0.3"
+Optimisers = "0.3.3, 4"
 Zygote = "0.6"
diff --git a/examples/ConvMixer/Project.toml b/examples/ConvMixer/Project.toml
index acfbd4758..afe7bf29e 100644
--- a/examples/ConvMixer/Project.toml
+++ b/examples/ConvMixer/Project.toml
@@ -31,7 +31,7 @@ LuxCUDA = "0.3.2"
 MLDatasets = "0.7.14"
 MLUtils = "0.4.4"
 OneHotArrays = "0.2.5"
-Optimisers = "0.3.3"
+Optimisers = "0.3.3, 4"
 PreferenceTools = "0.1.2"
 Printf = "1.10"
 ProgressBars = "1.5.1"
diff --git a/examples/HyperNet/Project.toml b/examples/HyperNet/Project.toml
index 9213cd35f..b82231620 100644
--- a/examples/HyperNet/Project.toml
+++ b/examples/HyperNet/Project.toml
@@ -21,7 +21,7 @@ LuxCUDA = "0.3"
 MLDatasets = "0.7"
 MLUtils = "0.4"
 OneHotArrays = "0.2"
-Optimisers = "0.3"
+Optimisers = "0.3.3, 4"
 Setfield = "1"
 Statistics = "1"
 Zygote = "0.6"
diff --git a/examples/ImageNet/Project.toml b/examples/ImageNet/Project.toml
index 7abae248c..27e370638 100644
--- a/examples/ImageNet/Project.toml
+++ b/examples/ImageNet/Project.toml
@@ -38,7 +38,7 @@ MLUtils = "0.4.4"
 MPI = "0.20.21"
 NCCL = "0.1.1"
 OneHotArrays = "0.2.5"
-Optimisers = "0.3.3"
+Optimisers = "0.3.3, 4"
 ParameterSchedulers = "0.4.2"
 Random = "1.10"
 Setfield = "1.1.1"
diff --git a/examples/NeuralODE/Project.toml b/examples/NeuralODE/Project.toml
index 69f354cfb..302b234a8 100644
--- a/examples/NeuralODE/Project.toml
+++ b/examples/NeuralODE/Project.toml
@@ -21,7 +21,7 @@ LuxCUDA = "0.3"
 MLDatasets = "0.7"
 MLUtils = "0.4"
 OneHotArrays = "0.2"
-Optimisers = "0.3"
+Optimisers = "0.3.3, 4"
 OrdinaryDiffEqTsit5 = "1"
 SciMLSensitivity = "7.63"
 Statistics = "1"
diff --git a/examples/PINN2DPDE/Project.toml b/examples/PINN2DPDE/Project.toml
index 7b1a5787a..751c175a7 100644
--- a/examples/PINN2DPDE/Project.toml
+++ b/examples/PINN2DPDE/Project.toml
@@ -18,7 +18,7 @@ Lux = "1"
 LuxCUDA = "0.3.3"
 MLUtils = "0.4.4"
 OnlineStats = "1.7.1"
-Optimisers = "0.3.3"
+Optimisers = "0.3.3, 4"
 Printf = "1.10"
 Random = "1.10"
 Statistics = "1.10"
diff --git a/examples/PolynomialFitting/Project.toml b/examples/PolynomialFitting/Project.toml
index b607ee600..940ea7dd7 100644
--- a/examples/PolynomialFitting/Project.toml
+++ b/examples/PolynomialFitting/Project.toml
@@ -14,6 +14,6 @@ ADTypes = "1"
 CairoMakie = "0.12"
 Lux = "1"
 LuxCUDA = "0.3"
-Optimisers = "0.3"
+Optimisers = "0.3.3, 4"
 Statistics = "1"
 Zygote = "0.6"
diff --git a/examples/SimpleChains/Project.toml b/examples/SimpleChains/Project.toml
index 8d504559f..4028a4696 100644
--- a/examples/SimpleChains/Project.toml
+++ b/examples/SimpleChains/Project.toml
@@ -16,7 +16,7 @@ Lux = "1"
 MLDatasets = "0.7.14"
 MLUtils = "0.4"
 OneHotArrays = "0.2.5"
-Optimisers = "0.3.2"
+Optimisers = "0.3.3, 4"
 Random = "1"
 SimpleChains = "0.4.6"
 Zygote = "0.6.69"
diff --git a/examples/SimpleRNN/Project.toml b/examples/SimpleRNN/Project.toml
index 2bd4f5864..89f833426 100644
--- a/examples/SimpleRNN/Project.toml
+++ b/examples/SimpleRNN/Project.toml
@@ -16,6 +16,6 @@ JLD2 = "0.5"
 Lux = "1"
 LuxCUDA = "0.3"
 MLUtils = "0.4"
-Optimisers = "0.3"
+Optimisers = "0.3.3, 4"
 Statistics = "1"
 Zygote = "0.6"
diff --git a/lib/LuxCore/test/Project.toml b/lib/LuxCore/test/Project.toml
index 6d3c3d7f7..be5a6f628 100644
--- a/lib/LuxCore/test/Project.toml
+++ b/lib/LuxCore/test/Project.toml
@@ -15,6 +15,6 @@ EnzymeCore = "0.8.5"
 ExplicitImports = "1.9.0"
 Functors = "0.4.12"
 MLDataDevices = "1.0.0"
-Optimisers = "0.3.3"
+Optimisers = "0.3.3, 4"
 Random = "1.10"
 Test = "1.10"
diff --git a/test/Project.toml b/test/Project.toml
index 90ee23de9..c3b5a23ba 100644
--- a/test/Project.toml
+++ b/test/Project.toml
@@ -65,7 +65,7 @@ MLUtils = "0.4.3"
 NNlib = "0.9.24"
 Octavian = "0.3.28"
 OneHotArrays = "0.2.5"
-Optimisers = "0.3.3"
+Optimisers = "0.3.3, 4"
 Pkg = "1.10"
 Preferences = "1.4.3"
 Random = "1.10"