diff --git a/library/train_util.py b/library/train_util.py
index 5a8da90e1..c4845c54b 100644
--- a/library/train_util.py
+++ b/library/train_util.py
@@ -2994,7 +2994,7 @@ def int_or_float(value):
         "--optimizer_type",
         type=str,
         default="",
-        help="Optimizer to use / オプティマイザの種類: AdamW (default), AdamW8bit, PagedAdamW, PagedAdamW8bit, PagedAdamW32bit, Lion8bit, PagedLion8bit, Lion, SGDNesterov, SGDNesterov8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, AdaFactor",
+        help="Optimizer to use / オプティマイザの種類: AdamW (default), AdamW8bit, PagedAdamW, PagedAdamW8bit, PagedAdamW32bit, Lion8bit, PagedLion8bit, Lion, AdEMAMix8bit, PagedAdEMAMix8bit, SGDNesterov, SGDNesterov8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, AdaFactor",
     )
 
     # backward compatibility
@@ -4032,7 +4032,7 @@ def task():
 
 
 def get_optimizer(args, trainable_params):
-    # "Optimizer to use: AdamW, AdamW8bit, Lion, SGDNesterov, SGDNesterov8bit, PagedAdamW, PagedAdamW8bit, PagedAdamW32bit, Lion8bit, PagedLion8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, Adafactor"
+    # "Optimizer to use: AdamW, AdamW8bit, Lion, SGDNesterov, SGDNesterov8bit, PagedAdamW, PagedAdamW8bit, PagedAdamW32bit, Lion8bit, PagedLion8bit, AdEMAMix8bit, PagedAdEMAMix8bit, DAdaptation(DAdaptAdamPreprint), DAdaptAdaGrad, DAdaptAdam, DAdaptAdan, DAdaptAdanIP, DAdaptLion, DAdaptSGD, Adafactor"
 
     optimizer_type = args.optimizer_type
     if args.use_8bit_adam:
diff --git a/requirements.txt b/requirements.txt
index 15e6e58f1..e6e1bf6fc 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,7 +6,7 @@ ftfy==6.1.1
 opencv-python==4.8.1.78
 einops==0.7.0
 pytorch-lightning==1.9.0
-bitsandbytes==0.43.0
+bitsandbytes==0.44.0
 prodigyopt==1.0
 lion-pytorch==0.0.6
 tensorboard