Add gradient clipping options to optimizer

Introduces options for clipping gradients by global norm or by value,
configurable via `config.opt_enable_grad_global_norm_clipping` and
`config.opt_enable_grad_clipping`, as well as  `config.max_grad_norm`
and `config.max_grad_value`.

Co-authored-by: martinarroyo <martinarroyo@google.com>

Author: ninatu

src/maxdiffusion/configs/base14.yml

@@ -206,6 +206,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 1.e-2 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base21.yml

@@ -211,6 +211,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 1.e-2 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_2_base.yml

@@ -221,6 +221,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 1.e-2 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_flux_dev.yml

@@ -245,6 +245,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 0 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_flux_dev_multi_res.yml

@@ -232,6 +232,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 1.e-2 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_flux_schnell.yml

@@ -240,6 +240,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 1.e-2 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_wan_14b.yml

@@ -302,6 +302,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 0.0 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_wan_1_3b.yml

@@ -258,6 +258,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 0.0 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_wan_27b.yml

@@ -268,6 +268,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 0.0 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False

src/maxdiffusion/configs/base_wan_i2v_14b.yml

@@ -263,6 +263,9 @@ adam_b1: 0.9 # Exponential decay rate to track the first moment of past gradient
 adam_b2: 0.999 # Exponential decay rate to track the second moment of past gradients.
 adam_eps: 1.e-8 # A small constant applied to denominator outside of the square root.
 adam_weight_decay: 0.0 # AdamW Weight decay
+opt_enable_grad_clipping: False
+max_grad_value: 1.0
+opt_enable_grad_global_norm_clipping: False
 max_grad_norm: 1.0
 
 enable_profiler: False