fbshipit-source-id: e833f2d6926cd4dd03063cc657886685a84b7b14

Author: vineelpratap

flashlight/autograd/Variable.h

@@ -222,8 +222,8 @@ class Variable {
 
   /**
    * Run backward pass on the Variable.  Gradient of all the inputs
-   * in the computation graph leading up to the Variable on which the function is
-   * computed.
+   * in the computation graph leading up to the Variable on which the function
+   * is computed.
    * @param[in] grad gradient w.r.t to the Variable
    * @param[in] retainGraph If False, clears the input Variables stored
    * by the Variable
@@ -232,8 +232,9 @@ class Variable {
 
   /**
    * Run backward pass on the Variable. Gradient of all the inputs
-   * in the computation graph leading up to the Variable on which the function is
-   * computed. Gradient w.r.t the all the elements in the variable is set to 1.0
+   * in the computation graph leading up to the Variable on which the function
+   * is computed. Gradient w.r.t the all the elements in the variable is set
+   * to 1.0
    * @param[in] retainGraph If False, clears the input Variables stored
    * by the Variable
    */

flashlight/nn/modules/AdaptiveSoftMaxLoss.h

@@ -65,8 +65,8 @@ class AdaptiveSoftMaxLoss : public BinaryModule {
    * first tail bucket will contain `50 - 5 = 45` targets (subtracting the size
    * of the head bucket), the second tail bucket will contain `100 - 50 = 50`
    * targets (subtracting the size of the first tail bucket). Cutoffs must be
-   * specified to accommodate all targets: any remaining targets are not assigned
-   * to an 'overflow' bucket.
+   * specified to accommodate all targets: any remaining targets are not
+   * assigned to an 'overflow' bucket.
    * @param div_value determines the number of hidden units in the intermediate
    * layer for each tail bucket:
    * \f[