default decoder learning rate to what was in the paper

dalle2_pytorch/optimizer.py

@@ -7,7 +7,7 @@ def separate_weight_decayable_params(params):
 
 def get_optimizer(
     params,
-    lr = 2e-5,
+    lr = 1e-4,
     wd = 1e-2,
     betas = (0.9, 0.999),
     eps = 1e-8,

dalle2_pytorch/trainer.py

@@ -363,7 +363,7 @@ class DecoderTrainer(nn.Module):
         self,
         decoder,
         use_ema = True,
-        lr = 2e-5,
+        lr = 1e-4,
         wd = 1e-2,
         eps = 1e-8,
         max_grad_norm = None,

setup.py

@@ -10,7 +10,7 @@ setup(
       'dream = dalle2_pytorch.cli:dream'
     ],
   },
-  version = '0.3.0',
+  version = '0.3.1',
   license='MIT',
   description = 'DALL-E 2',
   author = 'Phil Wang',