Adding BNB 8-bit Adam

model/supervised_finetuning/configs/config.yaml

@@ -22,7 +22,7 @@ defaults:
   loss_fn: CrossEntropyLoss
   eval_size:
   log_dir: "base"
-  quantization:
+  quantization: false
 
 galactica-125:
   learning_rate: 5e-5
@@ -62,4 +62,4 @@ debug:
   gradient_accumulation_steps: 1
   per_device_train_batch_size: 1
   per_device_eval_batch_size: 1
-  quantization:
+  quantization: false