Merge pull request #22 from zhaiwenxi/docs-dpa-adapt-lr-batch-size

zhaiwenxi · web-flow · commit 8e7c1ff52547 · 2026-06-15T11:27:43.000+08:00
docs: show lr and batch size for dpa adapt tuning
diff --git a/doc/dpa_adapt/README.md b/doc/dpa_adapt/README.md
@@ -40,6 +40,8 @@ model = DPAFineTuner(
     pretrained="DPA-3.1-3M", 
     strategy="frozen_head",  #"frozen_head" | "finetune"
     property_name="homo",
+    learning_rate=1e-3,
+    batch_size=512,
 )
 model.fit(train_data="/data/train", valid_data="/data/valid")
 

Original file line number	Diff line number	Diff line change
`@@ -40,6 +40,8 @@ model = DPAFineTuner(`
`40`	`40`	`pretrained="DPA-3.1-3M",`
`41`	`41`	`strategy="frozen_head", #"frozen_head" \| "finetune"`
`42`	`42`	`property_name="homo",`
	`43`	`+ learning_rate=1e-3,`
	`44`	`+ batch_size=512,`
`43`	`45`	`)`
`44`	`46`	`model.fit(train_data="/data/train", valid_data="/data/valid")`
`45`	`47`