Try to fix Inductor CI periodic tests (#160932)

- hf_Reformer: this one starts failing due to increased graph breaks due to transformers pin bump (#159291). We can likely just bump the expected graph break count.
- dla102: this one starts timing out on 8/13 Wed between commit 6e8865f and ee1b041. But based on the PT2 dashboard, this model actually doesn't have compile time or runtime regression. Will try to bump up the timeout and see if it can work.
- hf_BigBird: this one has its accuracy status improved since today. Will update hf_BigBird accuracy status.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/160932
Approved by: https://github.com/zou3519, https://github.com/huydhn, https://github.com/malfet

benchmarks/dynamo/ci_expected_accuracy/aot_inductor_huggingface_inference.csv

@@ -58,7 +58,7 @@ DistilBertForQuestionAnswering,pass,0
 
 
 
-DistillGPT2,pass,2
+DistillGPT2,pass,0
 
 
 

benchmarks/dynamo/ci_expected_accuracy/cpu_aot_inductor_freezing_huggingface_inference.csv

@@ -58,7 +58,7 @@ DistilBertForQuestionAnswering,pass,0
 
 
 
-DistillGPT2,pass,2
+DistillGPT2,pass,0
 
 
 

benchmarks/dynamo/ci_expected_accuracy/cpu_inductor_amp_freezing_timm_inference.csv

@@ -46,7 +46,7 @@ deit_base_distilled_patch16_224,pass,0
 
 
 
-dla102,pass,0
+dla102,timeout,0
 
 
 

benchmarks/dynamo/ci_expected_accuracy/cpu_inductor_amp_freezing_torchbench_inference.csv

@@ -346,7 +346,7 @@ vgg16,pass,0
 
 
 
-vision_maskrcnn,fail_accuracy,30
+vision_maskrcnn,fail_accuracy,29
 
 
 

benchmarks/dynamo/ci_expected_accuracy/cpu_inductor_freezing_timm_inference.csv

@@ -46,7 +46,7 @@ deit_base_distilled_patch16_224,pass,0
 
 
 
-dla102,pass,0
+dla102,timeout,0
 
 
 

benchmarks/dynamo/ci_expected_accuracy/dynamic_aot_eager_torchbench_inference.csv

@@ -146,7 +146,7 @@ hf_Bert_large,pass,0
 
 
 
-hf_BigBird,fail_to_run,0
+hf_BigBird,pass,0
 
 
 

benchmarks/dynamo/ci_expected_accuracy/dynamic_aot_eager_torchbench_training.csv

@@ -110,7 +110,7 @@ hf_GPT2_large,pass_due_to_skip,0
 
 
 
-hf_Reformer,fail_to_run,19
+hf_Reformer,fail_to_run,21
 
 
 

benchmarks/dynamo/ci_expected_accuracy/dynamic_cpu_aot_inductor_freezing_torchbench_inference.csv

@@ -34,7 +34,7 @@ basic_gnn_gin,pass,0
 
 
 
-basic_gnn_sage,fail_to_run,0
+basic_gnn_sage,pass,0
 
 
 

benchmarks/dynamo/ci_expected_accuracy/dynamic_inductor_torchbench_inference.csv

@@ -146,7 +146,7 @@ hf_Bert_large,pass,0
 
 
 
-hf_BigBird,fail_to_run,0
+hf_BigBird,fail_accuracy,0
 
 
 

benchmarks/dynamo/ci_expected_accuracy/dynamic_inductor_torchbench_training.csv

@@ -110,7 +110,7 @@ hf_GPT2_large,pass_due_to_skip,0
 
 
 
-hf_Reformer,fail_to_run,19
+hf_Reformer,fail_to_run,21