migrate example configs to canonical attn_implementation

examples/gpt-oss/gpt-oss-120b-fft-fsdp2-offload.yaml

@@ -47,7 +47,7 @@ learning_rate: 2e-5
 bf16: true
 tf32: true
 
-flash_attention: true
+attn_implementation: flash_attention_2
 attn_implementation: kernels-community/vllm-flash-attn3  # this is not needed if using flash_attn >= 2.8.3
 
 gradient_checkpointing: true

examples/gpt-oss/gpt-oss-20b-fft-deepspeed-zero3.yaml

@@ -43,7 +43,7 @@ learning_rate: 2e-5
 bf16: true
 tf32: true
 
-flash_attention: true
+attn_implementation: flash_attention_2
 attn_implementation: kernels-community/vllm-flash-attn3  # this is not needed if using flash_attn >= 2.8.3
 
 gradient_checkpointing: true

examples/gpt-oss/gpt-oss-20b-fft-fsdp2-offload.yaml

@@ -44,7 +44,7 @@ learning_rate: 2e-5
 bf16: true
 tf32: true
 
-flash_attention: true
+attn_implementation: flash_attention_2
 attn_implementation: kernels-community/vllm-flash-attn3  # this is not needed if using flash_attn >= 2.8.3
 
 gradient_checkpointing: true

examples/gpt-oss/gpt-oss-20b-fft-fsdp2.yaml

@@ -43,7 +43,7 @@ learning_rate: 2e-5
 bf16: true
 tf32: true
 
-flash_attention: true
+attn_implementation: flash_attention_2
 attn_implementation: kernels-community/vllm-flash-attn3  # this is not needed if using flash_attn >= 2.8.3
 
 gradient_checkpointing: true

examples/gpt-oss/gpt-oss-20b-sft-lora-singlegpu.yaml

@@ -56,7 +56,7 @@ learning_rate: 2e-4
 bf16: true
 tf32: true
 
-flash_attention: true
+attn_implementation: flash_attention_2
 attn_implementation: kernels-community/vllm-flash-attn3  # this is not needed if using flash_attn >= 2.8.3
 
 gradient_checkpointing: true

examples/gpt-oss/gpt-oss-safeguard-20b-sft-lora-singlegpu.yaml

@@ -56,7 +56,7 @@ learning_rate: 2e-4
 bf16: true
 tf32: true
 
-flash_attention: true
+attn_implementation: flash_attention_2
 attn_implementation: kernels-community/vllm-flash-attn3  # this is not needed if using flash_attn >= 2.8.3
 
 gradient_checkpointing: true