replace attention in the yaml config with an enum

2025-04-04 23:37:30 -04:00
parent 0d71b0aa5f
commit ba47adc24b
101 changed files with 268 additions and 122 deletions
--- a/examples/phi/phi-ft.yml
+++ b/examples/phi/phi-ft.yml
@@ -48,7 +48,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: True
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_steps: 100
 evals_per_epoch: 4
--- a/examples/phi/phi-qlora.yml
+++ b/examples/phi/phi-qlora.yml
@@ -51,7 +51,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: True
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_steps: 100
 evals_per_epoch: 4
--- a/examples/phi/phi2-ft.yml
+++ b/examples/phi/phi2-ft.yml
@@ -48,7 +48,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: True
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_steps: 100
 evals_per_epoch: 4
--- a/examples/phi/phi3-ft-fsdp.yml
+++ b/examples/phi/phi3-ft-fsdp.yml
@@ -49,7 +49,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: true
 resume_from_checkpoint:
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 warmup_steps: 100
 evals_per_epoch: 4
--- a/examples/phi/phi3-ft.yml
+++ b/examples/phi/phi3-ft.yml
@@ -44,7 +44,8 @@ gradient_checkpointing_kwargs:
  use_reentrant: True
 early_stopping_patience: 3
 logging_steps: 1
-flash_attention: true
+attention: flash
+

 eval_steps: 1000
 save_steps: 5000