tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity

fix duplicate attn_implementation in gpt-oss yamls and flaky caplog tests

Browse Source
This commit is contained in:
Wing Lian
2026-04-25 08:53:28 +00:00
parent aeca18a8b0
commit 6886def92c
7 changed files with 28 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/gpt-oss/gpt-oss-120b-fft-fsdp2-offload.yaml
View File

@@ -47,7 +47,6 @@ learning_rate: 2e-5
bf16: true
tf32: 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

1
examples/gpt-oss/gpt-oss-20b-fft-deepspeed-zero3.yaml
View File

@@ -43,7 +43,6 @@ learning_rate: 2e-5
bf16: true
tf32: 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

1
examples/gpt-oss/gpt-oss-20b-fft-fsdp2-offload.yaml
View File

@@ -44,7 +44,6 @@ learning_rate: 2e-5
bf16: true
tf32: 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

1
examples/gpt-oss/gpt-oss-20b-fft-fsdp2.yaml
View File

@@ -43,7 +43,6 @@ learning_rate: 2e-5
bf16: true
tf32: 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

1
examples/gpt-oss/gpt-oss-20b-sft-lora-singlegpu.yaml
View File

@@ -56,7 +56,6 @@ learning_rate: 2e-4
bf16: true
tf32: 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

1
examples/gpt-oss/gpt-oss-safeguard-20b-sft-lora-singlegpu.yaml
View File

@@ -56,7 +56,6 @@ learning_rate: 2e-4
bf16: true
tf32: 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