disable valset by default (#6690)

Former-commit-id: 77bbf65905
2025-12-14 19:06:26 +08:00 · 2025-01-17 21:09:30 +08:00
parent 770433fa33
commit bbf334f823
30 changed files with 142 additions and 114 deletions
--- a/examples/extras/adam_mini/qwen2_full_sft.yaml
+++ b/examples/extras/adam_mini/qwen2_full_sft.yaml
@@ -34,7 +34,7 @@ bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/apollo/llama3_full_sft.yaml
+++ b/examples/extras/apollo/llama3_full_sft.yaml
@@ -39,7 +39,7 @@ pure_bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/badam/llama3_full_sft.yaml
+++ b/examples/extras/badam/llama3_full_sft.yaml
@@ -37,7 +37,7 @@ lr_scheduler_type: cosine
 warmup_ratio: 0.1

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/fsdp_qlora/llama3_lora_sft.yaml
+++ b/examples/extras/fsdp_qlora/llama3_lora_sft.yaml
@@ -7,6 +7,7 @@ trust_remote_code: true
 stage: sft
 do_train: true
 finetuning_type: lora
+lora_rank: 8
 lora_target: all

 ### dataset
@@ -35,7 +36,7 @@ bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/galore/llama3_full_sft.yaml
+++ b/examples/extras/galore/llama3_full_sft.yaml
@@ -38,7 +38,7 @@ pure_bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/llama_pro/llama3_freeze_sft.yaml
+++ b/examples/extras/llama_pro/llama3_freeze_sft.yaml
@@ -36,7 +36,7 @@ bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/loraplus/llama3_lora_sft.yaml
+++ b/examples/extras/loraplus/llama3_lora_sft.yaml
@@ -6,6 +6,7 @@ trust_remote_code: true
 stage: sft
 do_train: true
 finetuning_type: lora
+lora_rank: 8
 lora_target: all
 loraplus_lr_ratio: 16.0

@@ -35,7 +36,7 @@ bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/mod/llama3_full_sft.yaml
+++ b/examples/extras/mod/llama3_full_sft.yaml
@@ -35,7 +35,7 @@ pure_bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500
--- a/examples/extras/pissa/llama3_lora_sft.yaml
+++ b/examples/extras/pissa/llama3_lora_sft.yaml
@@ -6,6 +6,7 @@ trust_remote_code: true
 stage: sft
 do_train: true
 finetuning_type: lora
+lora_rank: 8
 lora_target: all
 pissa_init: true
 pissa_iter: 16
@@ -37,7 +38,7 @@ bf16: true
 ddp_timeout: 180000000

 ### eval
-val_size: 0.1
-per_device_eval_batch_size: 1
-eval_strategy: steps
-eval_steps: 500
+# val_size: 0.1
+# per_device_eval_batch_size: 1
+# eval_strategy: steps
+# eval_steps: 500