allow ppo scripts to take additional args

volcengine · Dec 2, 2024 · d922f7d · d922f7d
1 parent af7fa67
commit d922f7d
Show file tree

Hide file tree

Showing 8 changed files with 8 additions and 8 deletions.
diff --git a/examples/ppo_trainer/run_deepseek7b_llm.sh b/examples/ppo_trainer/run_deepseek7b_llm.sh
@@ -35,4 +35,4 @@ python3 -m verl.trainer.main_ppo \
     trainer.n_gpus_per_node=8 \
     trainer.nnodes=1 \
     trainer.save_freq=-1 \
-    trainer.total_epochs=15
+    trainer.total_epochs=15 $@
diff --git a/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh b/examples/ppo_trainer/run_deepseek_full_hh_rlhf.sh
@@ -38,4 +38,4 @@ python3 -m verl.trainer.main_ppo --config-path=./config --config-name='ppo_megat
     trainer.nnodes=1 \
     trainer.save_freq=-1 \
     trainer.test_freq=5 \
-    trainer.total_epochs=100
+    trainer.total_epochs=100 $@
diff --git a/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh b/examples/ppo_trainer/run_deepseek_math_gsm8k_megatron.sh
@@ -37,4 +37,4 @@ python3 -m verl.trainer.main_ppo --config-path=./config --config-name='ppo_megat
     trainer.nnodes=1 \
     trainer.save_freq=-1 \
     trainer.test_freq=5 \
-    trainer.total_epochs=100
+    trainer.total_epochs=100 $@
diff --git a/examples/ppo_trainer/run_deepseek_megatron.sh b/examples/ppo_trainer/run_deepseek_megatron.sh
@@ -28,4 +28,4 @@ python3 -m verl.trainer.main_ppo --config-path=./config --config-name='ppo_megat
     trainer.n_gpus_per_node=8 \
     trainer.nnodes=1 \
     trainer.save_freq=-1 \
-    trainer.total_epochs=15
+    trainer.total_epochs=15 $@
diff --git a/examples/ppo_trainer/run_gemma.sh b/examples/ppo_trainer/run_gemma.sh
@@ -36,4 +36,4 @@ python3 -m verl.trainer.main_ppo \
     trainer.nnodes=1 \
     trainer.save_freq=-1 \
     trainer.test_freq=10 \
-    trainer.total_epochs=15
+    trainer.total_epochs=15 $@
diff --git a/examples/ppo_trainer/run_qwen2-7b.sh b/examples/ppo_trainer/run_qwen2-7b.sh
@@ -44,4 +44,4 @@ python3 -m verl.trainer.main_ppo \
     trainer.nnodes=1 \
     trainer.save_freq=-1 \
     trainer.test_freq=10 \
-    trainer.total_epochs=15
+    trainer.total_epochs=15 $@
diff --git a/examples/ppo_trainer/run_qwen2-7b_rm.sh b/examples/ppo_trainer/run_qwen2-7b_rm.sh
@@ -51,4 +51,4 @@ python3 -m verl.trainer.main_ppo \
     trainer.nnodes=1 \
     trainer.save_freq=-1 \
     trainer.test_freq=5 \
-    trainer.total_epochs=15
+    trainer.total_epochs=15 $@
diff --git a/examples/ppo_trainer/run_qwen2.5-32b.sh b/examples/ppo_trainer/run_qwen2.5-32b.sh
@@ -45,4 +45,4 @@ python3 -m verl.trainer.main_ppo \
     trainer.nnodes=4 \
     trainer.save_freq=-1 \
     trainer.test_freq=10 \
-    trainer.total_epochs=15
+    trainer.total_epochs=15 $@