rm a verl param

hiyuchang · hiyuchang · commit 45689433c45f · 2025-07-03T16:47:02.000+08:00
diff --git a/examples/async_gsm8k/verl_config.yaml b/examples/async_gsm8k/verl_config.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: True  # False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True # False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/dpo_humanlike/train_dpo.yaml b/examples/dpo_humanlike/train_dpo.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 32
     ppo_micro_batch_size_per_gpu: 2 # NOTE
     use_dynamic_bsz: False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/grpo_alfworld/alfworld.yaml b/examples/grpo_alfworld/alfworld.yaml
@@ -13,7 +13,7 @@ cluster:
   gpu_per_node: 8
 buffer:
   total_epochs: 20
-  batch_size: 4
+  batch_size: 32
   max_retry_times: 3
   max_retry_interval: 1
   explorer_input:
diff --git a/examples/grpo_alfworld/train_alfworld.yaml b/examples/grpo_alfworld/train_alfworld.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 1536
     ppo_micro_batch_size_per_gpu: 1
     use_dynamic_bsz: False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/grpo_gsm8k/train_gsm8k.yaml b/examples/grpo_gsm8k/train_gsm8k.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: True  # False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True # False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/grpo_gsm8k_experience_pipeline/train_gsm8k.yaml b/examples/grpo_gsm8k_experience_pipeline/train_gsm8k.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: True  # False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True # False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/grpo_gsm8k_task_pipeline/train_gsm8k.yaml b/examples/grpo_gsm8k_task_pipeline/train_gsm8k.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: True  # False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True # False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/grpo_math/train_math.yaml b/examples/grpo_math/train_math.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: True  # False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True # False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/grpo_sciworld/train_sciworld.yaml b/examples/grpo_sciworld/train_sciworld.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 1536
     ppo_micro_batch_size_per_gpu: 1
     use_dynamic_bsz: False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/grpo_webshop/train_webshop.yaml b/examples/grpo_webshop/train_webshop.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 1536
     ppo_micro_batch_size_per_gpu: 1
     use_dynamic_bsz: False
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/mix_math/train_mix_math.yaml b/examples/mix_math/train_mix_math.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: True  # False
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True # False
     ppo_max_token_len_per_gpu: 25600 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/opmd_gsm8k/train_opmd_gsm8k.yaml b/examples/opmd_gsm8k/train_opmd_gsm8k.yaml
@@ -31,7 +31,6 @@ actor_rollout_ref:
     use_remove_padding: True
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
diff --git a/examples/ppo_countdown/train_countdown.yaml b/examples/ppo_countdown/train_countdown.yaml
@@ -7,7 +7,6 @@ actor_rollout_ref:
     use_remove_padding: True
   actor:
     strategy: fsdp  # This is for backward-compatibility
-    ppo_mini_batch_size: 128
     ppo_micro_batch_size_per_gpu: 4
     use_dynamic_bsz: True
     ppo_max_token_len_per_gpu: 16384 # n * ${data.max_prompt_length} + ${data.max_response_length}
@@ -61,7 +60,6 @@ critic:
         # transformer_layer_cls_to_wrap: None
         min_num_params: 0
       fsdp_size: -1
-  ppo_mini_batch_size: ${actor_rollout_ref.actor.ppo_mini_batch_size}
   ppo_micro_batch_size_per_gpu: 8
   forward_micro_batch_size_per_gpu: ${critic.ppo_micro_batch_size_per_gpu}
   use_dynamic_bsz: ${actor_rollout_ref.actor.use_dynamic_bsz}
