From 369e2ea7876406389ec66e16550a2d59835b9a0b Mon Sep 17 00:00:00 2001
From: Haibin Lin <haibin.lin@bytedance.com>
Date: Mon, 2 Dec 2024 23:06:10 -0800
Subject: [PATCH] fix lint

---
 verl/trainer/ppo/ray_trainer.py              | 16 +++++++++++-----
 verl/trainer/ppo/workers/fsdp_workers.py     | 18 ++++++++++++------
 verl/trainer/ppo/workers/megatron_workers.py | 18 ++++++++++++------
 3 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/verl/trainer/ppo/ray_trainer.py b/verl/trainer/ppo/ray_trainer.py
index 776c0fb..9569eaf 100644
--- a/verl/trainer/ppo/ray_trainer.py
+++ b/verl/trainer/ppo/ray_trainer.py
@@ -293,11 +293,17 @@ def _validate(self):
 
             test_gen_batch = test_batch.pop(['input_ids', 'attention_mask', 'position_ids'])
             test_gen_batch.meta_info = {
-                'eos_token_id': self.tokenizer.eos_token_id,
-                'pad_token_id': self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
-                'recompute_log_prob': False,
-                'do_sample': False,
-                'validate': True,
+                'eos_token_id':
+                    self.tokenizer.eos_token_id,
+                'pad_token_id':
+                    self.tokenizer.pad_token_id
+                    if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
+                'recompute_log_prob':
+                    False,
+                'do_sample':
+                    False,
+                'validate':
+                    True,
             }
 
             test_output_gen_batch = self.actor_rollout_wg.generate_sequences(test_gen_batch)
diff --git a/verl/trainer/ppo/workers/fsdp_workers.py b/verl/trainer/ppo/workers/fsdp_workers.py
index 4f4de81..4e94439 100644
--- a/verl/trainer/ppo/workers/fsdp_workers.py
+++ b/verl/trainer/ppo/workers/fsdp_workers.py
@@ -117,9 +117,12 @@ def _build_model_optimizer(self,
         actor_model_config = AutoConfig.from_pretrained(local_path, trust_remote_code=trust_remote_code)
 
         override_config_kwargs = {
-            'bos_token_id': self.tokenizer.bos_token_id,
-            'eos_token_id': self.tokenizer.eos_token_id,
-            'pad_token_id': self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
+            'bos_token_id':
+                self.tokenizer.bos_token_id,
+            'eos_token_id':
+                self.tokenizer.eos_token_id,
+            'pad_token_id':
+                self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
         }
         override_config_kwargs.update(override_model_config)
         update_model_config(actor_model_config, override_config_kwargs=override_config_kwargs)
@@ -471,9 +474,12 @@ def _build_critic_model_optimizer(self, config):
         from omegaconf import OmegaConf
         override_config = OmegaConf.to_container(self.config.model.get('override_config', OmegaConf.create()))
         override_config_kwargs = {
-            'bos_token_id': self.tokenizer.bos_token_id,
-            'eos_token_id': self.tokenizer.eos_token_id,
-            'pad_token_id': self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
+            'bos_token_id':
+                self.tokenizer.bos_token_id,
+            'eos_token_id':
+                self.tokenizer.eos_token_id,
+            'pad_token_id':
+                self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
         }
         override_config_kwargs.update(override_config)
         if self.rank == 0:
diff --git a/verl/trainer/ppo/workers/megatron_workers.py b/verl/trainer/ppo/workers/megatron_workers.py
index 2dd1005..7fc46a0 100644
--- a/verl/trainer/ppo/workers/megatron_workers.py
+++ b/verl/trainer/ppo/workers/megatron_workers.py
@@ -465,9 +465,12 @@ def _build_critic_model_optimizer(self,
         critic_model_config = AutoConfig.from_pretrained(local_path)
 
         override_config_kwargs = {
-            'bos_token_id': self.tokenizer.bos_token_id,
-            'eos_token_id': self.tokenizer.eos_token_id,
-            'pad_token_id': self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
+            'bos_token_id':
+                self.tokenizer.bos_token_id,
+            'eos_token_id':
+                self.tokenizer.eos_token_id,
+            'pad_token_id':
+                self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
         }
         override_config_kwargs.update(override_model_config)
         update_model_config(critic_model_config, override_config_kwargs=override_config_kwargs)
@@ -628,9 +631,12 @@ def _build_rm_model(self, model_path, megatron_config: ModelParallelConfig, over
         rm_model_config = AutoConfig.from_pretrained(local_path)
 
         override_config_kwargs = {
-            'bos_token_id': self.tokenizer.bos_token_id,
-            'eos_token_id': self.tokenizer.eos_token_id,
-            'pad_token_id': self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
+            'bos_token_id':
+                self.tokenizer.bos_token_id,
+            'eos_token_id':
+                self.tokenizer.eos_token_id,
+            'pad_token_id':
+                self.tokenizer.pad_token_id if self.tokenizer.pad_token_id is not None else self.tokenizer.eos_token_id,
         }
         override_config_kwargs.update(override_model_config)
         update_model_config(rm_model_config, override_config_kwargs=override_config_kwargs)