Loading docs/configs/general-config.md +1 −1 Original line number Diff line number Diff line Loading @@ -152,7 +152,7 @@ trainer.n_gpus_per_node=4 trainer.nnodes=1 trainer.save_freq=70 trainer.test_freq=20 trainer.total_training_steps=200 trainer.total_training_steps=300 trainer.val_before_train=True trainer.val_generations_to_log_to_wandb=8 ``` Loading scripts/examples/alfworld_aico/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -67,7 +67,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=3 \ rollout_manager.use_multi_turn_reward=False \ Loading scripts/examples/alfworld_trico/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -68,7 +68,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=3 \ rollout_manager.use_multi_turn_reward=False \ Loading scripts/examples/frozen_lake_aico/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=5 \ rollout_manager.use_multi_turn_reward=False \ Loading scripts/examples/frozen_lake_aico_service/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -64,7 +64,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=5 \ rollout_manager.use_multi_turn_reward=False \ Loading Loading
docs/configs/general-config.md +1 −1 Original line number Diff line number Diff line Loading @@ -152,7 +152,7 @@ trainer.n_gpus_per_node=4 trainer.nnodes=1 trainer.save_freq=70 trainer.test_freq=20 trainer.total_training_steps=200 trainer.total_training_steps=300 trainer.val_before_train=True trainer.val_generations_to_log_to_wandb=8 ``` Loading
scripts/examples/alfworld_aico/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -67,7 +67,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=3 \ rollout_manager.use_multi_turn_reward=False \ Loading
scripts/examples/alfworld_trico/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -68,7 +68,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=3 \ rollout_manager.use_multi_turn_reward=False \ Loading
scripts/examples/frozen_lake_aico/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -63,7 +63,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=5 \ rollout_manager.use_multi_turn_reward=False \ Loading
scripts/examples/frozen_lake_aico_service/run.sh +1 −1 Original line number Diff line number Diff line Loading @@ -64,7 +64,7 @@ python3 -m vagen.trainer.main_ppo \ trainer.nnodes=1 \ trainer.save_freq=70 \ trainer.test_freq=20 \ trainer.total_training_steps=200 \ trainer.total_training_steps=300 \ rollout_manager.max_turns=3 \ rollout_manager.window_size=5 \ rollout_manager.use_multi_turn_reward=False \ Loading
