File size: 3,800 Bytes
7155cf2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 |
# Copyright 2024 Bytedance Ltd. and/or its affiliates
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Note that we don't combine the main with ray_trainer as ray_trainer is used by other main.
"""
import json
import ray
from omegaconf import OmegaConf
from ..single_controller.ray import RayWorkerGroup
from ..utils.tokenizer import get_processor, get_tokenizer
from ..workers.fsdp_workers import FSDPWorker
from ..workers.reward import CustomRewardManager
from .config import PPOConfig
from .ray_trainer import RayPPOTrainer, ResourcePoolManager, Role
# please make sure main_task is not scheduled on head
@ray.remote(num_cpus=1)
class Runner:
"""A runner for RL training."""
def run(self, config: PPOConfig):
# print config
config.deep_post_init()
print(json.dumps(config.to_dict(), indent=2))
# instantiate tokenizer
tokenizer = get_tokenizer(
config.worker.actor.model.model_path,
trust_remote_code=config.worker.actor.model.trust_remote_code,
use_fast=True,
)
processor = get_processor(
config.worker.actor.model.model_path,
trust_remote_code=config.worker.actor.model.trust_remote_code,
use_fast=True,
)
# define worker classes
ray_worker_group_cls = RayWorkerGroup
role_worker_mapping = {
Role.ActorRollout: ray.remote(FSDPWorker),
Role.Critic: ray.remote(FSDPWorker),
Role.RefPolicy: ray.remote(FSDPWorker),
}
global_pool_id = "global_pool"
resource_pool_spec = {
global_pool_id: [config.trainer.n_gpus_per_node] * config.trainer.nnodes,
}
mapping = {
Role.ActorRollout: global_pool_id,
Role.Critic: global_pool_id,
Role.RefPolicy: global_pool_id,
}
resource_pool_manager = ResourcePoolManager(resource_pool_spec=resource_pool_spec, mapping=mapping)
reward_fn = CustomRewardManager(tokenizer=tokenizer, config=config.worker.reward)
val_reward_fn = CustomRewardManager(tokenizer=tokenizer, config=config.worker.reward)
trainer = RayPPOTrainer(
config=config,
tokenizer=tokenizer,
processor=processor,
role_worker_mapping=role_worker_mapping,
resource_pool_manager=resource_pool_manager,
ray_worker_group_cls=ray_worker_group_cls,
reward_fn=reward_fn,
val_reward_fn=val_reward_fn,
)
trainer.init_workers()
trainer.fit()
def main():
cli_args = OmegaConf.from_cli()
default_config = OmegaConf.structured(PPOConfig())
if hasattr(cli_args, "config"):
config_path = cli_args.pop("config", None)
file_config = OmegaConf.load(config_path)
default_config = OmegaConf.merge(default_config, file_config)
ppo_config = OmegaConf.merge(default_config, cli_args)
ppo_config = OmegaConf.to_object(ppo_config)
if not ray.is_initialized():
# this is for local ray cluster
ray.init(runtime_env={"env_vars": {"TOKENIZERS_PARALLELISM": "true", "NCCL_DEBUG": "WARN"}})
runner = Runner.remote()
ray.get(runner.run.remote(ppo_config))
if __name__ == "__main__":
main()
|