merged latest

This commit is contained in:
Shannon Sands 2025-05-15 11:54:33 -07:00
parent ba6ba173c1
commit d768ad68aa
9 changed files with 28 additions and 3232 deletions

View file

@ -9,7 +9,12 @@ from typing import Dict, List, Optional, Tuple, Union
from dotenv import load_dotenv
from openai import AsyncOpenAI
from atroposlib.envs.base import BaseEnv, BaseEnvConfig, OpenaiConfig, ScoredDataGroup
from atroposlib.envs.base import (
APIServerConfig,
BaseEnv,
BaseEnvConfig,
ScoredDataGroup,
)
from atroposlib.utils.tokenize_for_trainer import tokenize_for_trainer
from .curriculum import MathCurriculum
@ -76,7 +81,7 @@ class InfiniteMathEnv(BaseEnv):
def __init__(
self,
config: InfiniteMathEnvConfig,
server_configs: Union[List[OpenaiConfig], OpenaiConfig],
server_configs: Union[List[APIServerConfig], APIServerConfig],
slurm=True,
testing=False,
):
@ -611,10 +616,10 @@ class InfiniteMathEnv(BaseEnv):
return scored_data
@classmethod
def config_init(cls) -> Tuple[InfiniteMathEnvConfig, List[OpenaiConfig]]:
def config_init(cls) -> Tuple[InfiniteMathEnvConfig, List[APIServerConfig]]:
"""Initialize environment and OpenAI configurations with default values."""
env_config = InfiniteMathEnvConfig(
tokenizer_name="NousResearch/Nous-Hermes-2-Yi-34B",
tokenizer_name="NousResearch/Nous-Hermes-3-Llama-3-8B-Preview",
group_size=8,
use_wandb=True,
max_num_workers=64,
@ -644,8 +649,8 @@ class InfiniteMathEnv(BaseEnv):
)
server_configs = [
OpenaiConfig(
model_name="NousResearch/Nous-Hermes-2-Yi-34B",
APIServerConfig(
model_name="NousResearch/Nous-Hermes-3-Llama-3-8B-Preview",
base_url="http://localhost:9004/v1",
api_key="x",
num_requests_for_eval=64,
@ -653,11 +658,6 @@ class InfiniteMathEnv(BaseEnv):
]
return env_config, server_configs
@classmethod
def cli(cls):
"""Command Line Interface runner for the environment."""
super().cli()
if __name__ == "__main__":
InfiniteMathEnv.cli()