// Map VERL training configuration to AgentJet configuration. Find VERL config in verl_default.yaml, check for existing mappings in config_auto_convertion_verl.jsonc, add new mappings to ajet_default.yaml and the conversion schema, and optionally add parameters to AgentJetJob.
Execute AgentJet reinforcement learning experiments using experiment blueprints in classic (non-swarm) mode. Handles full lifecycle: launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when the user wants to run AgentJet training experiments without the swarm distributed framework.
Execute AgentJet reinforcement learning experiments using experiment blueprints in swarm mode. Handles full lifecycle: generate blueprint if needed, launch experiment in tmux, monitor progress, analyze errors, collect results, and write finish flag. Use when the user wants to run or debug AgentJet training experiments.
Install AgentJet swarm server using Conda. Handles Python 3.10 environment creation, dependency installation with the verl training backbone, flash-attn compilation, and optional PyPI mirror for China users.
Install and run the AgentJet Swarm Server in a Docker container with NVIDIA GPU support. Use when the user wants to deploy a swarm server on a GPU machine via Docker, including GPU driver setup, Docker mirror configuration, model weight mounting, and server startup.
Download per-step time-series metric data (reward, entropy, response length, etc.) from a SwanLab cloud run URL as a pandas.DataFrame. Use when the user provides a SwanLab URL and wants to fetch or analyze training curves.
Install AgentJet client for connecting to a swarm server. Use when the user only needs to run the AgentJet client (not a swarm server) and does not need to run models locally, e.g. on a laptop. Installs basic requirements via `pip install -e .`.
| name | map-verl-config |
| description | Map VERL training configuration to AgentJet configuration. Find VERL config in verl_default.yaml, check for existing mappings in config_auto_convertion_verl.jsonc, add new mappings to ajet_default.yaml and the conversion schema, and optionally add parameters to AgentJetJob. |
| license | Complete terms in LICENSE.txt |
find user requested verl config in codebase/agentjet/ajet/default_config/verl/verl_default.yaml
check codebase/agentjet/ajet/default_config/verl/config_auto_convertion_verl.jsonc, whether a mapping to this config already exists.
if not, add a config under ajet field in codebase/agentjet/ajet/default_config/ajet_default.yaml, and add a mapping in codebase/agentjet/ajet/default_config/verl/config_auto_convertion_verl.jsonc
double check, confirm that default value in ajet_default.yaml is the same as verl config in verl_default.yaml, and the mapping is correct in config_auto_convertion_verl.jsonc
ask user whether to add to AgentJetJob (ajet/copilot/job.py), if the user confirms:
overrides dictajet/default_config/ajet_config_schema.pyajet.trainer_common.optim.lr, need:
AjetOptim dataclass with lr: float = 1e-6AjetTrainerCommon must have optim: AjetOptim = field(default_factory=AjetOptim)getattr() to fail at runtime