feat(logging): add swanlab backend for training runs (#17)

* feat(logging): add swanlab backend + evo1 stage2 optimizations

- Add SwanLab logging support (auto-selects when SWANLAB_API_KEY is set)
- Add stage2 training optimizations: tensor fastpath, gradient checkpointing
- Document stage2 config override behavior and runnable value-model alternative

Cherry-picked from: bfdc28c, bcecabb

* refactor(logging): separate SwanLabLogger from WandBLogger

- Restore WandBLogger to its original clean form with all comments
- Add SwanLabLogger as a separate class with the same interface
- Add make_logger() factory function to select backend based on
  SWANLAB_API_KEY environment variable
- Move evo1 stage2 runtime logging from lerobot_train.py into
  EVO1Policy.__init__ where it belongs
- Add ImportError handling for swanlab dependency

* fix(logging): gracefully fall back to WandB when swanlab is not installed

If SWANLAB_API_KEY is set but the swanlab package is not installed,
make_logger() now logs a warning and falls back to WandBLogger instead
of crashing with an ImportError at training startup.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Elvinyk <223015152@link.cuhk.edu.cn>
Co-authored-by: MrBlue0632 <2028207642@qq.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
这个提交包含在:
MrBlue0632
2026-04-14 10:31:40 +08:00
提交者 GitHub
父节点 bd3d1fc549
当前提交 c1b2795640
共有 9 个文件被更改,包括 217 次插入 和 26 次删除

查看文件

@ -150,13 +150,11 @@ def train(cfg: TrainRLServerPipelineConfig, job_name: str | None = None):
logging.info(f"Learner logging initialized, writing to {log_file}")
logging.info(pformat(cfg.to_dict()))
# Setup WandB logging if enabled
if cfg.wandb.enable and cfg.wandb.project:
from lerobot.rl.wandb_utils import WandBLogger
# Setup logging
from lerobot.rl.wandb_utils import make_logger
wandb_logger = WandBLogger(cfg)
else:
wandb_logger = None
wandb_logger = make_logger(cfg)
if wandb_logger is None:
logging.info(colored("Logs will be saved locally.", "yellow", attrs=["bold"]))
# Handle resume logic

查看文件

@ -201,3 +201,106 @@ class WandBLogger:
wandb_video = self._wandb.Video(video_path, fps=self.env_fps, format="mp4")
self._wandb.log({f"{mode}/video": wandb_video}, step=step)
class SwanLabLogger:
"""A helper class to log training metrics using SwanLab."""
def __init__(self, cfg: TrainPipelineConfig):
try:
import swanlab
except ImportError:
raise ImportError(
"SwanLab is required when SWANLAB_API_KEY is set. "
"Install it with: pip install swanlab"
)
self.cfg = cfg.wandb
self.log_dir = cfg.output_dir
self.job_name = cfg.job_name
self.env_fps = cfg.env.fps if cfg.env else None
swanlab.login(api_key=os.environ["SWANLAB_API_KEY"])
self._run = swanlab.init(
project=self.cfg.project,
workspace=self.cfg.entity,
experiment_name=self.job_name,
description=self.cfg.notes,
tags=cfg_to_group(cfg, return_list=True, truncate_tags=True),
logdir=str(self.log_dir),
config=cfg.to_dict(),
mode=self.cfg.mode if self.cfg.mode in ["offline", "disabled"] else "cloud",
id=cfg.wandb.run_id,
resume="must" if cfg.resume else None,
)
run_id = getattr(self._run, "id", None)
cfg.wandb.run_id = run_id
logging.info(colored("Logs will be synced with swanlab.", "blue", attrs=["bold"]))
try:
import swanlab.data as swanlab_data
run_url = swanlab_data.get_url()
if run_url:
logging.info(f"Track this run --> {colored(run_url, 'yellow', attrs=['bold'])}")
except Exception:
pass
def log_policy(self, checkpoint_dir: Path):
return
def log_dict(
self, d: dict, step: int | None = None, mode: str = "train", custom_step_key: str | None = None
):
if mode not in {"train", "eval"}:
raise ValueError(mode)
if step is None and custom_step_key is None:
raise ValueError("Either step or custom_step_key must be provided.")
data = {}
if custom_step_key is not None and custom_step_key in d:
value_custom_step = d[custom_step_key]
data[f"{mode}/{custom_step_key}"] = value_custom_step
if step is None:
step = int(value_custom_step)
for k, v in d.items():
if not isinstance(v, (int | float | str)):
logging.warning(
f'SwanLab logging of key "{k}" was ignored as its type "{type(v)}" is not handled by this wrapper.'
)
continue
if custom_step_key is not None and k == custom_step_key:
continue
data[f"{mode}/{k}"] = v
if data:
self._run.log(data, step=step)
def log_video(self, video_path: str, step: int, mode: str = "train"):
if mode not in {"train", "eval"}:
raise ValueError(mode)
try:
import swanlab
self._run.log({f"{mode}/video": swanlab.Video(video_path)}, step=step)
except Exception as exc:
logging.warning("Failed to log video to SwanLab: %s", exc)
def make_logger(cfg: TrainPipelineConfig) -> WandBLogger | SwanLabLogger | None:
"""Create a training logger based on config and environment.
Returns SwanLabLogger if SWANLAB_API_KEY is set, WandBLogger otherwise.
Returns None if logging is disabled.
"""
if not (cfg.wandb.enable and cfg.wandb.project):
return None
if os.getenv("SWANLAB_API_KEY"):
try:
return SwanLabLogger(cfg)
except ImportError:
logging.warning(
"swanlab package is not installed but SWANLAB_API_KEY is set. "
"Falling back to WandB. Install swanlab with: pip install swanlab"
)
return WandBLogger(cfg)