zyzhang1130

May I further clarify that the reason you want to put test data in separate sub-folders is it because data in test folder was used during the training stage for...

https://github.com/ying-wen/pymarl/blob/master/src/envs/smarts_env.py also has issue because AgentPolicy is deprecated (- Removed deprecated class `AgentPolicy` from `agent.py`.)

Does the multiagent setting work now by any chance?

the front part was just running normally: ``` (base) zeyu@ZYNitro5:~$ conda activate smarts (smarts) zeyu@ZYNitro5:~$ cd SMARTS/competition/track1/train (smarts) zeyu@ZYNitro5:~/SMARTS/competition/track1/train$ python3.8 train.py python3.8: can't open file 'train.py': [Errno 2] No such...

Does changing hyperparameters in SMARTS/competition/track1/train/config.yaml count? Like changing epochs train_steps (I changed it from the default value to the following. ``` # Training epochs: 5_00 # Number of training loops....

Further update of [https://github.com/modelscope/agentscope/pull/169](https://github.com/modelscope/agentscope/pull/169) is moved here.

> Would it be possible for you to exclude the changes that are not related to the Gemini Wrapper from this PR? The SFT-related modifications seem to be intertwined with...

Need to disable E203 for pre-commit run. It automatically reformats `examples/load_finetune_huggingface_model/huggingface_model.py' line147 by adding whitespace before ':' and then flags it as an error.

> The **Description** of this PR seems outdated, please update it accordingly. Done.

> Please see inline comments, and: > > 1. It's not clear who is responsible to fine-tune the model, the agent or model wrapper? Since the new model configuration has...