annw0922

Why mean over all actions sampled in multi outcome sampling

1

https://github.com/EricSteinberger/Deep-CFR/blob/master/DeepCFR/workers/la/sampling_algorithms/MultiOutcomeSampler.py as 'aprx_imm_reg' here is computed for every action and put to buffer without being summed up, I have no idea why 'aprx_imm_reg *= legal_action_mask / n_actions_to_smpl ' I think...

请教一个问题，chatglm2在用lora微调时，不添加attention mask也可以么？

2

`def data_collator(features: list) -> dict: len_ids = [len(feature["input_ids"]) for feature in features] longest = max(len_ids) input_ids = [] labels_list = [] for ids_l, feature in sorted(zip(len_ids, features), key=lambda x: -x[0]):...