Results 3 issues of Leon Lin

The loss for vae took two parameters which named mu and logvar respectively, so this loss function depends on the parameters produced in the middle layer, how can I change...

参照推理的 tutorial ,基于PIQA 数据集进行推理,连续执行 44 次后,出现 OOM: 代码参考; for data in data_list: inference_results = beam_search.generate([data], max_length=100, repetition_penalty=1.1) for res in inference_results: print(res) === ========报错信息============== RuntimeError: CUDA out of memory. Tried...

CPM 使用微调脚本训练, 不开启 --use-delta 这一选项,则出现如下错误: Traceback (most recent call last): File "finetune_cpm_bee.py", line 503, in main() File "finetune_cpm_bee.py", line 499, in main finetune(args, tokenizer, model, optimizer, lr_scheduler, optim_manager) File "finetune_cpm_bee.py",...