Vae
Vae
> Yes. You probably have a machine with more than one gpu right? I run the funtune.py on a machine with A100*8, Is there a way to solve this problem?
> If you want to use all the GPUs , invoke with torchrun > > For instance with 2 GPUs I'd run `OMP_NUM_THREADS=4 WORLD_SIZE=2 CUDA_VISIBLE_DEVICES=0,1 torchrun --nproc_per_node=2 --master_port=1234 finetune.py` >...
或者有人能告诉我怎么打印每一步的训练损失和每个epoch的验证损失么，谢谢大家！！！
> 这里你预测dev时，输出出现了空值。调整一下max_ @luolanfeixue emmm，你知道怎么打印验证集的损失么，这份代码好像只打印训练损失
I referred to Example usage to invoke the finetune.py: python finetune.py \ --base_model 'decapoda-research/llama-7b-hf' \ --data_path './alpaca_data_cleaned.json' \ --output_dir './lora-alpaca'
> After installing the dependent environment, the following error was reported when running finetune. py. Does anyone know the reason or solution. > > Traceback (most recent call last): File...
> @dsh54054 Do you solve the problem? I met the same problem @LutaoChu emmm，I found that the finetune. py script I used was too old. After using the latest version...
> 你好 使用最新重构后的代码执行并发，依然还是集中在单卡上运行 hi，请问一下你解决这个问题了么，我现在也遇到了这个问题，想知道解决方案
same promple, When a large amount of text is used for inference, there is a probability that the problem of incomplete speech may occur earlier, with a probability of 1/50
点赞，有指导意义，有空试一下