Can not reproduce the result of Roberta-Base

[Ther-nullptr]

Does anyone have reproduce the LoRA result of roberta-base? I found the reproduction result of LoRA cannot achieve the result that paper has claimed.

e.g.: Paper claimed that the RTE has achieved 86.6 accuracy, but my result has only achieved ~60 accuracy.

[jcluo-2022]

I also met this question,

Specifcally, I downloaded the LoRa weights and run the following commands.

python -m torch.distributed.launch- -nproc_per_node=1 examples/text-classification/run_glue.py --model_name_or_path roberta-base --lora_path ./cp/roberta_base_lora_mnli.bin --task_name mnli --do_eval --output_dir ./output --apply_lora --lora_r 8 --lora_alpha 8

It turns out that the accuracy is 0.6655 while the number in paper is 0.875

[Car-pe]

Hello, I guess you used the wrong hyper parameters since the gap is really large. But I also can not reproduce the result, the paper claimed the STSB has achieved 91.5, but my result is 91.03.

And for Roberta-large, I also can not reproduce the results. Cola: 68.2(paper) - 67.0(my), gap is 1.2 Stab: 92.6(paper) - 92.2(my), gap is 0.4 Mrpc:90.9(paper) - 90.7(my), gap is 0.2