Skip to main content
fastai_community
Projects
glue-benchmark
Reports
Small LMs

Small LMs

Comparison of small language models performance on common downstream tasks
Arto
Created on April 7|Last edited on April 7

SST2


02k4k6k8kStep0.10.20.30.40.50.60.7
3k4k5k6k7k8kStep0.20.220.240.260.28
3k4k5k6k7k8kStep0.890.90.910.920.93
Run set 2
4



MRPC


Run set
3


Created with ❤️ on Weights & Biases.

https://wandb.ai/fastai_community/glue-benchmark/reports/Small-LMs--VmlldzoxODA0NTY4
Made with Weights & Biases. Sign up or log in to create reports like this one.