This model was finetuned on RACE for multiple choice (text classification). The initial model used was distilbert-uncased-base
https://huggingface.co/distilbert-uncased-baseThe model was trained using the code from
https://github.com/zphang/lrqa. Please refer to and cite the authors.
Use the code below to get started with the model.
Experiments were conducted using a private infrastructure, which has a carbon efficiency of 0.178 kgCO$_2$eq/kWh. A cumulative of 4 hours of computation was performed on hardware of type A100 PCIe 40/80GB (TDP of 250W).
Total emissions are estimated to be 0.18 kgCO$_2$eq of which 0 percent were directly offset.
Estimations were conducted using the \href{
https://mlco2.github.io/impact#compute}{MachineLearning Impact calculator} presented in \cite{lacoste2019quantifying}.
