distilbert-base-uncased-race

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This model was finetuned on RACE for multiple choice (text classification). The initial model used was distilbert-uncased-base https://huggingface.co/distilbert-uncased-base

The model was trained using the code from https://github.com/zphang/lrqa. Please refer to and cite the authors.

Model Details

• Initial model: distilbert-uncased-base
• LR: 1e-5
• Epochs: 3
• Warmup Ratio: 0.1 (10%)
• Batch Size: 16
• Max Seq Len: 512

Model Description

<!-- Provide a longer summary of what this model is. -->

• Model type: [DistilBERT]
• Language(s) (NLP): [English]
• License: [Apache-2.0]
• Finetuned from model [optional]: [distilbert-uncased-base]

Model Sources [optional]

<!-- Provide the basic links for the model. -->

• Repository: [https://github.com/zphang/lrqa]
• Dataset: [https://huggingface.co/datasets/race]

Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

[More Information Needed]

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

[More Information Needed]

Model Examination [optional]

<!-- Relevant interpretability work for the model goes here -->

[More Information Needed]

Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

• Hardware Type: A100 - 40GB
• Hours used: 4
• Cloud Provider: Private
• Compute Region: Portugal
• Carbon Emitted: 0.18 kgCO2

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}.