Model Card for Model ID
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
- Model type: [DistilBERT]
- Language(s) (NLP): [English]
- License: [Apache-2.0]
- Finetuned from model [optional]: [distilbert-uncased-base]
Model Sources [optional]
- Repository: [https://github.com/zphang/lrqa]
- Dataset: [https://huggingface.co/datasets/race]
Bias, Risks, and 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
[More Information Needed]
Model Examination [optional]
[More Information Needed]
Environmental Impact
- 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}.
- Downloads last month
- 9