|
Improve the baseline model performance on the babyLM Benchmark. |
|
|
|
Summary: This shared task challenges community members to train a language model **from scratch** on the same amount of linguistic data available to a child. Submissions should be implemented in Huggingface |
|
|
|
To run the baseline model, execute train.py. It will train a standard gpt2 model on the babyLM data. The final model will be saved to output/ folder. |
|
|
|
When you submit your final answer, you will be evaluated on the performance of the checkpoint saved in the output folder. It will be evaluated on a held-out test set. |
