47 lines
2.2 KiB
Markdown
47 lines
2.2 KiB
Markdown
---
|
|
license: unknown
|
|
language:
|
|
- en
|
|
---
|
|
|
|
# Baby Llama
|
|
|
|
Our submission to the `strict-small` track of the [BabyLM challenge](https://babylm.github.io/index.html).
|
|
|
|
Baby Llama is a 58M-parameter model, distilled from an ensemble consisting of LLaMA-360M and GPT2-705M, both trained on the `babylm_10M` dataset.
|
|
|
|
See the associated [paper](https://arxiv.org/abs/2308.02019) for a detailed discussion of the training procedure and of the model performance.
|
|
The training code is available at [https://github.com/timinar/BabyLlama](https://github.com/timinar/BabyLlama).
|
|
|
|
### Hyperparameters for the tasks that require fine-tuning
|
|
|
|
When evaluating the model on the [tasks that require fine-tuning](https://github.com/babylm/evaluation-pipeline/tree/main#fine-tuning),
|
|
we noticed that the [default hyperparameters](https://github.com/babylm/evaluation-pipeline/tree/main#hyperparameters)
|
|
suggested by the BabyLM organizers lead to severe overfitting in a number of tasks.
|
|
To avoid this issue, we have re-tuned those hyperparameters.
|
|
The sets of hyperparameters selected for each task are listed in the table below.
|
|
|
|
| Task | Maximum learning rate | Batch size | Maximum epochs | Patience | Evaluate every (steps) | Random seed |
|
|
| ---- | ------------- | ---------- | -------- | -------- | ---------- | ---- |
|
|
| CoLA | 4e-5 | 64 | 3 | 10 | 20 | 12 |
|
|
| SST-2 | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| MRPC | 3e-5 | 64 | 3 | 10 | 20 | 12 |
|
|
| QQP | 4e-5 | 64 | 10 | 10 | 1000 | 12 |
|
|
| MNLI | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| MNLI-mm |5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| QNLI | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| RTE | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| BoolQ | 3e-4 | 16 | 10 | 10 | 10| 12 |
|
|
| MultiRC | 1e-4 | 64 | 7 | 10 | 1000 | 42 |
|
|
| WSC | 5e-7 | 1 | 10 | 1000 | 2000 | 12 |
|
|
| CR (Control) | 5e-5 | 64 | 10 | 10 | 100 | 12 |
|
|
| LC (Control) | 1e-3 | 64 | 1 | 2 | 10 | 12 |
|
|
| MV (Control) | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| RP (Control) | 1e-3 | 64 | 1 | 10 | 10 | 12 |
|
|
| SC (Control) | 1e-3 | 64 | 2 | 10 | 10 | 12 |
|
|
| CR\_LC | 1e-3 | 64 | 2 | 10 | 10 | 12 |
|
|
| CR\_RTP | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| MV\_LC | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| MV\_RTP | 5e-5 | 64 | 6 | 10 | 200 | 12 |
|
|
| SC\_LC | 1e-3 | 64 | 2 | 10 | 10 | 12 |
|
|
| SC\_RP | 1e-3 | 64 | 2 | 10 | 10 | 12 | |