chuanli-lambda's picture
Create README.md
8645542
---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
license: apache-2.0
datasets:
- Dahoas/synthetic-instruct-gptj-pairwise
---
This model is created by finetuning `EleutherAI/pythia-1.4b-deduped` on the `Dahoas/synthetic-instruct-gptj-pairwise` for two epochs.
You can try a [demo](https://cloud.lambdalabs.com/demos/ml/qa-14b-2000) of the model hosted on [Lambda Cloud](https://lambdalabs.com/service/gpu-cloud).
It took 8xA100 80GB 2 hours to train the model. We set `batch_size_per_gpu` to `8` (so global batch size is 64), and learning rate to `0.00002` (with linear decay to zero at the last trainig step).
The Weights and Biases record of the training can be found [here](https://wandb.ai/chuanli11/ft-synthetic-instruct-gptj-pairwise-pythia1.4b?workspace=user-chuanli11).