Commit ·
8645542
1
Parent(s): 5b60466
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- pytorch
|
| 6 |
+
- causal-lm
|
| 7 |
+
- pythia
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
datasets:
|
| 10 |
+
- Dahoas/synthetic-instruct-gptj-pairwise
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
This model is created by finetuning `EleutherAI/pythia-1.4b-deduped` on the `Dahoas/synthetic-instruct-gptj-pairwise` for two epochs.
|
| 14 |
+
|
| 15 |
+
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).
|
| 16 |
+
|
| 17 |
+
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).
|
| 18 |
+
|
| 19 |
+
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).
|
| 20 |
+
|
| 21 |
+
|