Archives/gpt4all
2
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all synced 2024-11-06 09:20:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: rephrase

Browse Source
This commit is contained in:
Zach Nussbaum 2023-04-13 19:13:37 +00:00
parent a42a8643ad
commit 6bcb8bab0f
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TRAINING_LOG.md
View File

@ -244,7 +244,7 @@ We tried training a full model using the parameters above, but found that during
We trained multiple [GPT-J models](https://huggingface.co/EleutherAI/gpt-j-6b) with varying success. We found that training the full model lead to diverged post epoch 1. ![](figs/overfit-gpt-j.png). We release the checkpoint after epoch 1.
Using Atlas, we extracted the embeddings and calculated the per sequence level loss. We then uploaded [this to Atlas](https://atlas.nomic.ai/map/gpt4all-j-post-epoch-1-embeddings) and noticed that the higher loss items seem to cluster. On further inspection, the highest density clusters seemded to be of prompt/response pairs that asked for creative-like generations such as `Generate a story about ...` ![](figs/clustering_overfit.png)
Using Atlas, we extracted the embeddings of each point in the dataset and calculated the loss per sequence. We then uploaded [this to Atlas](https://atlas.nomic.ai/map/gpt4all-j-post-epoch-1-embeddings) and noticed that the higher loss items seem to cluster. On further inspection, the highest density clusters seemded to be of prompt/response pairs that asked for creative-like generations such as `Generate a story about ...` ![](figs/clustering_overfit.png)