mirror of
https://github.com/nomic-ai/gpt4all.git
synced 2024-10-01 01:06:10 -04:00
fix: rephrase
This commit is contained in:
parent
781ba27806
commit
f35732283b
@ -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)
|
||||
|
||||
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user