yujunjun/LLMs-from-scratch
1
0
Fork 0
mirror of https://github.com/rasbt/LLMs-from-scratch.git synced 2025-08-29 11:00:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

clarify overfitting

Browse Source
This commit is contained in:
rasbt 2024-05-09 09:09:26 -05:00
parent ad200a4f3f
commit dadd0f7ea3
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ch06/01_main-chapter-code/ch06.ipynb
View File

@ -2043,7 +2043,7 @@
"metadata": {},
"source": [
"- We can see that the training and test set performances are practically identical\n",
"- However, based on the slightly lower test set performance, we can see that the model overfits the training data to a very small degree\n",
"- However, based on the slightly lower test set performance, we can see that the model overfits the training data to a very small degree, as well as the validation data that has been used for tweaking some of the hyperparameters, such as the learning rate\n",
"- This is normal, however, and this gap could potentially be further reduced by increasing the model's dropout rate (`drop_rate`) or the `weight_decay` in the optimizer setting"
]
},
@ -2265,7 +2265,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
"version": "3.10.6"
}
},
"nbformat": 4,