osmarks/nanogpt-experiments
1
0
Fork 0
mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2024-12-18 14:10:28 +00:00
Code Issues Releases Wiki Activity

Merge pull request #66 from PWhiddy/patch-1

Browse Source 
fix typo ( params -> tokens)
This commit is contained in:
Andrej 2023-01-18 22:29:51 -08:00 committed by GitHub
commit 9e150b808e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
scaling_laws.ipynb
View File

@ -566,7 +566,7 @@
"source": [
"In the plot above, basically the models on the left of best are too small and trained for too long. The models on the right of best are way too large and trained for too little. The model at the red line is just right.\n",
"\n",
"Now, the Chinchilla paper says that best model size for this flop budget is 400M params and 9.2B tokens (instead of 316M params 11.65B params) so there is some unresolved disagreement here too..."
"Now, the Chinchilla paper says that best model size for this flop budget is 400M params and 9.2B tokens (instead of 316M params and 11.65B tokens) so there is some unresolved disagreement here too..."
]
},
{