issues
search
huggingface
/
datablations
Scaling Data-Constrained Language Models
https://arxiv.org/abs/2305.16264
Apache License 2.0
307
stars
18
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
wonder if LR=1e-3 for mup is optimal value from small-scale proxy model and dropout is crucial for multi-epoch
#13
SeunghyunSEO
opened
1 month ago
4
Question about the smoothing method applied over Figure 4.
#12
thu-yao-01-luo
closed
5 months ago
1
Flop contour
#11
borgr
closed
9 months ago
2
Names was never defined
#10
borgr
closed
10 months ago
2
Question about prediction using scaling law
#9
x54-729
closed
1 year ago
2
V3
#8
Muennighoff
closed
1 year ago
0
Figure issue about your paper (Figure 4 and Figure 15)
#7
MatthewYZhang
opened
1 year ago
1
A question about the conclusion of this paper
#6
OleNet
opened
1 year ago
1
Fix typo in hub_sync.py
#5
eltociear
closed
1 year ago
0
Update perplexity_histogram.ipynb
#4
Muennighoff
closed
1 year ago
0
release v0.1
#3
Muennighoff
closed
1 year ago
0
WIP: Stability study
#2
NouamaneTazi
closed
1 year ago
0
Add python script to launch jobs
#1
NouamaneTazi
opened
1 year ago
2