formll
/

resolving-scaling-law-discrepancies

Model card Files Files and versions Community

resolving-scaling-law-discrepancies / dataset=rw /hparams=base_warmup=short_decay=chinchilla /params=220M_maxstep=18420

1 contributor

History: 3 commits

TomerPorian's picture

Delete epoch_xx.pt file

5be2014 verified 5 months ago

flop_1.28e+19_step_18422.pt

1.05 GB
LFS

Add files using large-upload tool 5 months ago
flop_6.40e+18_step_9212.pt
Detected Pickle imports (3)
- "collections.OrderedDict",
- "torch.FloatStorage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
1.05 GB
LFS

Add files using large-upload tool 5 months ago