Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
omarmomen
/
structformer_s1_final_with_pos
like
0
Fill-Mask
Transformers
PyTorch
omarmomen/babylm_10M
English
structformer
custom_code
arxiv:
2310.20589
License:
mit
Model card
Files
Files and versions
Community
1
Train
Use this model
refs/pr/1
structformer_s1_final_with_pos
/
finetune
/
mnli
/
train_results.json
Omar
update
abe8798
almost 2 years ago
raw
Copy download link
history
blame
Safe
197 Bytes
{
"epoch"
:
3.7
,
"train_loss"
:
0.6384720687866211
,
"train_runtime"
:
4882.2407
,
"train_samples"
:
259780
,
"train_samples_per_second"
:
532.092
,
"train_steps_per_second"
:
4.434
}