Saran
saran1999
AI & ML interests
None yet
Recent Activity
new activity
3 days ago
answerdotai/ModernBERT-base:Loss = 0 and Gradient = NaN in ModernBERT Fine-Tuning for Regression
new activity
9 days ago
answerdotai/ModernBERT-base:nan or 0.0 loss when training with flash attention
new activity
9 days ago
answerdotai/ModernBERT-base:Loss = 0 and Gradient = NaN in ModernBERT Fine-Tuning for Regression
Organizations
None yet
saran1999's activity
Loss = 0 and Gradient = NaN in ModernBERT Fine-Tuning for Regression
4
#63 opened 9 days ago
by
saran1999
nan or 0.0 loss when training with flash attention
16
#59 opened 10 days ago
by
roadtoagi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/677a6a5ab06a2c07ece49e9d/JUYG31uT4i0SuYrbK2k7y.jpeg)
Loss = 0 and Gradient = NaN in ModernBERT Fine-Tuning for Regression
4
#63 opened 9 days ago
by
saran1999
nan or 0.0 loss when training with flash attention
16
#59 opened 10 days ago
by
roadtoagi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/677a6a5ab06a2c07ece49e9d/JUYG31uT4i0SuYrbK2k7y.jpeg)
Loss = 0 and Gradient = NaN in ModernBERT Fine-Tuning for Regression
4
#63 opened 9 days ago
by
saran1999
nan or 0.0 loss when training with flash attention
16
#59 opened 10 days ago
by
roadtoagi
![](https://cdn-avatars.huggingface.co/v1/production/uploads/677a6a5ab06a2c07ece49e9d/JUYG31uT4i0SuYrbK2k7y.jpeg)