NVIDIA Deep Learning Examples
BERT PyTorch checkpoint (Large, SST-2, seqLen128, AMP)
Model
NVIDIA Deep Learning Examples
BERT PyTorch checkpoint (Large, SST-2, seqLen128, AMP)

BERT Large PyTorch checkpoint finetuned on GLUE/SST-2 dataset using AMP

1 Version
21.11.0_ampSelected
09/22/2022 5:40 PM UTC1.25 GBAccuracy: 92.773 EpochsBatch Size: 1024GPU: V100
architecture
KeyValue
taskSST-2
typeLarge
performance
KeyValue
accuracy92.77
training
KeyValue
batch_size1024
LR1e-05
training_precisionAMP
max_seq_length128
epochs3
datasetsst-2
warmup_proportion0.1