ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA Deep Learning Examples
NVIDIA Deep Learning Examples
BERT PyTorch checkpoint (Dist-4L-288D, SST-2, seqLen128, AMP)
Model
NVIDIA Deep Learning Examples
NVIDIA Deep Learning Examples
BERT PyTorch checkpoint (Dist-4L-288D, SST-2, seqLen128, AMP)

BERT Distilled 4L-288D PyTorch checkpoint distilled on GLUE/SST-2 dataset using AMP

1 Version
21.11.0_ampSelected
07/07/2022 2:22 PM UTC49.92 MBAccuracy: 90.823 EpochsBatch Size: 256GPU: V100
architecture
KeyValue
attn_heads12
taskSST-2
hidden_size288
layers4
typeDist-4L-288D
performance
KeyValue
accuracy90.82
training
KeyValue
batch_size256
LR3e-05
training_precisionAMP
max_seq_length128
epochs3
datasetsst-2
warmup_proportion0.1