List your company

Language Model Pre-training on BERT-Large NVIDIA V100 (train)

96Max Batch SizeCheckpoint
0.3225.165074.84Oct 19, 2022

Evaluation results

MethodLinks
CheckpointSequence Length=1282022.1096
TempoSequence Length=1282022.1041
BaselineSequence Length=1282022.1028
CheckpointSequence Length=5122022.1018
TempoSequence Length=5122022.107
BaselineSequence Length=5122022.104