NVIDIA Deep Learning Examples
Use the NGC CLI to download:
Copied!
Model
NVIDIA Deep Learning Examples
DLRM checkpoint (TensorFlow2, TF32, BS64k, Base, FL15)DLRM TensorFlow2 checkpoint trained on Criteo Dataset with FreqLimit=15 on A100 with TF32
Use the NGC CLI to download:
Copied!
2 Versions
11/22/2022 11:19 PM UTC15.61 GBAccuracy: 0.802671 EpochsBatch Size: 65536GPU: A100Copied!
11/22/2022 11:19 PM UTC15.61 GBAccuracy: 0.802671 EpochsBatch Size: 65536GPU: A100
Copied!
architecture
| Key | Value |
|---|---|
| type | base |
performance
| Key | Value |
|---|---|
| validation_loss | 0.12572 |
| accuracy | 0.80267 |
| train_loss | 0.12391 |
| AUC | 0.80267 |
training
| Key | Value |
|---|---|
| batch_size | 65536 |
| training_precision | TF32 |
| epochs | 1 |
| dataset | Criteo (FL15) |
22.06_ampSelected11/22/2022 11:06 PM UTC15.61 GBAccuracy: 0.802581 EpochsBatch Size: 65536GPU: A100Copied!
22.06_ampSelected
11/22/2022 11:06 PM UTC15.61 GBAccuracy: 0.802581 EpochsBatch Size: 65536GPU: A100
Copied!
architecture
| Key | Value |
|---|---|
| type | base |
performance
| Key | Value |
|---|---|
| validation_loss | 0.12574 |
| accuracy | 0.80258 |
| train_loss | 0.12401 |
| AUC | 0.80258 |
training
| Key | Value |
|---|---|
| batch_size | 65536 |
| training_precision | AMP |
| epochs | 1 |
| dataset | Criteo (FL15) |