train_simple.py [38:47]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        default_lr=1e-5,
        eval_batch_size=2,
        gradient_checkpointing=True,
        # Should use model_parallel on V100s (note: ironically if you have a single V100 it should run,
        # but if you have multiple it won't run without model_parallel because of the overhead of data
        # parallel training).
        model_parallel=(
            torch.cuda.get_device_properties(0).total_memory < 35e9
            and torch.cuda.device_count() > 1
        ),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



train_simple.py [51:57]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        default_lr=1e-5,
        eval_batch_size=2,
        gradient_checkpointing=True,
        model_parallel=(
            torch.cuda.get_device_properties(0).total_memory < 35e9
            and torch.cuda.device_count() > 1
        ),
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -