| # @package _group_ | |
| common: | |
| fp16: true | |
| log_format: json | |
| log_interval: 200 | |
| tensorboard_logdir: tb | |
| fp16_no_flatten_grads: true | |
| checkpoint: | |
| save_interval: 5 | |
| save_interval_updates: 25000 | |
| keep_interval_updates: 1 | |
| no_epoch_checkpoints: true | |
| task: | |
| _name: mae_image_pretraining | |
| data: /datasets01/imagenet_full_size/061417/ | |
| rebuild_batches: true | |
| dataset: | |
| num_workers: 6 | |
| batch_size: 64 | |
| skip_invalid_size_inputs_valid_test: true | |
| required_batch_size_multiple: 1 | |
| disable_validation: true | |
| distributed_training: | |
| distributed_world_size: 16 | |
| ddp_backend: c10d | |
| criterion: | |
| _name: model | |
| optimization: | |
| max_update: 375300 | |
| lr: [0.0006] | |
| optimizer: | |
| _name: composite | |
| groups: | |
| with_decay: | |
| lr_float: 6e-4 | |
| optimizer: | |
| _name: adam | |
| adam_betas: [0.9,0.95] | |
| weight_decay: 0.05 | |
| lr_scheduler: | |
| _name: cosine | |
| warmup_updates: 50040 | |
| no_decay: | |
| lr_float: 6e-4 | |
| optimizer: | |
| _name: adam | |
| adam_betas: [0.9,0.95] | |
| weight_decay: 0 | |
| lr_scheduler: | |
| _name: cosine | |
| warmup_updates: 50040 | |
| lr_scheduler: pass_through | |
| model: | |
| _name: mae | |