v1.0

examples/data2vec/config/v2/text_finetuning/mrpc.yaml

+# @package _group_
+
+common:
+  fp16: true
+  fp16_init_scale: 4
+  threshold_loss_scale: 1
+  fp16_scale_window: 128
+  log_format: json
+  log_interval: 200
+  user_dir: ${env:PWD}/examples/data2vec
+
+task:
+  _name: sentence_prediction
+  data: ???
+  init_token: 0
+  separator_token: 2
+  num_classes: 2
+  max_positions: 512
+  d2v2_multi: True
+
+checkpoint:
+  best_checkpoint_metric: acc_and_f1
+  maximize_best_checkpoint_metric: true
+  no_epoch_checkpoints: true
+
+distributed_training:
+  find_unused_parameters: true
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+
+criterion:
+  _name: sentence_prediction
+  report_acc_and_f1: True
+
+dataset:
+  batch_size: 16
+  required_batch_size_multiple: 1
+  max_tokens: 4400
+  num_workers: 1
+
+optimizer:
+  _name: adam
+  weight_decay: 0.1
+  adam_betas: (0.9,0.98)
+  adam_eps: 1e-06
+
+lr_scheduler:
+  _name: polynomial_decay
+  warmup_updates: 137
+
+optimization:
+  clip_norm: 0.0
+  lr: [2e-05]
+  max_update: 2296
+  max_epoch: 10
+
+model:
+  _name: data2vec_text_classification
+  model_path: ???

examples/data2vec/config/v2/text_finetuning/qnli.yaml

+# @package _group_
+
+common:
+  fp16: true
+  fp16_init_scale: 4
+  threshold_loss_scale: 1
+  fp16_scale_window: 128
+  log_format: json
+  log_interval: 200
+  user_dir: ${env:PWD}/examples/data2vec
+
+task:
+  _name: sentence_prediction
+  data: ???
+  init_token: 0
+  separator_token: 2
+  num_classes: 2
+  max_positions: 512
+  d2v2_multi: True
+
+checkpoint:
+  best_checkpoint_metric: accuracy
+  maximize_best_checkpoint_metric: true
+  no_epoch_checkpoints: true
+
+distributed_training:
+  find_unused_parameters: true
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+
+criterion:
+  _name: sentence_prediction
+
+dataset:
+  batch_size: 32
+  required_batch_size_multiple: 1
+  max_tokens: 4400
+  num_workers: 1
+
+optimizer:
+  _name: adam
+  weight_decay: 0.1
+  adam_betas: (0.9,0.98)
+  adam_eps: 1e-06
+
+lr_scheduler:
+  _name: polynomial_decay
+  warmup_updates: 1986
+
+optimization:
+  clip_norm: 0.0
+  lr: [2e-05]
+  max_update: 33112
+  max_epoch: 10
+
+model:
+  _name: data2vec_text_classification
+  model_path: ???

examples/data2vec/config/v2/text_finetuning/qqp.yaml

+# @package _group_
+
+common:
+  fp16: true
+  fp16_init_scale: 4
+  threshold_loss_scale: 1
+  fp16_scale_window: 128
+  log_format: json
+  log_interval: 200
+  user_dir: ${env:PWD}/examples/data2vec
+
+task:
+  _name: sentence_prediction
+  data: ???
+  init_token: 0
+  separator_token: 2
+  num_classes: 2
+  max_positions: 512
+  d2v2_multi: True
+
+checkpoint:
+  best_checkpoint_metric: acc_and_f1
+  maximize_best_checkpoint_metric: true
+  no_epoch_checkpoints: true
+
+distributed_training:
+  find_unused_parameters: true
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+
+criterion:
+  _name: sentence_prediction
+  report_acc_and_f1: True
+
+dataset:
+  batch_size: 32
+  required_batch_size_multiple: 1
+  max_tokens: 4400
+  num_workers: 1
+
+optimizer:
+  _name: adam
+  weight_decay: 0.1
+  adam_betas: (0.9,0.98)
+  adam_eps: 1e-06
+
+lr_scheduler:
+  _name: polynomial_decay
+  warmup_updates: 28318
+
+optimization:
+  clip_norm: 0.0
+  lr: [2e-05]
+  max_update: 113272
+  max_epoch: 10
+
+model:
+  _name: data2vec_text_classification
+  model_path: ???

examples/data2vec/config/v2/text_finetuning/rte.yaml

+# @package _group_
+
+common:
+  fp16: true
+  fp16_init_scale: 4
+  threshold_loss_scale: 1
+  fp16_scale_window: 128
+  log_format: json
+  log_interval: 200
+  user_dir: ${env:PWD}/examples/data2vec
+
+task:
+  _name: sentence_prediction
+  data: ???
+  init_token: 0
+  separator_token: 2
+  num_classes: 2
+  max_positions: 512
+  d2v2_multi: True
+
+checkpoint:
+  best_checkpoint_metric: accuracy
+  maximize_best_checkpoint_metric: true
+  no_epoch_checkpoints: true
+
+distributed_training:
+  find_unused_parameters: true
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+
+criterion:
+  _name: sentence_prediction
+
+dataset:
+  batch_size: 16
+  required_batch_size_multiple: 1
+  max_tokens: 4400
+  num_workers: 1
+
+optimizer:
+  _name: adam
+  weight_decay: 0.1
+  adam_betas: (0.9,0.98)
+  adam_eps: 1e-06
+
+lr_scheduler:
+  _name: polynomial_decay
+  warmup_updates: 122
+
+optimization:
+  clip_norm: 0.0
+  lr: [2e-05]
+  max_update: 2036
+  max_epoch: 10
+
+model:
+  _name: data2vec_text_classification
+  model_path: ???

examples/data2vec/config/v2/text_finetuning/run_config/local.yaml

+# @package _global_
+hydra:
+  sweep:
+    dir: ${env:PWD}/tmp_dbg/${now:%H-%M-%S}
+
+distributed_training:
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+  
+common:
+  log_interval: 1
+  
+dataset:
+  num_workers: 0

examples/data2vec/config/v2/text_finetuning/sst_2.yaml

+# @package _group_
+
+common:
+  fp16: true
+  fp16_init_scale: 4
+  threshold_loss_scale: 1
+  fp16_scale_window: 128
+  log_format: json
+  log_interval: 200
+  user_dir: ${env:PWD}/examples/data2vec
+
+task:
+  _name: sentence_prediction
+  data: ???
+  init_token: 0
+  separator_token: 2
+  num_classes: 2
+  max_positions: 512
+  d2v2_multi: True
+
+checkpoint:
+  best_checkpoint_metric: accuracy
+  maximize_best_checkpoint_metric: true
+  no_epoch_checkpoints: true
+
+distributed_training:
+  find_unused_parameters: true
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+
+criterion:
+  _name: sentence_prediction
+
+dataset:
+  batch_size: 32
+  required_batch_size_multiple: 1
+  max_tokens: 4400
+  num_workers: 1
+
+optimizer:
+  _name: adam
+  weight_decay: 0.1
+  adam_betas: (0.9,0.98)
+  adam_eps: 1e-06
+
+lr_scheduler:
+  _name: polynomial_decay
+  warmup_updates: 1256
+
+optimization:
+  clip_norm: 0.0
+  lr: [2e-05]
+  max_update: 20935
+  max_epoch: 10
+
+model:
+  _name: data2vec_text_classification
+  model_path: ???

examples/data2vec/config/v2/text_finetuning/sts_b.yaml

+# @package _group_
+
+common:
+  fp16: true
+  fp16_init_scale: 4
+  threshold_loss_scale: 1
+  fp16_scale_window: 128
+  log_format: json
+  log_interval: 200
+  user_dir: ${env:PWD}/examples/data2vec
+
+task:
+  _name: sentence_prediction
+  data: ???
+  init_token: 0
+  separator_token: 2
+  num_classes: 1
+  max_positions: 512
+  d2v2_multi: True
+
+checkpoint:
+  best_checkpoint_metric: pearson_and_spearman
+  maximize_best_checkpoint_metric: true
+  no_epoch_checkpoints: true
+
+distributed_training:
+  find_unused_parameters: true
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+
+criterion:
+  _name: sentence_prediction
+  regression_target: true
+  report_pearson_and_spearman: True
+
+dataset:
+  batch_size: 16
+  required_batch_size_multiple: 1
+  max_tokens: 4400
+  num_workers: 1
+
+optimizer:
+  _name: adam
+  weight_decay: 0.1
+  adam_betas: (0.9,0.98)
+  adam_eps: 1e-06
+
+lr_scheduler:
+  _name: polynomial_decay
+  warmup_updates: 214
+
+optimization:
+  clip_norm: 0.0
+  lr: [4e-05]
+  max_update: 3598
+  max_epoch: 10
+
+model:
+  _name: data2vec_text_classification
+  model_path: ???

examples/data2vec/config/vision/finetuning/imagenet.yaml

+# @package _group_
+
+common:
+  fp16: true
+  log_format: json
+  log_interval: 200
+  tensorboard_logdir: tb
+
+checkpoint:
+  save_interval: 1
+  save_interval_updates: 25000
+  keep_interval_updates: 1
+  no_epoch_checkpoints: true
+  best_checkpoint_metric: accuracy
+
+task:
+  _name: image_classification
+  data: /datasets01/imagenet_full_size/061417
+
+dataset:
+  num_workers: 6
+  batch_size: 64
+  skip_invalid_size_inputs_valid_test: true
+  required_batch_size_multiple: 1
+  valid_subset: val
+
+distributed_training:
+  distributed_world_size: 8
+  ddp_backend: c10d
+
+criterion:
+  _name: model
+  log_keys:
+    - correct
+
+optimization:
+  max_update: 100000
+  lr: [0.0005]
+
+optimizer:
+  _name: adam
+  adam_betas: (0.9,0.98)
+  adam_eps: 1e-06
+  weight_decay: 0.01
+
+lr_scheduler:
+  _name: cosine
+  warmup_updates: 10000
+
+model:
+  _name: data2vec_image_classification
+  model_path: ???

examples/data2vec/config/vision/finetuning/mae_imagenet_clean.yaml

+# @package _group_
+
+common:
+  fp16: true
+  log_format: json
+  log_interval: 200
+  tensorboard_logdir: tb
+  fp16_no_flatten_grads: true
+
+checkpoint:
+  save_interval: 1
+  save_interval_updates: 25000
+  keep_interval_updates: 1
+  no_epoch_checkpoints: true
+  best_checkpoint_metric: accuracy
+  maximize_best_checkpoint_metric: true
+
+task:
+  _name: mae_image_classification
+  data: /datasets01/imagenet_full_size/061417
+
+dataset:
+  num_workers: 6
+  batch_size: 32
+  skip_invalid_size_inputs_valid_test: true
+  required_batch_size_multiple: 2
+  valid_subset: val
+
+distributed_training:
+  distributed_world_size: 16
+  ddp_backend: c10d
+
+criterion:
+  _name: model
+  log_keys:
+    - correct
+
+optimization:
+  max_update: 250200
+  lr: [0.001]
+
+optimizer:
+  _name: composite
+  dynamic_groups: true
+  groups:
+    default:
+      lr_float: 0.001
+      optimizer:
+        _name: adam
+        adam_betas: [0.9,0.95]
+        weight_decay: 0.05
+      lr_scheduler:
+        _name: cosine
+        warmup_updates: 16000
+        min_lr: 1e-6
+
+
+lr_scheduler: pass_through
+
+model:
+  _name: mae_image_classification
+  mixup: 0.7
+  mixup_prob: 0.9
+
+  model_path: ???

examples/data2vec/config/vision/finetuning/mae_imagenet_huge_clean.yaml

+# @package _group_
+
+common:
+  fp16: true
+  log_format: json
+  log_interval: 200
+  tensorboard_logdir: tb
+  fp16_no_flatten_grads: true
+
+checkpoint:
+  save_interval: 1
+  save_interval_updates: 25000
+  keep_interval_updates: 1
+  no_epoch_checkpoints: true
+  best_checkpoint_metric: accuracy
+  maximize_best_checkpoint_metric: true
+
+task:
+  _name: mae_image_classification
+  data: /datasets01/imagenet_full_size/061417
+
+dataset:
+  num_workers: 6
+  batch_size: 32
+  skip_invalid_size_inputs_valid_test: true
+  required_batch_size_multiple: 2
+  valid_subset: val
+
+distributed_training:
+  distributed_world_size: 16
+  ddp_backend: c10d
+
+criterion:
+  _name: model
+  log_keys:
+    - correct
+
+optimization:
+  max_update: 125200
+  lr: [0.0005]
+  clip_norm: 4
+
+optimizer:
+  _name: composite
+  dynamic_groups: true
+  groups:
+    default:
+      lr_float: 0.0005
+      optimizer:
+        _name: adam
+        adam_betas: [0.9,0.95]
+        weight_decay: 0.05
+      lr_scheduler:
+        _name: cosine
+        warmup_updates: 16000
+        min_lr: 1e-20
+
+
+lr_scheduler: pass_through
+
+model:
+  _name: mae_image_classification
+  mixup: 0.7
+  mixup_prob: 0.9
+  layer_decay: 0.75
+  drop_path_rate: 0.2
+
+  model_path: ???

examples/data2vec/config/vision/finetuning/mae_imagenet_large_clean.yaml

+# @package _group_
+
+common:
+  fp16: true
+  log_format: json
+  log_interval: 200
+  tensorboard_logdir: tb
+  fp16_no_flatten_grads: true
+
+checkpoint:
+  save_interval: 1
+  save_interval_updates: 25000
+  keep_interval_updates: 1
+  no_epoch_checkpoints: true
+  best_checkpoint_metric: accuracy
+  maximize_best_checkpoint_metric: true
+
+task:
+  _name: mae_image_classification
+  data: /datasets01/imagenet_full_size/061417
+
+dataset:
+  num_workers: 6
+  batch_size: 32
+  skip_invalid_size_inputs_valid_test: true
+  required_batch_size_multiple: 2
+  valid_subset: val
+
+distributed_training:
+  distributed_world_size: 16
+  ddp_backend: c10d
+
+criterion:
+  _name: model
+  log_keys:
+    - correct
+
+optimization:
+  max_update: 125200
+  lr: [0.0005]
+  clip_norm: 4
+
+optimizer:
+  _name: composite
+  dynamic_groups: true
+  groups:
+    default:
+      lr_float: 0.0005
+      optimizer:
+        _name: adam
+        adam_betas: [0.9,0.95]
+        weight_decay: 0.05
+      lr_scheduler:
+        _name: cosine
+        warmup_updates: 16000
+        min_lr: 1e-7
+
+
+lr_scheduler: pass_through
+
+model:
+  _name: mae_image_classification
+  mixup: 0.7
+  mixup_prob: 0.9
+  layer_decay: 0.75
+  drop_path_rate: 0.2
+
+  model_path: ???

examples/data2vec/config/vision/finetuning/run_config/local.yaml

+# @package _global_
+hydra:
+  sweep:
+    dir: ${env:PWD}/tmp_dbg/${now:%H-%M-%S}
+
+distributed_training:
+  distributed_world_size: 1
+  nprocs_per_node: 1
+  distributed_port: -1
+  
+common:
+  log_interval: 1
+  
+dataset:
+  num_workers: 0

examples/data2vec/config/vision/finetuning/run_config/slurm_1.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+          - common.user_dir
+  sweep:
+    dir: /checkpoint/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 80
+    gpus_per_node: 8
+    tasks_per_node: 1
+    mem_gb: 450
+    nodes: 1
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: devlab,learnlab,learnfair,scavenge
+    constraint: volta32gb,ib4
+    max_num_timeout: 30

examples/data2vec/config/vision/finetuning/run_config/slurm_1_aws.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+          - common.user_dir
+  sweep:
+    dir: /checkpoint/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 80
+    gpus_per_node: 8
+    tasks_per_node: 1
+    mem_gb: 0
+    nodes: 1
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: wav2vec,learnlab,learnfair
+    max_num_timeout: 30

examples/data2vec/config/vision/finetuning/run_config/slurm_2.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+          - common.user_dir
+          - task.local_cache_path
+  sweep:
+    dir: /checkpoint/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 10
+    gpus_per_node: 8
+    tasks_per_node: 8
+    mem_gb: 450
+    nodes: 2
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: devlab,learnlab,learnfair,scavenge
+    constraint: volta32gb,ib4
+    max_num_timeout: 30

examples/data2vec/config/vision/finetuning/run_config/slurm_2_aws.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+          - common.user_dir
+          - task.local_cache_path
+          - model.model_path
+  sweep:
+    dir: /fsx-wav2vec/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 10
+    gpus_per_node: 8
+    tasks_per_node: 8
+    mem_gb: 0
+    nodes: 2
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: wav2vec,learnlab,learnfair
+    max_num_timeout: 30

examples/data2vec/config/vision/finetuning/run_config/slurm_3.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+  sweep:
+    dir: /checkpoint/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 80
+    gpus_per_node: 8
+    tasks_per_node: 1
+    mem_gb: 450
+    nodes: 3
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: devlab,learnlab,learnfair,scavenge
+    constraint: volta32gb,ib4
+    max_num_timeout: 30

examples/data2vec/config/vision/finetuning/run_config/slurm_4.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+  sweep:
+    dir: /checkpoint/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 10
+    gpus_per_node: 8
+    tasks_per_node: 8
+    mem_gb: 450
+    nodes: 4
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: devlab,learnlab,learnfair,scavenge
+    constraint: volta32gb,ib4
+    max_num_timeout: 30

examples/data2vec/config/vision/finetuning/run_config/slurm_4_aws.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+          - common.user_dir
+  sweep:
+    dir: /checkpoint/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 10
+    gpus_per_node: 8
+    tasks_per_node: 8
+    mem_gb: 0
+    nodes: 4
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: wav2vec,learnlab,learnfair
+    max_num_timeout: 30

examples/data2vec/config/vision/finetuning/run_config/slurm_6_aws.yaml

+# @package _global_
+
+hydra:
+  job:
+    config:
+      override_dirname:
+        kv_sep: ':'
+        item_sep: '/'
+        exclude_keys:
+          - run_config
+          - distributed_training.distributed_port
+          - distributed_training.distributed_world_size
+          - model.pretrained_model_path
+          - model.target_network_path
+          - next_script
+          - task.cache_in_scratch
+          - task.data
+          - checkpoint.save_interval_updates
+          - checkpoint.keep_interval_updates
+          - checkpoint.save_on_overflow
+          - common.log_interval
+          - common.user_dir
+  sweep:
+    dir: /checkpoint/${env:USER}/${env:PREFIX}/${hydra.job.config_name}_${hydra.launcher.gpus_per_node}/${hydra.job.override_dirname}
+    subdir: ''
+  launcher:
+    submitit_folder: ${hydra.sweep.dir}
+    timeout_min: 4320
+    cpus_per_task: 10
+    gpus_per_node: 8
+    tasks_per_node: 8
+    mem_gb: 0
+    nodes: 6
+    name: ${env:PREFIX}_${hydra.job.config_name}
+    partition: wav2vec,learnlab,learnfair
+    max_num_timeout: 30