rotate-freebase-distributed-relation-rLB-2@2.yaml

dataset:
  files:
    test_small:
      filename: test_small.del
      type: triples
    test_tiny:
      filename: test_tiny.del
      type: triples
    test_tiny_tiny:
      filename: test_tiny_tiny.del
      type: triples
    valid_small:
      filename: valid_small.del
      type: triples
    valid_tiny:
      filename: valid_tiny.del
      type: triples
    valid_tiny_tiny:
      filename: valid_tiny_tiny.del
      type: triples
  name: freebase
distributed_model:
  base_model:
    type: rotate
entity_ranking:
  chunk_size: 15000
eval:
  batch_size: 45
  num_workers: 4
  split: test_small
import:
- rotate
- distributed_model
job:
  device_pool:
  - cuda:0
  - cuda:1
  distributed:
    parameter_server: lapse
    entity_localize: true
    gloo_socket_ifname: bond0
    num_eval_workers: 4
    num_machines: 2
    num_partitions: 8
    num_workers: 8
    num_workers_machine: 4
    partition_type: relation
    relation_sync_level: partition
lookup_embedder:
  dim: 128
  initialize: xavier_uniform_
  initialize_args:
    normal_:
      mean: 0.0
      std: 0.7247714657764338
    uniform_:
      a: -0.7264893817037996
    xavier_normal_:
      gain: 1.0
    xavier_uniform_:
      gain: 1.0
  regularize_args:
    weighted: true
  sparse: true
model: distributed_model
modules:
- kge.job
- kge.model.embedder
- kge.model
negative_sampling:
  combined: true
  implementation: batch
  num_samples:
    o: 400
    s: 191
  sampling_type: pooled
  shared: true
  shared_type: naive
rotate:
  entity_embedder:
    dropout: -0.4202541569247842
    regularize_weight: 0.0016039710378808378
  relation_embedder:
    dropout: -0.4545119274407625
    regularize_weight: 9.709504921691681e-20
train:
  auto_correct: true
  batch_size: 1024
  loss_arg: .nan
  lr_scheduler: ReduceLROnPlateau
  lr_scheduler_args:
    factor: 0.95
    mode: max
    patience: 9
    threshold: 0.0001
  max_epochs: 10
  num_workers: 4
  optimizer:
    default:
      args:
        lr: 0.16755594652229405
      type: dist_rowadagrad
  type: distributed_negative_sampling
valid:
  early_stopping:
    patience: 10
    threshold:
      epochs: 50
      metric_value: 0.1
  every: 10
  split: valid_tiny_tiny