program: run_seq2seq_flax.py
entity: wandb
project: hf-flax-dalle-mini
method: random
metric:
  name: eval/loss
  goal: minimize
parameters:
  learning_rate:
    distribution: log_uniform
    # from exp(min) to exp(max), ie 1e-5 to 1e-3 on log scale
    min: -11.5
    max: -6.9
  gradient_accumulation_steps:
    value: 8
  warmup_steps:
    value: 1000
command:
  - python3
  - ${program}
  - "--output_dir"
  - "./output_sweep"
  - "--overwrite_output_dir"
  - "--adafactor"
  - "--num_train_epochs"
  - 1
  - "--max_train_samples"
  - 1000
  - "--per_device_train_batch_size"
  - 32
  - "--per_device_eval_batch_size"
  - 32
  - "--preprocessing_num_workers"
  - 80
  - "--do_train"
  - "--do_eval"
  - ${args}