name: DEFAULT
project: Spikey

slurm:
  name: 'Spikey_{config[name]}'
  partitions:
    - single
  standard_output: ./reports/slurm/out_%A_%a.log
  standard_error: ./reports/slurm/err_%A_%a.log
  num_parallel_jobs: 50
  cpus_per_task: 4
  memory_per_cpu: 1000
  time_limit: 1440  # in minutes
  ntasks: 1
  venv: '.venv/bin/activate'
  sh_lines:
    - 'mkdir -p {tmp}/wandb'
    - 'mkdir -p {tmp}/local_pycache'
    - 'export PYTHONPYCACHEPREFIX={tmp}/local_pycache'

runner: spikey

scheduler:
  reps_per_version: 1
  agents_per_job: 1
  reps_per_agent: 1

wandb:
  project: '{config[project]}'
  group: '{config[name]}'
  job_type: '{delta_desc}'
  name: '{job_id}_{task_id}:{run_id}:{rand}={config[name]}_{delta_desc}'
  tags:
    - '{config[env][name]}'
    - '{config[algo][name]}'
  sync_tensorboard: False
  monitor_gym: False
  save_code: False

---
name: Test

preprocessing:
  use_delta_encoding: true  # Whether to use delta encoding.

predictor:
  type: lstm  # Options: 'lstm', 'fixed_input_nn'
  input_size: 1  # Input size for the LSTM predictor.
  hidden_size: 128  # Hidden size for the LSTM or Fixed Input NN predictor.
  num_layers: 2  # Number of layers for the LSTM predictor.
  fixed_input_size: 10  # Input size for the Fixed Input NN predictor. Only used if type is 'fixed_input_nn'.

training:
  epochs: 10  # Number of training epochs.
  batch_size: 32  # Batch size for training.
  learning_rate: 0.001  # Learning rate for the optimizer.
  eval_freq: 2  # Frequency of evaluation during training (in epochs).
  save_path: models  # Directory to save the best model and encoder.
  num_points: 1000  # Number of data points to visualize

bitstream_encoding:
  type: arithmetic  # Use arithmetic encoding.

data:
  url: https://content.neuralink.com/compression-challenge/data.zip  # URL to download the dataset.
  directory: data  # Directory to extract and store the dataset.
  split_ratio: 0.8  # Ratio to split the data into train and test sets.