cfg_base.yaml

model:
  arch: unimernet
  model_type: unimernet
  model_config:
    model_name: ./models/unimernet_base
    max_seq_len: 1536

  load_pretrained: True
  pretrained: './models/unimernet_base/pytorch_model.pth'
  tokenizer_config:
    path: ./models/unimernet_base

datasets:
  formula_rec_eval:
    vis_processor:
      eval:
        name: "formula_image_eval"
        image_size:
          - 192
          - 672
   
run:
  runner: runner_iter
  task: unimernet_train

  batch_size_train: 64
  batch_size_eval: 64
  num_workers: 1

  iters_per_inner_epoch: 2000
  max_iters: 60000

  seed: 42
  output_dir: "../output/demo"

  evaluate: True
  test_splits: [ "eval" ]

  device: "cuda"
  world_size: 1
  dist_url: "env://"
  distributed: True
  distributed_type: ddp  # or fsdp when train llm

  generate_cfg:
    temperature: 0.0