# Copyright (c) 2022, salesforce.com, inc.
 # All rights reserved.
 # SPDX-License-Identifier: BSD-3-Clause
 # For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause

model:
  arch: sevila
  model_type: pretrain_flant5xl
  load_finetuned: True
  finetuned: 'checkpoints/blip2_pretrained_flant5xl.pth'
  use_grad_checkpoint: False
  freeze_vit: True
  frame_num: 8
  answer_num: 4
  task: freeze_qa_vid
  qformer_input_text: False

datasets:
  how2qa:
    vis_processor:
        eval:
          name: "blip_video_eval"
          n_frms: 4
          image_size: 224
    text_processor:
        eval:
          name: "blip_question"
          max_words: 50

run:
  task: videoqa
  # optimizer
  lr_sched: "linear_warmup_cosine_lr"
  init_lr: 1e-5
  min_lr: 0
  warmup_lr: 1e-8
  warmup_steps: 200
  weight_decay: 0.05
  max_epoch: 5
  batch_size_train: 32
  batch_size_eval: 32
  num_workers: 8
  accum_grad_iters: 1

  max_len: 30
  min_len: 8
  num_beams: 5

  seed: 42
  output_dir: ""

  amp: True
  resume_ckpt_path: null

  evaluate: False
  train_splits: ["train"]
  valid_splits: ["val"]
  test_splits: ["val"]

  device: "cuda"
  world_size: 1
  dist_url: "env://"
  distributed: True
  find_unused_parameters: True