lavis/projects/blip2/train/caption_coco_ft.yaml

 # 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: blip2_opt
  model_type: caption_coco_opt2.7b
  load_finetuned: False
  use_grad_checkpoint: True
  freeze_vit: False

datasets:
  coco_caption: # name of the dataset builder
    vis_processor:
        train:
          name: "blip2_image_train"
          image_size: 364
        eval:
          name: "blip_image_eval"
          image_size: 364
    text_processor:
        train:
          name: "blip_caption"
          prompt: "a photo of "
        eval:
          name: "blip_caption"
    # build_info:
    #     images:
    #         storage: '/export/share/datasets/vision/coco/images/'

run:
  task: captioning
  # optimizer
  lr_sched: "linear_warmup_cosine_lr"
  init_lr: 1e-5
  min_lr: 0
  warmup_lr: 1e-8
  warmup_steps: 1000
  weight_decay: 0.05
  max_epoch: 5
  batch_size_train: 16
  batch_size_eval: 8
  num_workers: 4
  accum_grad_iters: 1

  max_len: 30
  min_len: 8
  num_beams: 5

  seed: 42
  output_dir: "output/BLIP2/Caption_coco"

  amp: True
  resume_ckpt_path: null

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

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