seed: 0
run_mode: 'train'
output_dir: './output' # path to save checkpoint/strategy
load_checkpoint: ''
src_strategy_path_or_dir: ''
auto_trans_ckpt: False  # If true, auto transform load_checkpoint to load in distributed model
only_save_strategy: False
resume_training: False

# context
context:
  mode: 0 #0--Graph Mode; 1--Pynative Mode
  device_target: "Ascend"
  enable_graph_kernel: False
  graph_kernel_flags: "--opt_level=0"
  max_call_depth: 10000
  save_graphs: False
  device_id: 0

# aicc
remote_save_url: "Please input obs url on AICC platform."

# runner
runner_config:
  epochs: 5
  batch_size: 32
  image_size: 224
  sink_mode: False
  sink_size: 2

# parallel
use_parallel: False
parallel:
  parallel_mode: 0 # 0-data parallel, 1-semi-auto parallel, 2-auto parallel, 3-hybrid parallel
  gradients_mean: True
  enable_alltoall: False
  full_batch: False
  search_mode: "sharding_propagation"
  enable_parallel_optimizer: False
  strategy_ckpt_save_file: "./ckpt_strategy.ckpt"
parallel_config:
  data_parallel: 1
  model_parallel: 1
  expert_parallel: 1
  pipeline_stage: 1
  micro_batch_num: 1
  gradient_aggregation_group: 4
micro_batch_interleave_num: 1

# recompute
recompute_config:
  recompute: False
  parallel_optimizer_comm_recompute: False
  mp_comm_recompute: True
  recompute_slice_activation: False

# autotune
auto_tune: False
filepath_prefix: './autotune'
autotune_per_step: 10

# profile
profile: False
profile_start_step: 1
profile_stop_step: 10
init_start_profile: False
profile_communication: False
profile_memory: True

# Trainer
trainer:
  type: ContrastiveLanguageImagePretrainTrainer
  model_name: 'clip_vit_b_32'

# train dataset
train_dataset: &train_dataset
  data_loader:
    type: Flickr8kDataLoader
    dataset_dir: "./checkpoint_download/Flickr8k"
    stage: "train"
    column_names: ["image", "text"]
  text_transforms:
    type: RandomChoiceTokenizerForward
    max_length: 77
    padding: "max_length"
    random_seed: 2022
  transforms:
    - type: Resize
      size: 224
    - type: CenterCrop
      size: 224
    - type: ToTensor
    - type: Normalize
      mean: [0.48145466, 0.4578275, 0.40821073]
      std: [0.26862954, 0.26130258, 0.27577711]
      is_hwc: False
  tokenizer:
    type: CLIPTokenizer
    pad_token: '!'
  num_parallel_workers: 8
  python_multiprocessing: False
  drop_remainder: True
  batch_size: 32
  repeat: 1
  numa_enable: False
  prefetch_size: 30
  seed: 2022
train_dataset_task:
  type: ContrastiveLanguageImagePretrainDataset
  dataset_config: *train_dataset

# model
model:
  arch:
    type: CLIPModel
  model_config:
    type: CLIPConfig
    text_config:
      type: CLIPTextConfig
      vocab_size: 49408
      hidden_size: 512
      intermediate_size: 2048
      num_hidden_layers: 12
      num_attention_heads: 8
      max_position_embeddings: 77
      hidden_act: "quick_gelu"
      attention_dropout: 0.0
      drop_out: 0.0
      initializer_range: 0.02
      initializer_factor: 1.0
    vision_config:
      type: CLIPVisionConfig
      hidden_size: 768
      intermediate_size: 3072
      num_hidden_layers: 12
      num_attention_heads: 12
      image_size: 224
      patch_size: 32
      hidden_act: "quick_gelu"
      dropout: 0.0
      attention_dropout: 0.0
      initializer_range: 0.02
      initializer_factor: 1.0
    dtype: float16  # type of tensors
    checkpoint_name_or_path: clip_vit_b_32   # the loaded model type
    projection_dim: 512  # feature dims
    logit_scale_init_value: 2.6592


# lr sechdule
layer_scale: False
layer_decay: 0.65

# optimizer
optimizer:
  type: adamw
  weight_decay: 0.001
  learning_rate: 0.00001
lr_scale: False
lr_scale_factor: 256

# callbacks
callbacks:
  - type: MFLossMonitor
  - type: CheckpointMointor
    prefix: "mindformers"
    save_checkpoint_steps: 100
    integrated_save: True
    async_save: False
  - type: ObsMonitor
eval_callbacks:
  - type: ObsMonitor

# processor
processor:
  type: CLIPProcessor
  image_processor:
    type: CLIPImageProcessor
    image_resolution: 224  # input image size
  tokenizer:
    type: CLIPTokenizer
    pad_token: '!' # corresponding token id is 0