SYSTEM = ''
accumulative_counts = 256
batch_size = 1
betas = (
    0.9,
    0.999,
)
custom_hooks = [
    dict(
        tokenizer=dict(
            padding_side='right',
            pretrained_model_name_or_path=
            '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
            trust_remote_code=True,
            type='transformers.AutoTokenizer.from_pretrained'),
        type='xtuner.engine.DatasetInfoHook'),
    dict(
        evaluation_images='/mnt/program/wlx_data/experiments/assets/view.jpg',
        evaluation_inputs=[
            'Please describe this picture in detail',
            'What should I be cautious about when I visit this place?',
        ],
        every_n_iters=5000,
        image_processor=dict(
            crop_size=384,
            pretrained_model_name_or_path=
            'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
            size=384,
            trust_remote_code=True,
            type='transformers.CLIPImageProcessor.from_pretrained'),
        prompt_template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        system='',
        tokenizer=dict(
            padding_side='right',
            pretrained_model_name_or_path=
            '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
            trust_remote_code=True,
            type='transformers.AutoTokenizer.from_pretrained'),
        type='xtuner.engine.EvaluateChatHook'),
]
data_path = '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/densefusion/filtered_densefusion.jsonl'
data_root = '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/densefusion/'
dataloader_num_workers = 16
default_hooks = dict(
    checkpoint=dict(
        by_epoch=False,
        interval=10000,
        max_keep_ckpts=2,
        type='mmengine.hooks.CheckpointHook'),
    logger=dict(interval=10, type='mmengine.hooks.LoggerHook'),
    param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'),
    sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'),
    timer=dict(type='mmengine.hooks.IterTimerHook'))
env_cfg = dict(
    cudnn_benchmark=False,
    dist_cfg=dict(backend='nccl'),
    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
evaluation_freq = 5000
evaluation_images = '/mnt/program/wlx_data/experiments/assets/view.jpg'
evaluation_inputs = [
    'Please describe this picture in detail',
    'What should I be cautious about when I visit this place?',
]
image_folder = '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/densefusion/data/MiraData/frames/'
image_processor = dict(
    crop_size=384,
    pretrained_model_name_or_path='laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
    size=384,
    trust_remote_code=True,
    type='transformers.CLIPImageProcessor.from_pretrained')
language_prefix = '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/'
launcher = 'pytorch'
llava_dataset_1 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/event_relationship_mcq.json',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_10 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/sharegpt4video_qa/sharegpt4video_qa.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/sharegpt4video_qa/data/ShareGPT4Video-raw/vqa_frames/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_11 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/m4/filtered_m4.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/m4/data/M4-Instruct-Data/images/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/m4/data/M4-Instruct-Data/images/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_12 = dict(
    data_path=
    '/data1/exs_data/datasets/AuroraCap-trainset/language_sharegpt4video_caption/language_sharegpt4video_caption.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/data1/exs_data/datasets/AuroraCap-trainset/language_sharegpt4video_caption/data/ShareGPT4Video-raw/caption_frames/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_13 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/miradata/filtered_miradata.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/miradata/data/MiraData/frames/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/miradata/data/MiraData/frames/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_14 = dict(
    data_path=
    '/data1/exs_data/datasets/AuroraCap-trainset/language_sharegpt4v/language_sharegpt4v.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/data1/exs_data/datasets/AuroraCap-trainset/language_sharegpt4v/data/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/data1/exs_data/datasets/AuroraCap-trainset/language_sharegpt4v/data/tokenized_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_15 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/densefusion/filtered_densefusion.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/densefusion/data/MiraData/frames/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_2 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/event_relationship_qa.json',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_3 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/hr_video_grid_mcq.json',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_4 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/hr_video_grid_qa.json',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_5 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/long_video_caption.json',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_6 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/spatial_niah_mcq.json',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_7 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/allava_caption_laion/filtered_allava_caption_laion.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/allava_caption_laion/data/ALLaVA-4V/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/allava_caption_laion/data/ALLaVA-4V/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_8 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/allava_instruct_laion/filtered_allava_instruct_laion.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/allava_instruct_laion/data/ALLaVA-4V/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    offline_processed_text_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/allava_instruct_laion/data/ALLaVA-4V/tokenized-by-rwkv7/tokenized_sandwich_data',
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_dataset_9 = dict(
    data_path=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/cambrian/filtered_cambrian.jsonl',
    dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
    image_folder=
    '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/cambrian/data/Cambrian-10M/images/',
    image_processor=dict(
        crop_size=384,
        pretrained_model_name_or_path=
        'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
        size=384,
        trust_remote_code=True,
        type='transformers.CLIPImageProcessor.from_pretrained'),
    max_length=4096,
    pad_image_to_square=True,
    template_map_fn=dict(
        template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
        type='xtuner.dataset.map_fns.template_map_fn_factory'),
    tokenizer=dict(
        padding_side='right',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        trust_remote_code=True,
        type='transformers.AutoTokenizer.from_pretrained'),
    type='xtuner.dataset.AuroraDataset')
llava_ov_strategy = False
llm_name_or_path = '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf'
load_from = None
log_level = 'INFO'
lr = 8e-05
max_epochs = 1
max_length = 4096
max_norm = 1
model = dict(
    freeze_llm=False,
    freeze_proj=False,
    freeze_visual_encoder=False,
    llava_ov_strategy=False,
    llm=dict(
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
        quantization_config=None,
        torch_dtype='torch.float16',
        trust_remote_code=True,
        type='fla.models.rwkv7.RWKV7ForCausalLM.from_pretrained'),
    pretrained_pth=
    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf/projector',
    slowfast=False,
    type='xtuner.model.AuroraModel',
    visual_encoder=dict(
        order='descending',
        pretrained_model_name_or_path=
        '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf/visual_encoder',
        sort_after_merge=True,
        type='xtuner.model.aurora.AuroraSigEncoder.from_pretrained',
        visual_token_merge_ratio=1.0))
optim_type = 'torch.optim.AdamW'
optim_wrapper = dict(
    optimizer=dict(
        betas=(
            0.9,
            0.999,
        ),
        lr=8e-05,
        type='torch.optim.AdamW',
        weight_decay=0),
    type='DeepSpeedOptimWrapper')
param_scheduler = [
    dict(
        begin=0,
        by_epoch=True,
        convert_to_iter_based=True,
        end=0.03,
        start_factor=1e-05,
        type='mmengine.optim.LinearLR'),
    dict(
        T_max=1,
        begin=0.03,
        by_epoch=True,
        convert_to_iter_based=True,
        eta_min=0.0,
        type='mmengine.optim.CosineAnnealingLR'),
]
pretrained_pth = '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf/projector'
prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.vicuna'
randomness = dict(deterministic=False, seed=None)
resume = False
runner_type = 'FlexibleRunner'
save_steps = 10000
save_total_limit = 2
size = 384
slowfast = False
strategy = dict(
    config=dict(
        bf16=dict(enabled=True),
        fp16=dict(enabled=False, initial_scale_power=16),
        gradient_accumulation_steps='auto',
        gradient_clipping='auto',
        train_micro_batch_size_per_gpu='auto',
        zero_allow_untested_optimizer=True,
        zero_force_ds_cpu_optimizer=False,
        zero_optimization=dict(overlap_comm=True, stage=1)),
    exclude_frozen_parameters=True,
    gradient_accumulation_steps=256,
    gradient_clipping=1,
    sequence_parallel_size=1,
    train_micro_batch_size_per_gpu=1,
    type='xtuner.engine.DeepSpeedStrategy')
tokenizer = dict(
    padding_side='right',
    pretrained_model_name_or_path=
    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
    trust_remote_code=True,
    type='transformers.AutoTokenizer.from_pretrained')
train_cfg = dict(by_epoch=True, max_epochs=1, val_interval=1)
train_dataloader = dict(
    batch_size=1,
    collate_fn=dict(type='xtuner.dataset.collate_fns.default_collate_fn'),
    dataset=dict(
        datasets=[
            dict(
                data_path=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/event_relationship_mcq.json',
                dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
                image_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/',
                image_processor=dict(
                    crop_size=384,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=384,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                tokenizer=dict(
                    padding_side='right',
                    pretrained_model_name_or_path=
                    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                    trust_remote_code=True,
                    type='transformers.AutoTokenizer.from_pretrained'),
                type='xtuner.dataset.AuroraDataset'),
            dict(
                data_path=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/event_relationship_qa.json',
                dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
                image_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/',
                image_processor=dict(
                    crop_size=384,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=384,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/tokenized-by-rwkv7/tokenized_sandwich_data',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                tokenizer=dict(
                    padding_side='right',
                    pretrained_model_name_or_path=
                    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                    trust_remote_code=True,
                    type='transformers.AutoTokenizer.from_pretrained'),
                type='xtuner.dataset.AuroraDataset'),
            dict(
                data_path=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/hr_video_grid_mcq.json',
                dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
                image_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/',
                image_processor=dict(
                    crop_size=384,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=384,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                tokenizer=dict(
                    padding_side='right',
                    pretrained_model_name_or_path=
                    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                    trust_remote_code=True,
                    type='transformers.AutoTokenizer.from_pretrained'),
                type='xtuner.dataset.AuroraDataset'),
            dict(
                data_path=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/hr_video_grid_qa.json',
                dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
                image_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/',
                image_processor=dict(
                    crop_size=384,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=384,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/tokenized-by-rwkv7/tokenized_sandwich_data',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                tokenizer=dict(
                    padding_side='right',
                    pretrained_model_name_or_path=
                    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                    trust_remote_code=True,
                    type='transformers.AutoTokenizer.from_pretrained'),
                type='xtuner.dataset.AuroraDataset'),
            dict(
                data_path=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/long_video_caption.json',
                dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
                image_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/',
                image_processor=dict(
                    crop_size=384,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=384,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/tokenized-by-rwkv7/tokenized_sandwich_data',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                tokenizer=dict(
                    padding_side='right',
                    pretrained_model_name_or_path=
                    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                    trust_remote_code=True,
                    type='transformers.AutoTokenizer.from_pretrained'),
                type='xtuner.dataset.AuroraDataset'),
            dict(
                data_path=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/spatial_niah_mcq.json',
                dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
                image_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/',
                image_processor=dict(
                    crop_size=384,
                    pretrained_model_name_or_path=
                    'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                    size=384,
                    trust_remote_code=True,
                    type='transformers.CLIPImageProcessor.from_pretrained'),
                max_length=4096,
                offline_processed_text_folder=
                '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
                pad_image_to_square=True,
                template_map_fn=dict(
                    template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                    type='xtuner.dataset.map_fns.template_map_fn_factory'),
                tokenizer=dict(
                    padding_side='right',
                    pretrained_model_name_or_path=
                    '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                    trust_remote_code=True,
                    type='transformers.AutoTokenizer.from_pretrained'),
                type='xtuner.dataset.AuroraDataset'),
        ],
        type='xtuner.dataset.ConcatDataset'),
    num_workers=16,
    sampler=dict(shuffle=True, type='mmengine.dataset.DefaultSampler'))
train_dataset = dict(
    datasets=[
        dict(
            data_path=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/event_relationship_mcq.json',
            dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
            image_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/',
            image_processor=dict(
                crop_size=384,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=384,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            tokenizer=dict(
                padding_side='right',
                pretrained_model_name_or_path=
                '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                trust_remote_code=True,
                type='transformers.AutoTokenizer.from_pretrained'),
            type='xtuner.dataset.AuroraDataset'),
        dict(
            data_path=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/event_relationship_qa.json',
            dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
            image_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/',
            image_processor=dict(
                crop_size=384,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=384,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/event_relationship_qa/tokenized-by-rwkv7/tokenized_sandwich_data',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            tokenizer=dict(
                padding_side='right',
                pretrained_model_name_or_path=
                '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                trust_remote_code=True,
                type='transformers.AutoTokenizer.from_pretrained'),
            type='xtuner.dataset.AuroraDataset'),
        dict(
            data_path=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/hr_video_grid_mcq.json',
            dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
            image_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/',
            image_processor=dict(
                crop_size=384,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=384,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            tokenizer=dict(
                padding_side='right',
                pretrained_model_name_or_path=
                '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                trust_remote_code=True,
                type='transformers.AutoTokenizer.from_pretrained'),
            type='xtuner.dataset.AuroraDataset'),
        dict(
            data_path=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/hr_video_grid_qa.json',
            dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
            image_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/',
            image_processor=dict(
                crop_size=384,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=384,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/hr_video_grid_qa/tokenized-by-rwkv7/tokenized_sandwich_data',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            tokenizer=dict(
                padding_side='right',
                pretrained_model_name_or_path=
                '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                trust_remote_code=True,
                type='transformers.AutoTokenizer.from_pretrained'),
            type='xtuner.dataset.AuroraDataset'),
        dict(
            data_path=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/long_video_caption.json',
            dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
            image_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/',
            image_processor=dict(
                crop_size=384,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=384,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/long_video_caption/tokenized-by-rwkv7/tokenized_sandwich_data',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            tokenizer=dict(
                padding_side='right',
                pretrained_model_name_or_path=
                '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                trust_remote_code=True,
                type='transformers.AutoTokenizer.from_pretrained'),
            type='xtuner.dataset.AuroraDataset'),
        dict(
            data_path=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/spatial_niah_mcq.json',
            dataset_map_fn='xtuner.dataset.map_fns.aurora_map_fn',
            image_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/',
            image_processor=dict(
                crop_size=384,
                pretrained_model_name_or_path=
                'laion/CLIP-ViT-bigG-14-laion2B-39B-b160k',
                size=384,
                trust_remote_code=True,
                type='transformers.CLIPImageProcessor.from_pretrained'),
            max_length=4096,
            offline_processed_text_folder=
            '/mnt/program/wlx_data/datasets/TIGER-Lab/VISTA-400K/spatial_niah_mcq/tokenized-by-rwkv7/tokenized_sandwich_data',
            pad_image_to_square=True,
            template_map_fn=dict(
                template='xtuner.utils.PROMPT_TEMPLATE.vicuna',
                type='xtuner.dataset.map_fns.template_map_fn_factory'),
            tokenizer=dict(
                padding_side='right',
                pretrained_model_name_or_path=
                '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf',
                trust_remote_code=True,
                type='transformers.AutoTokenizer.from_pretrained'),
            type='xtuner.dataset.AuroraDataset'),
    ],
    type='xtuner.dataset.ConcatDataset')
visual_encoder_name_or_path = '/mnt/program/wlx_data/experiments/language-aurora-rwkv7-0317/iter_570893.hf/visual_encoder'
visual_token_merge_ratio = 1.0
visualizer = None
warmup_ratio = 0.03
weight_decay = 0
work_dir = '/mnt/program/wlx_data/experiments/video-aurora-rwkv7-0329'