{
    "dataset_param": {
        "dataset_type": "huggingface",
        "preprocess_parameters": {
            "model_name_or_path": "./ckpt/hf_path/GLM-4.5V",
            "use_fast_tokenizer": true,
            "split_special_tokens": false,
            "image_max_pixels": 262144,
            "image_min_pixels": 1024,
            "video_max_pixels": 16384,
            "video_min_pixels": 0,
            "video_fps": 2.0,
            "video_maxlen": 64
        },
        "basic_parameters": {
            "template": "glm4v_moe",
            "dataset_dir": "./data",
            "dataset": "./data/mllm_format_llava_instruct_data.json",
            "cache_dir": "./data/cache_dir",
            "enable_thinking": false,
            "overwrite_cache": false,
            "train_on_prompt": false,
            "mask_history": false,
            "preprocessing_batch_size": 1000,
            "preprocessing_num_workers": 16,
            "max_samples": null,
            "tool_format": null
        },
        "attr": {
            "system": null,
            "images": "images",
            "videos": null,
            "messages": "messages",
            "role_tag": "role",
            "content_tag": "content",
            "user_tag": "user",
            "assistant_tag": "assistant",
            "observation_tag": null,
            "function_tag": null,
            "system_tag": null
        }
    },
    "dataloader_param": {
        "dataloader_mode": "sampler",
        "drop_last": true,
        "sampler_type": "BaseRandomBatchSampler",
        "collate_param": {
            "model_name": "glm4v_moe",
            "ignore_pad_token_for_loss": true
        },
        "pin_memory": true,
        "shuffle": true
    }
}